Prompt information input method, device, equipment, storage medium and program product

Abstract

This application discloses a method, apparatus, device, storage medium, and program product for inputting prompt information. The method includes: displaying a target interface; responding to an information editing operation triggered in a prompt input area, displaying predicted prompt information in a predicted prompt display area based on the current information obtained from the information editing operation in the prompt input area. The predicted prompt information includes at least one element control corresponding to an information element, the element control being used to carry the element content of its corresponding information element and supporting adjustment of the element content of the information element; and responding to an adoption operation triggered for the predicted prompt information in the predicted prompt display area, displaying the predicted prompt information in the prompt input area. This method can automatically and efficiently generate high-quality prompt information based on user input. The AI ​​model then performs corresponding tasks based on this high-quality prompt information, which not only improves processing efficiency but also enhances the usability of the output processing results.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, storage medium, and program product for inputting prompt information. Background Technology

[0002] In artificial intelligence (AI) generation applications (such as AI software development platforms, AI dialogue sandboxes, AI content creation tools, etc.), the main form of product interaction is currently driven by inputting natural language prompts to drive the AI ​​model to produce results.

[0003] In related technologies, AI-generated applications typically provide a blank prompt input box, requiring users to manually enter prompts. However, user-input prompts are inefficient, and the quality of the input is difficult to control. For example, in many cases, user-input prompts are neither accurate nor comprehensive, which further reduces the processing efficiency of the AI ​​model and results in poor usability of the output. Summary of the Invention

[0004] This application provides a method, apparatus, device, storage medium, and program product for inputting prompt information, which can automatically and efficiently generate high-quality prompt information based on user input. The AI ​​model then performs corresponding tasks based on the high-quality prompt information, which not only improves processing efficiency but also enhances the usability of the output processing results.

[0005] The first aspect of this application provides a method for inputting prompt information, the method comprising:

[0006] Display a target interface, the target interface including a prompt input area for inputting prompt information;

[0007] In response to an information editing operation triggered in the prompt input area, a prediction prompt information is displayed in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area. The prediction prompt information includes at least one element control corresponding to an information element. The element control is used to carry the element content of the corresponding information element and supports adjusting the element content of the information element.

[0008] In response to an adoption operation triggered by the prediction prompt information in the prediction prompt display area, the prediction prompt information is displayed in the prompt input area.

[0009] Optionally, the method further includes:

[0010] If a content adjustment operation has been triggered by the element control in the prediction prompt information, in response to an adjustment reversal operation triggered by the prediction prompt display area, the prediction prompt information prior to triggering the content adjustment operation is displayed in the prediction prompt display area.

[0011] A second aspect of this application provides a prompt information input device, the device comprising:

[0012] An interface display module is used to display a target interface, the target interface including a prompt input area for inputting prompt information;

[0013] The prompt display module is used to respond to the information editing operation triggered in the prompt input area, and display the prediction prompt information in the prediction prompt display area according to the current information obtained by the information editing operation in the prompt input area. The prediction prompt information includes at least one element control corresponding to the information element. The element control is used to carry the element content of the corresponding information element and supports adjusting the element content of the information element.

[0014] The prompt adoption module is used to display the prediction prompt information in the prompt input area in response to the adoption operation triggered by the prediction prompt information in the prediction prompt display area.

[0015] A third aspect of this application provides a computer device, the device comprising a processor and a memory:

[0016] The memory is used to store computer programs;

[0017] The processor is configured to perform the steps of the prompt information input method as described in the first aspect above, according to the computer program.

[0018] A fourth aspect of this application provides a computer-readable storage medium for storing a computer program for performing the steps of the prompt information input method described in the first aspect.

[0019] A fifth aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of the prompt information input method described in the first aspect.

[0020] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0021] This application provides a method for inputting prompt information. This method automatically generates high-quality predicted prompt information based on user input and allows users to adjust the predicted prompt information to suit their needs using element controls within the predicted prompt information. Specifically, the method includes: displaying a target interface including a prompt input area for inputting prompt information; responding to an information editing operation triggered in the prompt input area, displaying predicted prompt information in a predicted prompt display area based on the current information obtained from the information editing operation in the prompt input area. The predicted prompt information includes at least one element control corresponding to an information element, which carries and displays the specific element content of its corresponding information element and supports adjustment of the specific element content; responding to an adoption operation triggered for the predicted prompt information in the predicted prompt display area, displaying the predicted prompt information in the prompt input area, thus using the predicted prompt information as the actual application prompt information. Therefore, through the above method, corresponding predicted prompt information can be automatically generated based on the information currently edited by the user in the prompt input area, improving the input efficiency of prompt information. Furthermore, since predicted prompt information is usually generated by expanding or standardizing the expression based on the current information in the prompt input area, the predicted prompt information is typically richer and more accurate, meaning it has high quality. Furthermore, the predicted prompts include element controls that support adjusting the content of the elements they contain. Users can quickly fine-tune the predicted prompts using these controls, adjusting the content of each information element to obtain accurate prompts that meet their specific needs. Using these predicted prompts in subsequent applications allows AI models to perform corresponding tasks based on these high-quality, user-relevant prompts, thereby improving the processing efficiency of the AI ​​models and ensuring the usability of the output results. Attached Figure Description

[0022] 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.

[0023] Figure 1 A schematic diagram of a prompt information input method provided for related technologies;

[0024] Figure 2 A schematic diagram illustrating another method for inputting prompt information for related technologies;

[0025] Figure 3 An architecture diagram of a computer system provided in an embodiment of this application;

[0026] Figure 4 This is a schematic diagram illustrating an application scenario of the prompt information input method provided in the embodiments of this application;

[0027] Figure 5 A flowchart illustrating the prompt information input method provided in this application embodiment;

[0028] Figure 6 This is a schematic diagram of the prediction prompt display area provided in the embodiments of this application;

[0029] Figure 7 A schematic diagram illustrating a content replacement operation provided in an embodiment of this application;

[0030] Figure 8 A schematic diagram illustrating another content replacement operation provided in an embodiment of this application;

[0031] Figure 9 A schematic diagram illustrating yet another content replacement operation provided in an embodiment of this application;

[0032] Figure 10 A schematic diagram illustrating the content deletion operation provided in this application embodiment;

[0033] Figure 11 This is a schematic diagram of the element control recycling area provided in an embodiment of this application;

[0034] Figure 12 This is a schematic diagram illustrating the refresh prediction prompt information provided in an embodiment of this application;

[0035] Figure 13 A schematic diagram illustrating the operation of triggering the above prompt provided in an embodiment of this application;

[0036] Figure 14 A schematic diagram illustrating the operation of triggering the following prompt for viewing, provided in an embodiment of this application;

[0037] Figure 15 A schematic diagram illustrating the display history notification information list provided in an embodiment of this application;

[0038] Figure 16 A schematic diagram illustrating the reference prompt information provided in the embodiments of this application;

[0039] Figure 17 A schematic diagram of the settings interface provided in an embodiment of this application;

[0040] Figure 18 A flowchart illustrating the reminder information input method provided in this application embodiment;

[0041] Figure 19 This is a schematic diagram of the structure of the prompt information input device provided in the embodiments of this application;

[0042] Figure 20 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application;

[0043] Figure 21 This is a schematic diagram of the server structure provided in an embodiment of this application. Detailed Implementation

[0044] 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. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0045] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0046] It should be noted that this application may display a prompt interface, pop-up window, or output voice prompt information before the user logs into the application, before collecting user-related data, or during the process of collecting user-related data. This prompt interface, pop-up window, or voice prompt information is used to inform the user that their relevant data is being collected. This ensures that the application only begins executing the steps related to collecting user-related data after receiving confirmation from the user regarding the prompt interface or pop-up window; otherwise (i.e., without receiving confirmation from the user), the steps related to collecting user-related data end, meaning no user-related data is collected. In other words, all user data collected in this application is collected with the user's consent and authorization, and the collection, use, and processing of relevant user data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0047] Currently, AI-generated applications typically provide a blank prompt input box, requiring users to manually enter prompts to drive the AI ​​model to perform corresponding tasks. However, user-input prompts are inefficient, and the quality of the input is difficult to control. For example, in many cases, user-input prompts are neither accurate nor comprehensive, further reducing the processing efficiency of the AI ​​model and resulting in poor usability of the output.

[0048] To address the above issues, related technologies offer solutions for optimizing prompts, providing improved prompts based on user-inputted information. Below are two common solutions for providing optimized prompts:

[0049] Option 1: Free-form prompts combined with AI-generated optimized prompts. This approach is used in early large language models (such as ChatGPT), drawing instructions in image generation models (Midjourney / “imagine”), and the homepage input boxes of game development platforms (such as AI Generated Content (AIGC)). In this approach, the user interface (UI) typically consists of a single multi-line text box combined with optimized controls. Users first need to write a complete natural language description or key string as a prompt based on their experience. Then, after clicking the optimized control, the optimized prompt directly replaces the user's original input. For example, see [reference needed]. Figure 1 , Figure 1 A schematic diagram illustrating a prompt information input method provided for related technologies, such as... Figure 1 As shown in interface a, the user needs to input the complete prompt information in the text input control at once. Then, by clicking the "Enhance Prompt Word" control 101, a prompt information optimization operation is triggered. The terminal device responds to this optimization operation by having an AI model optimize the prompt information input by the user and return the optimized prompt information, such as... Figure 1 As shown in interface b, the text input control includes optimized prompts.

[0050] Option 2: Inline Autocomplete for Input Controls. This option is used in applications such as GitHub Copilot (intelligent programming assistant) and Gmail Smart Compose (intelligent composer). In this option, the input suggestions are optimized in real-time as the user enters them, and the optimized suggestions are displayed. The user can then choose to accept the optimized suggestions. For example, see... Figure 2 , Figure 2 A schematic diagram illustrating another method for inputting prompt information for related technologies, such as... Figure 2 As shown, in an Integrated Development Environment (IDE), text editor, or AI chat tool, during the user's input of prompt information, the optimized prompt information can be displayed in the form of "Ghost Text." That is, above the input control, the prompt information optimized from the user's input is displayed in gray font. When the user clicks a preset control (such as the Tab key or Enter key), an adoption operation is triggered. In response to this adoption operation, the optimized prompt information is directly appended to the end of the prompt information entered by the user.

[0051] However, the solutions mentioned above are all limited in their ability to make local adjustments to the optimized prompts; that is, they only allow users to globally accept or reject the optimized prompts. If users want to make local adjustments to the optimized prompts, they must use an extremely cumbersome method. Specifically, users need to first globally accept the optimized prompts, then position the cursor at the content to be adjusted, select the content to be modified, and then re-enter the new content to achieve fine-tuning of the optimized prompts. This modification method is difficult to operate on mobile devices and is highly susceptible to accidental deletion of other content.

[0052] To address the problems existing in the aforementioned related technologies, this application provides a method for inputting prompt information. The method includes: displaying a target interface including a prompt input area for inputting prompt information; responding to an information editing operation triggered in the prompt input area, displaying predicted prompt information in a predicted prompt display area based on the current information obtained from the information editing operation in the prompt input area; the predicted prompt information includes at least one element control corresponding to an information element, the element control carrying and displaying the specific element content of its corresponding information element, and supporting adjustment of the specific element content of the information element; responding to an adoption operation triggered for the predicted prompt information in the predicted prompt display area, displaying the predicted prompt information in the prompt input area, i.e., using the predicted prompt information as the actual application prompt information. Therefore, through the above method, corresponding predicted prompt information can be automatically generated based on the information currently edited by the user in the prompt input area, thereby improving the input efficiency of prompt information. Furthermore, since the predicted prompt information is usually generated by expanding or standardizing the expression based on the current information in the prompt input area, the predicted prompt information is usually richer and more accurate, i.e., the predicted prompt information has high quality. Furthermore, the predictive prompts include element controls that support adjusting the content of the elements they contain. Users can quickly fine-tune the predictive prompts using these controls, adjusting the content of each information element individually to obtain accurate prompts that meet their specific needs. This allows for quick and accurate local modifications to the predictive prompts while avoiding accidental deletion of other information elements. Using these predictive prompts in subsequent applications allows AI models to execute tasks based on these high-quality, user-relevant prompts, thereby improving the processing efficiency of the AI ​​models and ensuring the usability of the output results.

[0053] To facilitate understanding of the prompt information input method provided in the embodiments of this application, the computer system used to implement the prompt information input method will be described exemplarily below.

[0054] See Figure 3 , Figure 3 An architecture diagram of a computer system provided in an embodiment of this application. Figure 3 The computer system 310 described herein is a system architecture for implementing the prompt information input method in the embodiments of this application. The computer system 310 includes a terminal device 320 and a server 340.

[0055] The terminal device 320 has a client application for the target application installed and running. This target application can be an application that drives an AI model to perform tasks based on prompts, such as, but not limited to, AI Generated Content (AIGC) applications. This embodiment of the application does not limit the type of the target application. The client application can be, for example, an application (App) or a mini-program on the terminal device 320, or it can be in the form of a webpage. This embodiment of the application does not limit the form of the client application on the terminal device 320.

[0056] Terminal device 320 can be a user-used terminal device. The prompt information input method in this application embodiment can be implemented through the client of the target application in terminal device 320. Specifically, the client running in terminal device 320 can display a target interface, which includes a prompt input area for inputting prompt information. In response to an information editing operation triggered in the prompt input area, based on the current information obtained from the information editing operation in the prompt input area, predicted prompt information is displayed in the predicted prompt display area. The predicted prompt information includes at least one element control corresponding to an information element. The element control is used to carry the element content of its corresponding information element and supports adjusting the element content of the information element. In response to an adoption operation triggered for the predicted prompt information in the predicted prompt display area, the predicted prompt information is displayed in the prompt input area.

[0057] Terminal device 320 can refer to one of a plurality of terminal devices, but this embodiment uses terminal device 320 as an example only. The device types of terminal device 320 include, but are not limited to, at least one of the following: smartphone, tablet computer, wearable device, laptop computer, desktop computer, smart home device, or smart vehicle device.

[0058] Those skilled in the art will understand that the number of terminal devices 320 described above can be more or less. For example, there may be only one terminal device 320, or there may be multiple or more terminal devices 320. This application does not limit the number or type of terminal devices 320.

[0059] Terminal device 320 can connect to server 340 via wireless network or wired network.

[0060] Server 340 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services such as cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0061] For example, server 340 is used to provide background services for clients of a target application running on terminal device 320. Server 340 includes processor 344 and memory 342. Memory 342 is used to store relevant computer programs, such as computer programs related to the background services to be provided. Processor 344 is used to execute the computer programs stored in memory 342 to provide corresponding background services to the client. For example, based on prompts entered by the user in the prompt input area provided by the client, it controls an AI model to perform corresponding tasks.

[0062] Optionally, server 340 undertakes the main computing work and terminal device 320 undertakes the secondary computing work; or, server 340 undertakes the secondary computing work and terminal device 320 undertakes the main computing work; or, server 340 and terminal device 320 adopt a distributed computing architecture for collaborative computing.

[0063] See Figure 4 , Figure 4 This is a schematic diagram illustrating an application scenario of the prompt information input method provided in this application embodiment. The method is executed by a computer device, which may be, for example, a computer device... Figure 3 The terminal device 320 shown. The steps of the prompt information input method performed by the terminal device 320 are as follows:

[0064] The client application in terminal device 320 can display the target interface, which includes a prompt input area for inputting prompt information, such as... Figure 4 As shown, the target interface 401 includes a prompt input area 402 for inputting prompt information, where users can input prompt information.

[0065] In the terminal device 320, the client of the target application responds to an information editing operation triggered in the prompt input area. Based on the current information obtained from the information editing operation in the prompt input area, it displays predicted prompt information in the predicted prompt display area. The predicted prompt information includes at least one element control corresponding to an information element. The element control carries the element content of its corresponding information element and supports adjusting the element content. Taking the information editing operation as inputting information in a blank prompt input area as an example, such as... Figure 4 As shown in interface 403, the user enters "dungeon" in the prompt input area 402, which generates corresponding prediction prompt information and displays it in the prediction prompt display area 404. The prediction prompt information includes multiple element controls, which are used to carry the element content corresponding to multiple information elements, such as element control 405 carrying "2D", element control 406 carrying "vertical", and element control 407 carrying "top view", etc. The user can adjust the element content carried by the element control. For example, the user can click the switch icon in element control 405 carrying "2D" to trigger the switching of the element content carried by element control 405, switching "2D" to "3D", as shown in interface figure 408. For another example, the user can click the drop-down icon in element control 407 carrying "top view" to trigger the display of multiple candidate element contents under the information element corresponding to element control 407. The user can select the desired element content from the multiple candidate element contents, and element control 407 carries the element content selected by the user.

[0066] In terminal device 320, the client of the target application responds to the adoption operation triggered by the prediction prompt information in the prediction prompt display area, and displays the prediction prompt information in the prompt input area. For example... Figure 4 As shown in interface 408, users can click the "Confirm" control 409 to trigger an adoption operation based on the prediction prompt information displayed in the prediction prompt display area; furthermore, as... Figure 4 As shown in the interface diagram 410, in response to the adoption operation, the predicted prompt information in the predicted prompt display area will be displayed in the prompt input area 402, namely, "a 3D vertical top-down dungeon game with procedural rooms, drops, a boss every 5 floors, and pixel-style graphics".

[0067] Using the above method, corresponding predicted prompts can be automatically generated based on the information currently being edited by the user in the prompt input area, thereby improving the input efficiency of prompts. Since predicted prompts are usually generated by expanding or standardizing the current information in the prompt input area, they are typically richer and more accurate, meaning they are of high quality. Furthermore, the predicted prompts include element controls that support adjusting the content of the elements they contain. Users can quickly fine-tune the predicted prompts using these controls, adjusting the content of each information element to obtain accurate prompts that meet the user's actual needs. Using these predicted prompts in subsequent applications allows AI models to perform corresponding tasks based on these high-quality, user-relevant prompts, thus improving the processing efficiency of the AI ​​models and ensuring the usability of the output results.

[0068] It should be understood that Figure 4 The application scenarios shown are merely examples. In practical applications, the prompt information input method provided in this application embodiment can also be applied to other scenarios. No limitation is made here on the application scenarios of the prompt information input method provided in this application embodiment.

[0069] The following describes in detail the prompt information input method provided in this application through method embodiments.

[0070] See Figure 5 , Figure 5 This is a flowchart illustrating the prompt information input method provided in an embodiment of this application. This prompt information input method can be executed by a computer device; for ease of description, the following description uses a terminal device as the executing entity for this prompt information input method. Figure 5 As shown, the method for inputting this prompt message includes the following steps:

[0071] S501: Display the target interface, which includes a prompt input area for entering prompt information.

[0072] The prompt input area is a region used to support user input of prompt information. It can support prompt information in the form of text, voice, links, files, images, videos, etc. This application does not specifically limit the types of information supported by the prompt input area. The prompt information is a natural language description or structured instruction that drives an AI model (such as a Large Language Model (LLM)) to perform a corresponding task. For example, it can be natural language descriptive text. This application does not specifically limit the prompt information.

[0073] The target interface is an interface provided by the target application for inputting prompt information, including a prompt input area where users can input prompt information. The target application is an application that drives an AI model to perform corresponding tasks based on the prompt information. This target application may include, but is not limited to, AIGC applications, AI dialogue applications, AI game development platforms, and AI content creation tools. This application does not specifically limit the target application in this regard.

[0074] For example, a user can trigger the launch of a target application on the terminal device by clicking the icon of the target application displayed on the terminal device screen. After the target application is launched, the target interface can be displayed on the terminal device screen to support the user to enter prompt information in the prompt input area included in the target interface.

[0075] S502: In response to an information editing operation triggered in the prompt input area, based on the current information obtained from the information editing operation in the prompt input area, display the prediction prompt information in the prediction prompt display area. The prediction prompt information includes at least one element control corresponding to an information element. The element control is used to carry the element content of its corresponding information element and supports adjusting the element content of the information element.

[0076] Information editing operation refers to the operation of a user to edit prompt information in the prompt input area. It may include, but is not limited to, information input operation, information deletion operation, and information modification operation. This application does not specifically limit the information editing operation.

[0077] The current information in the prompt input area refers to the information displayed in the prompt input area after the user performs an information editing operation. Corresponding predictive prompt information can be generated based on this. For example, if the prompt input area is initially blank, the user can input information (such as characters exceeding a preset character threshold) through the information input control; the input information is the current information in the prompt input area. Alternatively, if the prompt input area already includes basic input information, the user can perform operations such as inputting, deleting, or modifying information based on this basic prompt information; the information obtained after performing these operations on the basic prompt information is the current information in the prompt input area. This application does not specifically limit the current information in the prompt input area.

[0078] Prediction is a prompt generated based on the current information in the prompt input area. Prediction is typically of high quality, accurately instructing subsequent AI models to perform corresponding tasks. For example, a prompt generation model (such as a large language model) can automatically expand or complete the current information in the prompt input area to generate a complex sentence with complete semantics and execution capability, which serves as the prediction prompt. This application does not specifically limit the method of generating the prediction prompt.

[0079] The predictive prompt information includes at least one element control corresponding to an information element. An information element refers to an adjustable information attribute included in the predictive prompt information, such as game type, layout, perspective, and level content. This application does not specifically limit the information element. The element content corresponding to an information element refers to the specific content corresponding to the adjustable information attribute included in the predictive prompt information, such as the game type being 2D, the layout being portrait, the perspective being top-down, and the level content being a boss every 5 levels. This application does not specifically limit the element content corresponding to an information element. An element control is used to carry the content of its corresponding information element and supports adjusting the content of that information element. That is, by triggering an operation on the element control, the content carried by the element control can be changed, thereby achieving fine-tuning of the predictive prompt information. For example, a content replacement operation can be triggered by the element control to replace the original content carried by the element control with other content, or a content deletion operation can be triggered by the element control to delete the element control and its carried content. The appearance of the element control is different from ordinary text. For example, it can be represented as a capsule control (such as a light background, rounded corners, etc.) to prompt the user that the content carried by the element control can be adjusted. In this regard, this application does not specifically limit the appearance of the element control.

[0080] The prediction area is used to carry prediction information. For example, it can be a floating UI panel (Popover) independent of the prompt input area. It can be located above or below the prompt input area without changing the position of the prompt input area. In this regard, this application does not specifically limit the position and form of the prediction area.

[0081] For example, taking the information editing operation as entering information in a blank prompt input area as an example, you can refer to... Figure 6 , Figure 6 This is a schematic diagram of the prediction prompt display area provided in the embodiments of this application, such as... Figure 6As shown, the user can input the information "Dungeon" in the prompt input area. The terminal device responds to this input by generating corresponding predicted prompt information based on the current information "Dungeon" in the prompt input area, and displays the predicted prompt information in the predicted prompt display area 601. The predicted prompt information includes plain text and element controls that carry the corresponding information elements. For example, the predicted prompt information is "A 2D vertical top-down dungeon game with procedural rooms, loot, a boss every 5 floors, pixel-style graphics." This includes element controls carrying "2D," "vertical," "top-down," "procedural rooms," "loot," "a boss every 5 floors," and "pixel-style." Users can adjust the content of these element controls; for example, clicking on an element control can replace its content with other content.

[0082] S503: In response to an adoption operation triggered by a prediction prompt in the prediction prompt display area, display the prediction prompt in the prompt input area.

[0083] The "Accept" operation is used to accept the predicted prompts from the display area as prompts for subsequent applications. This means the predicted prompts can be filled into the prompt input area for display. For example, the Accept operation can be triggered by clicking or double-clicking the confirm control, using a preset gesture (such as swiping up or down), or pressing the Enter key. This application does not specifically limit the triggering method for the Accept operation.

[0084] For example, the prediction prompt display area includes a confirmation control. Users can trigger an adoption operation by clicking the confirmation control. In response to the adoption operation triggered by the prediction prompt information in the prediction prompt display area, the terminal device can display the prediction prompt information in the prompt input area. That is, it determines that the prediction prompt information in the prediction prompt display area will be used as the prompt information for subsequent applications. In other words, users can directly use the prediction prompt information to drive the AI ​​model to perform the corresponding task. Alternatively, users can further optimize and adjust the prediction prompt information in the prompt input area later.

[0085] Additionally, after the adoption action is triggered, a collapse animation of the prediction prompt display area can be displayed (such as moving towards the prompt input box and fading out), thus preventing the prediction prompt display area from being displayed.

[0086] In the prompt information input method provided in this application embodiment, the method can automatically generate high-quality predictive prompt information based on the information input by the user, and supports the user to adjust the predictive prompt information according to their own needs through element controls in the predictive prompt information. Through the above method, corresponding predictive prompt information can be automatically generated based on the information currently edited by the user in the prompt input area, thereby improving the input efficiency of prompt information. Furthermore, since the predictive prompt information is usually generated by expanding or standardizing the current information in the prompt input area, the predictive prompt information is usually rich and accurate, i.e., the predictive prompt information has high quality. In addition, the predictive prompt information includes element controls that support adjusting the content of the elements it carries. Users can quickly fine-tune the predictive prompt information through these element controls, i.e., adjusting the content of the information elements in the predictive prompt information on an element-by-element basis, thereby obtaining accurate predictive prompt information that meets the user's actual needs. Using the above-mentioned predictive prompt information as prompt information for subsequent practical applications allows subsequent AI models to perform corresponding tasks based on this high-quality predictive prompt information that meets the user's actual needs, thereby improving the processing efficiency of the AI ​​model and ensuring the usability of the output processing results.

[0087] • How to replace element content using element controls:

[0088] In one possible implementation, the element content it carries can be replaced by an element control. That is, the method provided in this application embodiment may further include the following step S11 (not shown in the figure):

[0089] S11: In response to the content replacement operation triggered by the first element control, the original first element content carried by the first element control is replaced with the second element content, and the adjusted prediction prompt information is displayed in the prediction prompt display area. The first element control can be any element control.

[0090] The first element control can be any element control in the predicted prompt information that supports replacing the content of the element it carries. For example, the first element control can be an element control that includes a toggle component or an element control that includes a drop-down list component. In this regard, this application does not specifically limit the first element control.

[0091] The content replacement operation is used to replace the original element content of the first element control with other element content, that is, to replace the first element content with the second element content. For example, the content replacement operation can be triggered by clicking the switching component in the first element control, triggering a preset gesture (such as swiping left or right) on the first element control, or triggering the display of each candidate element content corresponding to the first element control and selecting the desired element content. In this regard, this application does not specifically limit the triggering method of the content replacement operation.

[0092] The first element content refers to the element content originally carried by the first element control, and the second element content is the element content carried by the first element control after the content replacement operation is triggered. Both the first element content and the second element content are candidate element content under the information element corresponding to the first element control. That is, the user can select the required element content from the candidate element content under the information element corresponding to the first element control according to their own needs. The above-mentioned candidate element content is generated for the information element corresponding to the first element control when generating predictive prompt information based on the current information in the prompt input area. In this regard, this application does not specifically limit the first element content and the second element content.

[0093] For example, taking the first element control as an element control that includes a switching component, the user can trigger a content replacement operation by clicking the switching component in the first element control. In response to the content replacement operation, the terminal device can directly replace the original first element content carried by the first element control with the second element content. Accordingly, the prediction prompt display area will display the adjusted prediction prompt information, that is, the prediction prompt display area will display prediction prompt information including the second element content.

[0094] Therefore, by using the above method, the content replacement operation can be quickly triggered through the first element control, and its original first element content can be quickly replaced with the second element content. This provides a content adjustment method with simple operation logic and intuitive triggering method, which significantly reduces the difficulty of making local fine-tuning of prediction prompt information and improves the efficiency of fine-tuning prediction prompt information.

[0095] As an example, the first element control can trigger the display of multiple candidate element contents, and then the second element content can be selected from these multiple candidate element contents. That is, the "in response to the content replacement operation triggered by the first element control, the first element content originally carried by the first element control is replaced with the second element content" in S11 above may include the following steps S11-11 to S11-12 (not shown in the figure):

[0096] S11-11: In response to a candidate content viewing operation triggered by the first element control, display the content of multiple candidate elements under the first information element corresponding to the first element control.

[0097] The first information element refers to the information element corresponding to the first element control. It can be any information element in the prediction prompt information that supports replacing its element content. In this regard, this application does not specifically limit the first information element.

[0098] The multiple candidate element contents under the first information element refer to the candidate options corresponding to the first information element. When generating predictive prompt information based on the current information in the prompt input area, multiple candidate element contents under each information element that supports replacing element contents can be generated simultaneously. Based on this, the element controls corresponding to such information elements can realize the element content replacement function. In this regard, this application does not specifically limit the multiple candidate element contents under the first information element.

[0099] The candidate content viewing operation is used to trigger the viewing of multiple candidate element contents under the first information element corresponding to the first element control. For example, the first element control may include a drop-down list component. Clicking the drop-down list component in the first element control can trigger the candidate content viewing operation. This application does not specifically limit the triggering method of the candidate content viewing operation. Specifically, when the state of the first element control changes from the default state to the click state, it is confirmed to enter the selected state, at which time the multiple candidate element contents under the first information element corresponding to the first element control can be displayed in list form. Correspondingly, when the state of the first element control changes from the selected state to clicking the outside, it is confirmed to restore the default state, at which time the display of the multiple candidate element contents under the first information element corresponding to the first element control can be cancelled.

[0100] For example, taking a first element control that includes a dropdown list component, a user can trigger a candidate content viewing operation by clicking the dropdown list component in the first element control. In response to this operation, the terminal device can display multiple candidate element contents under the first information element corresponding to the first element control in a list format. The expansion direction of this list can be determined based on the display position of the first element control; for example, the list expands downwards when the first element control is in the upper half of the screen, and expands upwards when it is in the lower half (near the soft keyboard). Specifically, the distance between the first element control and the top and bottom of the target interface can be calculated using the `getBoundingClientRect` method to determine whether the list (DropDown) expands upwards or downwards. When the soft keyboard pops up, the position is further calibrated through the visual viewport application programming interface (visualViewportAPI) to prevent the list from being obscured by the keyboard.

[0101] For example, you can refer to Figure 7 , Figure 7 This is a schematic diagram of a content replacement operation provided in an embodiment of this application, such as... Figure 7 As shown in interface a, when a user clicks the dropdown list component 701 in the first element control, a candidate content viewing operation is triggered. In response to this candidate content viewing operation, as shown... Figure 7 As shown in interface b, the interface displays a candidate list 702 corresponding to the first information element of the first element control. The candidate list 702 includes multiple candidate element contents corresponding to the first information element, such as top view, horizontal scrolling view, isometric view, and main view.

[0102] S11-12: In response to a selection operation triggered by the content of the second element among multiple candidate element contents, the content of the second element is displayed through the first element control.

[0103] The content of the second element can be any one of the multiple candidate element contents under the first information element corresponding to the first element control. In this regard, this application does not specifically limit the content of the second element.

[0104] The selection operation is used to indicate that the selected candidate element content should be used as the second element content. For example, the selection operation can be triggered by clicking on the candidate element content or clicking the corresponding confirmation control. This application does not specifically limit the triggering method of the selection operation. Specifically, when the state of the first element control changes from the selected state to selecting candidate element content (pickCandidate), it confirms that the default state including the new element content has been entered. At this time, the list of candidate element content can be collapsed, and prediction prompt information including the second element content can be displayed in the prediction prompt display area.

[0105] For example, a selection operation can be triggered by clicking on the content of a candidate element. In response to this selection operation, the selected candidate element content can be used as the second element content, and the second element content can be displayed through the first element control. For example, Figure 7 As shown in interface b, when the user clicks on "First View" in candidate list 702, a selection operation is triggered for "First View." In response to this selection operation, "First View" can be used as the second element. Furthermore, as... Figure 7 As shown in interface c, the first element control 703 displays the "main view".

[0106] Therefore, by using the above method, the first element control can be used to trigger the viewing of multiple candidate element contents corresponding to the first information element. This triggering method is simple and intuitive, making it easy for users to quickly find the second element contents that meet their actual needs, thereby efficiently and accurately replacing the element contents carried by the first element control.

[0107] As another example, the content of the first element carried by the first element control can be quickly switched to the content of the second element through the first element control. That is, the "responding to the content replacement operation triggered by the first element control, the content of the first element originally carried by the first element control is replaced with the content of the second element" in S11 above may include the following steps S11-21 (not shown in the figure):

[0108] S11-21: In response to the content switching operation triggered by the first element control, the first element content originally displayed by the first element control is switched to the second element content. Both the first element content and the second element content are candidate element content under the first information element corresponding to the first element control.

[0109] The content switching operation is used to indicate that the content originally carried by the first element control is switched to other element content, such as switching the content originally carried by the first element control to the content of the second element. For example, if the number of candidate element contents under the first information element corresponding to the first element control is small, such as the number of candidate element contents under the first information element being less than a preset threshold (such as 2 or 3), the first element control may include a switching component that supports quick switching. In this case, the content switching operation can be triggered by clicking the switching component in the first element control. Alternatively, the first element control may also support triggering the content switching operation by performing a preset gesture (such as swiping left or right). In this regard, this application does not specifically limit the triggering method of the content switching operation.

[0110] For example, when the number of candidate element contents under the first information element is less than a preset threshold, taking a first element control including a switching component as an example, the user can trigger a content switching operation by clicking the switching component in the first element control. In response to this content switching operation, the terminal device can switch the first element content originally displayed by the first element control to the second element content. For example, refer to... Figure 8 , Figure 8 This is a schematic diagram illustrating another content replacement operation provided in an embodiment of this application, as shown below. Figure 8 As shown in interface a, the first element control includes a toggle component 801. Clicking this toggle component 801 triggers a content switching operation. In response to this content switching operation, as shown... Figure 8 As shown in interface b, the "2D" content originally displayed by the first element control can be switched to the content of the second element, such as switching it to "3D".

[0111] It should be noted that, in order to better reflect the switching of the element content carried by the first element control, the display style of the first element control can be changed accordingly when the element content carried by the first element control is switched. That is, the display style of the first element control when carrying the first element content is different from the display style when carrying the second element content. For example, when the first element control carries the first element content, its background color can be gray, while when the first element control switches to carrying the second element content, its background color can become yellow. This application embodiment does not limit the change of the display style of the first element control in any way.

[0112] Therefore, by using the above method, when the number of candidate element contents under the first information element corresponding to the first element control is small, the content switching operation can be triggered quickly with one click through the first element control, thereby quickly completing the switching of the element content carried by the first element control, simplifying the operation path of element content replacement, and improving the ease of operation.

[0113] In one possible implementation, the first element control may further include a custom sub-control, which allows users to implement custom element content. That is, the method provided in this application embodiment may further include the following step S12 (not shown in the figure):

[0114] S12: In response to the operation of inputting the content of the third element through a custom sub-control, the content of the third element is displayed through the first element control, and the adjusted prediction prompt information is displayed in the prediction prompt display area.

[0115] The third element content is user-defined element content used to replace the first element content. This application does not specifically limit the third element content.

[0116] Custom sub-controls are used to customize the content of elements displayed by the first element control. That is, new element content can be added through custom sub-controls. Custom sub-controls can be input controls. For example, they can be located in the drop-down list corresponding to the first element control, or on the side (such as the left or right side) of the toggle component corresponding to the first element control. This application does not specifically limit the position and appearance of custom sub-controls.

[0117] For example, taking a custom sub-control located in the dropdown list corresponding to the first element control, and the custom sub-control being an input control, when a user clicks the dropdown list component in the first element control, the dropdown list corresponding to the first element control can be displayed. The dropdown list includes a custom sub-control, through which the user can input content for a third element. In response to this input operation, the first element control can display the content of the third element, and the adjusted prediction prompt information is displayed in the prediction prompt display area, that is, prediction prompt information including the content of the third element is displayed in the prediction prompt display area. For example, refer to... Figure 9 , Figure 9 This is a schematic diagram illustrating another content replacement operation provided in an embodiment of this application. Taking an example where the first element control includes a dropdown list component, and a custom sub-control is located in the dropdown list corresponding to the first element control, as shown below... Figure 9 As shown in interface a, after the user clicks the dropdown list component 901 of the first element control, the dropdown list corresponding to the first element control can be displayed, including the custom sub-control 902. For example... Figure 9 As shown in interface b, the user can input the content of a third element in the custom sub-control 902, such as "side view". In response to this input, as... Figure 9 As shown in interface c, the first element control 903 in the prediction prompt information in the prediction prompt display area can display the "side view".

[0118] Therefore, by using the above method, when the content of the candidate element corresponding to the first information element does not meet the user's needs, a custom sub-control can be used to support the user to independently input the content of the third element, thereby meeting the personalized content editing needs and improving the user satisfaction of the adjusted prediction prompt information.

[0119] • How to delete element content using an element control:

[0120] In one possible implementation, the information elements and their corresponding element content in the prediction prompt information can be deleted using the second element control. That is, the method provided in this application embodiment may further include the following step S21 (not shown in the figure):

[0121] S21: In response to the content deletion operation triggered by the second element control, delete the second element control and its contained element content in the prediction prompt information, and display the adjusted prediction prompt information in the prediction prompt display area. The second element control can be any element control.

[0122] The second element control refers to any element control in the prediction prompt that can be deleted. That is, a content deletion operation can be triggered on the second element control to delete the second element control and its contained element content. In practical applications, the second element control can correspond to a non-essential information element in the prediction prompt. Non-essential information elements are auxiliary information elements referenced by the AI ​​model when performing tasks; even if the prompt does not include the information element, it can still drive the AI ​​model to perform the corresponding task. Optionally, the element content carried by the second element control can be a fixed value, meaning that the second element control does not support replacing its contained element content, but only supports triggering a content deletion operation through it. Alternatively, the second element control can also be a control that supports replacing element content, such as the first element control mentioned above. This application does not specifically limit the second element control in this regard.

[0123] The content deletion operation is used to indicate the deletion of the second element control and the element content it contains. For example, the content deletion operation can be triggered by clicking the second element control in the deletion selection state, dragging the second element control to the preset deletion area, clicking the deletion component in the second element control, or double-clicking the second element control. In this regard, this application does not specifically limit the triggering method of the content deletion operation.

[0124] For example, if the content of the second element control is a fixed value, the user can trigger the content deletion operation by clicking on the second element control when it is in the deletion selected state through a preset deletion operation.

[0125] For example, when the content of the element controlled by the second element control supports switching, the user can first select the element control to be deleted. The selected element control becomes the second element control, which is then in a selected state (Selected). This second element control may be highlighted and have a darkened border. Furthermore, a content deletion operation can be triggered on the second element control using preset deletion methods. For instance, clicking on the selected second element control puts it in a delete-select state. Clicking the selected second element control again will then trigger the content deletion operation.

[0126] In response to the content deletion operation, the terminal device can delete the second element control and its contained element content from the preset prompt information, and display the adjusted prediction prompt information in the prediction prompt display area, that is, display the prediction prompt information that does not include the second element control and its contained element content in the prediction prompt display area.

[0127] Therefore, by using the above method, the content deletion operation can be triggered independently through the second element control, allowing for the targeted deletion of unwanted element controls and their contained content without needing to clear the entire control. This method enables precise deletion of element content, increasing operational flexibility.

[0128] As an example, the second element control can be first controlled to be in a delete selected state, and then a delete confirmation can be triggered for the second element control in the delete selected state. That is, S21 above can include the following steps S211-S212 (not shown in the figure):

[0129] S211: In response to a deletion selection operation triggered on the second element control, control the second element control to present a deleted selection state.

[0130] The delete selection operation is used to indicate that the second element control to be deleted is selected. For example, the delete selection operation can be triggered by clicking or double-clicking the second element control or by a preset gesture. This application does not specifically limit the triggering method of the delete selection operation.

[0131] The "Warning" state indicates that the second element control is selected and can be deleted. For example, the "Warning" state can be represented by a red outline combined with red text, or by deleting the control. This application does not specifically limit the representation of the "Warning" state. Specifically, when the state of the second element control changes from selected to self-click, it confirms that it has entered the "Warning" state, at which point the second element control can be controlled to display the "Warning" state.

[0132] For example, a user can trigger a delete selection operation by clicking the second element control. In response to the delete selection operation, the terminal device can control the second element control to present a deleted selection state, such as displaying a delete control in the second element control, and using red lines to indicate the boundary of the second element control, while using red text to indicate the element content carried by the second element control.

[0133] For example, you can refer to Figure 10 , Figure 10 This is a schematic diagram of the content deletion operation provided in the embodiments of this application, such as... Figure 10 As shown in interface a, users can trigger a deletion operation on the second element control 1001 by clicking on it, as it does not support replacing element content. In response to this deletion operation, the second element control can be controlled to display a deleted selection state, as shown below. Figure 10 As shown in interface b, the delete control 1002 is displayed in the second element control 1001, and the boundary of the second element control is indicated by a black bold line, while the element content carried by the second element control is indicated by black bold text.

[0134] S212: In response to a deletion confirmation operation triggered for a second element control that is in the deletion selection state, delete the second element control and its contained element content in the prediction prompt message.

[0135] The deletion confirmation operation is used to confirm the deletion of a second element control that is in the deletion selection state. For example, the deletion confirmation operation can be triggered by clicking on the second element control in the deletion selection state, or by clicking on the delete control within the second element control in the deletion selection state. This application does not specifically limit the triggering method of the deletion confirmation operation. Specifically, when the state of the second element control changes from the deletion selection state to clicking on itself, it confirms entering the removed state, at which point the second element control and its contained element content in the predicted prompt information can be deleted.

[0136] For example, a user can click the delete control in the second element control that is in the delete selected state to trigger a delete confirmation operation. In response to this confirmation operation, the terminal device deletes the second element control and its contained content from the predicted deletion prompt. For example, as... Figure 10 As shown in interface b, when a user clicks the delete control 1002 in the second element control 1001, a delete confirmation operation can be triggered. In response to this delete confirmation operation, as shown... Figure 10 As shown in interface c, the second element control and its contained element content in the prediction prompt information are deleted, that is, the prediction prompt display area does not display the second element control and its contained element content.

[0137] Therefore, the two-confirmation deletion mechanism provided by the above method can prevent users from accidentally touching the second element control and causing the content of the element it carries to be accidentally deleted, effectively avoiding misoperation and improving the fault tolerance rate of deletion operation.

[0138] As an example, after the second element control enters the deletion selection state, a countdown begins. If the deletion is not confirmed before the timeout, the second element control is retained. That is, the method provided in this application embodiment may also include the following steps S213 to S214 (not shown in the figure):

[0139] S213: In response to the second element control entering the deletion selection state, start the deletion countdown.

[0140] The deletion countdown is provided after the second element control enters the deletion selection state. It is used to confirm whether to delete the second element control. That is, if a deletion confirmation operation is triggered for the second element control in the deletion selection state before the countdown ends, the deletion of the second element control and its contained element content is confirmed. If no deletion confirmation operation is triggered for the second element control in the deletion selection state before the countdown ends, the deletion of the second element control and its contained element content is canceled. For example, the deletion countdown can be a preset time threshold, such as 3 seconds. This application does not specifically limit the deletion countdown.

[0141] For example, if the second element control is detected to be in the delete selected state, the delete countdown will start automatically.

[0142] S214: If no deletion confirmation is received before the deletion countdown ends, control the second element control to exit the deletion selection state.

[0143] For example, taking a 3-second countdown for deletion as an example, if no confirmation operation is received for the second element control in the deletion selection state before the 3-second countdown ends, the deletion of the second element control and its contained element content is cancelled. This means the second element control can be controlled to exit the deletion selection state and return to the default state. Specifically, when the state of the second element control changes from deletion selection to timeout, it is confirmed to enter the default state, at which point the second element control can be controlled to exit the deletion selection state.

[0144] Therefore, the above method provides an automatic timeout cancellation mechanism. Even if the user accidentally touches the second element control and enters the deletion selection state, the deletion selection state can be automatically cancelled and the second element control can be restored without actively triggering the deletion confirmation operation. This further avoids content loss caused by accidental deletion and improves the fault tolerance rate of the deletion operation.

[0145] In one possible implementation, the deleted second element control and its element content can be added to the element control recycle area, and subsequently, the deleted second element control and its element content can be restored. That is, the method provided in this application embodiment may further include the following steps S22-S23 (not shown in the figure):

[0146] S22: After the second element control and its contained element content are deleted, display the second element control and its contained element content in the element control recycle area.

[0147] The element control recycling area is used to temporarily store deleted element controls and the element content they contain. It can be located above, below, or to the side of the prediction prompt display area. This application does not specifically limit the location of the element control recycling area.

[0148] For example, after the second element control and its contained element content are deleted, instead of directly clearing the underlying data, the second element control and its contained element content can be temporarily mounted in the element control recycle area. For example, refer to... Figure 11 , Figure 11 This is a schematic diagram of the element control recycling area provided in the embodiments of this application, such as... Figure 11 As shown in interface a, after the second element control and its contained element content are deleted, the deleted second element control 1102 and its contained element content can be displayed in the element control recycling area 1101.

[0149] S23: In response to a restore operation triggered for a second element control in the element control recycle area, restore the display of the second element control and its contained element content in the adjusted prediction prompt information.

[0150] The recovery operation is used to restore the deleted second element control and the content of the element it carries. For example, the recovery operation can be triggered by dragging or clicking the second element control in the element control recycle area. This application does not specifically limit the triggering method of the recovery operation.

[0151] For example, a user can trigger a restore operation by clicking on a second element control in the element control recycle area. In response to this restore operation, the terminal device can restore the display of the second element control and its contained element content in the adjusted predictive prompt information, based on the position of the second element control before it was deleted. For example, ... Figure 11 As shown in interface a, clicking the second element control 1102 located in the element control recycle area triggers a restore operation. In response to this restore operation, as... Figure 11 As shown in interface b, the second element control 1102 and its contained element content can be restored and displayed in the prediction prompt display area.

[0152] Therefore, by using the above method, the deleted element control and its contained element content can be stored in the element control recycling area, and the deleted element control can be quickly restored from there. This solves the problem of important element content being accidentally deleted and cannot be restored in a timely manner, and reduces the subsequent risks of deletion operations.

[0153] • How to implement the withdrawal and content adjustment operation:

[0154] In one possible implementation, the content adjustment operation triggered by the element control can be revoked, that is, the method provided in this application embodiment may further include the following step S31:

[0155] S31: If a content adjustment operation has been triggered by an element control in the prediction prompt information, in response to an adjustment reversal operation triggered by the prediction prompt display area, the prediction prompt information prior to the content adjustment operation is displayed in the prediction prompt display area.

[0156] Content adjustment operation refers to the operation of adjusting the content of the element carried by the element control. Specifically, it can be the content replacement operation introduced in S11 above, or the content deletion operation introduced in S21 above. This application embodiment does not limit the content adjustment operation in any way.

[0157] An adjustment withdrawal operation refers to the operation of restoring the predicted prompt information before the content adjustment operation was performed. In other words, by performing an adjustment withdrawal operation, the modifications made to the predicted prompt information by the content adjustment operation can be undone. For example, the adjustment withdrawal operation can be triggered by clicking the withdrawal control deployed in the predicted prompt display area, or it can be triggered by performing a preset gesture in the predicted prompt display area. This application embodiment does not limit the triggering method of the adjustment withdrawal operation in any way.

[0158] For example, when the content adjustment operation is a content replacement operation, such as replacing the content of the first element held by the first element control with the content of the second element, if the user triggers an adjustment cancellation operation through the prediction prompt display area, the prediction prompt information before the content replacement operation can be restored in the prediction prompt display area, even though the first element control resumes to hold the content of the first element. Similarly, when the content adjustment operation is a content deletion operation, such as deleting the second element control and its held element content, if the user triggers an adjustment cancellation operation through the prediction prompt display area, the prediction prompt information before the content deletion operation can be restored in the prediction prompt display area, that is, the second element control and its held element content are restored in the prediction prompt information.

[0159] It should be understood that in practical applications, if a user iterates and triggers multiple content adjustment operations on the initially displayed prediction prompt information in the prediction prompt display area, the system can correspondingly support the user to iterate and trigger multiple adjustment reversal operations to gradually restore the prediction prompt information before each content adjustment operation.

[0160] Therefore, by using the above method, if a user is not satisfied with the predicted prompt information obtained after triggering the content adjustment operation, they can trigger the adjustment reversal operation to restore the predicted prompt information before the content adjustment operation, thereby quickly restoring the predicted prompt information and meeting the user's need to revert the content adjustment operation in many situations.

[0161] • How to refresh prediction prompts:

[0162] In one possible implementation, the prediction prompt information in the prediction prompt display area can be refreshed, that is, the method provided in this application embodiment may further include the following step S41 (not shown in the figure):

[0163] S41: In response to a refresh operation triggered by the first prediction prompt information currently displayed in the prediction prompt display area, based on the current information obtained from the information editing operation in the prompt input area, refresh and display the second prediction prompt information in the prediction prompt display area. The second prediction prompt information is different from the first prediction prompt information.

[0164] The first prediction prompt information refers to the prediction prompt information currently displayed in the prediction prompt display area. The second prediction prompt information is obtained after refreshing the first prediction prompt information and is different from the first prediction prompt information. For example, the second prediction prompt information can be generated by the prompt generation model based on the current information in the prompt input area to perform automatic expansion or completion generation. In this regard, this application does not specifically limit the first prediction prompt information and the second prediction prompt information.

[0165] The refresh operation is used to refresh the first prediction prompt information currently displayed in the prediction prompt display area. For example, the refresh operation can be triggered by clicking the refresh control or performing a preset gesture. This application does not specifically limit the triggering method of the refresh operation.

[0166] For example, if the current information in the prompt input area remains unchanged, the user can trigger a refresh operation on the first predicted prompt information currently displayed in the predicted prompt display area by clicking the refresh control. In response to the refresh operation, the terminal device can regenerate the second predicted prompt information based on the current information obtained through the information editing operation in the prompt input area, and refresh and display the second predicted prompt information in the predicted prompt display area.

[0167] It should be noted that in practical applications, a refresh count threshold can be set to prevent users from triggering refresh operations more than this threshold, thereby avoiding the waste of processing resources due to frequent refresh operations. It should be understood that the refresh count threshold can be set according to the functions used by the user or the user's level. For example, a higher refresh count threshold can be set for functions that consume fewer processing resources, while a lower threshold can be set for functions that consume more processing resources. Alternatively, a higher refresh count threshold can be set for higher-level users, and a lower threshold for lower-level users. This application does not limit the method of setting the refresh count threshold in any way.

[0168] Therefore, by using the above method, when a user is not satisfied with the first prediction prompt currently displayed in the prediction prompt display area, a refresh operation can be performed to regenerate and display a differentiated second prediction prompt based on the current information in the prompt input area, thereby providing the user with new prediction prompts to choose from, and further improving the selectivity of prediction prompts.

[0169] As an example, the prediction prompt information in the prediction prompt display area can be refreshed by refreshing the refresh control, that is, the above S41 may include the following steps S411-S412 (not shown in the figure):

[0170] S411: In response to a refresh operation triggered by the refresh control for the first predicted prompt information, control the refresh control to enter an unavailable state.

[0171] The refresh control entering an unavailable state is used to indicate that the refresh control cannot provide refresh functionality, that is, the refresh operation cannot be triggered by the refresh control at this time. For example, the refresh control can be grayed out (disabled) and a spinning animation (spinner) can be displayed to indicate that the refresh control has entered an unavailable state. This application does not specifically limit the way the refresh control enters an unavailable state.

[0172] For example, the prediction prompt display area includes a refresh control, which can be referenced. Figure 12 , Figure 12 This is a schematic diagram illustrating the refresh prediction prompt information provided in an embodiment of this application, such as... Figure 12 As shown in interface a, the user can trigger a refresh operation on the first predicted prompt information by clicking the refresh control 1201. In response to this refresh operation, the terminal device can control the refresh control 1201 to enter an unavailable state, such as... Figure 12 As shown in interface b, refresh control 1201 is grayed out.

[0173] Specifically, after a refresh request is initiated, the refresh status variable is set to true (isRefreshing=true), and the refresh control enters an unavailable state. This status variable is reset after the request succeeds or fails. If the response speed is too slow, a timeout fallback mechanism can be used; if the request fails, the current predicted message will not be cleared, and only a light notification (Toast) will be displayed.

[0174] S412: After obtaining the second prediction prompt information, display the second prediction prompt information in the prediction prompt display area, and control the refresh control to restore its usability.

[0175] The "Refresh Control Restored to Available" state indicates that the refresh control can provide refresh functionality, meaning that a refresh operation can be triggered through the refresh control.

[0176] In response to a refresh operation, the terminal device can invoke a prompt generation model (such as a large language model) to regenerate a second predicted prompt based on the current information in the prompt input area. After obtaining the second predicted prompt, it can display the newly generated prompt in the prediction prompt display area and restore the refresh control to an available state, indicating that refresh operations can continue to be triggered via the refresh control. Simultaneously, the refresh control's appearance can be restored to its initial state. For example, as shown... Figure 12 As shown in interface c, taking the second prediction prompt as “a 3D side-scrolling main-view dungeon game with standardized layout, dropped items, one monster every two floors, and cool style graphics” as an example, after obtaining the second prediction prompt, the second prediction prompt can be displayed in the prediction prompt display area 1202, and the grayed-out refresh control 1201 is canceled, so that the refresh control 1201 is restored to a usable state.

[0177] Therefore, by using the above method, the refresh control can be used to trigger the refresh of the prediction prompt information displayed in the prediction prompt display area. In response to the refresh operation, the refresh control can be controlled to enter an unavailable state, which can effectively prevent users from repeatedly clicking the refresh control multiple times in a short period of time, prevent batch duplicate requests or request conflicts, and ensure the stability of system operation.

[0178] • How to view historical notification information:

[0179] In one possible implementation, if at least one refresh operation is triggered while keeping the current information in the prompt input area unchanged, then adjacent generated predicted prompt information can be viewed. That is, the method provided in this application embodiment may further include the following steps S51 or S52 (not shown in the figure):

[0180] S51: In response to the previous prediction prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, the previous prediction prompt information is displayed in the prediction prompt display area. The current prediction prompt information is generated in response to the refresh operation triggered by the previous prediction prompt information.

[0181] It should be understood that, while keeping the current information in the input area unchanged, triggering at least one refresh operation on the prediction prompt information in the prediction prompt display area can generate multiple different prediction prompt information. In this case, the above prompt viewing operation or the following prompt viewing operation can be realized.

[0182] The above-mentioned prompt viewing operation is used to indicate that when the current prediction prompt is not the first prediction prompt generated, the prompt can be viewed before the current prediction prompt. For example, the above-mentioned prompt viewing operation can be triggered by a preset gesture (such as swiping left or right), a preset control (such as a key to control direction ("A" key or "D" key)), or by scrolling with the mouse wheel (such as horizontal scrolling). This application does not specifically limit the triggering method of the above-mentioned prompt viewing operation.

[0183] The preceding prediction prompt is generated based on the current information in the prompt input area, preceding the current prediction prompt. In other words, the current prediction prompt is a new prompt generated after a refresh operation is triggered when the preceding prediction prompt is displayed in the prediction prompt display area. This application does not specifically limit the preceding prediction prompt to the current prediction prompt.

[0184] For example, a user can trigger the viewing of the above prompt by a preset gesture (such as swiping right on the current prediction prompt information). In response to this viewing action, the terminal device can display a preset switching animation (such as a horizontal panning animation) and show the above prediction prompt information in the prediction prompt display area. For example, see... Figure 13 , Figure 13 This is a schematic diagram illustrating the operation of triggering the above prompt provided in an embodiment of this application, such as... Figure 13 As shown in interface a, the current prediction prompt can be "A 3D vertical top-down dungeon game with procedural rooms, loot, a boss every 5 floors, and pixel-style graphics". The user can swipe right on the current prediction prompt to trigger the above prompt viewing operation. In response to the above prompt viewing operation, the above prediction prompt can be displayed in the prediction prompt display area 1301, such as "A 3D horizontal top-down dungeon game with standardized layout, loot, a monster every 2 floors, and cool style graphics".

[0185] Furthermore, users can use the above-mentioned prediction prompts displayed in the prediction prompt display area to trigger operations such as adoption, content replacement, and deletion. In other words, users can directly use the above-mentioned prediction prompts to drive the AI ​​model to perform corresponding tasks, or users can further optimize and adjust the above-mentioned prediction prompts.

[0186] S52: In response to a subsequent prediction prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, the following prediction prompt information is displayed in the prediction prompt display area. The following prediction prompt information is generated in response to a refresh operation triggered by the current prediction prompt information.

[0187] The following prompt viewing operation is used to indicate that when the current prediction prompt is not the last prediction prompt generated, the following prompt viewing operation is to be viewed. For example, the following prompt viewing operation can be triggered by a preset gesture (such as swiping left or right), a preset control (such as a key to control the direction ("A" key or "D" key)), or by scrolling with the mouse wheel (such as horizontal scrolling). This application does not specifically limit the triggering method of the following prompt viewing operation.

[0188] The current prediction prompt is the prediction prompt currently displayed in the prediction prompt display area. It can be a prediction prompt generated based on the current information in the prompt input area, preceding the following prediction prompt. That is, the following prediction prompt is a new prediction prompt generated after a refresh operation is triggered when the current prediction prompt is displayed in the prediction prompt display area. In this regard, this application does not specifically limit the following prediction prompt and the current prediction prompt.

[0189] For example, a user can trigger a "view the following text" action by using a preset gesture (such as swiping left on the current prediction prompt). In response to this action, the terminal device can display the following prediction prompt in the prediction prompt display area. For example, see... Figure 14 , Figure 14 This is a schematic diagram illustrating the operation of triggering the following prompt for viewing, as provided in the embodiments of this application. Figure 14 As shown in interface a, the current prediction prompt can be "A 3D side-scrolling dungeon game with standardized layout, dropped items, one monster every 2 floors, and cool-style graphics". The user can swipe left on the current prediction prompt to trigger the following prompt viewing operation. In response to the following prompt viewing operation, the following prediction prompt can be displayed in the prediction prompt display area 1401, such as "A 3D vertical top-down dungeon game with procedural rooms, dropped items, one boss every 5 floors, and pixel-style graphics".

[0190] Furthermore, users can trigger actions such as adoption, content replacement, and deletion based on the predicted information displayed in the prediction prompt area. In other words, users can directly use the predicted information to drive the AI ​​model to perform corresponding tasks, or they can further optimize and adjust the predicted information.

[0191] Therefore, by using the above method, under the premise that the current information in the prompt input area remains unchanged and multiple sets of differentiated prediction prompts are generated by triggering a refresh, the historically generated prediction prompt information can be reviewed through the context viewing operation. This solves the problem that the original prediction prompt information is directly overwritten and cannot be retrieved after the refresh, and completely preserves the prediction prompt information from multiple rounds, thus meeting the user's needs for review and comparison.

[0192] In another possible implementation, at least one refresh operation can be triggered while keeping the current information in the prompt input area unchanged. Alternatively, a list of historical prompt information can be viewed, and the target predicted prompt information to be used can be selected from it. That is, the method provided in this application embodiment may also include the following steps S61-S62 (not shown in the figure):

[0193] S61: In response to a historical prompt viewing operation triggered by the predicted prompt display area, display a list of historical prompt information, which includes multiple predicted prompts generated based on the current information.

[0194] The historical prompt viewing operation is used to indicate the viewing of multiple predicted prompt messages generated based on the current information. For example, the historical prompt viewing operation can be triggered by clicking the historical prompt message control. This application does not specifically limit the triggering method of the historical prompt viewing operation.

[0195] The historical alert list is used to store multiple prediction alerts generated based on the current information. These prediction alerts can be arranged in order of their generation time.

[0196] For example, the prediction prompt display area includes a historical prompt information control. Users can trigger a historical prompt viewing operation by clicking the historical prompt information control. In response to this historical prompt viewing operation, the terminal device can display a list of historical prompt information, including multiple prediction prompts generated based on current information. For example, see... Figure 15 , Figure 15 This is a schematic diagram illustrating the display history prompt information list provided in an embodiment of this application, such as... Figure 15 As shown in interface a, users can click the history notification information control 1501 to trigger a history notification viewing operation. In response to this history notification viewing operation, as shown... Figure 15 As shown in interface b, a list of historical prompts 1502 can be displayed, including prediction prompt 1 generated at 16:55, prediction prompt 2 generated at 17:10, prediction prompt 3 generated at 17:30, etc.

[0197] S62: In response to a selection operation triggered by a target prediction prompt among multiple prediction prompts, display the target prediction prompt in the prediction prompt display area.

[0198] The target prediction prompt refers to the selected prediction prompt among multiple prediction prompts. It can be any one of the multiple prediction prompts. This application does not specifically limit the target prediction prompt.

[0199] For example, a user can select any one of the multiple prediction prompts as the target prediction prompt. For instance, a user can click on a prediction prompt in the historical prompt list to trigger the selection operation. The selected prediction prompt can then be used as the target prediction prompt. In response to this selection operation, the terminal device can display the target prediction prompt in the prediction prompt display area. That is, the prediction prompt display area displays the plain text and various element controls and their respective element content included in the target prediction prompt.

[0200] Therefore, by using the above method, multiple predicted suggestions generated based on the same input content can be displayed in a historical suggestion list, allowing for a visual preview of all predicted suggestions and improving browsing efficiency. Furthermore, the desired predicted suggestion can be quickly identified without having to search through the list step by step, simplifying the operation process and reducing the user's search costs.

[0201] In one possible implementation, multiple predicted prompts generated for the same input information can be cached using a history stack. That is, the method provided in this application embodiment may further include the following step S71 (not shown in the figure):

[0202] S71: Store multiple prediction prompts generated based on the current information into the history stack. The multiple prediction prompts are arranged in the history stack according to their respective generation times.

[0203] The history stack is used to provide the preceding prediction prompt information in response to the preceding prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, or to provide the following prediction prompt information in response to the following prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, or to provide a list of historical prompt information in response to the historical prompt viewing operation triggered by the prediction prompt display area.

[0204] The History Stack stores multiple predicted prompts generated based on the current information in the prompt input area. These predicted prompts can be arranged according to their respective generation times, allowing for unified management and providing data support for subsequent viewing of each generated prompt. Specifically, an array structure `historyStack:Prediction` can be maintained on the front end, along with a cursor for positioning. Each refresh, adoption, or content replacement operation updates the cursor position. When the number of records exceeds a capacity threshold (e.g., 20 records), the oldest record is discarded according to the First In First Out (FIFO) rule. The previous / next prompt viewing operation is triggered by touch start / touchmove / touchend (mobile devices) or scroll wheel events (wheel), or the left / right arrow keys (ArrowLeft / ArrowRight) to increase or decrease the cursor value. As can be seen, mobile devices can trigger the above-mentioned or below-mentioned prompt viewing actions via touch gestures (such as tap / swipe). Personal computers (PCs) support triggering these actions via mouse clicks, horizontal scrolling with the scroll wheel, the Shift key combined with the scroll wheel, and the arrow keys (← / →). Additionally, it supports triggering the adoption action via Enter and switching focus between different element controls via Tab. Based on the cross-platform compatibility methods described above, consistent availability and accessibility across various input devices are guaranteed.

[0205] In practical applications, if the current information in the prompt input area remains unchanged, each time a refresh operation is triggered and a new prediction prompt is generated, the generated prediction prompt can be automatically stored in the history stack.

[0206] For example, when a context view operation is triggered for the current predicted prompt in the prediction prompt display area, the context predicted prompt information can be retrieved from the history stack. For instance, the prediction prompt information whose generation time is before and adjacent to the generation time of the current prediction prompt information can be used as the context predicted prompt information. Alternatively, when a context view operation is triggered for the current predicted prompt in the prediction prompt display area, the context predicted prompt information can be retrieved from the history stack. For instance, the prediction prompt information whose generation time is after and adjacent to the generation time of the current prediction prompt information can be used as the context predicted prompt information. Alternatively, when a history prompt view operation is triggered through the prediction prompt display area, multiple prediction prompt information can be retrieved from the history stack to provide a history prompt information list.

[0207] Therefore, the historical record stack can cache multiple prediction prompts for the same input information, and the generation time can be used as the sorting rule to achieve structured management of prediction prompts, which facilitates quick retrieval and calling of data later.

[0208] • How to trigger the generation of prediction prompts:

[0209] In one possible implementation, if the prompt input area does not include input information, inputting input information that meets the prediction information conditions in the prompt input area can trigger the display of the prediction prompt display area. That is, the above-mentioned S502 may include the following step S81 (not shown in the figure):

[0210] S81: In response to the operation of inputting initial input information that meets the preset information conditions in the prompt input area, display the prediction prompt display area and display the prediction prompt information corresponding to the initial input information in the prediction prompt display area.

[0211] The preset information conditions are the conditions that trigger the display of the prediction prompt display area. For example, the preset information conditions may be that the number of characters in the initial input information entered in the prompt input area must exceed a preset character count threshold (such as 1-2 characters). When the initial input information meets the preset information conditions, the prediction prompt display area can be displayed; otherwise, when the initial input information does not meet the preset information conditions, the prediction prompt display area cannot be displayed. In this regard, this application does not specifically limit the preset information conditions.

[0212] The initial input information is the information entered when no input information is provided in the prompt input area, such as natural descriptive text or a few characters. This application does not specifically limit the initial input information.

[0213] For example, taking the preset information conditions described above as an example, in the initial guidance state (QuickStart), the user can enter initial input information (such as a few characters) in the prompt input area. If the number of characters in the initial input information exceeds a preset character threshold, it is considered that the initial input information meets the preset information conditions, and a predicted prompt display area can be displayed. For example, in response to the input operation of the initial input information that meets the preset information conditions, the terminal device can display the predicted prompt display area floating above the prompt input area, and can display the predicted prompt information generated based on the initial input information in the predicted prompt display area. At the same time, the position of the prompt input area remains unchanged to ensure visual stability.

[0214] The initial guidance state refers to the system's preset content (such as a welcome message) or preset content (such as reference prompts) that can be displayed in a loop on the target interface when the prompt input area does not contain input information, in order to reduce the user's unfamiliarity with the blank prompt input area.

[0215] Specifically, debounce processing logic can be attached to the input change event / input event (onChange / onInput) callback in the prompt input area. The debounce delay duration is set to 150 milliseconds to 300 milliseconds. After the user's input operation pauses, the currently entered information in the prompt input area is used as context information to call the prediction prompt service. The prediction prompt service generates prediction prompt information based on this. The prediction prompt service can return structured prediction prompt information. The data format can be: {prediction result (fragments): array (Array) <{type (type): "plain text (text)"|"element control (pill)", element content (value), list of candidate element content (candidates)?}>}, indicating that the type in the returned prediction result can be plain text or element control. When the type is element control, it needs to include the element content displayed by the element control and a list of multiple candidate element contents corresponding to the information element of the element control, rather than a plain text string. Based on this, the prediction prompt information generated based on the initial input information can be displayed in the prediction prompt display area.

[0216] The predictive tooltip display area can be rendered as a separate layer, specifically through ReactPortal, Vue Teleport, or a native absolutely positioned (position: absolute) top-level container. The predictive tooltip display area is rendered above the tooltip input area and anchored to the top of the input area using absolute positioning, ensuring that the underlying Document Object Model (DOM) does not reflow due to the popup's display. The entrance and exit animations of the predictive tooltip display area are implemented using Cascading Style Sheets Transition (CSS Transition) or JavaScript animations driven by RequestAnimationFrame.

[0217] Therefore, by using the above method, hiding the prediction prompt display area when there is no initial input information or the initial input information does not meet the preset information conditions can avoid unnecessary elements obstructing the view. The prediction prompt display area only pops up and displays after the initial input information meets the preset information conditions, thus ensuring a clean and simple interface and reducing unnecessary visual interference. Furthermore, displaying the prediction prompt display area only after ensuring the initial input information meets the preset information conditions, and displaying the generated prediction prompt information through the prediction prompt display area, avoids generating prediction prompt information based on input information without substantial content, reducing the waste of processing resources.

[0218] In one possible implementation, when the prompt input area includes basic input information, adjusting the basic input information in the prompt input area can trigger the display of the predictive prompt display area. That is, the above-mentioned S502 may include the following step S91 (not shown in the figure):

[0219] S91: In response to an information adjustment operation triggered in the prompt input area for basic input information, a prediction prompt display area is displayed, and based on the adjusted information obtained after the information adjustment operation, prediction prompt information is displayed in the prediction prompt display area. The adjustment range of the information adjustment operation for the basic input information meets the preset adjustment conditions.

[0220] Basic input information refers to the input information already included in the prompt input area, such as natural descriptive text or a few characters. This application does not specifically limit the basic input information.

[0221] Information adjustment operations are used to adjust basic input information. For example, information adjustment operations may include, but are not limited to, information addition operations triggered by basic input information, information deletion operations triggered by basic input information, and information modification operations triggered by basic input information. This application does not specifically limit information adjustment operations in this regard.

[0222] The preset adjustment conditions are used to decide whether to respond to the current information adjustment operation and generate predictive prompts. If the adjustment range of the information adjustment operation on the basic input information meets the preset adjustment conditions, then predictive prompts are generated based on the adjusted information obtained through the information adjustment operation. This indicates that the adjusted information is valid input information and has a significant difference from the basic input information. In this case, a predictive prompt display area can be displayed, showing the predictive prompts generated based on the adjusted information. Conversely, if the adjustment range of the information adjustment operation on the basic input information does not meet the preset adjustment conditions, then no predictive prompts will be generated based on the adjusted information obtained through the information adjustment operation. This indicates that there is no significant difference between the adjusted information and the basic input information, and in this case, it is not necessary to display the predictive prompt display area. For example, the preset adjustment conditions may specify that the semantic similarity between the adjusted information and the basic input information does not exceed a preset similarity threshold, or that the number of adjusted characters corresponding to the information adjustment operation exceeds a preset number of characters. This application does not specifically limit the preset adjustment conditions in this regard.

[0223] For example, taking the preset adjustment conditions described above as an example, when the prompt input area includes basic input information, the user can trigger an information adjustment operation based on the basic input information. If the number of characters of the newly entered information based on the basic input information exceeds the preset number of characters, it means that the adjustment range of the information adjustment operation on the basic input information meets the preset adjustment conditions. Then, the prediction prompt display area can be displayed, and the prediction prompt information generated based on the adjusted information can be displayed therein.

[0224] Therefore, using the above method, for scenarios where basic input information already exists in the prompt input area, predicted prompt information can be triggered and displayed after the user adjusts the basic input information. Furthermore, by setting preset adjustment conditions, the predicted prompt display area is only activated when the user's adjustment of the basic input information reaches a specified threshold; minor adjustments will not trigger an update of the predicted prompt information. This effectively prevents frequent changes to element content, ensuring a clean interface and allowing for focused operation. Simultaneously, by setting predictive adjustment conditions to determine whether to generate predicted prompt information, it avoids generating predicted prompt information based on invalid adjustments, reducing the waste of processing resources.

[0225] In one possible implementation, one of the multiple reference prompts can be selected and filled into the prompt input area. That is, the method provided in this application embodiment may also include the following steps S101-S102 (not shown in the figure):

[0226] S101: Display at least one reference prompt message on the target interface.

[0227] The reference prompts are pre-set prompts used to drive the AI ​​model to perform corresponding tasks. For example, the reference prompts can be pre-packaged complete prompts, or they can be complete prompts used in historical projects. Furthermore, the reference prompts can be displayed as tags on the target interface; however, this application does not specifically limit the reference prompts or their presentation.

[0228] For example, a user can launch the target application on the terminal device by clicking its icon displayed on the device screen. Once launched, the target application's interface can be displayed on the device screen. This interface can display at least one reference prompt message presented as a label, and this prompt message can be displayed using a preset display method (such as a carousel or static list). For example, refer to... Figure 16 , Figure 16 A schematic diagram of the reference prompt information provided in the embodiments of this application, such as Figure 16 As shown, the target interface includes pre-packaged reference prompts in the form of tags: "Dungeon" 1601, "Shooting" 1602, and "Racing" 1603.

[0229] S102: In response to a selection operation triggered by a target reference message in at least one reference message, display the target reference message in the prompt input area as the basic input information.

[0230] The target reference prompt information refers to the selected reference prompt information, which is used as the basic input information. At this time, the basic input information can be directly used as the prompt information applied when the AI ​​model performs the corresponding task. It can be any reference prompt information. This application does not specifically limit the target reference prompt information.

[0231] For example, a user can click on one of the reference prompts to trigger a selection. In response to this selection, the selected prompt becomes the target prompt, which can then be displayed in the input area, such as showing its complete content. Furthermore, the complete content of the target prompt can be used as the base input, allowing the user to adjust it to their needs. Based on these adjustments, predictive prompts can be generated for the user to choose from.

[0232] Therefore, by using the above method, the target reference prompt information can be used as the basic input information, so that the user does not need to manually input the basic input information. The information can be quickly adjusted based on this, and rich and accurate predictive prompt information can be generated based on the adjusted information.

[0233] It should be understood that in practical applications, after selecting the target reference prompt and filling its corresponding complete content into the prompt input area, the target reference prompt can be directly used as the prompt for subsequent practical applications. This eliminates the need for users to manually edit the input information, allowing them to quickly obtain high-quality prompts. This alleviates the blank canvas anxiety that beginners often experience when facing a blank prompt input area, and eliminates the need for subsequent prediction steps, simplifying the prompt determination process, improving the input efficiency of prompts, and contributing to a better user experience.

[0234] • How to disable the prediction hint display area:

[0235] In one possible implementation, the prediction prompt display area can be turned off in the following manner, that is, the method provided in this application embodiment may further include the following steps S111 or S112 (not shown in the figure):

[0236] S111: In response to an adoption operation triggered by a prediction tip display area, cancel the display of the prediction tip display area.

[0237] For example, the prediction prompt display area includes a confirmation control. Users can trigger an acceptance operation by clicking the confirmation control. In response to the acceptance operation triggered by the prediction prompt information in the prediction prompt display area, the terminal device can display the prediction prompt information in the prompt input area and automatically cancel the display of the prediction prompt display area.

[0238] Specifically, when the adoption operation is triggered, the prediction results are iterated through, and constant information and the selected value of the pill control (i.e., the content of the selected element corresponding to the information element) are concatenated in the order of the statements to obtain the final prediction prompt information. Then, this can be filled back into the value attribute of the prompt input area to display the prediction prompt information in the prompt input area and trigger the input change event / input event (onChange / input) to ensure compatibility with downstream business logic.

[0239] S112: In response to a close operation triggered on the prediction hint display area, cancel the display of the prediction hint display area.

[0240] The close operation is used to cancel the display of the prediction prompt display area. For example, the close operation can be triggered by clicking the close control in the prediction prompt display area. This application does not specifically limit the triggering method of the close operation.

[0241] For example, the prediction prompt display area includes a close control. Users can trigger a close operation by clicking the close control, and the terminal device can cancel the display of the prediction prompt display area in response to the close operation.

[0242] It should be noted that after a user manually closes the prediction prompt display area by triggering a close operation, they can still click to view the prediction prompt display area again. For example, in response to the triggered close operation, after the prediction prompt display area is canceled, a corresponding restore control can be provided. Users can click the restore control to restore the prediction prompt display area.

[0243] Furthermore, if a user triggers another information editing operation in the prompt input area when the prediction prompt display area is closed—for example, editing existing information in the prompt input area beyond a preset number of characters—a refreshed prediction prompt message can be displayed on the target interface. For instance, a refresh prompt message can be displayed at the restore control corresponding to the prediction prompt display area, indicating that the prediction prompt message should be refreshed based on the current information editing operation. At this time, the user can click the restore control to restore the prediction prompt display area, where the refreshed prediction prompt message will be displayed. This prediction prompt message is generated based on the current information obtained from the current information editing operation.

[0244] Therefore, by using the above method, two closing logics are provided: automatic closing and manual closing. This can adapt to different user operation intentions, thus satisfying the need for quick use and supporting independent control of the interface state, thereby improving the degree of freedom of interaction.

[0245] • Enable or disable the prediction hint function via a toggle switch:

[0246] In one possible implementation, the settings interface includes a switch control for the prediction prompt function, which can control the activation of the prediction prompt function. That is, the method provided in this application embodiment may further include the following steps S121-S122 (not shown in the figure):

[0247] S121: Display settings interface, which includes a switch control for the prediction prompt function. The prediction prompt function is used to indicate the display of prediction prompt information based on the current information in the prompt input area.

[0248] The AI ​​Prediction feature's toggle control (Settings Toggle) indicates whether the AI ​​Prediction feature is enabled. The AI ​​Prediction feature generates corresponding prediction prompts based on the current information obtained from the information editing operation in the prompt input area.

[0249] The settings interface refers to the interface in the target application used to set relevant attributes. The settings interface includes a toggle switch for the prediction hint function, which users can use to select whether to enable or disable the prediction hint function.

[0250] For example, a user can click a settings control in the target application, and the terminal device can display a settings interface in response to this action. For instance, see [reference 1]. Figure 17 , Figure 17 A schematic diagram of the settings interface provided in the embodiments of this application, as shown below. Figure 17 As shown, the settings interface includes a switch control 1701 for the prediction prompt function.

[0251] S122: When the switch control is in the on state, execute the information editing operation triggered in the prompt input area, and display the predicted prompt information in the predicted prompt display area based on the current information obtained from the information editing operation in the prompt input area; when the switch control is in the off state, refuse to execute the information editing operation triggered in the prompt input area, and display the predicted prompt information in the predicted prompt display area based on the current information obtained from the information editing operation in the prompt input area.

[0252] For example, the toggle control for the prediction prompt function can be in the off state by default. Users can trigger the on operation by clicking the toggle control, and the terminal device responds to this operation by turning the toggle control on. When the toggle control is on, it indicates that the prediction prompt function is on. The corresponding prediction prompt information can be generated based on the current information obtained from the information editing operation in the prompt input area, and the prediction prompt information is displayed in the prediction prompt display area. For details, please refer to the implementation method described in step S502 above, which will not be repeated here.

[0253] For example, the toggle switch for the prediction prompt function can be on by default. Users can trigger a shutdown operation by clicking the toggle switch, and the terminal device responds to this shutdown operation by turning the toggle switch off. When the toggle switch is off, the prediction prompt function is disabled. It cannot generate corresponding prediction prompts based on the current information obtained through information editing in the prompt input area, nor can it display the prediction prompts in the prompt display area. Only the functions supported by the prompt input area are retained to accommodate different users (such as users with strong prompt writing skills or users who prefer to input their own prompts).

[0254] Specifically, the system reads the prediction suggestion function's enabled status (aiPredictionEnabled) at the input field of the suggestion input area. This configuration can be stored locally or issued by the server. When this value is false, all subsequent prediction requests and panel rendering logic are short-circuited, meaning that the corresponding prediction suggestion information cannot be generated based on the current information in the suggestion input area, and the prediction suggestion information cannot be displayed in the prediction suggestion display area; at the same time, the existing prediction suggestion display area is unloaded to release system resources.

[0255] Therefore, by using the above method, an independent switch control for the predictive prompt function is provided, allowing users to choose to enable or disable the predictive prompt function according to their own usage habits, thereby helping to meet users' personalized usage needs.

[0256] • Methods for generating and rendering prediction prompts:

[0257] In one possible implementation, the prediction prompt information can be generated by referring to the following steps S131-S132 (not shown in the figure):

[0258] S131: Based on the current information in the prompt input area, construct a prediction prompt generation instruction. The prediction prompt generation instruction is used to instruct the generation of prediction prompt information according to the current information, distinguish between adjustable information elements and non-adjustable constant information in the prediction prompt information, and generate at least one candidate element content for each information element.

[0259] Adjustable information elements refer to information elements in the prediction prompt that can be adjusted, while non-adjustable constant information refers to fixed information in the prediction prompt that cannot be adjusted, such as fixed text. In this regard, this application does not specifically limit the types of adjustable information elements and non-adjustable constant information.

[0260] For example, a predictive prompt generation instruction can be constructed based on the current information in the prompt input area. This instruction instructs the generation of predictive prompt information according to the current information, distinguishing between adjustable information elements and non-adjustable constant information in the predictive prompt information, and generating at least one candidate element content for each information element. This ensures that the prompt generation model can generate predictive prompt information through the instruction, resulting in predictive prompt information that includes both adjustable information elements and non-adjustable constant information, with each information element including at least one candidate element content. For instance, the current information in the prompt input area can be filled into a preset expansion template to obtain the predictive prompt generation instruction.

[0261] S132: Through the prompt generation model, predictive prompt information is generated according to the predictive prompt generation instruction. The predictive prompt information includes constant information arranged in word order and candidate element content corresponding to each information element.

[0262] A prompt generation model refers to a model that generates predicted prompt information based on predicted prompt generation instructions. For example, it can be a large language model, such as Deepseek, or a generative pre-trained encoder model (GPT). This application does not specifically limit the prompt generation model to a large language model.

[0263] After determining the predictive prompt generation instruction, it is input into a prompt generation model (such as a large language model) for processing. This yields the predicted prompt information, which includes constant information arranged in word order and candidate elements corresponding to each information element. In other words, the predicted prompt information possesses complete semantic meaning. Users can directly use this information to drive the AI ​​model to perform corresponding tasks, or they can further optimize and adjust it in the prompt input area. Furthermore, the candidate element content corresponding to each information element provides data support for subsequent content replacement operations.

[0264] Therefore, by using the prompt generation model and generating instructions based on the prediction prompts, prediction prompt information that supports local adjustments can be generated. By distinguishing between non-adjustable constant information and adjustable information elements, the quality and standardization of the constant information part are ensured. For adjustable information elements, candidate element content is further configured, ensuring that the information elements can be quickly adjusted in the future, thereby helping to provide rich and accurate prediction prompt information.

[0265] In one possible implementation, "displaying prediction prompt information in the prediction prompt display area" in S503 above may include the following steps S141-S142 (not shown in the figure):

[0266] S141: For each constant information in the prediction prompt information, render and display the constant information in text form in the prediction prompt display area.

[0267] For example, for each constant information in the prediction prompt information, each constant information can be rendered and displayed in the prediction prompt display area as text, that is, the constant information in the prediction prompt display area is plain text and does not support adjustment.

[0268] S142: For each information element in the prediction prompt information, render and display the information element in the form of a control in the prediction prompt display area. The information element carries the preferred element content corresponding to the information element. The preferred element content is the candidate element content corresponding to the information element that meets the content preference condition.

[0269] Content preference criteria are used to determine preferred element content. If the content of a candidate element corresponding to an information element satisfies the content preference criteria, then the candidate element content can be used as the preferred element content. For example, the content preference criteria can stipulate that the candidate element content with the highest prediction probability is the preferred element content. In this regard, this application does not specifically limit the content preference criteria.

[0270] The preferred element content is the candidate element content displayed by the information element control. It is the candidate element content corresponding to the information element that meets the content preference conditions. This application does not specifically limit the preferred element content.

[0271] For example, taking the content preference conditions described above as an example, for each information element in the prediction prompt information, each information element can be rendered and displayed in the prediction prompt display area in the form of a control. Furthermore, the preferred element content corresponding to the information element can be displayed through the control corresponding to the information element, such as displaying the candidate element content with the highest usage frequency corresponding to the information element through the control corresponding to the information element.

[0272] Specifically, the predicted suggestion information returned by the prediction suggestion service is rendered according to the word order. When the type is equal to text (type === "text"), that is, for each constant information in the predicted suggestion information, the fragment is displayed using an inline tag (span) component; when the type is equal to a pill control (type === "pill"), the fragment is displayed using a pill component with interactive attributes; each pill component is attached with its corresponding candidate element content (candidates) list, the currently selected value (selectedValue), and state (state). The state can be any one of the following: default state, selected state, or deleted selected state.

[0273] Therefore, through the aforementioned differentiated rendering methods, the fixed and adjustable content in the predictive prompts can be clearly distinguished, making it easier for users to quickly identify the location of editable and replaceable content. Furthermore, by automatically filtering preferred elements based on content selection criteria, the initial predictive prompts are ensured to align with user needs, thus enhancing the user experience.

[0274] • This application provides an exemplary description of the prompt information input method.

[0275] Finally, it can be combined Figure 18 The method for inputting prompt information provided in the embodiments of this application will be described in its entirety by way of example. Figure 18 This is a flowchart illustrating the reminder information input method provided in the embodiments of this application, such as... Figure 18As shown, the system first enters state 1: Default Input 1801, which displays a preset welcome message and reference prompts on the target interface, waiting for the user to input information. Next, the user inputs initial information 1802, and the system can detect in real time whether the initial input meets the preset information conditions. If the initial input meets the preset information conditions, the system enters state 2: Generate Predictive Prompt Information 1803, which displays the predictive prompt display area, showing the predicted prompt information corresponding to the initial input. Next, you can enter interaction branch A 1804. If a candidate content viewing operation is triggered for the first element control, a drop-down list containing multiple candidate element contents is displayed under the first information element corresponding to the first element control, so that the second element content to be replaced can be selected. For details, refer to steps S11-11 to S11-12 above. You can also enter interaction branch B 1805. If a delete selection operation is triggered for the second element control, the second element control is controlled to be in a deleted selection state. Then, a delete confirmation operation is triggered for the second element control in the deleted selection state, which can delete the second element control and its element content in the prediction prompt information. For details, refer to steps S211-S212 above. You can also enter interaction branch C 1806. If a refresh operation is triggered for the first prediction prompt information currently displayed in the prediction prompt display area, the second prediction prompt information is refreshed and displayed. For details, refer to S41 above.

[0276] Finally, you can enter state 3: Acceptance Confirmation 1807, which displays the prediction prompt information in the prompt input area. After the acceptance operation is triggered, the animation of the prediction prompt display area collapsing can also be displayed (such as moving towards the prompt input box and fading out), and then the prediction prompt display area will not be displayed.

[0277] Based on the prompt information input method provided in the preceding embodiments, this application also provides a prompt information input device. The following, in conjunction with... Figure 19 To explain, Figure 19 This is a schematic diagram of the structure of the prompt information input device 1900 provided in the embodiments of this application. The device includes:

[0278] The interface display module 1901 is used to display a target interface, the target interface including a prompt input area for inputting prompt information;

[0279] The prompt display module 1902 is used to respond to the information editing operation triggered in the prompt input area, and display the prediction prompt information in the prediction prompt display area according to the current information obtained by the information editing operation in the prompt input area. The prediction prompt information includes at least one element control corresponding to an information element. The element control is used to carry the element content of the corresponding information element and supports adjusting the element content of the information element.

[0280] The prompt adoption module 1903 is used to display the prediction prompt information in the prompt input area in response to the adoption operation triggered by the prediction prompt information in the prediction prompt display area.

[0281] Optionally, the device further includes:

[0282] The content replacement module is used to respond to the content replacement operation triggered by the first element control, replace the original first element content of the first element control with the second element content, and display the adjusted prediction prompt information in the prediction prompt display area. The first element control can be any of the element controls.

[0283] Optionally, the content replacement module is specifically used for:

[0284] In response to a candidate content viewing operation triggered by the first element control, multiple candidate element contents under the first information element corresponding to the first element control are displayed;

[0285] In response to a selection operation triggered by the second element content among the plurality of candidate element contents, the second element content is displayed via the first element control.

[0286] Optionally, the content replacement module is specifically used for:

[0287] In response to a content switching operation triggered by the first element control, the content of the first element originally displayed by the first element control is switched to the content of the second element. Both the first element content and the second element content are candidate element content under the first information element corresponding to the first element control.

[0288] Optionally, the first element control further includes a custom sub-control, and the device further includes:

[0289] A custom module is used to respond to the operation of inputting third element content through the custom sub-control, display the third element content through the first element control, and display the adjusted prediction prompt information in the prediction prompt display area.

[0290] Optionally, the device further includes:

[0291] The deletion module is used to respond to a content deletion operation triggered by the second element control, delete the second element control and its contained element content in the prediction prompt information, and display the adjusted prediction prompt information in the prediction prompt display area. The second element control can be any one of the element controls.

[0292] Optionally, the deletion module is specifically used for:

[0293] In response to a deletion selection operation triggered on the second element control, control the second element control to present a deleted selection state;

[0294] In response to a deletion confirmation operation triggered for the second element control in the deleted selected state, the second element control and its contained element content in the prediction prompt information are deleted.

[0295] Optionally, the device further includes:

[0296] The countdown module is used to start the deletion countdown in response to the second element control entering the deletion selection state;

[0297] The cancel deletion module is used to control the second element control to exit the deletion selection state if no deletion confirmation operation is received before the deletion countdown ends.

[0298] Optionally, the device further includes:

[0299] The recycling module is used to display the second element control and its element content in the element control recycling area after the second element control and its element content are deleted.

[0300] The recovery module is used to respond to a recovery operation triggered for the second element control in the element control recycling area, and to restore the display of the second element control and its element content in the adjusted prediction prompt information.

[0301] Optionally, the device further includes:

[0302] The adjustment withdrawal module is used to, in response to the adjustment withdrawal operation triggered by the prediction prompt display area, display the prediction prompt information prior to triggering the content adjustment operation in the prediction prompt display area when a content adjustment operation has been triggered by the element control in the prediction prompt information.

[0303] Optionally, the device further includes:

[0304] The refresh module is used to respond to a refresh operation triggered by the first prediction prompt information currently displayed in the prediction prompt display area, and refresh and display a second prediction prompt information in the prediction prompt display area based on the current information obtained by the information editing operation in the prompt input area. The second prediction prompt information is different from the first prediction prompt information.

[0305] Optionally, the refresh module is specifically used for:

[0306] In response to the refresh operation triggered by the refresh control in response to the first predicted prompt information, the refresh control is controlled to enter an unavailable state;

[0307] After the second prediction prompt information is obtained, the second prediction prompt information is displayed in the prediction prompt display area, and the refresh control is controlled to restore its usability.

[0308] Optionally, if the refresh operation is triggered at least once while keeping the current information in the prompt input area unchanged, the device further includes:

[0309] The above text viewing module is used to respond to the above text viewing operation triggered by the current prediction prompt information in the prediction prompt display area, and to display the above prediction prompt information in the prediction prompt display area. The current prediction prompt information is generated in response to the refresh operation triggered by the above prediction prompt information.

[0310] or,

[0311] The following text viewing module is used to respond to the following text viewing operation triggered by the current prediction prompt information in the prediction prompt display area, and to display the following text prediction prompt information in the prediction prompt display area. The following text prediction prompt information is generated in response to the refresh operation triggered by the current prediction prompt information.

[0312] Optionally, if the refresh operation is triggered at least once while keeping the current information in the prompt input area unchanged, the device further includes:

[0313] The historical prompt information viewing module is used to display a historical prompt information list in response to a historical prompt viewing operation triggered by the predicted prompt display area. The historical prompt information list includes multiple predicted prompt information generated based on the current information.

[0314] The selection module is used to display the target prediction prompt in the prediction prompt display area in response to a selection operation triggered by the target prediction prompt among the multiple prediction prompts.

[0315] Optionally, the device further includes:

[0316] The storage module is used to store multiple prediction prompts generated based on the current information into a history stack, wherein the multiple prediction prompts are arranged in the history stack according to their respective generation times;

[0317] The history stack is used to provide the preceding prediction prompt information in response to the preceding prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, or to provide the following prompt information in response to the following prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, or to provide a list of historical prompt information in response to the historical prompt viewing operation triggered by the prediction prompt display area.

[0318] Optionally, when the prompt input area does not include input information, the prompt display module 1902 is specifically used for:

[0319] In response to the operation of inputting initial input information that meets preset information conditions in the prompt input area, the prediction prompt display area is displayed, and the prediction prompt information corresponding to the initial input information is displayed in the prediction prompt display area.

[0320] Optionally, when the prompt input area includes basic input information, the prompt display module 1902 is specifically used for:

[0321] In response to an information adjustment operation triggered in the prompt input area for the basic input information, the prediction prompt display area is displayed, and the prediction prompt information is displayed in the prediction prompt display area based on the adjusted information obtained after the information adjustment operation. The adjustment range of the information adjustment operation for the basic input information meets preset adjustment conditions.

[0322] Optionally, the device further includes:

[0323] A reference prompt information display module is used to display at least one reference prompt information on the target interface;

[0324] The basic input information determination module is used to display the target reference prompt information in the prompt input area as the basic input information in response to a selection operation triggered by the target reference prompt information in the at least one reference prompt information.

[0325] Optionally, the device further includes:

[0326] The cancel display module is used to cancel the display of the prediction prompt display area in response to the adoption operation triggered by the prediction prompt information in the prediction prompt display area;

[0327] or,

[0328] The closing module is used to cancel the display of the prediction prompt display area in response to a closing operation triggered on the prediction prompt display area.

[0329] Optionally, the device further includes:

[0330] The settings interface display module is used to display the settings interface, which includes a switch control for the prediction prompt function. The prediction prompt function is used to instruct the display of the prediction prompt information based on the current information in the prompt input area.

[0331] The switch module is configured to, when the switch control is in the on state, execute the information editing operation triggered in the prompt input area, and display the prediction prompt information in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area; when the switch control is in the off state, refuse to execute the information editing operation triggered in the prompt input area, and display the prediction prompt information in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area.

[0332] Optionally, the device further includes the following module for generating the prediction prompt information:

[0333] The construction module is used to construct a prediction prompt generation instruction based on the current information in the prompt input area. The prediction prompt generation instruction is used to instruct the generation of the prediction prompt information according to the current information, distinguish the adjustable information elements and non-adjustable constant information in the prediction prompt information, and generate at least one candidate element content for each information element.

[0334] The generation module is used to generate the prediction prompt information according to the prediction prompt generation instruction through the prompt generation model. The prediction prompt information includes constant information arranged in word order and candidate element content corresponding to each information element.

[0335] Optionally, the prompt display module 1902 is specifically used for:

[0336] For each constant information in the prediction prompt information, the constant information is rendered and displayed in text form in the prediction prompt display area;

[0337] For each information element in the prediction prompt information, the information element is rendered and displayed in the form of a control in the prediction prompt display area. The preferred element content corresponding to the information element is displayed through the information element. The preferred element content is the candidate element content corresponding to the information element that meets the content preference conditions.

[0338] This application also provides a computer device, which may specifically be a terminal device or a server. The terminal device and server provided in this application will be described below from the perspective of hardware implementation.

[0339] See Figure 20 , Figure 20 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Figure 20 As shown, for ease of explanation, only the parts relevant to the embodiments of this application are illustrated. For specific technical details not disclosed, please refer to the method section of the embodiments of this application.

[0340] refer to Figure 20 The terminal device includes: a radio frequency (RF) circuit 1210, a memory 1220, an input unit 1230 (including a touch panel 1231 and other input devices 1232), a display unit 1240 (including a display panel 1241), a sensor 1250, an audio circuit 1260 (connected to a speaker 1261 and a microphone 1262), a wireless fidelity (WiFi) module 1270, a processor 1280, and a power supply 1290, etc. Those skilled in the art will understand that... Figure 20 The terminal device structure shown does not constitute a limitation on the computer and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0341] The memory 1220 can be used to store software programs and modules. The processor 1280 executes various computer functions and data processing by running the software programs and modules stored in the memory 1220. The memory 1220 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer (such as audio data, telephone directory, etc.). In addition, the memory 1220 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0342] The processor 1280 is the control center of the computer, connecting various parts of the computer through various interfaces and lines. It performs various computer functions and processes data by running or executing software programs and / or modules stored in the memory 1220, and by calling data stored in the memory 1220. Optionally, the processor 1280 may include one or more processing units; preferably, the processor 1280 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 1280.

[0343] In this embodiment, the processor 1280 included in the terminal is used to execute the steps in the prompt information input method described in the foregoing embodiments.

[0344] See Figure 21 , Figure 21 This is a schematic diagram of the structure of a server 1300 provided in an embodiment of this application. The server 1300 can vary significantly due to different configurations or performance, and may include one or more central processing units (CPUs) 1322 (e.g., one or more processors) and memory 1332, and one or more storage media 1330 (e.g., one or more mass storage devices) for storing application programs 1342 or data 1344. The memory 1332 and storage media 1330 can be temporary or persistent storage. The program stored in the storage media 1330 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the server. Furthermore, the CPU 1322 may be configured to communicate with the storage media 1330 and execute the series of instruction operations stored in the storage media 1330 on the server 1300.

[0345] Server 1300 may also include one or more power supplies 1326, one or more wired or wireless network interfaces 1350, one or more input / output interfaces 1358, and / or one or more operating systems, such as Windows Server. TM Mac OS X TM Unix TM Linux TM FreeBSD TM etc.

[0346] The steps performed by the server in the above embodiments can be based on this Figure 21 The server structure shown is illustrated. The CPU 1322 is used to execute the steps in the prompt information input methods described in the foregoing embodiments.

[0347] This application also provides a computer-readable storage medium for storing a computer program that performs the steps in the prompt information input method described in the foregoing embodiments.

[0348] This application also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in the prompt information input method described in the foregoing embodiments.

[0349] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0350] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0351] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0352] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0353] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing computer programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0354] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0355] The above-described 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.

Claims

1. A method for inputting prompt information, characterized in that, The method includes: Display a target interface, the target interface including a prompt input area for inputting prompt information; In response to an information editing operation triggered in the prompt input area, a prediction prompt information is displayed in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area. The prediction prompt information includes at least one element control corresponding to an information element. The element control is used to carry the element content of the corresponding information element and supports adjusting the element content of the information element. In response to an adoption operation triggered by the prediction prompt information in the prediction prompt display area, the prediction prompt information is displayed in the prompt input area.

2. The method according to claim 1, characterized in that, The method further includes: In response to a content replacement operation triggered by a first element control, the original first element content carried by the first element control is replaced with the second element content, and the adjusted prediction prompt information is displayed in the prediction prompt display area. The first element control can be any one of the element controls.

3. The method according to claim 2, characterized in that, The step of responding to a content replacement operation triggered by a first element control by replacing the original first element content carried by the first element control with the second element content includes: In response to a candidate content viewing operation triggered by the first element control, multiple candidate element contents under the first information element corresponding to the first element control are displayed; In response to a selection operation triggered by the second element content among the plurality of candidate element contents, the second element content is displayed via the first element control.

4. The method according to claim 2, characterized in that, The step of responding to a content replacement operation triggered by a first element control by replacing the original first element content carried by the first element control with the second element content includes: In response to a content switching operation triggered by the first element control, the content of the first element originally displayed by the first element control is switched to the content of the second element. Both the first element content and the second element content are candidate element content under the first information element corresponding to the first element control.

5. The method according to claim 3 or 4, characterized in that, The first element control also includes a custom child control, and the method further includes: In response to the operation of inputting third element content through the custom sub-control, the third element content is displayed through the first element control, and the adjusted prediction prompt information is displayed in the prediction prompt display area.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: In response to a content deletion operation triggered by the second element control, the second element control and its contained element content in the prediction prompt information are deleted, and the adjusted prediction prompt information is displayed in the prediction prompt display area. The second element control can be any one of the element controls.

7. The method according to claim 6, characterized in that, The step of deleting the second element control and its contained element content from the prediction prompt information in response to the content deletion operation triggered by the second element control includes: In response to a deletion selection operation triggered on the second element control, control the second element control to present a deleted selection state; In response to a deletion confirmation operation triggered for the second element control in the deleted selected state, the second element control and its contained element content in the prediction prompt information are deleted.

8. The method according to claim 7, characterized in that, The method further includes: In response to the second element control entering the deletion selection state, a deletion countdown begins; If no deletion confirmation is received before the deletion countdown ends, the second element control is controlled to exit the deletion selection state.

9. The method according to any one of claims 6 to 8, characterized in that, The method further includes: After the second element control and its contained element content are deleted, the second element control and its contained element content are displayed in the element control recycle area. In response to a recovery operation triggered for the second element control in the element control recycle area, the second element control and its contained element content are restored to be displayed in the adjusted prediction prompt information.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: In response to a refresh operation triggered by the first prediction prompt information currently displayed in the prediction prompt display area, a second prediction prompt information is refreshed and displayed in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area. The second prediction prompt information is different from the first prediction prompt information.

11. The method according to claim 10, characterized in that, The step of responding to a refresh operation triggered by the first prediction prompt information currently displayed in the prediction prompt display area, and refreshing and displaying the second prediction prompt information in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area, includes: In response to the refresh operation triggered by the refresh control in response to the first predicted prompt information, the refresh control is controlled to enter an unavailable state; After the second prediction prompt information is obtained, the second prediction prompt information is displayed in the prediction prompt display area, and the refresh control is controlled to restore its usability.

12. The method according to claim 10 or 11, characterized in that, If at least one refresh operation is triggered while keeping the current information in the prompt input area unchanged, the method further includes: In response to a previous context view operation triggered by the current prediction context information in the prediction context display area, the previous prediction context information is displayed in the prediction context display area. The current prediction context information is generated in response to the refresh operation triggered by the previous prediction context information. or, In response to a subsequent prediction prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, subsequent prediction prompt information is displayed in the prediction prompt display area. The subsequent prediction prompt information is generated in response to the refresh operation triggered by the current prediction prompt information.

13. The method according to claim 10 or 11, characterized in that, If at least one refresh operation is triggered while keeping the current information in the prompt input area unchanged, the method further includes: In response to a historical prompt viewing operation triggered through the predicted prompt display area, a historical prompt information list is displayed, which includes multiple predicted prompt information generated based on the current information; In response to a selection operation triggered by the target prediction prompt among the multiple prediction prompts, the target prediction prompt is displayed in the prediction prompt display area.

14. The method according to claim 12 or 13, characterized in that, The method further includes: Multiple prediction prompts generated based on the current information are stored in the history stack, and the multiple prediction prompts are arranged in the history stack according to their respective generation times; The history stack is used to provide the preceding prediction prompt information in response to the preceding prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, or to provide the following prompt information in response to the following prompt viewing operation triggered by the current prediction prompt information in the prediction prompt display area, or to provide a list of historical prompt information in response to the historical prompt viewing operation triggered by the prediction prompt display area.

15. The method according to any one of claims 1 to 14, characterized in that, When the prompt input area does not contain input information, the step of responding to an information editing operation triggered in the prompt input area and displaying prediction prompt information in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area includes: In response to the operation of inputting initial input information that meets preset information conditions in the prompt input area, the prediction prompt display area is displayed, and the prediction prompt information corresponding to the initial input information is displayed in the prediction prompt display area.

16. The method according to any one of claims 1 to 14, characterized in that, When the prompt input area includes basic input information, the step of responding to an information editing operation triggered in the prompt input area and displaying prediction prompt information in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area includes: In response to an information adjustment operation triggered in the prompt input area for the basic input information, the prediction prompt display area is displayed, and the prediction prompt information is displayed in the prediction prompt display area based on the adjusted information obtained after the information adjustment operation. The adjustment range of the information adjustment operation for the basic input information meets preset adjustment conditions.

17. The method according to claim 16, characterized in that, The method further includes: At least one reference prompt message is displayed on the target interface; In response to a selection operation triggered by a target reference prompt in the at least one reference prompt, the target reference prompt is displayed in the prompt input area as the basic input information.

18. The method according to any one of claims 1 to 17, characterized in that, The method further includes: In response to the adoption operation triggered by the prediction prompt information in the prediction prompt display area, the prediction prompt display area is canceled. or, In response to a close operation triggered on the prediction prompt display area, the prediction prompt display area is de-displayed.

19. The method according to any one of claims 1 to 18, characterized in that, The method further includes: The display settings interface includes a switch control for the prediction prompt function, which is used to instruct the display of the prediction prompt information based on the current information in the prompt input area. When the switch control is in the ON state, the information editing operation triggered in the prompt input area is executed, and the prediction prompt information is displayed in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area; when the switch control is in the OFF state, the information editing operation triggered in the prompt input area is rejected, and the prediction prompt information is displayed in the prediction prompt display area based on the current information obtained from the information editing operation in the prompt input area.

20. The method according to any one of claims 1 to 19, characterized in that, The prediction prompt information is generated in the following way: Based on the current information in the prompt input area, a prediction prompt generation instruction is constructed. The prediction prompt generation instruction is used to instruct the generation of the prediction prompt information according to the current information, distinguish the adjustable information elements and the non-adjustable constant information in the prediction prompt information, and generate at least one candidate element content for each information element. The prediction prompt generation model generates the prediction prompt information according to the prediction prompt generation instruction. The prediction prompt information includes constant information arranged in word order and candidate element content corresponding to each information element.

21. The method according to claim 20, characterized in that, The step of displaying prediction prompt information in the prediction prompt display area includes: For each constant information in the prediction prompt information, the constant information is rendered and displayed in text form in the prediction prompt display area; For each information element in the prediction prompt information, the information element is rendered and displayed in the form of a control in the prediction prompt display area. The preferred element content corresponding to the information element is displayed through the information element. The preferred element content is the candidate element content corresponding to the information element that meets the content preference conditions.

22. A prompt information input device, characterized in that, The device includes: An interface display module is used to display a target interface, the target interface including a prompt input area for inputting prompt information; The prompt display module is used to respond to the information editing operation triggered in the prompt input area, and display the prediction prompt information in the prediction prompt display area according to the current information obtained by the information editing operation in the prompt input area. The prediction prompt information includes at least one element control corresponding to the information element. The element control is used to carry the element content of the corresponding information element and supports adjusting the element content of the information element. The prompt adoption module is used to display the prediction prompt information in the prompt input area in response to the adoption operation triggered by the prediction prompt information in the prediction prompt display area.

23. A computer device, characterized in that, The device includes a processor and a memory; The memory is used to store computer programs; The processor is configured to execute the prompt information input method according to any one of claims 1 to 21 according to the computer program.

24. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, which, when executed by an electronic device, implements the prompt information input method according to any one of claims 1 to 21.

25. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the prompt information input method according to any one of claims 1 to 21.

Images