Interface display method and device, electronic equipment and storage medium

Abstract

The application discloses an interface display method and device, electronic equipment and a storage medium. The interface display method comprises the following steps: acquiring input prompt information, wherein the prompt information is used for prompting an intelligent assistant application to output corresponding content; and displaying target content output by the intelligent assistant application according to the prompt information in an interface, wherein paragraph content in the target content is an interactive interface element. The method can improve the visual effect of the output result of the intelligent assistant application and meet the interactive demand of the user for the output result.

Description

Technical Field

[0001] This application relates to the field of electronic equipment technology, and more specifically, to an interface display method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the continuous development of Artificial Intelligence (AI) technology, AI-based applications are becoming increasingly common. Currently, in AI-based dialogue scenarios, it is often used to realize Artificial Intelligence Generated Content (AIGC), but the presentation of the generated results in related technologies is not ideal. Summary of the Invention

[0003] This application proposes an interface display method, apparatus, electronic device, and storage medium, which can improve the visual effect of the output results of intelligent assistant applications and meet the user's interactive needs for the output results.

[0004] In a first aspect, embodiments of this application provide an interface display method, the method comprising: acquiring input prompt information, the prompt information being used to prompt a smart assistant application to output corresponding content; and displaying target content output by the smart assistant application according to the prompt information in the interface, wherein paragraph content in the target content is an interactive interface element.

[0005] Secondly, embodiments of this application provide an interface display device, the device comprising: an information acquisition module and a content display module, wherein the information acquisition module is used to acquire input prompt information, the prompt information being used to prompt a smart assistant application to output corresponding content; the content display module is used to display target content output by the smart assistant application according to the prompt information on the interface, wherein paragraph content in the target content is an interactive interface element.

[0006] Thirdly, embodiments of this application provide an electronic device, including: one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to perform the interface display method provided in the first aspect above.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, which can be called by a processor to execute the interface display method provided in the first aspect above.

[0008] The solution provided in this application acquires input prompt information, which prompts the intelligent assistant application to output corresponding content. The target content output by the intelligent assistant application based on the prompt information is displayed on the interface, and the paragraph content within the target content is an interactive interface element. Therefore, because the output of the intelligent assistant application is presented as interactive interface elements, the visual effect of the output result is improved, and the user's interactive needs for the output result are met, thus enhancing the user experience. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A flowchart illustrating an interface display method according to an embodiment of this application is shown.

[0011] Figure 2 A flowchart illustrating an interface display method according to another embodiment of this application is shown.

[0012] Figure 3 A schematic diagram of an interface provided in an embodiment of this application is shown.

[0013] Figure 4 A schematic diagram of an interface provided in an embodiment of this application is shown.

[0014] Figure 5 A schematic diagram of an interface provided in an embodiment of this application is shown.

[0015] Figure 6 A schematic diagram of an interface provided in an embodiment of this application is shown.

[0016] Figure 7 A schematic diagram of an interface provided in an embodiment of this application is shown.

[0017] Figure 8 A flowchart illustrating an interface display method according to yet another embodiment of this application is shown.

[0018] Figure 9 A flowchart illustrating an interface display method according to another embodiment of this application is shown.

[0019] Figure 10 A flowchart illustrating an interface display method according to yet another embodiment of this application is shown.

[0020] Figure 11A schematic diagram of an interface provided in an embodiment of this application is shown.

[0021] Figure 12 A schematic diagram of an interface provided in an embodiment of this application is shown.

[0022] Figure 13 A schematic diagram illustrating the principle of the interface display method provided in the embodiments of this application is shown.

[0023] Figure 14 A block diagram of an interface display device according to an embodiment of this application is shown.

[0024] Figure 15 This is a block diagram of an electronic device for performing the interface display method according to an embodiment of this application.

[0025] Figure 16 This is a storage unit in this application embodiment for storing or carrying program code that implements the interface display method according to this application embodiment. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0027] With the rapid development of AI technology, Large Language Models (LLMs) have gradually moved from theoretical research to large-scale applications, attracting widespread attention, especially as deep learning-based language models have demonstrated outstanding capabilities in tasks such as text generation, language understanding, and conversion. The application of large models is particularly prominent in the dialogue scenarios of intelligent assistants. Trained on large datasets, large models can generate highly coherent and natural dialogue content, significantly improving the user experience.

[0028] In dialogue scenarios, large language models are often used to implement AIGC (Artificial Intelligence Content Generation) in intelligent assistants, thereby meeting users' needs in daily life and work. AIGC is a technology that automatically generates content through artificial intelligence techniques such as deep learning algorithms. It can understand natural language instructions and quickly generate high-quality, diverse, and creative content based on user needs. When presenting AIGC-based generated results, the text results are usually displayed directly, which makes it difficult to provide users with an intuitive experience, affects the readability of the generated results, and results in a poor presentation effect.

[0029] To address the aforementioned problems, the inventors have proposed an interface display method, apparatus, electronic device, and storage medium as described in the embodiments of this application. By presenting paragraph content using interactive interface elements when displaying the output of a smart assistant application, the visual effect of the output results can be improved, and the user's interactive needs for the output results can be met, thereby enhancing the user experience. The specific interface display method will be described in detail in subsequent embodiments.

[0030] The interface display method provided in the embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0031] Please see Figure 1 , Figure 1 A flowchart illustrating an embodiment of the interface display method provided in this application is shown. In a specific embodiment, the interface display method is applied to, for example... Figure 14 The interface display device 600 and the electronic device 100 equipped with the interface display device 600 are shown. Figure 15 The following will use an electronic device as an example to illustrate the specific process of this embodiment. Of course, it is understood that the electronic device used in this embodiment can be a smartphone, tablet computer, smartwatch, e-reader, laptop computer, etc., and is not limited thereto. The following will focus on... Figure 1 The process shown will be described in detail, and the interface display method may specifically include the following steps:

[0032] Step S110: Obtain the input prompt information, which is used to prompt the smart assistant application to output the corresponding content.

[0033] The intelligent assistant application is an application that utilizes artificial intelligence technology to help users complete various tasks and provide necessary information and services. Users can ask questions to the intelligent assistant application through a dialogue interface to complete the tasks they require. The intelligent assistant application may deploy a large language model, which is an artificial intelligence technology based on deep learning. By training on massive amounts of text data, it learns the statistical rules and semantic relationships of language, thereby generating natural, fluent content that conforms to human language habits. In the embodiments of this application, the intelligent assistant application can call the large language model to output corresponding content based on the prompts input by the user.

[0034] Hints can be text or data specifically designed to guide a large language model in an intelligent assistant application to generate output of a particular type or style. They can be provided within the context of the large model (such as a deep learning model or a natural language processing model). Hints aim to activate the relevant knowledge and capabilities within the model, enabling it to respond or complete tasks in the expected manner. Hints are widely used in large language models, particularly in the field of Natural Language Processing (NLP).

[0035] In this embodiment, the electronic device can acquire input prompts to guide the smart assistant application to output content that satisfies the user's intent. The scenario in which the electronic device acquires the prompts for inputting into the smart assistant application is not limited; for example, it can be used in scenarios such as text generation, question-and-answer systems, translation, summary generation, and content search.

[0036] In some implementations, the interface currently displayed by the electronic device can be an application interface that can invoke a smart assistant application, and the application interface may include an input area for inputting prompt information. The electronic device can respond to input operations in the input area and obtain the above-mentioned prompt information input by the user.

[0037] In one possible implementation, the electronic device can respond to a text input operation in the input area by acquiring the text information entered by the user through a virtual keyboard or a physical keyboard as the above prompt information; or it can respond to a paste operation in the input area by acquiring the text information pasted into the input area as the above prompt information.

[0038] In one possible implementation, the electronic device can respond to a voice input operation in the input area, collect the user's voice input, perform voice recognition processing on the collected voice, and use the recognized text as the above prompt information.

[0039] Step S120: Display the target content output by the smart assistant application according to the prompt information on the interface, wherein the paragraph content in the target content is an interactive interface element.

[0040] In this embodiment, after receiving the above prompt information, the electronic device can respond to the prompt information and display the output result obtained by the smart assistant application based on the above prompt information on the interface. The output result can be generated by the smart assistant application using a large language model based on the above prompt information. Specifically, the target content output by the smart assistant application based on the prompt information can be obtained and displayed on the interface. When displaying the target content, the paragraph content within the target content is an interactive interface element. The interactive interface element can refer to interface components that users can operate on and trigger predefined actions. These operations can include clicking, hovering, dragging, inputting text, selecting options, etc.; interactive interface elements can include selectable text boxes, service cards, hyperlinks, buttons, etc. Since the paragraph content within the target content output by the smart assistant application is an interactive interface element when displaying the target content on the interface, compared to simply displaying text in related technologies, the visual effect of the displayed output result is improved. Furthermore, users can perform desired operations on the corresponding content in the output result, thereby satisfying the user's interactive needs.

[0041] In some implementations, when displaying the target content on the interface, at least a portion of the target content may be interactive interface elements. When displaying these paragraphs, the paragraph content can be converted into interactive interface elements.

[0042] In one possible implementation, corresponding interface components, such as text boxes, service cards, and buttons, can be displayed for each paragraph, and the paragraph content can be shown within these components. This allows users to directly see that the paragraph content is interactive, thereby improving the presentation of the content output by the smart assistant application.

[0043] In one possible implementation, specific words or phrases in the paragraph content can also be converted into hyperlinks. When a word that has been converted into a hyperlink is clicked, the user can jump to another page or another location in the target content in response to the click.

[0044] In one possible implementation, the displayed target content may include multimedia information, which may include at least one of images, audio, and video. The multimedia information may be generated by a large language model in the intelligent assistant application, or it may be determined based on the content output by the large language model, further by calling system resource data and at least one of third-party services. When the paragraph content includes multimedia information, a video player, audio playback control bar, image container, etc., may also be displayed within the displayed paragraph content in relation to the multimedia information.

[0045] Of course, when an electronic device displays the target content output by a smart assistant application on the interface, there are no restrictions on the specific interactive interface elements displayed for the paragraph content within the target content.

[0046] The interface display method provided in this application obtains input prompt information, which prompts the smart assistant application to output corresponding content. In response to the prompt information, the target content output by the smart assistant application according to the prompt information is displayed on the interface. The paragraph content in the target content is an interactive interface element. Therefore, since the paragraph content is presented as interactive interface elements when presenting the output results of the smart assistant application, the visual effect of the output results can be improved. It can also make up for the lack of interactive elements in the display of the output results of smart assistant applications in related technologies, making the presented output results easier to read, easier to see, and easier to operate. Especially when dealing with complex user needs (such as travel planning, activity arrangement, etc.), it can better meet the user's interactive needs for the output results and improve the user experience.

[0047] Please see Figure 2 , Figure 2 A flowchart illustrating another embodiment of the interface display method provided in this application is shown. This interface display method is applied to the aforementioned electronic device, and will be discussed below. Figure 2 The process shown will be described in detail, and the interface display method may specifically include the following steps:

[0048] Step S210: Obtain the input prompt information, which is used to prompt the smart assistant application to output the corresponding content.

[0049] Step S220: Display the target content output by the smart assistant application according to the prompt information on the interface, wherein the paragraph content in the target content is an interactive interface element.

[0050] In the embodiments of this application, steps S210 and S220 can be referred to the contents of other embodiments, and will not be repeated here.

[0051] Step S230: If an operation is received targeting the target paragraph content in the target content, at least one content operation control corresponding to the target paragraph content is displayed on the interface.

[0052] In this embodiment, after the electronic device displays the target content output by the smart assistant application on the interface, since the paragraph content within the target content is an interactive interface element, the electronic device can detect operations on the interface to detect user interactions with the interface elements corresponding to the paragraph content. Upon receiving an operation on the target paragraph content, at least one content operation control corresponding to the target paragraph content can be displayed on the interface to meet the user's processing needs for the target paragraph content. The operation on the target paragraph content can be a click operation, a press operation, etc., and the specific operation type is not limited.

[0053] In some implementations, when an electronic device receives an operation on the target paragraph content, the content operation controls displayed on the interface may include at least one of the following: a control for triggering the regeneration of the paragraph content, a control for copying the paragraph content, a control for selecting text within the paragraph content, a control for sharing the paragraph content, a control for collapsing or expanding the paragraph content, a radio button for selecting the paragraph content, a checkbox for selecting the paragraph content, and a tab for switching between displaying different paragraph content. For example, please refer to... Figure 3 and Figure 4 , Figure 3 The interface A1 shown displays the output of the smart assistant application; after detecting an operation on the paragraph content, such as... Figure 4 As shown, interface A1 can display a regenerate control A2, a copy content control A3, a select text control A4, and a share control A5. The regenerate control A2 triggers the regeneration of paragraph content, the copy content control A3 triggers the copying of paragraph content, the select text control A4 triggers the selection of text within the paragraph content, and the share control A5 triggers the sharing of the paragraph content. Of course, the content manipulation controls displayed on the interface are not limited to these; for example, they could also include a save control for saving paragraph content.

[0054] In one possible implementation, when an electronic device receives an operation targeting a target paragraph, and displays the corresponding operation controls on the interface, it can display operation controls matching the content type of the target paragraph. This ensures that the displayed operation controls match the content type of the paragraph being operated on, making it easier for the user to select the desired operation controls and facilitating the user's manipulation of the content output by the smart assistant application. The content type corresponding to the target paragraph can refer to all content types included in the target paragraph, such as text, images, audio, and video. For example, for paragraphs containing only text, controls for copying and sharing the paragraph can be displayed; for paragraphs including images in addition to text, controls for saving and editing images can be displayed; and for paragraphs including videos in addition to text, controls for playing and downloading videos can be displayed.

[0055] In one possible implementation, when an electronic device receives an operation targeting a paragraph, it can display operation controls on the interface that match the content characteristics of the target paragraph. Paragraph content characteristics can be features extracted from the paragraph that reflect its semantic, functional, or structural attributes. Understandably, different content characteristics may lead to different user operations on the paragraph content. Therefore, displaying operation controls based on the paragraph's content characteristics allows users to quickly select the desired operation controls, facilitating their manipulation of the output content.

[0056] In one possible implementation, when the electronic device receives an operation on the target paragraph content, it can display the above-mentioned operation controls on the interface, and at the same time, determine the user's intent based on the above-mentioned prompt information input by the user. Based on the user's intent, the usage scenario of the smart assistant application can be determined, such as scheduling, learning, travel, activity arrangement, or cooking. According to the determined usage scenario, the corresponding content operation controls can be displayed on the interface. Understandably, the user's required operations on the content output by the smart assistant application differ in different usage scenarios. Therefore, upon detecting a user's operation on the paragraph content, displaying the content operation controls corresponding to the usage scenario allows the user to quickly select the required operation controls, facilitating the user's operation on the output content.

[0057] Of course, in the above embodiments, the electronic device can also display the corresponding content operation controls by combining the content type and content characteristics of the target paragraph content and at least two of the above usage scenarios.

[0058] In some implementations, when an electronic device detects an operation on the target paragraph content and displays content manipulation controls on the interface, if the number of content manipulation controls exceeds the target number, it can further sort the content manipulation controls based on the number of times the user has historically used different content manipulation controls within the target time period prior to the current time, obtaining a sorting result. Content manipulation controls with more historical usage times will appear higher in the sorting result. Then, N content manipulation controls are selected from the sorting result for display, along with controls that trigger the display of more content manipulation controls. This allows the user to trigger the display of more content manipulation controls by operating on those controls when needed.

[0059] Step S240: If an operation is received for the content operation control, perform the target processing corresponding to the content operation control on the target paragraph content.

[0060] In this embodiment, after the electronic device displays the content manipulation controls corresponding to the target paragraph content on the interface, it can detect operations on the interface. Upon receiving an operation on any content manipulation control, it can perform target processing on the target paragraph content corresponding to that content manipulation control. The target processing performed on the target paragraph content can be determined by the function of the manipulated content manipulation control.

[0061] In some implementations, target processing includes: regenerating paragraph content for the target paragraph content via the smart assistant application, copying the target paragraph content, selecting the target paragraph content, or sharing the target paragraph content.

[0062] In one possible implementation, the above-mentioned operation controls may include a first control for triggering the regeneration of paragraph content. Upon receiving an operation on this first control, such as a click or press, the electronic device can respond to the detected operation and regenerate the paragraph content for the target paragraph content via a smart assistant application. For example, in a scheduling scenario, the target paragraph content is the planning content for a target date generated by the smart assistant application. Upon detecting an operation on the control used to trigger the smart assistant application to regenerate the paragraph content, the planning content for that target date can be regenerated via the smart assistant application. After obtaining the content regenerated by the smart assistant application for the target paragraph content, the original target paragraph content can be replaced. This allows users to regenerate any unsatisfactory paragraph content directly within the current interface, enabling partial content regeneration. Users can clearly define the scope of changes needed through interface operations, making precise local modifications and presenting them in a clear and concise manner, avoiding information redundancy, improving information delivery efficiency, shortening conversation length, and making reading and contextual navigation more convenient for users. Moreover, processing only content that users explicitly request and that truly needs modification avoids unnecessary system overhead, saves computing resources, reduces time latency, and improves system response speed. Local modifications are integrated into the conversation in a reasonable way, maintaining a stable conversation view, allowing users to easily form a coherent understanding when reviewing the dialogue history, reducing cognitive burden, and improving dialogue efficiency.

[0063] For example, please see Figure 4 ,exist Figure 4 The interface A1 shown includes a regeneration control A2 for triggering the regeneration of paragraph content. Upon receiving an action on the regeneration control A2, the smart assistant application can regenerate the paragraph content for "First Day Morning." Please refer to [link / reference needed]. Figure 5 , Figure 6 and Figure 7 This allows the regenerated paragraph content to be gradually generated at the location of the paragraph content of "First Day Morning", thereby achieving the regeneration and replacement of the paragraph content of "First Day Morning".

[0064] Optionally, when the electronic device receives an operation on the first control mentioned above, the target paragraph content displayed on the interface can be updated to regenerated content. This regenerated content is generated by the intelligent assistant application by calling a large language model and based on the original content of the target paragraph content and context information. The original content of the target paragraph content can be the original content of the target paragraph content output by the intelligent assistant application based on the above prompt information; the context information of the target paragraph content can include the preceding and following text, the topic, and the purpose of the paragraph content. The original content of the target paragraph content and the context information can be input into the large language model deployed in the intelligent assistant application, and prompt words can be provided to instruct the large language model to regenerate the paragraph content. This allows for the generation of regenerated paragraph content for the target paragraph content, replacing the original target content displayed on the interface with the regenerated content.

[0065] In the above implementation, when regenerating paragraph content through the large language model in the intelligent assistant application, prompt information for driving the large language model to regenerate paragraph content can be regenerated based on the original content of the target paragraph content and context information. Then, the regenerated prompt information is input into the large language model to obtain the regenerated paragraph content output by the large language model.

[0066] Optionally, after receiving the operation on the first control, the electronic device can determine the interface range and user intent of the target paragraph content based on the input prompts. Then, based on the interface range, it can determine the original content of the target paragraph from the output of the smart assistant application and determine the range of content to be regenerated. Next, based on the user intent, the original content, and the range of content, it can regenerate the paragraph content using the smart assistant application. Finally, it can maintain the view position corresponding to the target paragraph content and update the regenerated paragraph content in the original view position, thus replacing the original paragraph content. This ensures that the foreground presentation strategy of the smart assistant application's output content does not disrupt the continuity and stability of single-turn replies and the overall conversation content during partial regeneration, allowing it to naturally integrate into the existing interface framework and conversation view, thereby improving the user's sensory experience and reading efficiency.

[0067] Optionally, when regenerating paragraph content for the target paragraph using a smart assistant application, additional input prompts can be obtained, and the paragraph content can be regenerated by combining the original content and context information of the target paragraph. For example, upon receiving an operation on the first control, an input box for prompts can be displayed. The electronic device can obtain the additional input prompts and then combine them to regenerate the paragraph content, thereby improving the accuracy of the regenerated paragraph content.

[0068] In one possible implementation, the above content operation controls may include a second control for triggering the copying of paragraph content, for example, see [link to relevant documentation]. Figure 4 ,exist Figure 4 The interface A1 shown contains a copy control A3; when the electronic device detects an operation on this control, it can respond to the detected operation and copy the target paragraph content, allowing the user to paste the target paragraph content into other interfaces.

[0069] In one possible implementation, the above-mentioned operation controls may include a third control for triggering the selection of paragraph content. Upon receiving an operation on this control, the electronic device can respond to the detected operation by selecting the target paragraph content, allowing the user to perform other operations on the selected target paragraph content.

[0070] In one possible implementation, the above content operation controls may include a fourth control for triggering the selection of text within the paragraph content; for example, please refer to [link to relevant documentation]. Figure 4 ,exist Figure 4 The interface A1 shown displays a text selection control A4; when the electronic device receives an operation on this control, it can respond to the detected operation and select text content from the target paragraph content so that the user can perform other operations on the selected text content.

[0071] In one possible implementation, the above content operation controls may include a fifth control for triggering the sharing of paragraph content, for example, see [link to relevant documentation]. Figure 4 ,exist Figure 4 The interface A1 shown displays a sharing control A5. Upon detecting an operation on this control, the electronic device can, in response to the detected operation, share the target paragraph content to a target application. Specifically, after detecting an operation on the control, the application identifier of at least one application to which the content is to be shared can be displayed; upon detecting a selection operation on the target application identifier, the target paragraph content can be shared to the application corresponding to the target application identifier.

[0072] Of course, the target processing of the target paragraph content is not limited to the above implementation methods, and may also include other processing. The specific processing of the target paragraph content can be determined according to the specific content operation controls being operated on.

[0073] In some implementations, when the electronic device displays the above-mentioned target content on the interface, it may display service cards, such as service cards inserted within paragraph content. The displayed service cards may be determined by calling system resource data and at least one third-party service. Upon detecting an operation on a service card, the electronic device may expand and display the service card in response to the detected operation, or display the card content as a floating window, allowing the user to view service information or perform other operations on the current interface. For example, in a travel planning scenario, service cards for third-party services such as "book a hotel," "book a flight," and "purchase tickets" may be inserted into the paragraph content. The electronic device may expand and display the service card in response to an operation on the service card, allowing the user to perform operations such as hotel booking, flight booking, and ticket purchase on the current interface.

[0074] The interface display method provided in this application presents paragraph content using interactive interface elements when displaying the output results of a smart assistant application. This improves the visual effect of the output results and better meets the user's interactive needs for the output results, thus enhancing the user experience. Furthermore, it can display corresponding content operation controls based on the user's operations on the paragraph content, allowing the user to process the paragraph content as needed, thereby satisfying the user's processing needs for the output results of the smart assistant application.

[0075] Please see Figure 8 , Figure 8 A flowchart illustrating another embodiment of the interface display method provided in this application is shown. This interface display method is applied to the aforementioned electronic device, and will be discussed below. Figure 8 The process shown will be described in detail, and the interface display method may specifically include the following steps:

[0076] Step S310: Obtain the input prompt information, which is used to prompt the smart assistant application to output the corresponding content.

[0077] Step S320: Display the target content output by the smart assistant application according to the prompt information on the interface, wherein the paragraph content in the target content is an interactive interface element.

[0078] In the embodiments of this application, steps S310 and S320 can be referred to the contents of other embodiments, and will not be repeated here.

[0079] Step S330: If a collapse operation is received for the target paragraph content in the target content, at least a portion of the target paragraph content displayed in the interface is hidden.

[0080] In this embodiment, after the electronic device displays the target content output by the smart assistant application on the interface, the electronic device can detect operations on the interface to detect user interaction with interface elements corresponding to the paragraph content. Upon receiving a collapse operation for the target paragraph content within the target content, at least a portion of the target paragraph content displayed on the interface can be hidden. This allows the user to view content other than the hidden content without needing to view certain information.

[0081] In some implementations, upon receiving a collapse operation targeting a specific paragraph within the target content, a portion of the target paragraph content may be hidden. Optionally, the hidden portion may be multimedia information within the target paragraph content; that is, images, videos, or other content that occupies a significant amount of display space within the target paragraph content may be hidden, allowing more text content to be displayed on the interface.

[0082] In some implementations, when a collapse operation is received for the target paragraph content within the target content, it can be understood as hiding all the content in the target paragraph content, or it can be understood as folding or collapsing the target paragraph content so that other paragraph content that has not been displayed can be shown on the interface.

[0083] In some implementations, the electronic device may display collapse controls corresponding to each paragraph in the interface; upon receiving an operation on the collapse control corresponding to the target paragraph, it may hide at least a portion of the target paragraph in response to the detected operation.

[0084] In one possible implementation, the target content displayed by the electronic device in the interface may include a title, and a collapse control is displayed at the location of the title; the electronic device may, in response to an operation of the collapse control at the location of the title, hide at least part of the content of the paragraphs under the title.

[0085] In some implementations, the electronic device may also, upon receiving a target touch operation on the target paragraph content, hide at least a portion of the target paragraph content in response to the received target touch operation. The target touch operation may be a press operation with press parameters satisfying target press conditions, a drag operation with drag parameters satisfying target drag conditions, etc., and the specific operation type is not limited. Target press conditions may include at least one of the following: press duration greater than target duration, press area greater than target area, and press pressure value greater than target pressure. Drag parameters may include the drag endpoint being located in the target area, or the drag distance being greater than the target drag distance.

[0086] In some implementations, the target paragraph content may include multiple paragraph contents, meaning that the electronic device may hide the multiple paragraph contents in response to a collapse operation on the multiple paragraph contents.

[0087] In one possible implementation, the target content displayed on the interface by the electronic device may include a title summarizing multiple paragraphs, and a collapse control is displayed at the location of the title. The electronic device can hide the multiple paragraphs in response to an operation on the collapse control. For example, in a travel planning scenario, the planning information for the same date output by a smart assistant application may include planning information for different time periods, with each time period corresponding to different paragraphs. The electronic device can display the title information for that date on the interface, and a collapse control is displayed at the location of the title information. Upon detecting an operation on the collapse control, the planning information for the different time periods corresponding to that date (i.e., the corresponding multiple paragraphs) can be hidden.

[0088] Step S340: If an expand operation is received for the target paragraph content in the target content, the hidden content in the target paragraph content is displayed on the interface.

[0089] In this embodiment, after the electronic device displays the target content output by the smart assistant application on the interface, the electronic device can detect operations on the interface to detect user interactions with interface elements corresponding to the paragraph content. Upon receiving an expand operation for the target paragraph content within the target content, the hidden content within the target paragraph content can be displayed on the interface. It is understood that when the electronic device displays the target content on the interface, considering that some paragraphs may contain a lot of content, at least a portion of the paragraph content may be hidden, or the electronic device may hide at least a portion of some paragraph content based on user operations. When the user needs to view this hidden content, they can expand the corresponding paragraph content to allow the user to view the hidden content.

[0090] In some implementations, the electronic device can display expansion controls corresponding to each paragraph in the interface; upon receiving an operation on the expansion control corresponding to the target paragraph, it can respond to the received operation by displaying the hidden content in the target paragraph in the interface.

[0091] In one possible implementation, the target content displayed by the electronic device on the interface may include a title, and an expand control is displayed at the location of the title; the electronic device may, in response to the operation of the expand control at the location of the title, display the hidden content of the target paragraph content under the title on the interface.

[0092] It should be noted that the above-mentioned expand control can be the same control as the collapse control mentioned in step S330. That is to say, this control can both trigger the hiding of paragraph content and trigger the display of the hidden content within the paragraph. Specifically, if at least part of the paragraph content is not hidden, and an operation on this control is received, then at least part of the paragraph content can be hidden; if at least part of the paragraph content is hidden, and an operation on this control is received, then the hidden content within the paragraph content can be displayed on the interface.

[0093] In some implementations, the electronic device may also, upon receiving a target touch operation on the target paragraph content, display the hidden content within the target paragraph content in response to the received target touch operation. The target touch operation may be a press operation with press parameters satisfying target press conditions, a drag operation with drag parameters satisfying target drag conditions, etc., and the specific operation type is not limited. Target press conditions may include at least one of the following: press duration greater than target duration, press area greater than target area, and press pressure value greater than target pressure. Drag parameters may include the drag endpoint being located in the target area, or the drag distance being greater than the target drag distance.

[0094] In some implementations, the target paragraph content may include multiple paragraph contents. That is, the electronic device can display the hidden multiple paragraph contents in the interface according to the expansion operation of the multiple paragraph contents.

[0095] In one possible implementation, the target content displayed by the electronic device on the interface may include a title summarizing multiple paragraphs, and an expand control is displayed at the location of the title; the electronic device may display the hidden multiple paragraphs on the interface upon receiving an operation on the expand control.

[0096] The interface display method provided in this application presents paragraph content using interactive interface elements when displaying the output results of a smart assistant application. This improves the visual effect of the output results and better meets the user's interactive needs for the output results, thus enhancing the user experience. Furthermore, the paragraph content can be hidden based on the collapse operation or displayed based on the expansion operation, thereby better meeting the user's viewing needs for the output results of the smart assistant application.

[0097] Please see Figure 9 , Figure 9 A flowchart illustrating an interface display method provided in another embodiment of this application is shown. This interface display method is applied to the aforementioned electronic device, and will be discussed below. Figure 9 The process shown will be described in detail, and the interface display method may specifically include the following steps:

[0098] Step S410: Obtain the input prompt information, which is used to prompt the smart assistant application to output the corresponding content.

[0099] In this embodiment, step S410 can be referred to the content of the foregoing embodiments, and will not be repeated here.

[0100] Step S420: In response to the prompt information, obtain the target content output by the smart assistant application according to the prompt information and the tags embedded in the target content, wherein the tags are used to indicate the attributes of the paragraph content corresponding to the tags.

[0101] In this embodiment, after receiving the above prompt information, the electronic device can respond to the prompt information by having the intelligent assistant application call a large language model to output corresponding content based on the prompt information. The output of the large language model can include the target content and embedded tags within it. The embedded tags can indicate the attributes of the corresponding paragraph content. The attributes of the paragraph content can include its information hierarchy within the target content. The target content output by the large language model can include multiple information hierarchies from high to low. For example, in a schedule planning scenario, it can include a main title for a day's schedule, subtitles for different time periods, and the planning content for each time period. The information hierarchy of the main title, subtitles, and planning content decreases sequentially.

[0102] In some implementations, at least one of the following can be used to fine-tune, adapt, and engineer the large language model deployed in the smart assistant application: the large language model can output the target content based on the prompt information while embedding the above tags in the large language model.

[0103] Fine-tuning refers to further training a pre-trained large language model on a specific task or dataset to optimize its performance on that task. Fine-tuning, on the other hand, involves using a small amount of labeled data specific to that task to adjust the model's parameters, making it better suited to that task. This method can significantly improve the model's performance on new tasks while reducing the computational resources and time required to train the model from scratch. In the above implementation, the large language model can be trained using embedded labeled sample data, enabling it to embed tags into its output.

[0104] Adaptation techniques can include model pruning, quantization, knowledge distillation, etc. The purpose of adaptation techniques is to adjust the behavior of the model to meet specific output requirements. In the above implementation, the behavior of the large language model can be adjusted so that the large language model can embed the above tags in the output content.

[0105] Cue word engineering refers to guiding a model to generate more desirable output by using carefully designed cue words or templates when providing input. This approach is particularly suitable for natural language processing tasks where the model's output largely depends on the context and format of the input text. By cleverly designing cue words, the model's ability to generate more accurate, relevant, or format-compliant output can be more effectively stimulated. In the above implementation, cue words can be used to prompt the large language model to embed these markers in the output content.

[0106] For example, in a travel planning scenario, the content output by the large language model is as follows:

[0107] “ <title> Berlin Arts and Culture Tour< / title>

[0108] <intro>Below is a detailed itinerary for a two-day art and culture tour of Berlin, with a special focus on art and cultural experiences.

[0109] <day>Day 1 - Leading the Way in Modern Art and Design

[0110] <section>Morning Attraction A

[0111] [FETCH_poi]Spot A”

[0112] above" <title>”、"< / title> <intro> ”、" <day> ”、" <section>"" indicates the information hierarchy of the content it marks, while "[FETCH_poi]" indicates the task of querying information for attraction A.

[0113] Step S430: Display the target content in the interface according to the marker, wherein the paragraph content in the target content is an interactive interface element.

[0114] In this embodiment, after obtaining the output target content and the tags embedded in the target content, the target content can be displayed on the interface according to the tags. Since the tags can reflect the attributes (information hierarchy) of the paragraph content, displaying the target content according to the tags can make the information hierarchy of the target content displayed on the interface clearer.

[0115] In some implementations, when displaying the target content on the interface according to the markers, the corresponding interface component can be displayed on the interface according to the markers, and the content corresponding to the markers in the target content can be displayed in the interface component. That is, the electronic device can determine the interface component corresponding to each paragraph content based on the above markers, so that each paragraph content can be displayed in the interface component corresponding to each paragraph content.

[0116] In one possible implementation, when the corresponding interface component is displayed in the interface according to the tag, the attribute corresponding to the tag can be parsed. For example, the tags output by the smart assistant application can be monitored by a real-time tag monitor for monitoring tags, and the attribute corresponding to the tag can be parsed. Then, the interface component that matches the parsed attribute is displayed in the interface, and the paragraph content in the target content that corresponds to the tag (i.e., the paragraph content marked or annotated by the tag) is displayed in the interface component.

[0117] In some implementations, when an electronic device displays target content on the interface based on markers in the target content, it can do so by using the markers, layout rules, style sheets, and visual elements corresponding to the intelligent assistant application's understanding of the intent behind the prompts. Understandably, the visual effects perceived by users for the same layout rules, style sheets, and visual elements differ depending on the usage scenario and needs (e.g., complex planning for different events such as travel, parties, and team building activities). Therefore, the target content can be displayed on the interface based on the layout rules, style sheets, and visual elements corresponding to the markers and intent understanding results. A style sheet is a set of rules used to define the appearance and format of an interface; visual elements refer to the basic units that constitute visual objects. In interface design, visual elements typically include lines, shapes, colors, textures, patterns, fonts, and images. Displaying target content according to the above layout rules, style sheets, and visual elements can be understood as matching the content to a generative interface framework. Therefore, it can automatically generate various interface elements and layouts based on user needs and context, offering high flexibility and personalization, thus ensuring a higher degree of fit between the displayed content and the usage scenario and needs.

[0118] In one possible implementation, when displaying the target content on the interface, the interface component corresponding to the mark can be determined from the visual elements corresponding to the intent understanding result, and the interface component can be displayed according to the layout rules and style sheets above. Then, the content corresponding to the mark can be displayed in the interface component. In addition, when displaying the interface, other content besides the target content can also be displayed according to the layout rules, style sheets and visual elements above.

[0119] In some implementations, the above markers can also be used to indicate processing tasks for paragraph content. In this case, the markers can be understood as embedded grammatical fragments containing tasks for processing the paragraph content. When the target content is displayed on the interface, if any marker for paragraph content indicates a processing task for that paragraph content, then the processing task indicated by the marker can be executed for the content corresponding to the marker based on at least one of the system resource data and the target service interface. Then, based on the content type corresponding to the processing task, an interface component corresponding to the content type is displayed on the interface, and the processing result of the processing task is displayed in the interface component.

[0120] In one possible implementation, before executing the processing task indicated by the tag for the content corresponding to the tag, the processing task indicated by the tag can be parsed and the content type corresponding to the processing task can be determined.

[0121] For example, in a travel planning scenario, the intelligent assistant application outputs content including attraction A, and embeds text instructions for querying information for attraction A. The task of querying attraction A can then be parsed. After parsing the task of querying attraction A, at least one of system resource data and third-party service interfaces can be called to query information about attraction A, and the content type corresponding to the queried information can be determined simultaneously. When displaying the content on the interface, the interface assembly engine can use the intent understanding results determined by the large speech model to match a suitable generative interface framework (layout rules, style sheets, and visual elements) from the resource library, call the interface components corresponding to the above content types, assemble the interface, and present the queried information in the interface components. For example, a service card can be called, and the queried information can be presented in the service card.

[0122] Through the above implementation methods, the limitation of information mainly relying on intelligent assistant applications can be broken, forming a chain that connects multiple service resources. By mobilizing system resource data and third-party service interfaces, a wider range of information can be obtained, providing users with real-time and personalized content, making the generated content more accurate and comprehensive. Furthermore, it can solve the problem of potential gaps in subsequent services related to the output content of large language modes, evolving the output content from readable to actionable, allowing users to conveniently achieve their intentions based on the generated content, such as completing business processes like hotel reservations and ticket purchases in AI dialogue scenarios.

[0123] The interface display method provided in this application presents paragraph content using interactive interface elements when displaying the output of a smart assistant application. This improves the visual effect of the output and better meets the user's interactive needs, enhancing the user experience. Furthermore, the content is displayed based on the tags embedded in the output by the large language, making the information hierarchy of the target content displayed on the interface clearer. In addition, this approach overcomes the shortcomings of limited media formats in related technologies, moving beyond simple text presentation to integrate diverse elements such as images, audio, and video, providing users with a more intuitive experience and greatly improving the user experience.

[0124] Please see Figure 10 , Figure 10 A flowchart illustrating another embodiment of the interface display method provided in this application is shown. This interface display method is applied to the aforementioned electronic device, and will be discussed below. Figure 10 The process shown will be described in detail, and the interface display method may specifically include the following steps:

[0125] Step S510: Obtain the input prompt information, which is used to prompt the smart assistant application to output the corresponding content.

[0126] In this embodiment, step S510 can be referred to the content of the foregoing embodiments, and will not be repeated here.

[0127] Step S520: Gradually display the target content that the smart assistant application streams according to the prompt information on the interface, where the paragraph content in the target content is an interactive interface element.

[0128] In this embodiment, when the smart assistant application outputs target content according to the prompts, the smart assistant application can output the target content in a streaming manner, that is, it continuously outputs the target content. Correspondingly, when displaying the results output by the smart assistant application on the interface, the content output by the smart assistant application can be displayed gradually, that is, the content is generated and displayed on the interface in real time in the form of a continuous stream, thereby achieving the effect of streaming on-screen display and further improving the presentation effect of the results output by the smart assistant application.

[0129] For example, please refer to Figure 3 , Figure 11 and Figure 12 In the context of travel planning, the following can be displayed sequentially. Figure 11 , Figure 12 and Figure 3 The interface shown continuously displays the content output by the smart assistant application, achieving a streaming effect.

[0130] Next, we will proceed through... Figure 13 The interface display method provided in the foregoing embodiments will be described.

[0131] Please see Figure 13 In implementing the interface display method provided in this application, a format adapter, a real-time tag detector, a resource scheduling service, and an interface assembly engine can be used to achieve the streaming integration and graphical representation of content, multimedia information, and service resources generated by the large language model in the intelligent assistant application. Specifically, the format adapter enables the large language model to embed tags and grammatical fragments into the output content. After the system service provides the corresponding prompts to the large language model, the large language model can process the prompts and begin outputting results. During the continuous output process, new elements or actions can be declared in multiple rounds. The declared elements are the attributes of the content indicated by the embedded tags, and the declared actions are the processing tasks performed on the paragraph content indicated by the embedded tags. The declared elements or actions are then output. The real-time tag detector, upon detecting a declaration type (i.e., tags embedded in the output content), if the declaration is an element, can notify the interface assembly engine to call the corresponding interface component (i.e., call the internal...) The attributes of the content correspond to the interface components, and the corresponding content of the tags can be updated in the interface components; if an action is declared, then the tag real-time monitor can listen to the action, that is, determine the processing task for the paragraph content corresponding to the tag, and send the determined action content (processing task) to the resource scheduling service; the resource scheduling service can obtain third-party media and service resources (that is, the processing result of the paragraph content corresponding to the tag by calling system resource data and third-party service interfaces) and send it back to the interface assembly engine; the interface assembly engine records the returned content into the corresponding interface components. After the content in the interface framework and interface components is recorded, all the content output by the smart assistant application is displayed in the interface.

[0132] Please see Figure 14 This diagram illustrates a structural block diagram of an interface display device 600 provided in an embodiment of this application. The interface display device 600 is applied to the aforementioned electronic device and includes an information acquisition module 610 and a content display module 620. The information acquisition module 610 acquires input prompt information, which prompts a smart assistant application to output corresponding content. The content display module 620 displays the target content output by the smart assistant application based on the prompt information on the interface, where paragraph content within the target content is an interactive interface element.

[0133] In some embodiments, the interface display device 600 may further include a control display module and a content processing module. The control display module is configured to, after displaying the target content output by the smart assistant application according to the prompt information on the interface, if an operation is received on a target paragraph within the target content, display at least one content operation control corresponding to the target paragraph content on the interface; the content processing module is configured to, if an operation is received on the content operation control, perform the target processing corresponding to the content operation control on the target paragraph content.

[0134] In one possible implementation, the target processing includes: generating the target paragraph content through the output of the smart assistant application, copying the target paragraph content, selecting the target paragraph content, or sharing the target paragraph content.

[0135] Optionally, the content manipulation control includes a first control for triggering the regeneration of paragraph content. The content processing module can be specifically used to: if an operation is received on the first control, update the target paragraph content displayed on the interface to the regenerated paragraph content. The regenerated paragraph content is generated by the smart assistant application based on the original content of the target paragraph content and context information.

[0136] In some embodiments, the interface display device 600 may further include a content hiding module and a content expanding module. The content hiding module is used to hide at least a portion of the target paragraph content displayed on the interface after the smart assistant application displays the target content output according to the prompt information, if a collapse operation is received for the target paragraph content within the target content. The content expanding module is used to display the hidden content within the target paragraph content on the interface if an expand operation is received for the target paragraph content within the target content.

[0137] In some implementations, the content display module 620 may be specifically used to: obtain the target content output by the smart assistant application according to the prompt information and the markers embedded in the target content, wherein the markers are used to indicate the attributes of the paragraph content corresponding to the markers; and display the target content in the interface according to the markers.

[0138] In one possible implementation, the content display module 620 may also be specifically used to: display a corresponding interface component in the interface according to the mark, and display the content in the target content that corresponds to the mark in the interface component.

[0139] Optionally, the content display module 620 can also be used to parse the attribute corresponding to the mark; display an interface component that matches the attribute in the interface, and display the paragraph content in the target content that corresponds to the mark in the interface component.

[0140] Optionally, the content display module 620 can also be used to display interface components corresponding to the mark in the interface according to the layout rules, style sheets and visual elements corresponding to the intent understanding result of the smart assistant application for the prompt information, and to display paragraph content in the target content corresponding to the mark in the interface components.

[0141] In one possible implementation, the content display module 620 may also be specifically used to: perform the processing task indicated by the tag on the content corresponding to the tag according to at least one of system resource data and target service interface; display an interface component corresponding to the content type in the interface according to the content type corresponding to the processing task, and display the processing result of the processing task in the interface component.

[0142] Optionally, the content display module 620 may also be used to parse the processing task indicated by the mark and determine the content type corresponding to the processing task before executing the processing task indicated by the mark for the content corresponding to the mark.

[0143] In some implementations, the content display module 620 may be specifically used to: gradually display the target content streamed by the smart assistant application according to the prompt information in the interface.

[0144] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0145] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0146] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0147] In summary, the solution provided in this application acquires input prompt information, which prompts the intelligent assistant application to output corresponding content. The target content output by the intelligent assistant application based on the prompt information is then displayed on the interface, with paragraphs within the target content being interactive interface elements. Therefore, because the output of the intelligent assistant application is presented as interactive interface elements, the visual effect of the output is improved, and the user's interactive needs for the output are met, thus enhancing the user experience.

[0148] Please refer to Figure 15 This document illustrates a structural block diagram of an electronic device according to an embodiment of this application. The electronic device 100 can be a smartphone, tablet computer, smartwatch, e-reader, laptop computer, or other electronic device capable of running applications. The electronic device 100 in this application may include one or more of the following components: a processor 110, a memory 120, a display screen 130, and one or more applications. The one or more applications may be stored in the memory 120 and configured to be executed by one or more processors 110. The one or more applications are configured to perform the methods described in the foregoing method embodiments.

[0149] The processor 110 uses various interfaces and lines to connect various parts within the electronic device 100. It executes various functions of the electronic device 100 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 120, and calling data stored in the memory 120.

[0150] The memory 120 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the various method embodiments described above, etc.

[0151] The display screen 130 is a display component used for displaying images and is usually located on the front panel of the electronic device 100.

[0152] Please refer to Figure 16 This diagram illustrates a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. The computer-readable medium 800 stores program code that can be called by a processor to execute the methods described in the above method embodiments.

[0153] The computer-readable storage medium 800 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 800 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 800 has storage space for program code 810 that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code 810 may be compressed, for example, in a suitable form.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.< / section> < / day> < / intro> < / section> < / day> < / intro>

Claims

1. A method for displaying an interface, characterized in that, The method includes: Obtain input prompt information, which is used to prompt the smart assistant application to output corresponding content; The interface displays the target content output by the smart assistant application based on the prompt information, and the paragraph content in the target content is an interactive interface element.

2. The method according to claim 1, characterized in that, After displaying the target content output by the smart assistant application in the interface according to the prompt information, the method further includes: If an operation is received targeting a paragraph within the target content, at least one content operation control corresponding to the target paragraph content is displayed on the interface; If an operation is received for the content manipulation control, the target paragraph content is processed according to the content manipulation control.

3. The method according to claim 2, characterized in that, The target processing includes: regenerating paragraph content for the target paragraph content through the smart assistant application, copying the target paragraph content, selecting the target paragraph content, or sharing the target paragraph content.

4. The method according to claim 3, characterized in that, The content manipulation control includes a first control for triggering the regeneration of paragraph content. If an operation is received on the content manipulation control, the target paragraph content is subjected to the target processing corresponding to the content manipulation control, including: If an operation is received for the first control, the target paragraph content displayed on the interface is updated to the regenerated paragraph content. The regenerated paragraph content is generated by the smart assistant application based on the original content of the target paragraph content and context information.

5. The method according to claim 1, characterized in that, After displaying the target content output by the smart assistant application in the interface according to the prompt information, the method further includes: If a collapse operation is received targeting a specific paragraph within the target content, at least a portion of the target paragraph content displayed in the interface is hidden; or If an operation to expand the target paragraph content is received, the hidden content within the target paragraph content will be displayed on the interface.

6. The method according to claim 1, characterized in that, Displaying the target content output by the smart assistant application based on the prompt information in the interface includes: The target content output by the smart assistant application based on the prompt information and the tags embedded in the target content are obtained, wherein the tags are used to indicate the attributes of the paragraph content corresponding to the tags; The target content is displayed in the interface according to the marked information.

7. The method according to claim 6, characterized in that, The step of displaying the target content in the interface according to the marker includes: The corresponding interface component is displayed in the interface according to the mark, and the content corresponding to the mark in the target content is displayed in the interface component.

8. The method according to claim 7, characterized in that, The step of displaying the corresponding interface component in the interface according to the mark, and displaying the content in the target content corresponding to the mark in the interface component, includes: Parse the attributes corresponding to the tag; Display interface components that match the attribute in the interface, and display the paragraph content in the target content that corresponds to the mark in the interface components.

9. The method according to claim 6, characterized in that, The step of displaying the target content in the interface according to the marker includes: Based on the markers, the layout rules, style sheets, and visual elements corresponding to the intelligent assistant application's understanding of the intent of the prompt information, the target content is displayed in the interface.

10. The method according to claim 6, characterized in that, The marker is also used to indicate a processing task for the paragraph content, and displaying the target content in the interface according to the marker includes: Based on system resource data and at least one of the target service interfaces, perform the processing task indicated by the tag for the content corresponding to the tag; Based on the content type corresponding to the processing task, display the interface component corresponding to the content type in the interface, and display the processing result of the processing task in the interface component.

11. The method according to claim 10, characterized in that, Before performing the processing task indicated by the tag on the content corresponding to the tag, the method further includes: The processing task indicated by the marker is parsed, and the content type corresponding to the processing task is determined.

12. The method according to any one of claims 1-11, characterized in that, Displaying the target content output by the smart assistant application based on the prompt information in the interface includes: The target content, which is streamed by the smart assistant application based on the prompts, is gradually displayed on the interface.

13. An interface display device, characterized in that, The device includes: an information acquisition module and a content display module, wherein... The information acquisition module is used to acquire input prompt information, which is used to prompt the smart assistant application to output corresponding content; The content display module is used to respond to the prompt information and display the target content output by the smart assistant application according to the prompt information on the interface. The paragraph content in the target content is an interactive interface element.

14. An electronic device, characterized in that, include: One or more processors; Memory; One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the method as described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1-12.

Images