Information interaction method, electronic device, storage medium, and computer program product

Abstract

Embodiments of the present disclosure provide an information interaction method, an electronic device, a storage medium, and a computer program product. An information input region displayed on an interaction interface comprises a prompt word input region, which can allow a user to fill in input content, and a context introduction region, which can allow a user to select which files to use as context. A file identifier of a file selected by the user as context is displayed in the context introduction region in the form of a label, dragging a file identifier label displayed in the context introduction region to the prompt word input region is supported, and the input content and the file identifier label are then flexibly combined in the prompt word input region, to obtain a prompt word for dialog interaction. Not only is convenient selection of one or more files as context by a user implemented, but flexible combination of prompt words is also implemented, thereby reducing operations of manually inputting information of the file as context by the user, avoiding spelling errors that may occur during manual input, simplifying user operation, and improving overall dialog efficiency and interaction experience.

Description

Information interaction methods, electronic devices, storage media and computer program products Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to an information interaction method, electronic device, storage medium, and computer program product. Background Technology

[0002] To enable Large Language Models (LLMs) to respond more effectively based on the user's current context and improve the interactive experience, users are typically guided to provide as much contextual information as possible when engaging with the LLM. For example, in intelligent coding scenarios, LLMs can provide developers with intelligent coding assistance, helping them write code, debug programs, and find documentation faster, thereby improving development efficiency. In actual coding processes, interactive dialogue often requires various types of files, such as images, code files, and code change logs, as contextual information. The user selects a file to use as contextual information and uploads it to the LLM. Then, the user enters prompts in natural language in the input box, describing their request related to the contextual information, including file information. Finally, the LLM responds based on the uploaded contextual information and prompts. In practical applications, users may need to upload multiple files as contextual information. This requires users to manually input information for multiple files when entering prompts, making the entire interactive process cumbersome, inefficient, and resulting in a poor user experience. Summary of the Invention

[0003] This disclosure provides, in various aspects, an information interaction method, an electronic device, a storage medium, and a computer program product to improve the efficiency and experience of dialogue interaction.

[0004] This disclosure provides an information interaction method applied to the field of code processing. The method includes: displaying an information input area on an interactive interface for code editing, the information input area including a prompt input area and a context introduction area; displaying input content in response to an input operation in the prompt input area; and selecting at least one file identifier from a plurality of optional file identifiers in response to a file selection operation triggered in the context introduction area, and displaying at least one file identifier label in the context introduction area. The file identifier label is a file identifier presented in the form of a label, and the file type corresponding to the file identifier includes at least one of the following: code files in the current software engineering project, image files, etc. The system includes: a file or code change log file; selecting a first file identifier label from at least one file identifier label; and displaying the first file identifier label in the prompt input area in response to a drag operation that moves the first file identifier label from the context introduction area to the prompt input area; combining the input content in the prompt input area and the first file identifier label into a prompt word in response to a send operation triggered in the prompt input area, and using at least one file corresponding to at least one file identifier label in the context introduction area as context information, and sending the prompt word and context information to the language model; and displaying the response content generated by the language model based on the prompt word and context information in the interactive information display area of ​​the interactive interface.

[0005] This disclosure also provides an electronic device, including: a memory and a processor; the memory for storing a computer program; and the processor coupled to the memory for executing the computer program to perform steps in an information interaction method.

[0006] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, enables the processor to implement the steps in the information interaction method.

[0007] This disclosure also provides a computer program product, including a computer program / instructions that, when executed by a processor, enable the processor to implement the steps in the information interaction method.

[0008] In this embodiment, the information input area displayed on the interactive interface includes both a prompt input area for users to fill in input content and a context introduction area for users to select which files to use as context. The file identifiers of the files selected by the user as context are displayed as tags in the context introduction area. Users can drag and drop these file identifier tags from the context introduction area to the prompt input area, allowing for flexible combination of input content and file identifier tags to generate prompts for the dialogue interaction. This approach enables users to conveniently select one or more files as context, flexibly combine prompts, reduces the need for manual input of context file information, avoids potential spelling errors during manual input, simplifies user operations, and improves overall dialogue efficiency and interactive experience. Attached Figure Description

[0009] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:

[0010] Figure 1 is a schematic diagram of an application scenario provided by an embodiment of this disclosure;

[0011] Figure 2 is a flowchart of an information interaction method provided in an embodiment of this disclosure;

[0012] Figure 3 is a flowchart of another information interaction method provided in an embodiment of this disclosure;

[0013] Figure 4 is a flowchart of another information interaction method provided in an embodiment of this disclosure;

[0014] Figure 5 is an exemplary interface diagram provided in an embodiment of this disclosure;

[0015] Figure 6 is another exemplary interface diagram provided in the embodiments of this disclosure;

[0016] Figure 7 is another exemplary interface diagram provided in the embodiments of this disclosure;

[0017] Figure 8 is another exemplary interface diagram provided in the embodiments of this disclosure;

[0018] Figure 9 is another exemplary interface diagram provided in an embodiment of this disclosure;

[0019] Figure 10 is another exemplary interface diagram provided in the embodiments of this disclosure;

[0020] Figure 11 is another exemplary interface diagram provided in an embodiment of this disclosure;

[0021] Figure 12 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this disclosure clearer, the technical solutions of this disclosure will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0023] In the embodiments of this disclosure, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the access relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone, where A and B can be singular or plural. In the textual description of this disclosure, the character " / " generally indicates that the preceding and following associated objects have an "or" relationship. Furthermore, in the embodiments of this disclosure, "first," "second," "third," etc., are only used to distinguish the content of different objects and have no other special meaning.

[0024] Figure 1 is a schematic diagram of an application scenario provided by an embodiment of this disclosure. Referring to Figure 1, developers open a code editor on various terminal devices such as desktop computers, laptops, or tablets, and perform code development work in the code editor with the support of input devices such as keyboards and mice. During code development, developers often use intelligent programming assistance tools installed on the terminal device to assist in the development work. In intelligent coding scenarios, intelligent programming assistance tools based on large language models can provide capabilities such as line-level / function-level real-time continuation coding, natural language code generation, unit test generation, code optimization, comment generation, code explanation, and exception handling, helping developers code efficiently and fluently.

[0025] In actual coding, the interaction between developers and the large language model often requires various types of files as context information, such as images, code files, and code change log files. Code files are the core of the software, containing all the program's logic. The file extension varies depending on the programming language used. Code files should follow certain naming conventions and coding standards to improve readability and maintainability. Typically, code files are organized into multiple folders, each representing a module or functional group. Code change log files are used to track every modification during software development. This helps team members understand the code's change history and is crucial for troubleshooting and version rollback. Code change log files are usually implemented through a version control system. Each time code is committed, developers need to provide detailed commit information, explaining the purpose and specific content of the change. This information is recorded in the version control system's log for future reference. The user selects a file as context information and uploads it to the large language model. Then, the user enters a prompt in natural language describing their request related to the context information, including the file information. Finally, the large language model responds based on the uploaded context information and prompts. In practical applications, users may need to upload multiple files as context information. As a result, users need to input information from multiple files when entering prompts, making the entire dialogue interaction process cumbersome, inefficient, and resulting in a poor user experience.

[0026] In this embodiment, the information input area displayed on the interactive interface includes both a prompt input area for users to fill in input content and a context introduction area for users to select which files to use as context. The file identifiers of the files selected by the user as context are displayed as tags in the context introduction area. Users can drag and drop these file identifier tags from the context introduction area to the prompt input area, allowing for flexible combination of input content and file identifier tags to generate prompts for the dialogue interaction. This not only enables users to conveniently select one or more files as context, but also allows for flexible combination of prompts, reducing the need for manual input of context file information, avoiding potential spelling errors during manual input, simplifying user operations, and improving overall dialogue efficiency and interactive experience. In particular, it can improve code development efficiency.

[0027] It should be noted that the application scenario shown in Figure 1 is merely an exemplary application scenario, and the embodiments of this disclosure do not limit the application scenario. The embodiments of this disclosure do not limit the devices included in Figure 1, nor do they limit the positional relationship between the devices in Figure 1.

[0028] The technical solutions of this disclosure and how they solve the aforementioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The technical solutions provided by each embodiment of this disclosure are described in detail below with reference to the accompanying drawings.

[0029] Figure 2 is a flowchart of an information interaction method provided in an embodiment of this disclosure. Referring to Figure 2, the method may include the following steps:

[0030] 201. Display an information input area on the interactive interface for code editing. The information input area includes a prompt word input area and a context introduction area.

[0031] Specifically, information interaction methods can be applied to various code processing fields, such as code generation, code optimization, and code comment generation, without limitation. Code editing can be performed on the interactive interface. Furthermore, the interactive interface can also be a graphical user interface for users to interact with the language model. Optionally, the language model may include, but is not limited to, large language models, autoregressive language models, and generative pre-trained transformers (GPT).

[0032] In practical applications, information input areas can be displayed on the interactive interface, but are not limited to this. The information input area is mainly used to receive user input, and it is usually represented by an input box. Users can enter various information such as plain text, images, and links in the information input area.

[0033] In this embodiment, the information input area may include a prompt input area and a context introduction area. The arrangement of the prompt input area and the context introduction area is not limited. For example, the context introduction area and the prompt input area can be arranged from top to bottom. Alternatively, they can be arranged from left to right. Or, they can be arranged from right to left.

[0034] In this embodiment, the prompt input area can be understood as an input box specifically for inputting prompts. Users can input various input content such as natural language text (also known as natural language text), images, links, etc. in the prompt input area without any restrictions.

[0035] In this embodiment, the context introduction area can be understood as an input box specifically for inputting context information. Users can input context information required for dialogue and interaction with the language model in the context introduction area.

[0036] 202. In response to input in the prompt input area, display the input content in the prompt input area.

[0037] In practical applications, users can input information related to the dialogue interaction as needed in the prompt input area. This information is referred to as the input content. The input content can describe the request information for this dialogue interaction. For example, in a coding scenario, the input content includes request information related to code optimization, described in natural language.

[0038] 203. In response to a file selection operation triggered in the context introduction area, select at least one file identifier from a plurality of optional file identifiers, and display at least one file identifier label in the context introduction area. The file identifier label is a file identifier presented in the form of a label. File identifiers include, but are not limited to: filename, file link, file path, etc.

[0039] In this embodiment, the context introduction area allows users to select one or more files as the context for dialogue interaction at once, reducing the number of operations required by the user and improving the user experience.

[0040] In practical applications, there are no restrictions on how file selection is triggered within the context area. For example, users can click, double-click, or long-press the context area to trigger a file selection. Alternatively, an add control can be displayed in the context area to guide the user to add the control and initiate the file selection.

[0041] In practical applications, upon receiving a file selection operation triggered in the context introduction area, the system can retrieve available files based on pre-specified folder paths, storage paths, etc., and display the file identifiers of the available files for the user to select. However, this is not the only possible approach. In practice, the types of available files include, but are not limited to, code files, image files, or code change log files from the current software project.

[0042] In practical applications, upon receiving a file selection operation triggered in the context introduction area, a context selection panel can pop up in the interactive interface, displaying multiple selectable file identifiers for the user to choose from. The form of the context selection panel is not limited to, but includes, an interface, a window, or a card, etc.

[0043] In some optional embodiments, the context selection panel may also include an input box, in which the user enters a file identifier, retrieves the file identifier, and displays the file identifier label corresponding to the retrieved file identifier in the context introduction area, thereby enriching the ways of file selection.

[0044] In some optional embodiments, the implementation of selecting at least one file identifier from multiple optional file identifiers and displaying at least one file identifier label in the context introduction area in response to a file selection operation triggered in the context introduction area includes: popping up a context selection panel in the interactive interface in response to a file selection operation triggered in the context introduction area. The context selection panel includes: a primary file list and / or an input box. The primary file list includes multiple file identifiers, and the input box is located near the prompt input area. In response to the operation of selecting at least one file identifier from the primary file list, at least one file identifier label is displayed in the context introduction area. And / or, in response to a file identifier entered in the input box, a file identifier is retrieved, and the file identifier label corresponding to the retrieved file identifier is displayed in the context introduction area.

[0045] Understandably, placing the input box in the context selection panel close to the prompt input area can effectively reduce the user's visual focus shift, thereby improving interaction efficiency and user experience.

[0046] In this embodiment, multiple selectable file identifiers are displayed in a list format in the context selection panel. For ease of understanding and differentiation, the list displayed in the context selection panel is referred to as the first-level file list. If any file identifier in the first-level file list has a sub-level file list, the sub-level file list of the file identifier is referred to as the second-level file list.

[0047] In some optional embodiments, the method further includes: if any file identifier in the primary file list exists in a secondary file list, then displaying an entry control for the secondary file list around the corresponding file identifier. In response to a triggering operation on the entry control, a sub-context selection panel is displayed. The sub-context selection panel displays the secondary file list, and in response to selecting at least one file identifier in the secondary file list, at least one file identifier label is displayed in the context introduction area.

[0048] In this embodiment, a multi-level file list facilitates the user's selection of more files as context information. In practical applications, the entry control can be presented as various types of controls such as arrows or plus signs. Users can perform various operations on the entry control, such as single-clicking, double-clicking, or long-pressing, to display a sub-context selection panel. Optionally, users can also click a key on the keyboard (e.g., the Enter key) to trigger the display of the sub-context selection panel. The form of the sub-context selection panel includes, but is not limited to, interfaces, windows, or cards. The sub-context selection panel displays a secondary file list with multiple file identifiers for the user to select from, and the file identifier selected by the user is simultaneously displayed in the context introduction area.

[0049] Optionally, the sub-context selection panel may also include an input box. In this way, in response to the file identifier entered in the input box in the sub-context selection panel, the file identifier is retrieved and the file identifier label corresponding to the retrieved file identifier is displayed in the context introduction area.

[0050] In some optional embodiments, the sub-context selection panel also displays a return prompt message to indicate whether to use the fourth shortcut key to return to the context selection panel. The method further includes: in response to a return operation triggered based on the return prompt message, exiting the display of the sub-context selection panel and displaying the context selection panel.

[0051] Specifically, the system supports efficient return to the context selection panel from the sub-context selection panel via return prompts and keyboard shortcuts, improving overall interaction efficiency. Optionally, a fourth keyboard shortcut may include, but is not limited to, the Enter key.

[0052] 204. Select a first file identifier label from at least one file identifier label. And in response to a drag operation that moves the first file identifier label from the context introduction area to the prompt input area, display the first file identifier label in the prompt input area.

[0053] In this embodiment, after selecting at least one file identifier tag and displaying it in the context introduction area, a first file identifier tag can be selected from the at least one file identifier tag, and the selected first file identifier tag can be dragged from the context introduction area to the prompt input area. This reduces the need for users to manually input information about the file as context when entering prompts, avoids spelling errors that may occur during manual input, simplifies user operations, and improves user convenience.

[0054] In practical applications, after displaying at least one file identifier label in the context introduction area, the user selects a first file identifier label from the at least one file identifier label via voice input. Alternatively, the user can move the mouse to move the focus, thereby controlling the file identifier label under focus and setting the focused file identifier label as the selected first file identifier label. Focus can indicate the interface element that the user can currently input or manipulate; the interface element can be, for example, a window, a text box, a button, or any other user interface element. In this embodiment, the file identifier label with focus is selected as the first file identifier label.

[0055] Optionally, selecting the first file identifier label from at least one file identifier label can be achieved as follows: when the focus is in the context introduction area, in response to a focus movement command sent by the keyboard, the focus is moved among at least one file identifier label, and the file identifier label that is focused when the focus stops moving is selected as the first file identifier label. The focus movement command is generated by operating a first shortcut key on the keyboard, which includes one or more keys on the keyboard.

[0056] In this embodiment, the file identification tab can be switched using a shortcut key. The first shortcut key can be, for example, the arrow keys on the keyboard, or a combination of the control keys and arrow keys on the keyboard; there is no limitation on this. Optionally, focus movement commands include, but are not limited to: focus movement commands that control the focus to move left, focus movement commands that control the focus to move right, focus movement commands that control the focus to move up, and focus movement commands that control the focus to move down.

[0057] For example, let's say the control keys are Ctrl, the left arrow key is ←, the right arrow key is →, the up arrow key is ↑, and the down arrow key is ↓. Use the shortcut (Ctrl+←) to move the focus to the left. Use (Ctrl+→) to move the focus to the right. Use (Ctrl+↑) to move the focus up. Use (Ctrl+↓) to move the focus down.

[0058] In practical applications, at least one file identifier label can be displayed in separate lines within the context area. That is, within the context area, at least one file identifier label can be arranged in one or more lines, with each line containing one or more file identifier labels. Focus movement commands that control leftward and rightward movement can be used to switch between file identifier labels on the same line. Focus movement commands that control upward and downward movement can be used to switch between file identifier labels spanning multiple lines.

[0059] In some optional implementations, a file preview interface can be displayed in response to a file preview command corresponding to the first file identifier label. The file preview interface includes the file content corresponding to the first file identifier. The file preview command is generated by pressing a second keyboard shortcut. The second shortcut can be any key or combination of keys on the keyboard, such as the Enter key.

[0060] It is worth noting that by supporting a preview of the file content corresponding to the selected first file identifier tag, users can be assisted in deciding whether to use the first file identifier tag as a prompt word in part of the message.

[0061] In practical applications, if a user, after previewing the file content corresponding to the first file identifier tag, decides that the first file identifier tag is not suitable as a prompt, the user can switch the selected first file identifier tag. For example, by continuing to initiate a focus movement command, the focus can be controlled to refocus on the new file identifier tag, and the newly refocused file identifier tag will become the new first file identifier tag.

[0062] In some alternative implementations, the first file identifier tag can also be removed from the context import area in response to a deletion instruction for the first file identifier tag.

[0063] In this embodiment, in addition to supporting the addition of file identification tags in the context introduction area, it also supports the deletion of file identification tags displayed in the context introduction area, thereby effectively managing the context introduction area.

[0064] In practical applications, there are no restrictions on how the delete command is triggered. Optionally, the delete command can be generated by pressing a third shortcut key on the keyboard. The third shortcut key can be any key or combination of keys on the keyboard, such as the delete key.

[0065] In some optional implementations, the first file identifier label can also be removed from the context area in response to a delete command for the first file identifier label. The delete command is generated by pressing a third keyboard shortcut. Focus is then refocused on the file identifier label to the left of the first file identifier label, and the refocused file identifier label is selected as the updated first file identifier label.

[0066] Understandably, after the currently focused first file identifier label is deleted, the focus is automatically moved to the file identifier label to the left of the deleted first file identifier label, and the file identifier label to be refocused is the updated first file identifier label. This avoids the user manually reselecting file identifier labels, improving the smoothness and efficiency of user operations.

[0067] In some optional embodiments, the mouse can be used to focus on either the context introduction area or the prompt input area. When the focus is on the context introduction area, related operations can be performed there. When the focus is on the prompt input area, related operations can be performed there.

[0068] In some optional embodiments, the area of ​​focus can be switched via keyboard operation to facilitate user operation.

[0069] For example, if the context introduction area is located above the prompt input area, the method further includes: when the focus is on the last file identifier label among at least one file identifier label, in response to a focus movement command sent from the keyboard to move the focus downwards, controlling the focus to move from the context introduction area to the prompt input area. Alternatively, when the focus is on the prompt input area, in response to a focus movement command sent from the keyboard to move the focus upwards, controlling the focus to move from the prompt input area to the context introduction area.

[0070] For example, if the context introduction area is located below the prompt input area, the method further includes: when the focus is on the first label in the context introduction area, in response to a focus movement command sent from the keyboard to move the focus upwards, controlling the focus to move from the context introduction area to the prompt input area. Alternatively, when the focus is on the prompt input area, in response to a focus movement command sent from the keyboard to move the focus downwards, controlling the focus to move from the prompt input area to the context introduction area.

[0071] In practical applications, users can drag the first file identifier label to any position in the prompt input area without restriction. Further optionally, in response to a drag operation that moves the first file identifier label from the context area to the prompt input area, the first file identifier label is displayed in the prompt input area as follows: In response to the drag operation, the cursor is moved within the prompt input area, and the first file identifier label is inserted and displayed at the position where the cursor stops moving.

[0072] A cursor is a visual element used to indicate a specific location on a screen, responding to keystrokes from the keyboard or mouse input. In document editing or text input areas, the cursor is typically displayed as a vertical line or underline to indicate the text insertion point. Users can move the cursor using the arrow keys on the keyboard or by clicking the mouse to input or edit text at the appropriate location. In graphical user interfaces, the cursor usually appears as an arrow to indicate the position of the mouse pointer. By moving the mouse, the user can control the movement of this cursor.

[0073] Understandably, by tracking the cursor position during dragging, the first file identifier tag can be precisely inserted into the prompt input area, improving the flexibility of combining prompts. For example, if there is already input content in the prompt input area, the first file identifier tag can be inserted at the beginning, middle, or end of the input content, without restriction.

[0074] 205. In response to a send operation triggered in the prompt input area, the input content in the prompt input area and the first file identifier tag are combined into a prompt word, and at least one file corresponding to at least one file identifier tag in the context introduction area is used as context information. The prompt word and context information are sent to the language model, and the response content generated by the language model based on the prompt word and context information is displayed in the interactive information display area of ​​the interactive interface.

[0075] In practical applications, the execution order of steps 202 and 203 is not restricted. For example, a user can first enter input content in the prompt input area, then add at least one file identifier tag in the context introduction area, and insert the file identifier tag from the context introduction area as part of the prompt input area. Alternatively, a user can first add at least one file identifier tag in the context introduction area, insert the file identifier tag from the context introduction area as part of the prompt input area, and then enter input content in the prompt input area. Yet another example is that a user can alternately enter input content in the prompt input area and add at least one file identifier tag in the context introduction area and insert it into the prompt input area.

[0076] In practical applications, after the user confirms that the prompt words in the prompt word input area meet the requirements, the user can trigger a send operation in the prompt word input area to send the prompt words and context information to the language model for processing. The response content generated by the language model based on the prompt words and context information can be displayed in the interactive information display area of ​​the interactive interface for the user to view. The interactive information display area is mainly used to display interactive information.

[0077] In practical applications, users can trigger the sending operation by clicking, double-clicking, or long-pressing the prompt word input area. Alternatively, a sending control can be provided in the prompt word input area, and users can trigger the sending operation by operating the sending control.

[0078] The technical solution provided in this disclosure includes an information input area on the interactive interface that includes both a prompt input area for users to fill in input content and a context introduction area for users to select which files to use as context. The file identifiers of the files selected by the user as context are displayed as tags in the context introduction area. Users can drag and drop these file identifier tags from the context introduction area to the prompt input area, allowing for flexible combination of input content and file identifier tags to generate prompts for the dialogue interaction. This approach not only enables users to conveniently select one or more files as context, but also allows for flexible combination of prompts, reducing the need for manual input of context file information, avoiding potential spelling errors during manual input, simplifying user operations, and improving overall dialogue efficiency and interactive experience.

[0079] In the above or following embodiments, to facilitate the management of prompt words and context information, the third file identifier tag can also be deleted from the prompt word input area and the context introduction area in response to a deletion operation triggered in the prompt word input area. The third file identifier tag is a file identifier tag already displayed in the prompt word input area.

[0080] It is understandable that the removal of the third file identifier from the prompt input area indicates that the content of the file corresponding to the third file identifier has little relevance to the dialogue interaction. Removing the third file identifier from the context introduction area means that the file corresponding to the third file identifier is no longer used as context, which helps to improve the personalization and context relevance of the dialogue interaction and ensures that the dialogue interaction can better understand and respond to the user's requests.

[0081] In some optional embodiments, users can also add file identifier tags as part of the prompt words in the prompt word input area to meet diverse prompt word combination needs. Based on this, embodiments of this disclosure also provide an information interaction method. Referring to Figure 3, the method may include:

[0082] 301. Display an information input area on the interactive interface for code editing. The information input area includes a prompt input area and a context introduction area.

[0083] 302. In response to an input operation in the prompt input area, display the input content in the prompt input area.

[0084] 303. In response to a file selection operation triggered in the prompt input area, select a second file identifier from a plurality of optional file identifier labels, and display the second file identifier label in the prompt input area and the context introduction area.

[0085] The implementation of triggering a file selection operation and selecting a second file identifier in the prompt input area is similar to the implementation of triggering a file selection operation and selecting at least one file identifier in the context introduction area, and will not be described in detail here.

[0086] Optionally, users can trigger file selection by pressing keys on the keyboard in the prompt input area. For example, when the focus is on the prompt input area, pressing the # key on the keyboard can bring up a context selection panel, where the user can select the second file identifier from multiple available file identifier labels.

[0087] It is understandable that selecting and displaying the second file identifier in the prompt input area indicates that the content of the file corresponding to the second file identifier is highly relevant to the dialogue interaction. Synchronizing the selection and display of the second file identifier in the prompt input area to the context introduction area can enrich the files that serve as context in the context introduction area, and can also introduce contexts that better meet the user's needs. This is conducive to improving the personalization and context relevance of the dialogue interaction, and ensuring that the dialogue interaction can better understand and respond to the user's requests.

[0088] 304. In response to a file selection operation triggered in the context introduction area, select at least one file identifier from a plurality of optional file identifiers and display at least one file identifier label in the context introduction area, wherein the file identifier label is a file identifier presented in the form of a label.

[0089] 305. Select a first file identifier label from at least one file identifier label. And in response to a drag operation that moves the first file identifier label from the context introduction area to the prompt input area, display the first file identifier label in the prompt input area.

[0090] 306. In response to a send operation triggered in the prompt input area, the input content in the prompt input area, the first file identifier tag, and the second file identifier tag are combined into a prompt word, and at least one file corresponding to at least one file identifier tag in the context introduction area is used as context information. The prompt word and context information are sent to the language model, and the response content generated by the language model based on the prompt word and context information is displayed in the interactive information display area of ​​the interactive interface.

[0091] It is understood that at least one file identification tag in the context introduction area includes a second file identification tag.

[0092] The technical solution provided in this disclosure includes an information input area on the interactive interface that includes both a prompt input area for users to fill in input content and a context introduction area for users to select which files to use as context. The file identifiers of the files selected by the user as context are displayed as tags in the context introduction area, and users can drag and drop these file identifier tags from the context introduction area to the prompt input area. A second file identifier can also be selected and displayed in the prompt input area. Furthermore, the input content and file identifier tags can be flexibly combined in the prompt input area to obtain prompts for the interactive dialogue. This allows users to conveniently select one or more files as context, flexibly combine prompts, reduce the need for manual input of context file information, avoid spelling errors that may occur during manual input, simplify user operations, and improve overall dialogue efficiency and interactive experience. In particular, it can improve code development efficiency.

[0093] This disclosure also provides an information interaction method. Referring to Figure 4, the method may include the following steps:

[0094] 401. Display an information input area on the interactive interface for code editing. The information input area includes a prompt input area and a context introduction area.

[0095] 402. In response to an input operation in the prompt input area, display the input content in the prompt input area.

[0096] 403. In response to a file selection operation triggered in the context introduction area, select at least one file identifier from a plurality of optional file identifiers and display at least one file identifier label in the context introduction area, wherein the file identifier label is a file identifier presented in the form of a label.

[0097] 404. In response to a send operation triggered in the prompt input area, the input content in the prompt input area is used as the prompt, and at least one file corresponding to at least one file identifier tag in the context introduction area is used as context information. The prompt and context information are sent to the language model, and the response content generated by the language model based on the prompt and context information is displayed in the interactive information display area of ​​the interactive interface.

[0098] Optionally, in response to a send operation triggered in the prompt input area, the implementation of sending the prompt and context information to the language model, using the input content in the prompt input area as the prompt and at least one file corresponding to at least one file identifier tag in the context introduction area as context information, is as follows: Select a first file identifier tag from at least one file identifier tag. Also, in response to a drag operation that moves the first file identifier tag from the context introduction area to the prompt input area, display the first file identifier tag in the prompt input area. In response to a send operation triggered in the prompt input area, combine the input content in the prompt input area and the first file identifier tag into a prompt, and use at least one file corresponding to at least one file identifier tag in the context introduction area as context information, then send the prompt and context information to the language model.

[0099] Optionally, in response to a send operation triggered in the prompt input area, the implementation of sending the prompt content as the prompt word and at least one file corresponding to at least one file identifier label in the context introduction area as context information, and sending the prompt word and context information to the language model, is as follows: In response to a file selection operation triggered in the prompt input area, a second file identifier is selected from multiple optional file identifier labels, and the second file identifier label is displayed in both the prompt input area and the context introduction area. In response to a send operation triggered in the prompt input area, the input content in the prompt input area and the first file identifier label are combined to form a prompt word, and at least one file corresponding to at least one file identifier label in the context introduction area is used as context information, and the prompt word and context information are sent to the language model.

[0100] The technical solution provided in this disclosure includes an information input area on the interactive interface that includes both a prompt input area for users to fill in input content and a context introduction area for users to select which files to use as context. This allows users to conveniently select one or more files as context and to input prompts on demand, simplifying user operations and improving overall dialogue efficiency and interactive experience. In particular, it can improve code development efficiency.

[0101] To better understand the technical solution disclosed herein, the following interface diagrams are provided for illustration.

[0102] Taking intelligent coding scenarios as an example, the developer's terminal device displays an interactive interface, as shown in Figures 5, 6, and 7. Developers can engage in artificial intelligence (AI) dialogue with the large language model on this interface. The interactive information display area shows dialogue information, and the interface also displays an information input area, which includes a context introduction area and a prompt word input area. When the developer moves the focus to the "+" button in the context introduction area and presses the Enter key, a context selection panel pops up on the interactive interface. The context selection panel includes a first-level file list and an input box. The first-level file list includes multiple optional file identifiers, such as file identifier 1 (#file, usually referring to source code files in the current software project), file identifier 2 (#codebase, usually referring to the project's codebase or code base), and file identifier 3 (#image, usually referring to image files included in the project), etc., without limitation. The input box is used to retrieve the desired file identifier. The file identifier selected by the user in the first-level file list is displayed as a label in the context introduction area. Referring to Figure 8, when the mouse pointer is focused on a label in the context introduction area, the file identifier label displayed in the context introduction area can be dragged to the prompt input area by dragging the mouse. When the user releases the mouse (i.e., releases the mouse button), the file identifier label can be placed at the cursor position in the prompt input area. Furthermore, the cursor can be moved during the dragging process, allowing the file identifier label to be placed anywhere in the input content, enabling flexible combinations of input content and file identifier labels. Users can enter input content in the prompt input area, such as "Hello, hello." The prompt input area also provides a send button. After the developer clicks the send button, the prompt in the prompt input area and the file corresponding to the file identifier label in the context introduction area are sent as context to the large language model for response, and the response content can be displayed in the interactive information display area.

[0103] Referring to Figure 9, it also supports interaction between the second-level file list (also known as the secondary list) and the first-level file list (also known as the primary list). When the focus is on the title area of ​​the second-level list, an operation prompt "Enter to back" appears to the right of the focused file icon. When the developer presses the Enter key, they return from the second-level list to the primary list. When the focus is on the primary list, an operation prompt "Enter to pick" is displayed on the focused file icon. The primary file list includes several optional file icons such as #file, #codebase, #image, file icon label 1 (Go c1.go), file icon label 2 (Go c2.go), file icon label 3 (Go c3.go), and file icon label 4 (Go c4.go). The second-level file list includes several optional file identifiers, such as file identifier 1 (#file), file identifier 11 (#file11), file identifier 12 (#file12), and file identifier 13 (#file13). #file11, #file12, and #file13 are the next-level file identifiers of #file.

[0104] Referring to Figure 10, keyboard shortcuts are supported for switching labels. When the focus is on the "Add" button in the context area, clicking the shortcut (Ctrl+→) moves the focus from the "Add" button to the first label (the first file identifier label). Clicking the shortcut (Ctrl+→) again moves the focus from the first label to the second label (the second file identifier label). Clicking the shortcut (Ctrl+←) moves the focus from the second label to the first label. Clicking the shortcut (Ctrl+←) again moves the focus from the first label back to the "Add" button. With the focus on the first label, clicking the shortcut (Ctrl+↓) moves the focus from the first label to the label on the next line, and clicking the shortcut (Ctrl+↑) moves the focus from the label on the next line back to the first label. Figure 10 includes labels for file identifiers such as "Go c1.go", "Go c2.go", "Go c3.go", and "Go c4.go". In Figure 10, the file identifier labels with darker colors are the focused file identifier labels, and the file identifier labels with lighter colors are the unfocused file identifier labels.

[0105] Referring to Figure 11, keyboard shortcuts are also supported for switching regions. When the focus (by the cursor) is on the prompt input area (i.e., when the cursor is in the prompt input area), clicking the shortcut (Ctrl+↑) moves the focus to the context introduction area. Clicking the shortcut again (Ctrl+↓) moves the focus back to the prompt input area.

[0106] It should be noted that the execution subject of each step in the method provided in the above embodiments can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 201 to 205 can be device A. Or, for example, the execution subject of steps 201 and 202 can be device A, and the execution subject of steps 203 to 205 can be device B, and so on.

[0107] Furthermore, in some of the processes described in the above embodiments and accompanying drawings, multiple operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or they may be executed in parallel. The operation numbers, such as 201, 202, etc., are merely used to distinguish different operations and do not represent any execution order. Additionally, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first" and "second" in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0108] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0109] Figure 12 is a schematic diagram of an electronic device provided in an embodiment of this disclosure. As shown in Figure 12, the electronic device includes a memory 11 and a processor 12.

[0110] Memory 11 is configured to store computer programs and can be configured to store various other data to support operation on the computing platform. Examples of this data include instructions for any application or method operating on the computing platform, contact data, phone book data, messages, pictures, videos, etc.

[0111] The memory 11 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0112] Processor 12, coupled to memory 11, is configured to execute a computer program in memory 11 to perform the following actions: Displaying an information input area on an interactive interface for code editing, the information input area including a prompt input area and a context introduction area. Responding to an input operation in the prompt input area, displaying the input content in the prompt input area. And responding to a file selection operation triggered in the context introduction area, selecting at least one file identifier from a plurality of optional file identifiers, and displaying at least one file identifier label in the context introduction area, the file identifier label being a file identifier presented in label form. Selecting a first file identifier label from the at least one file identifier label. And responding to a drag operation of dragging the first file identifier label from the context introduction area to the prompt input area, displaying the first file identifier label in the prompt input area. Responding to a send operation triggered in the prompt input area, combining the input content in the prompt input area and the first file identifier label into a prompt, and using at least one file corresponding to the at least one file identifier label in the context introduction area as context information, and sending the prompt and context information to the language model. Displaying a response generated by the language model based on the prompt and context information in an interactive information display area of ​​the interactive interface.

[0113] Optionally, when the processor 12 displays the first file identifier label in the prompt input area in response to a drag operation that drags the first file identifier label from the context introduction area to the prompt input area, it is specifically configured to: move the cursor in the prompt input area in response to the drag operation that drags the first file identifier label from the context introduction area to the prompt input area, and insert and display the first file identifier label at the position where the cursor stops moving.

[0114] Optionally, the processor 12 is further configured to: in response to a file selection operation triggered in the prompt input area, select a second file identifier from a plurality of optional file identifier labels, and display the second file identifier label in the prompt input area and the context introduction area. Accordingly, combining the input content in the prompt input area and the first file identifier label into a prompt word includes: combining the input content in the prompt input area, the first file identifier label, and the second file identifier label into a prompt word.

[0115] Optionally, the processor 12 is also configured to: in response to a deletion operation on a third file identifier tag triggered in the prompt input area, delete the third file identifier tag from the prompt input area and the context introduction area.

[0116] Optionally, when the processor 12 selects a first file identifier label from at least one file identifier label, it is specifically configured to: when the focus is located in the context introduction area, in response to a focus movement command sent by the keyboard, move the focus among at least one file identifier label, and select the file identifier label that was focused when the focus movement stops as the first file identifier label. The focus movement command is generated by operating a first shortcut key on the keyboard, which includes one or more keys on the keyboard.

[0117] Optionally, after the processor 12 selects the file identifier label that was focused on when the focus stopped moving as the first file identifier label, it is also set to:

[0118] In response to the file preview command corresponding to the first file identifier label, a file preview interface is displayed. The file preview interface includes the file content corresponding to the first file identifier. The file preview command is generated by operating the second shortcut key on the keyboard.

[0119] And / or, in response to a delete command targeting the first file identifier tag, remove the first file identifier tag from the context area. The delete command is generated by pressing a third keyboard shortcut.

[0120] Refocus on the file identifier label located to the left of the first file identifier label, and select the updated first file identifier label as the file identifier label to be refocused.

[0121] Optionally, the focus movement command includes at least one of the following: a focus movement command that controls the focus to move to the left, a focus movement command that controls the focus to move to the right, a focus movement command that controls the focus to move upward, and a focus movement command that controls the focus to move downward.

[0122] Optionally, if the context introduction area is located above the prompt input area, the processor 12 is further configured to: when the focus is on the last file identifier label in at least one file identifier label, in response to a focus movement command sent from the keyboard to move the focus downwards, control the focus to move from the context introduction area to the prompt input area. Alternatively, when the focus is on the prompt input area, in response to a focus movement command sent from the keyboard to move the focus upwards, control the focus to move from the prompt input area to the context introduction area.

[0123] Optionally, when processor 12 selects at least one file identifier from a plurality of optional file identifiers in response to a file selection operation triggered in the context introduction area, and displays at least one file identifier label in the context introduction area, it is specifically configured as follows:

[0124] In response to a file selection operation triggered in the context introduction area, a context selection panel pops up in the interactive interface. The context selection panel includes a first-level file list and / or an input box. The first-level file list includes multiple file identifiers, and the input box is located near the prompt input area.

[0125] In response to the operation of selecting at least one file identifier in the first-level file list, at least one file identifier label is displayed in the context introduction area.

[0126] And / or, in response to a file identifier entered in the input box, retrieve the file identifier and display the file identifier label corresponding to the retrieved file identifier in the context introduction area.

[0127] Optionally, processor 12 is also configured to display an entry control for the secondary file list around any file identifier in the primary file list if a secondary file list exists.

[0128] In response to a trigger action on the entry control, a sub-context selection panel is displayed. This sub-context selection panel shows a secondary file list and a return prompt message. The return prompt message indicates that the fourth shortcut key should be used to return to the context selection panel.

[0129] In response to the operation of selecting at least one file identifier in the secondary file list, at least one file identifier label is displayed in the context introduction area.

[0130] In response to a return operation triggered by a return prompt message, exit the display of the sub-context selection panel and display the context selection panel.

[0131] Further optionally, as shown in Figure 12, the electronic device may also include other components such as a communication component 13, a display 14, a power supply component 15, and an audio component 16. Figure 12 only schematically shows some components and does not imply that the electronic device only includes the components shown in Figure 12. Furthermore, the components within the dashed boxes in Figure 12 are optional, not mandatory, and their specific inclusion depends on the product form of the electronic device. The electronic device of this embodiment can be implemented as a desktop computer, laptop computer, smartphone, or Internet of Things (IoT) device, or as a server-side device such as a conventional server, cloud server, or server array. If the electronic device of this embodiment is implemented as a desktop computer, laptop computer, smartphone, or other terminal device, it may include the components within the dashed boxes in Figure 12. If the electronic device of this embodiment is implemented as a conventional server, cloud server, or server array, it may not include the components within the dashed boxes in Figure 12.

[0132] For a detailed description of the implementation process of each action by the processor, please refer to the relevant descriptions in the foregoing method embodiments or device embodiments, which will not be repeated here.

[0133] Accordingly, this disclosure also provides a computer-readable storage medium storing a computer program, which, when executed, can perform the steps that can be executed by an electronic device in the above method embodiments.

[0134] Accordingly, this disclosure also provides a computer program product, including a computer program / instructions, which, when executed by a processor, enable the processor to perform the steps that can be executed by an electronic device in the above method embodiments.

[0135] The aforementioned communication components are configured to facilitate wired or wireless communication between the device containing the communication components and other devices. The device containing the communication components can access wireless networks based on communication standards, such as Wireless Fidelity (WiFi), 2G, 3G, 4G / Long Term Evolution (LTE), 5G, or combinations thereof. In one exemplary embodiment, the communication components receive broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication components also include a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be based on Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wide Band (UWB), Bluetooth (BT), and other technologies.

[0136] The aforementioned display includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a Touch Panel, the screen can be implemented as a touchscreen to receive input signals from the user. The Touch Panel includes one or more touch sensors to sense touches, swipes, and gestures on the Touch Panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation.

[0137] The aforementioned power supply components provide power to various components within the device in which they reside. These power supply components may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device in which they reside.

[0138] The aforementioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) configured to receive external audio signals when the device containing the audio component is in an operating mode, such as call mode, recording mode, or voice recognition mode. The received audio signals can be further stored in memory or transmitted via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0139] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0141] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0142] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0143] In a typical configuration, a computing device includes one or more processors (Central Processing Units, CPUs), input / output interfaces, network interfaces, and memory.

[0144] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0145] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random-access memory (SRAM), dynamic random-access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0146] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0147] The above are merely embodiments of this disclosure and are not intended to limit the scope of this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of the claims of this disclosure.

Claims

1. An information interaction method applied in the field of code processing, the method comprising: An information input area is displayed on the interactive interface for code editing, the information input area including a prompt word input area and a context introduction area; In response to an operation input in the prompt input area, the input content is displayed in the prompt input area; In response to a file selection operation triggered in the context introduction area, at least one file identifier is selected from a plurality of optional file identifiers, and at least one file identifier label is displayed in the context introduction area. The file identifier label is a file identifier presented in the form of a label. The file type corresponding to the file identifier includes at least one of the following: code file, image file, or code change log file in the current software engineering project. Select a first file identifier label from the at least one file identifier label; And in response to a drag operation that moves a first file identifier label from the context introduction area to the prompt input area, the first file identifier label is displayed in the prompt input area; In response to a sending operation triggered in the prompt input area, the input content in the prompt input area and the first file identifier tag are combined into a prompt word, and at least one file corresponding to at least one file identifier tag in the context introduction area is used as context information, and the prompt word and the context information are sent to the language model; The interactive information display area in the interactive interface displays the response content generated by the language model based on the prompt words and the context information.

2. The method according to claim 1, wherein, In response to a drag operation that moves a first file identifier label from the context introduction area to the prompt input area, displaying the first file identifier label in the prompt input area includes: In response to a drag operation that moves a first file identifier tag from the context introduction area to the prompt input area, the cursor is moved in the prompt input area, and the first file identifier tag is inserted and displayed at the position where the cursor stops moving.

3. The method according to claim 1, wherein, Also includes: In response to a file selection operation triggered in the prompt input area, a second file identifier is selected from a plurality of optional file identifier labels, and the second file identifier label is displayed in the prompt input area and the context introduction area.

4. The method according to claim 3, wherein, The input content in the prompt input area and the first file identifier tag are combined to form a prompt word, including: The input content in the prompt input area, the first file identifier label, and the second file identifier label are combined to form the prompt word.

5. The method according to any one of claims 1 to 4, wherein, Also includes: In response to a deletion operation on a third file identifier tag triggered in the prompt input area, the third file identifier tag is deleted from the prompt input area and the context introduction area.

6. The method according to claim 1, wherein, Selecting a first file identifier tag from the at least one file identifier tag includes: When the focus is located in the context introduction area, in response to a focus movement command sent by the keyboard, the focus is moved among the at least one file identifier label, and the file identifier label that was focused when the focus stopped moving is selected as the first file identifier label; The focus movement command is generated by operating a first shortcut key on the keyboard, which includes one or more keys on the keyboard.

7. The method according to claim 6, wherein, After selecting the file identifier label that is focused on when the focus stops moving as the first file identifier label, the method further includes: In response to a file preview command corresponding to the first file identifier label, a file preview interface is displayed, the file preview interface including the file content corresponding to the first file identifier, the file preview command being generated by operating a second shortcut key on the keyboard; and / or, In response to a deletion command for the first file identifier tag, the first file identifier tag is deleted from the context import area; the deletion command is generated by operating a third shortcut key on the keyboard; The focus is refocused on the file identifier label located to the left of the first file identifier label, and the file identifier label on which the focus is refocused is selected as the updated first file identifier label.

8. The method according to claim 6, wherein, The focus movement command includes at least one of the following: a focus movement command that controls the focus to move to the left, a focus movement command that controls the focus to move to the right, a focus movement command that controls the focus to move upward, and a focus movement command that controls the focus to move downward.

9. The method according to claim 6, wherein, If the context introduction area is located above the prompt word input area, the method further includes: When the focus is on the last file identifier label among the at least one file identifier labels, in response to a focus movement command sent from the keyboard to move the focus downwards, the focus is moved from the context introduction area to the prompt input area; or... When the focus is on the prompt input area, in response to a focus movement command sent by the keyboard to move the focus upward, the focus is moved from the prompt input area to the context introduction area.

10. The method according to claim 1, wherein, In response to a file selection operation triggered in the context introduction area, at least one file identifier is selected from a plurality of optional file identifiers, and at least one file identifier label is displayed in the context introduction area, including: In response to a file selection operation triggered in the context introduction area, a context selection panel pops up in the interactive interface. The context selection panel includes a primary file list and / or an input box. The primary file list includes multiple file identifiers, and the input box is located near the prompt input area. In response to the operation of selecting at least one file identifier in the first-level file list, at least one file identifier label is displayed in the context introduction area; and / or, In response to a file identifier entered in the input box, the file identifier is retrieved, and the file identifier tag corresponding to the retrieved file identifier is displayed in the context introduction area.

11. The method according to claim 10, wherein, Also includes: If any file identifier in the first-level file list exists in a second-level file list, then an entry control for the second-level file list is displayed around the corresponding file identifier. In response to a trigger operation on the entry control, a sub-context selection panel is displayed; the sub-context selection panel displays the secondary file list; In response to the operation of selecting at least one file identifier in the secondary file list, at least one file identifier label is displayed in the context introduction area.

12. The method according to claim 11, wherein, The sub-context selection panel also displays a return prompt message, which prompts the user to use the fourth shortcut key to return to the context selection panel. It also includes: In response to the return operation triggered based on the return prompt information, exit the display of the sub-context selection panel and display the context selection panel.

13. The method according to claim 1, wherein, The method is applied to intelligent coding scenarios.

14. The method according to claim 6, wherein, The focus movement instructions include at least: a focus movement instruction that controls the focus to move to the left, a focus movement instruction that controls the focus to move to the right, a focus movement instruction that controls the focus to move upward, and a focus movement instruction that controls the focus to move downward. The focus movement instructions that control the focus to move to the left and the focus movement instructions that control the focus to move to the right are used to switch between file identifier labels on the same line, while the focus movement instructions that control the focus to move upward and the focus movement instructions that control the focus to move downward are used to switch between file identifier labels across multiple lines.

15. The method according to claim 1, wherein, Selecting a first file identifier tag from the at least one file identifier tag includes: The first file identifier tag is selected from at least one file identifier tag by means of language input.

16. The method according to claim 1, wherein, The at least one file identification label is displayed in the context introduction area in separate lines. The at least one file identification label is arranged in one or more lines, and any line includes one or more of the file identification labels.

17. The method according to claim 6, wherein, The area focused by the focal point is switched based on keyboard operation.

18. The method according to claim 2, wherein, When there is input content in the prompt input area, the first file identification tag is inserted at the beginning, middle or end of the input content.

19. An electronic device comprising: Memory and processor; The memory is used to store computer programs; The processor is coupled to the memory for executing the computer program to perform the steps of the method according to any one of claims 1-18.

20. A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method according to any one of claims 1-18.

Images