Text management method, electronic equipment, chip system and readable storage medium

Abstract

The invention discloses a text management method, electronic equipment, a chip system and a readable storage medium, and belongs to the technical field of terminals. Comprising the steps that in response to a first operation, a first interface is displayed in the multifunctional office platform, the first interface is an interface corresponding to a document management function, and the first interface comprises a first identifier of a first document text and a second identifier of a second document text; in response to a selection operation on the first identifier, displaying document key information of the first document text in a first specified area in the first interface; and in response to a selection operation on the second identifier, displaying the document key information of the second document text in the first specified area. Therefore, the user can quickly know the document, so that the document text which the user wants to search can be quickly searched, and the search efficiency of the document text is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of terminal, in particular to a text management method, an electronic device, a chip system and a readable storage medium. BACKGROUND

[0002] At present, a multi-functional office platform is provided in an electronic device, the multi-functional office platform integrates multiple application functions such as note and document management, so that a user can perform one-stop office through the multi-functional office platform. For example, the user can record notes through the multi-functional office platform, and can also read and edit documents through the multi-functional office platform.

[0003] When the user reads document texts through the multi-functional office platform, if it is needed to find document texts related to a certain content from multiple document texts, especially from multiple document texts with similar topics, the user needs to trigger the multi-functional office platform to open the multiple document texts one by one, and the user reads each opened document text to find the required document text. In this way, since it is needed to find the required document text by opening one by one, the finding efficiency is low, and the office efficiency of the user on the electronic device is reduced. SUMMARY

[0004] The present application provides a text management method, an electronic device, a chip system and a readable storage medium, which can solve the problem of low document text finding efficiency in related technologies, and affect the office efficiency of the user. The technical solution is as follows:

[0005] In a first aspect, a text management method is provided, applied to an electronic device, the electronic device comprising a multi-functional office platform, the multi-functional office platform providing multiple application functions, the multiple application functions comprising a document management function, and the method comprising:

[0006] In response to a first operation, a first interface is displayed in the multi-functional office platform, the first interface being an interface corresponding to the document management function, and the first interface comprising a first identifier of a first document text and a second identifier of a second document text. In response to a selection operation on the first identifier, document key information of the first document text is displayed in a first specified area in the first interface. In response to a selection operation on the second identifier, document key information of the second document text is displayed in the first specified area.

[0007] In this way, the user only needs to click the identifier of the document text to trigger the electronic device to display the document key information, so that the user can quickly understand the document, and then the user can quickly find the document text to be found, and the finding efficiency of the document text is improved.

[0008] As an example of the present application, in response to the selection operation on the second identifier, before displaying the document key information of the second document text in the first specified area, further comprising: in the case of receiving the selection operation on the second identifier, if the document key information of the second document text has not been displayed, displaying the first control in the first interface. Accordingly, in response to the selection operation on the second identifier, displaying the document key information of the second document text in the first specified area, comprising: in the case of receiving the triggering operation on the first control, in response to the selection operation on the second identifier, displaying the document key information of the second document text in the first specified area.

[0009] In this way, by displaying the first control, the document text is analyzed and processed by the AI model only with the authorization of the user to obtain and display the document key information, meeting the actual needs of the user and improving the user experience.

[0010] As an example of the present application, in response to the selection operation on the second identifier, displaying the document key information of the second document text in the first specified area, comprising: in response to the selection operation on the second identifier, canceling displaying the document key information of the first document text in the first specified area, and displaying the document key information of the second document text in the first specified area.

[0011] In this way, by canceling the display of the document key information of the first document text and displaying the document key information of the second document text, the user can quickly and intuitively understand the second document text, improving the efficiency of assisted reading.

[0012] As an example of the present application, in response to the selection operation on the first identifier, displaying the document key information of the first document text in the first specified area in the first interface, comprising: in response to the selection operation on the first identifier, displaying the thumbnail corresponding to the first document text in the first specified area, and displaying the document key information of the first document text in the first specified area. Accordingly, in response to the selection operation on the second identifier, canceling displaying the document key information of the first document text in the first specified area, and displaying the document key information of the second document text in the first specified area, comprising: in response to the selection operation on the second identifier, canceling displaying the document key information of the first document text in the first specified area, and canceling displaying the thumbnail corresponding to the first document text in the first specified area. Displaying the document key information of the second document text in the first specified area, and displaying the thumbnail corresponding to the second document text in the first specified area.

[0013] In this way, by displaying the thumbnail corresponding to the first document text, the user can also understand the first document text by viewing the thumbnail, and the efficiency of auxiliary reading is improved. Moreover, when the selection operation on the second identifier is received, by displaying only the document key information and the thumbnail of the second document text in the first specified area, the user can intuitively and quickly view.

[0014] As an example of the present application, the method further comprises: in response to an opening operation on the second document text, displaying a second interface, the second interface including text content of the second document text and an AI document assistant portal. In response to a second operation on the AI document assistant portal, displaying a first AI dialog box in the second interface, wherein the first AI dialog box is displayed side by side with the text content of the second document text. In response to a text addition operation triggered in the first AI dialog box, displaying an identifier of the added target text in the first AI dialog box, the text addition operation being used to determine the target text to be compared. In response to a first comparison instruction input in the first AI dialog box, displaying a first comparison result below the identifier of the target text in the first AI dialog box, the first comparison result being a comparison result of the target text and the content of the second document text.

[0015] In this way, by embedding the AI function in the multifunctional office platform, the user can trigger the electronic device to use the AI function to help the user compare multiple document texts during reading of the document text, thereby improving the reading efficiency of the user.

[0016] As an example of the present application, the number of target texts is multiple, and the method further comprises: in response to a second comparison instruction input in the first AI dialog box, displaying a second comparison result in the first AI dialog box, the second comparison result being a comparison result of the multiple target texts.

[0017] In this way, by receiving different comparison instructions, the multiple document texts are compared in a targeted manner, thereby meeting the actual needs of the user and improving the user experience.

[0018] As an example of the present application, in response to the second operation on the AI document assistant portal, after displaying the first AI dialog box in the second interface, the method further comprises: in response to a document content summary instruction input in the first AI dialog box, displaying a content summary result of the second document text in the first AI dialog box.

[0019] In this way, by displaying the first AI dialog box for the user, the user can input a document content summary instruction to trigger the electronic device to use the AI function to summarize the opened document text, thereby enabling the user to quickly understand the document text and improving the user experience.

[0020] As an example of the present application, in response to the second operation on the AI document assistant portal, after displaying the first AI dialogue box in the second interface, further comprising: in response to the first questioning instruction input in the first AI dialogue box, displaying the first answer corresponding to the first questioning instruction in the first AI dialogue box, the first questioning instruction is a questioning instruction for the second document text, and the first answer is an answer determined according to the second document text.

[0021] In this way, by displaying the first AI dialogue box for the user, the user can input the questioning instruction to trigger the electronic device to determine the corresponding answer based on the opened document text using the AI model, thereby enabling the user to quickly obtain the required understanding content and improving the user experience.

[0022] As an example of the present application, in response to the second operation on the AI document assistant portal, after displaying the first AI dialogue box in the second interface, further comprising: receiving a selection operation on the first document content in the second document text; in response to the polishing instruction input in the first AI dialogue box, performing at least one editing operation on the first document content, and displaying the editing result in the first AI dialogue box, the at least one editing operation includes expansion, abbreviation, synonym rewriting, language style rewriting and error correction; in response to the result replacement operation, replacing the first document content with the editing result.

[0023] In this way, the user can trigger the electronic device to perform at least one editing operation on the text content using the AI function by inputting the polishing instruction, without the need to find the editing portal one by one when the user wants to edit the text content in multiple ways, thereby improving the editing efficiency.

[0024] As an example of the present application, in response to the second operation on the AI document assistant portal, after displaying the first AI dialogue box in the second interface, further comprising: in response to the translation instruction input in the first AI dialogue box, translating the second document text into the language indicated by the translation instruction, and displaying the translation result in the first AI dialogue box.

[0025] In this way, by displaying the first AI dialogue box for the user, the user can input the translation instruction to trigger the electronic device to translate the opened document text using the AI function, avoiding the need for the user to rely on other third-party translation software, improving the translation efficiency, and thereby improving the user experience.

[0026] As an example of the present application, the plurality of application functions includes a note function, and the method further includes: receiving a third operation, displaying a third interface, the third interface being an interface corresponding to the note function, and the third interface including at least one note text; in response to an opening operation on a first note text in the at least one note text, displaying text content of the first note text in a second specified area in the third interface, and displaying an AI note assistant portal; in response to a fourth operation on the AI note assistant portal, displaying a second AI dialog box in the second specified area, wherein the first note text and the second AI dialog box are displayed side by side; and in response to a note summary instruction input in the second AI dialog box, displaying a content summary result of the first note text in the second AI dialog box.

[0027] In this way, by displaying the AI note assistant portal in the interface corresponding to the note function, the user can trigger the electronic device to display the second AI dialog box through the AI note assistant portal, so that the user can input a note summary instruction in the second AI dialog box to trigger the electronic device to summarize the opened note text using the AI function, thereby improving the user's reading note efficiency.

[0028] As an example of the present application, in response to the fourth operation on the AI note assistant portal, after displaying the second AI dialog box in the second specified area, the method further includes: in response to a second question instruction input in the second AI dialog box, displaying a second answer in the second AI dialog box, the second question instruction being a question instruction for the first note text, and the second answer being an answer determined based on the first note text.

[0029] In this way, by displaying the second AI dialog box for the user, the user can input a question instruction to trigger the electronic device to determine a corresponding answer based on the opened note text using the AI model, thereby enabling the user to quickly obtain the required understanding content and improving the user experience.

[0030] As an example of the present application, in response to the fourth operation on the AI note assistant portal, after displaying the second AI dialog box in the second specified area, the method further includes: in response to a layout instruction input in the second AI dialog box, displaying a layout result of the first note text in the second AI dialog box, and displaying a replacement control in the second AI dialog box; and in response to a trigger operation on the replacement control, replacing the text content in the first note text with the layout result.

[0031] In this way, by displaying the second AI dialog box for the user, the user can input a layout instruction to trigger the electronic device to perform layout on the opened note text using the AI model, for example, the layout operation includes at least one operation, i.e., the user can trigger the electronic device to perform at least one layout operation with one key, thereby improving the layout efficiency and improving the user experience.

[0032] As an example of the present application, the second AI dialogue box further includes a copy control and an export control, the copy control is used to copy the typesetting result, and the export control is used to export the typesetting result. In this way, the user can quickly copy or export the typesetting result, improving the operation efficiency.

[0033] As an example of the present application, the method further includes: in the case that the total number of words of the first note text exceeds the first word threshold, after displaying the text content of the first note text in the second specified area, displaying a note summary control on the second interface; in response to the triggering operation on the note summary control, displaying a second AI dialogue box in the second specified area, and displaying the content summary result in the second AI dialogue box.

[0034] In this way, by pushing the note summary control, the user can trigger the electronic device to summarize the opened note text using the AI model with one key, without the user inputting the note summary instruction, improving the operation convenience, thereby improving the summary efficiency.

[0035] As an example of the present application, the method further includes: in the case that the typesetting format of the first note text does not conform to the preset typesetting format, after displaying the text content of the first note text in the second specified area, displaying a typesetting control on the second interface; in response to the triggering operation on the typesetting control, displaying a second AI dialogue box in the second specified area, and displaying the text content after typesetting in the second AI dialogue box.

[0036] In this way, by pushing the typesetting control, the user can trigger the electronic device to typeset the opened note text using the AI model with one key, without the user inputting the typesetting instruction, improving the operation convenience, thereby improving the typesetting efficiency.

[0037] As an example of the present application, after receiving the third operation and displaying the second interface, the method further includes: in the case that there are multiple second note texts in the multi-functional office platform, and the total number of words of each of the multiple second note texts is less than the second word threshold, displaying a merge control on the second interface; in response to the triggering operation on the merge control, merging the text content of the multiple second note texts into a third note text.

[0038] In this way, by pushing the merge control, the user can trigger the electronic device to merge multiple scattered note texts using the AI model with one key, which can improve the management efficiency of the note text.

[0039] As an example of the present application, after receiving the third operation and displaying the second interface, the method further includes: displaying a knowledge classification view control in the second interface; in response to a triggering operation on the knowledge classification view control, displaying a note text graph in the second specified area, the note text graph being generated by clustering a plurality of note texts in the multi-functional office platform, the note text graph including a plurality of nodes; and in response to a triggering operation on any one of the plurality of nodes, displaying basic description information of the note text associated with the node information of the any one node.

[0040] The basic description information can include a title of the note text, a folder name of a folder to which the note text belongs, and the like.

[0041] In this way, by pushing the knowledge classification view control, the user can trigger the electronic device to cluster a plurality of note texts using an AI model to generate a graph by one key, thereby facilitating the user to quickly understand the overall situation of the note texts in the multi-functional office platform through the graph, and facilitating the user to quickly review the note texts.

[0042] In a second aspect, an electronic device is provided, which includes one or more processors, and a memory; the memory is coupled to the one or more processors, and is configured to store computer program codes, the computer program codes including computer instructions, the one or more processors being configured to invoke the computer instructions to cause the electronic device to perform the text management method according to the first aspect.

[0043] In a third aspect, a chip system is provided, which is applied to an electronic device, and includes one or more processors, the one or more processors being configured to invoke computer instructions to cause the electronic device to perform the text management method according to the first aspect.

[0044] In a fourth aspect, a computer readable storage medium is provided, which stores instructions, when the instructions are run on a computer, cause the computer to perform the text management method according to the first aspect.

[0045] In a fifth aspect, a computer program product is provided, which includes instructions, when the instructions are run on a computer, cause the computer to perform the text management method according to the first aspect.

[0046] The technical effects obtained by the second aspect, the third aspect, the fourth aspect and the fifth aspect are similar to the technical effects obtained by the corresponding technical means in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 is a schematic diagram of an application scenario according to an example embodiment;

[0048] Figure 2 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0049] Figure 3 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0050] Figure 4 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0051] Figure 5 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0052] Figure 6 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0053] Figure 7 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0054] Figure 8 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0055] Figure 9 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0056] Figure 10 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0057] Figure 11 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0058] Figure 12 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0059] Figure 13 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0060] Figure 14 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0061] Figure 15 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0062] Figure 16 is a schematic diagram of an application scenario according to another exemplary embodiment;

[0063] Figure 17is a schematic diagram of an application scenario according to another exemplary embodiment;

[0064] Figure 18 is a flowchart of a text management method according to an exemplary embodiment;

[0065] Figure 19 is a structural diagram of an electronic device according to an exemplary embodiment;

[0066] Figure 20 is an architectural diagram of a software system of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0067] For the purpose of making the objects, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0068] It should be understood that the "multiple" mentioned in the present application refers to two or more than two. In the description of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B; "and / or" in the present application is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, in order to clearly describe the technical solutions of the present application, the same items or similar items with basically the same functions and roles are distinguished by using "first", "second", etc. The skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. also do not necessarily mean different.

[0069] In the present application, the reference to "one embodiment" or "some embodiments" and the like means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in other some embodiments" and the like appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized.

[0070] The multifunctional office platform can also be referred to as a super workbench or a one-stop intelligent office platform. The multifunctional office platform integrates multiple office application functions, such as note, collection space, file management, and the like. The collection space refers to that when a user slides three fingers from the top of the screen to the bottom of the screen, the electronic device automatically saves the text in the interface as a text. The file management includes opening, classifying, and managing the document text.

[0071] When a user needs to find a document text from multiple document texts during learning or office work through the multifunctional office platform, a long time is usually needed, for example, the user needs to open each document text one by one through the multifunctional office platform, and then reads the opened document text to find the required document text. Since the text content of the document text is usually more, the user's reading time is long, which increases the finding time and reduces the finding efficiency of the document text.

[0072] In addition, when a user records, reads, or edits a text through the note and document management functions in the multifunctional office platform, the user usually needs to use some materials or edit and arrange the text. Since the data in the multifunctional office platform is much, the application functions are many, and the entrances are scattered, the user faces the problem of not knowing how to use or being difficult to use, so that the user cannot quickly and efficiently implement the office procedures such as editing and recording.

[0073] For example, in an exemplary application scenario, the user may need some materials during recording notes through the multifunctional office platform. In this case, the user usually needs to collect materials through the collection space function. For example, the user can search for materials from a webpage, and when the user sees the materials to be collected from the webpage, the user can slide three fingers from the top of the screen to the bottom of the screen to trigger the collection space operation. In response to the collection space operation of the user, the electronic device automatically saves the text in the webpage as a note text. However, when the materials collected in the electronic device are more, the user needs to arrange the multiple materials in the electronic device, which reduces the office efficiency. For another example, in another exemplary application scenario, the user may need to perform a series of text processing such as layout and error correction during writing through the multifunctional office platform. In some examples, the multifunctional office platform provides various editing entrances, such as adjusting font size, increasing numbering, aligning, centering, and the like. The user needs to trigger the corresponding editing function through each editing entrance to edit the text. However, since the entrances are scattered, the efficiency of text editing is reduced.

[0074] To this end, an embodiment of the present application provides a text management method, by embedding an artificial intelligence (AI) function in a multi-functional office platform, so that when a user uses notes and documents for office work, the user can quickly search for text and locate the required materials by using the large model capability, and can also efficiently assist in reading and writing, thereby improving the user's efficiency in office work and learning on an electronic device.

[0075] Next, taking the user's reading and editing of document text (which can be in the formats of doc, PDF, xls, or pptx, etc.) through the document management function in the multi-functional office platform as an example, the text management method provided by an embodiment of the present application is introduced.

[0076] As an example of the present application, an application icon of the multi-functional office platform can be provided in the desktop of the electronic device. If the user wants to use the multi-functional office platform for office work or learning, the user can click the application icon, and in response to the user's click operation on the application icon, the electronic device starts the multi-functional office platform. After the multi-functional office platform is started, a platform interface is displayed, and the platform interface is divided into multiple areas, different areas are used to display different controls or contents. For example, see Figure 1 (a) of FIG. or Figure 1 (b) of FIG., which are respectively a schematic diagram of a platform interface after the multi-functional office platform is started according to an exemplary embodiment, mainly including a first area S11 and a second area S12, wherein the first area S11 is used to display function icons of multiple application functions provided by the multi-functional office platform, for example, the multiple function icons in the first area S11 are in order from top to bottom as the smart interconnection icon, the note icon, the calendar icon, the user space icon, and the document management icon, and the user can use the corresponding application function in the multi-functional office platform by triggering different function icons; the second area S12 is used to display the interface corresponding to different application functions, that is, the interface displayed by the second area S12 corresponds to the function icon in the first area S11 that is in a selected state. For example, see Figure 1 (a) of FIG., in the case where the note icon is in a selected state, that is, the user is using the note function, the second area S12 displays the interface corresponding to the note function, and for another example, see Figure 1 (b) of FIG., in the case where the document management icon is in a selected state, that is, the user is using the document management function, the second area S12 displays the interface corresponding to the document management function.

[0077] After the multi-functional office platform is started, the interface corresponding to a certain application function can be displayed by default. Exemplarily, after the multi-functional office platform is started, the interface corresponding to the note function can be displayed by default, that is, after the multi-functional office platform is started, the interface corresponding to the note function is displayed by default. Figure 1The platform interface shown in (a) of FIG. 1, wherein the note icon in the first area S11 is displayed in a selected state, i.e., a selected state icon is displayed in the vicinity of the note icon, and in addition, the interface corresponding to the note function is displayed in the second area S12. Alternatively, when the user wants to use other application functions, the user can trigger the electronic device to display the interface corresponding to other application functions in the second area S12 of the multi-functional office platform through the function icon displayed in the first area S11. For example, when the user wants to read a document text, the user can click the document management icon in the leftmost area (i.e., the first area S11) of the platform interface. In response to the user's click operation on the document management icon, the electronic device displays the interface corresponding to the document management function in the second area S12, and the document management icon is displayed in a selected state.

[0078] Of course, the embodiments of the present application take the multi-functional office platform starting by default to display the interface corresponding to the note function as an example for illustration. In another example, the multi-functional office platform can also start by default to display the interface corresponding to other application functions, for example, the multi-functional office platform can also start by default to display the interface corresponding to the file management function, i.e., the multi-functional office platform displays the platform interface after starting, the file management icon in the first area S11 of the platform interface is in a selected state, and the second area S12 of the platform interface displays the interface corresponding to the file management function, as shown in (b) of FIG. 1. Figure 1 The embodiments of the present application are not limited in this regard.

[0079] In the case of displaying the interface corresponding to the document management function (hereinafter referred to as the document management interface) in the second area S12, if the user wants to quickly understand the content of any one document text in the document management interface, the user can click the identifier of the document text displayed in the document management interface. The identifier is used to uniquely identify a document text, for example, the identifier can include a document icon and a document title. In response to the user's click operation on the identifier of the document text, the electronic device displays the document key information of the document text in the first specified area of the document management interface. The document key information can enable the user to quickly understand the document text, for example, the document key information includes but is not limited to keywords, abstracts, and some important information. Alternatively, the electronic device can also display the thumbnail (which can be the thumbnail of the first page of the document text) corresponding to the document text in the first specified area.

[0080] As an example, the multi-functional office platform is embedded with an AI function. In the case where the electronic device detects the user's selection operation on the identifier of any one document text, the AI model can be called to analyze the any one document text through the AI model to obtain the document key information, and then display the document key information in the first specified area.

[0081] The first designated area can be set according to requirements. As an optional example, the first designated area can be the rightmost area of ​​the document management interface.

[0082] For example, see Figure 2 In Figure (a), when a user wants to quickly find out what a document text d1 is about, they can click on the identifier 21 of the document text d1 (which is not open) displayed in the document management interface. See also Figure 2 In Figure (b), in response to the user's click on identifier 21, the electronic device displays a thumbnail of the document text d1 in the rightmost area of ​​the document management interface. Figure 1 Furthermore, in the abbreviated text d1 of the document Figure 1 Below is the key information of document text d1, including keywords and a summary. This allows users to quickly understand the content of document text d1 and determine if it is the document they are looking for. If the key information of document text d1 indicates that it is not the document they are looking for, they can continue by clicking on the identifier 22 of the next document text d2 in the document management interface. Figure 2 As shown in Figure (c), in response to the user's click on identifier 22, the electronic device no longer displays the abbreviated version of document text d1 in the rightmost area of ​​the document management interface. Figure 1 Instead of displaying key information in the document, it shows a thumbnail of the document text d2. Figure 2 This method allows users to click on any document text identifier in the document management interface. The electronic device then uses an AI model to analyze the document text corresponding to the clicked identifier, obtaining key document information. This key information, along with a thumbnail, is then displayed, enabling users to quickly understand the document text and find the desired document, thus improving the speed of document retrieval.

[0083] It should be noted that this embodiment of the application illustrates the example of displaying key document information and a thumbnail of a document text in a first designated area after receiving a click operation on an identifier of a document text. In another example, after receiving a click operation on an identifier of a document text, only key document information may be displayed in the first designated area, that is, the thumbnail may not be displayed. This embodiment of the application does not limit this.

[0084] It should also be noted that this embodiment of the application illustrates the example of displaying only the document key information and thumbnail of one document text at a time in the first designated area. In another example, the document key information and thumbnails of multiple document texts can also be displayed in the first designated area. For example, a preset number of document key information and thumbnails can be displayed. The preset number can be set according to needs, for example, the preset number can be 2. This embodiment of the application does not limit this.

[0085] As an optional example, if the electronic device has not displayed the document's key information before the identifier of a document text was selected, then when the user selects the identifier, the electronic device may only display a thumbnail of the document text in a first designated area, without showing the key information. Furthermore, the electronic device may display a key information display control in the document management interface. This control is used to trigger the display of the document's key information for the selected document text. When the user wants to view the document's key information, they can click the key information display control. In response to the user's click, the electronic device analyzes the selected document text using an AI model to determine the key information, and then displays the key information below the thumbnail. See, for example... Figure 3 In Figure (a), after the user selects identifier 30 for document text d3, if the electronic device has not previously displayed key document information for document text d3, a thumbnail of document text d3 will be displayed in the far right area of ​​the document management interface. Figure 3 The document's key information is not displayed, but a key information display control (i.e., key information) 31 is displayed in the document management interface. When the user clicks the key information display control 31, see [link to relevant documentation]. Figure 3 In Figure (b), in response to the user's click on the key information display control 31, the electronic device displays the key document information 32 of the document text d3 in the document management interface. Thus, with user authorization, the document text is analyzed and processed by an AI model to obtain and display key document information, meeting the user's actual needs and improving the user experience.

[0086] Optionally, after the electronic device determines the key information of the document through the AI ​​model, it can store the key information of the document in a designated location. For example, the key information of the document can be stored in a designated location along with an identifier. In this way, when the identifier of the document text selected by the user is detected again, the key information of the document can be directly retrieved from the designated location, avoiding the need to determine the key information of the document through the AI ​​model every time, which can improve the information display speed.

[0087] See Figure 2 Figure (b) in the middle Figure 2 Figure (c) in the middleFigure 3 Figure (a) in the middle or Figure 3 In Figure (b), besides displaying a thumbnail of the document text and key document information in the first designated area, the electronic device can also provide multiple controls in the first designated area. Different controls can be used to trigger different operations on the selected document text. For example, the multiple controls include share, tag, favorite, copy, and open controls. Thus, users can perform further operations on the selected document text through multiple controls. For instance, the share control can trigger the electronic device to share the document text, the tag control can trigger the electronic device to add tags to the document text, the favorite control can trigger the electronic device to add the document text to the favorites folder, the copy control can trigger the electronic device to copy the document text, and the open control can trigger the electronic device to open the document text. Therefore, by providing multiple controls in the first designated area, the efficiency of user operations on the document text can be improved, enhancing the user experience.

[0088] When a user opens a document on a multi-functional office platform, the electronic device displays the document's interface, such as... Figure 4 As shown in Figure (a) S4, the document display interface S4 displays the text content of the document. In addition, the document display interface also displays an entry point for the AI ​​document assistant, such as... Figure 4 As shown in Figure 41 (a) above. While reading the document text, the user can click on the AI ​​Document Assistant entry point 41, see [link / reference]. Figure 4 In Figure (b), in response to the user's click on the document assistant entry 41, the electronic device displays a first AI dialog box 42 in the document display interface S4. The first AI dialog box 42 is displayed side by side with the text content of the document. In this way, the user can input commands through the first AI dialog box 42 to trigger the electronic device to use the AI ​​function embedded in the multi-functional office platform to assist the user in reading or editing the document text.

[0089] For example, in one instance, a user can trigger an electronic device to perform multi-document comparison by inputting a command through the first AI dialog box 42. Specifically, the first AI dialog box 42 provides a document upload control, through which the user can upload one or more (up to a specified number, such as 3) other texts from the electronic device, thus triggering a text addition operation. Accordingly, the electronic device determines the one or more other texts to be added. Then, the user can input a comparison command through the command input box provided in the first AI dialog box 42. In response to the comparison command, the electronic device compares the multiple texts indicated by the comparison command using an AI model and displays the comparison results in the first AI dialog box 42. As an example and not a limitation, the comparison results may include text summary comparison results and / or table comparison results. Text probability comparison results refer to comparison results expressed in text form, while table comparison results refer to comparison results expressed in table form.

[0090] For example, see Figure 4 In Figure (b), the first AI dialog box 42 includes a command input box 420, which in turn includes a document upload control 421. When a user needs to compare multiple documents, they can click the document upload control 421. In response to the user's click on the document upload control 421, the electronic device displays a file directory, allowing the user to select the text to be compared from the electronic device's storage space. After selecting the text to be compared, the electronic device can display the identifier of the text to be compared in the first AI dialog box 42. See, for example... Figure 5 In Figure (a), after the user uploads two text documents, the electronic device displays the identifiers of these two documents, 501 and 502, in the first AI dialog box 42. The user can then enter a comparison command in the command input box 420, such as "Compare these two documents." The user can then click the command confirmation control 422 in the command input box 420. Upon receiving the user's click on the command confirmation control 422, in response to the comparison command, the electronic device performs a comparative analysis of the two uploaded text documents using an AI model, obtains the comparison results, and displays the results in the first AI dialog box 42. Optionally, the comparison results can be displayed below the identifiers, for example, see [see...] Figure 5 Figure (b) shows the comparison results, which include textual summary comparison result 503 and table comparison result 504.

[0091] According to the comparison instruction input by the user, the electronic device compares different texts. In an example, the electronic device can also compare the uploaded text with the opened document text according to the comparison instruction input by the user. For example, the user can input the comparison instruction "compare the uploaded text with the opened document" in the instruction input box 420. In this case, in response to the comparison instruction, the electronic device compares the opened document text and the uploaded text through the AI model, obtains the comparison result, and then displays the comparison result in the first AI dialogue box 42.

[0092] It is worth mentioning that the user can upload one or more texts through the first AI dialogue box, and then input a comparison instruction in the first AI dialogue box to trigger the electronic device to compare the texts through the AI model. Without reading each text, the user can know the differences between the multiple texts, improving the reading efficiency.

[0093] It should be noted that the embodiments of the present application are described by taking the example that the user needs to input a comparison instruction in the first AI dialogue box 42 after uploading multiple texts. In another example, after the user uploads multiple texts, the electronic device can directly call the AI model to compare and analyze the multiple texts uploaded by the user, and display the comparison result in the first AI dialogue box 42. Alternatively, after the user uploads multiple texts, the electronic device can directly call the AI model to compare and analyze the multiple texts uploaded by the user and the opened document text, and display the comparison result in the first AI dialogue box 42. That is, the electronic device directly performs the comparison operation without the user inputting the comparison instruction, which can improve the comparison efficiency.

[0094] In another example of the present application, the user can input an instruction through the first AI dialogue box 42 to trigger the electronic device to assist the user in summarizing or asking questions about the opened document text using AI functions. That is, during the process of reading the document text, the user can also input an instruction through the first AI dialogue box 42 to trigger the electronic device to summarize the opened document text using the AI model, obtain the content summary result, and then display the content summary result in the first AI dialogue box 42. In addition, the user can also ask questions about the opened document text through the first AI dialogue box 42 to trigger the electronic device to determine the answer based on the opened document text through the AI model, and display the determined answer in the first AI dialogue box 42.

[0095] Taking the example of inputting an instruction through the first AI dialogue box 42 to trigger the electronic device to summarize the opened document text, referring to FIG. 4B, the user can input a summary instruction in the instruction input box 420 of the first AI dialogue box 42. In response to the summary instruction, the electronic device can obtain the content summary result of the opened document text through the AI model, and display the content summary result in the first AI dialogue box 42. Figure 6When the electronic device displays the first AI dialog box 42, the user can enter a document content summary command in the command input box of the first AI dialog box 42, and then click the command confirmation control 422 in the command input box. Correspondingly, the electronic device receives the document content summary command in the first AI dialog box 42. For example, the document content summary command can be... Figure 6 The 60 in the example refers to "summarizing the document on the left." Accordingly, the electronic device can invoke an AI model to summarize the opened document text, determine the summary result, and then refer to... Figure 6 In section 61, the electronic device displays a summary of the content in the first AI dialog box 42.

[0096] Of course, users can input other summary-related commands in the first AI dialog box 42 to trigger the electronic device to generate other forms of content summary results. For example, other summary-related commands could also include outline generation commands, mind map generation commands, etc. See, for example... Figure 7 Users can enter mind map generation instructions in the instruction input box of the first AI dialog box 42, such as... Figure 7 As shown in 70, one can input "Generate Mind Map" and then click the instruction confirmation control 422 in the instruction input box. Accordingly, the electronic device receives the mind map generation instruction in the first AI dialog box 42, then generates the mind map using the AI ​​model, and finally displays the mind map 71 in the first AI dialog box 42. Please continue to see... Figure 7 Users can also enter an outline generation command 72 in the command input box of the first AI dialog box 42, such as entering "Generate Outline", and then click the command confirmation control 422 in the command input box. Accordingly, the electronic device receives the outline generation command in the first AI dialog box 42, then generates an outline through the AI ​​model, and then displays the outline 73 in the first AI dialog box 42, thereby providing users with a similar writing approach.

[0097] In addition, users can also enter question commands for the opened document text in the first AI dialog box 42, for example, see Figure 8, the user can input the questioning instruction 1 in the instruction input box in the first AI dialogue box 42, and then click the instruction confirmation control 422 in the instruction input box. Correspondingly, after the electronic device receives the questioning instruction 1 in the first AI dialogue box 42, the electronic device can call the AI model to determine the answer 1 corresponding to the questioning instruction 1 based on the opened document text, and the electronic device displays the answer 1 in the first AI dialogue box 42. Then, the user can continue to input the questioning instruction 2 in the instruction input box in the first AI dialogue box 42, and then click the instruction confirmation control 422 in the instruction input box. Correspondingly, after the electronic device receives the questioning instruction 2 in the first AI dialogue box 42, the electronic device can call the AI model to determine the answer 2 corresponding to the questioning instruction 1 based on the opened document text, see Figure 8 , the electronic device displays the answer 2 in the first AI dialogue box 42. That is, the electronic device supports the user to continuously ask questions, and each determined answer can be the original content in the opened document text, or can be an answer summarized based on the opened document text.

[0098] Optionally, after displaying each answer, the electronic device can push one or more other questioning instructions below the answer in the form of a list or the like. The other questioning instructions can have different expression forms but similar semantics to the previous questioning instruction, for example, see Figure 8 After displaying the answer 1, the electronic device can display two other questioning instructions, i.e., recommended questioning 1 and recommended questioning 2, below the answer 1. The two other questioning instructions have similar semantics to the questioning instruction 1 but different ways of asking. For another example, after displaying the answer 2, the electronic device can display two other questioning instructions, i.e., recommended questioning 3 and recommended questioning 4, below the answer 2. The two other questioning instructions have similar semantics to the questioning instruction 2 but different ways of asking. In this way, in the case that the user clicks the other questioning instruction, the electronic device determines the answer from the opened document text by the AI model for the other questioning instruction clicked by the user, and displays the answer. Since the user does not need to input the instruction again, and different ways of asking are used for similar questions, the effectiveness of questioning can be improved, and the efficiency of questioning is also improved.

[0099] As an example of the present application, when the user needs to edit the document text, the user can also input the relevant instruction through the first AI dialogue box 42 to trigger the electronic device to edit the opened document text through the AI function. For example, the user can select a part of the text content in the opened document text, and then input the polishing instruction in the first AI dialogue box 42. In response to the polishing instruction, the electronic device can perform at least one editing operation on the selected part of the text content through the AI model, and display the editing result in the first AI dialogue box 42, wherein the at least one editing operation can include abbreviation, expansion, synonym rewriting, language style rewriting (such as written or oral rewriting), error correction (such as correcting wrong characters, syntax errors, and sentence errors), etc. Alternatively, the electronic device can also display a replacement control after displaying the editing result, and the replacement control can be used to trigger the replacement of the selected text content with the editing result. When the user wants to replace the selected part of the text content with the polished editing result, the user can click the replacement control. In response to the user's click operation on the replacement control, the electronic device replaces the selected part of the text content with the editing result.

[0100] For example, referring to (a) of FIG. 1, Figure 9 When the user wants to re-edit paragraph 1 in the opened document text, the user can select paragraph 1. Alternatively, the electronic device can display the selected paragraph 1 in the first AI dialogue box 42. Then, the user can input the polishing instruction in the instruction input box in the first AI dialogue box 42, for example, input the polishing instruction of "polish this paragraph", and then click the instruction confirmation control 422. Accordingly, referring to (b) of FIG. 1, Figure 9 After receiving the user's click operation on the instruction confirmation control 422, in response to the polishing instruction, the electronic device displays the editing result of paragraph 1 in the first AI dialogue box 42. Alternatively, the editing result can also be displayed below the "insert text" replacement control 90. When the user wants to replace paragraph 1 with the editing result, the user can click the replacement control 90. In response to the user's click operation on the replacement control 90, the electronic device replaces paragraph 1 with the editing result.

[0101] It should be noted that the present application is exemplified by editing part of the text content in the opened document text. In another example, the entire content of the document text can also be directly edited. For example, the user can input the instruction of "polish the left document" in the instruction input box in the first AI dialogue box 42. Accordingly, the electronic device performs at least one editing operation on the entire content of the opened document text and displays the editing result.

[0102] It is worth mentioning that when the user opens the document text through the multi-functional office platform, a series of editing operations such as expansion, abbreviation, style rewriting, etc. on the document text may be usually needed. In the multi-functional office platform, multiple editing entrances may be provided, and the user needs to find the editing entrance according to the needs and then trigger the electronic device to perform the corresponding editing operation. In the embodiment of the present application, the user can trigger the electronic device to perform at least one editing operation on the text content by inputting the polishing instruction through the AI function, without the need for the user to find the editing entrance one by one when the user wants to perform multiple editing on the text content, thereby improving the editing efficiency.

[0103] Of course, in some embodiments, the user can also input other editing instructions in the first AI dialogue box, such as rewriting instructions, abbreviation instructions, expansion instructions, synonym rewriting instructions, language style rewriting instructions, and error correction instructions, so that the electronic device edits part or all of the content in the opened document text. For example, the rewriting instruction can be "rewrite the selected document", the abbreviation instruction can be "abbreviate the selected document", the expansion instruction can be "expand the selected document", the synonym rewriting instruction can be "rewrite the selected document with synonyms", the language style rewriting instruction can be "rewrite the language of the selected document into a colloquial style", and the error correction instruction can be "correct the errors in the selected document". For specific implementation, please refer to the related implementation after the polishing instruction is input.

[0104] As an example of the present application, the user can also input instructions through the first AI dialogue box 42 to trigger the electronic device to translate the opened document text. For example, the user can input a translation instruction in the instruction input box in the first AI dialogue box 42, and accordingly, the electronic device translates the opened document text according to the translation instruction, such as translating into the language indicated by the translation instruction. Then the electronic device displays the translation result in the first AI dialogue box 42. For example, the user can input the translation instruction "translate the document on the left into English" in the instruction input box, and then click the instruction confirmation control 422. After receiving the user's click operation on the instruction confirmation control 422, in response to the translation instruction, the electronic device translates the opened document text through the AI model, and displays the translation result in the first AI dialogue box 42.

[0105] It should be noted that the above is an example of triggering the electronic device to display the first AI dialogue box 42 through the AI document assistant entrance when the user needs to use the AI function to assist in reading or editing during the reading of the document text. In one example, after opening the document text, or after the user selects part of the text content in the opened document text, the electronic device can push one or more controls to the user in the form of a bubble, etc. The user can trigger the electronic device to use the AI function through the pushed controls. For example, seeFigure 10 In (a) of FIG. 13, when the user selects part of the text content in the opened document, the electronic device can display the summary control, the polish control and the translation control in the vicinity of the selected text content, the summary control can be used to trigger the electronic device to summarize the selected text content and display the summary result in the first AI dialog box 42, the polish control can be used to trigger the electronic device to perform at least one editing operation on the selected text content and display the editing result in the first AI dialog box 42, and the translation control can be used to trigger the electronic device to translate the selected text content into a specified language and display the translation result in the first AI dialog box 42. For example, see (a) of FIG. 13. Figure 10 In (a) of FIG. 13, when the user clicks the polish control, in response to the user's click operation on the polish control, see (b) of FIG. 13, the electronic device displays the first AI dialog box 42 and displays the editing result in the first AI dialog box 42. In this way, by pushing one or more controls to the user, the user can trigger the electronic device to perform corresponding operations on the opened document text through the pushed controls, without the user needing to input instructions in the first AI dialog box 42, improving the convenience of operation and thus improving the user experience. Figure 10 In (a) of FIG. 13, when the user clicks the polish control, in response to the user's click operation on the polish control, see (b) of FIG. 13, the electronic device displays the first AI dialog box 42 and displays the editing result in the first AI dialog box 42. In this way, by pushing one or more controls to the user, the user can trigger the electronic device to perform corresponding operations on the opened document text through the pushed controls, without the user needing to input instructions in the first AI dialog box 42, improving the convenience of operation and thus improving the user experience.

[0106] It should be noted that when the electronic device displays the first AI dialog box 42, the user can continuously input different types of instructions in the first AI dialog box 42, and different types of instructions are used to trigger the electronic device to perform different operations. For example, a document content summary instruction can be input first, after the electronic device displays the content summary result, the user can continue to input a question instruction in the first AI dialog box 42, after the electronic device displays the answer, the user can continue to input a polish instruction in the first AI dialog box 42, and so on.

[0107] In addition, as an example of the present application, the electronic device displays the execution result corresponding to the instruction input by the user through the first AI dialog box 42 each time, and generally displays it word by word, in this process, the electronic device can display a stop control below the execution result, the stop control is used to trigger the stop of displaying the execution result. For example, see (b) of FIG. 13. Figure 6 During the display of the content summary result, the stop control 62 can be displayed below the content summary result, and if the user wants the electronic device to stop displaying the content summary result, the stop control 62 can be clicked. Correspondingly, in response to the user's click operation on the stop control 62, the electronic device stops displaying the content summary result, so that the user can continue to input the next instruction, thereby preventing the execution time from being too long and the user from waiting for a long time to input the next instruction.

[0108] In addition, after each time displaying the execution result, the electronic device can display a refresh control below the execution result, the refresh control being used to trigger the electronic device to determine the execution result again through the AI function. For example, refer to Figure 7 After displaying the outline, the electronic device can display a refresh control 74 below the outline, and if the user wants the electronic device to regenerate the outline, the refresh control 74 can be clicked. Correspondingly, in response to the user's click operation on the refresh control 74, the electronic device re-invokes the AI model (for example, an AI model in the cloud) to analyze the opened document text, obtains a new outline, and then displays the newly obtained outline in the first AI dialog box 42.

[0109] In addition, it should be further pointed out that after each time displaying the execution result corresponding to the instruction in the first AI dialog box 42, a like control, a share control, a copy control, and the like can be displayed below the execution result, for example, as shown in (b) of FIG. 1, so that the user can further operate the execution result through these controls. Among them, the like control and the share control can be used to trigger the electronic device to collect the user's satisfaction degree for the execution result, so as to facilitate subsequent optimization of the AI model and the like; the copy control can be used to trigger the electronic device to copy the execution result, and the share control can be used to trigger the electronic device to share the execution result. Figure 7

[0110] In addition, as an example of the present application, when displaying the first AI dialog box 42, the electronic device can also provide an instruction template control in the instruction input box, for example, refer to Figure 10 (b) of FIG. 1, the instruction input box also includes an instruction template control 101, and after the user clicks the instruction template control 101, in response to the user's triggering operation on the instruction template control 101, the electronic device can display an instruction template box in the vicinity of the instruction template control 101, as an example, the instruction template box includes an instruction template, which can be directly used as an instruction, that is, the user can click the instruction template in the instruction template box, and correspondingly, the electronic device performs the corresponding operation according to the instruction template clicked by the user. For example, the instruction template box includes instruction templates such as "summarize the content on the left" and "help me translate the document on the left". In this way, the user does not need to manually input the instruction, and the user operation efficiency is improved.

[0111] The above is described taking the document application scenario as an example. Next, the note application scenario will be introduced in combination with the accompanying drawings.

[0112] ​When the electronic device displays the interface corresponding to the note-taking function (hereinafter referred to as the note interface), users can create or open note texts in the multi-functional office platform. Correspondingly, the electronic device displays the created or opened note texts in the second designated area of ​​the note interface. At the same time, the electronic device can provide an AI note assistant entry point in the second designated area. Users can trigger the electronic device to call AI functions through the AI ​​note assistant entry point to perform operations such as summarizing, asking questions, or editing the created or opened note texts based on AI functions. The second designated area can be set according to needs.

[0113] For example, taking a user opening an existing text note, i.e., a note-reading scenario, see [link to example]. Figure 11 In Figure (a), the user can double-click Note 1 in the multi-functional office platform. See also... Figure 11 In Figure (b), in response to the user's double-click operation on Note 1, the electronic device displays the text content of Note 1 in the second designated area S111. Additionally, the second designated area S111 also provides a menu bar in the opened note reading interface, offering multiple controls that allow the user to edit, save, delete, and perform other operations on the opened note text. As an example, the menu bar may also provide an AI note-taking assistant entry 111. See [link to relevant documentation]. Figure 12 In Figure (a), when a user wants to summarize, ask questions, or edit the opened note text, they can click the AI ​​Notes Assistant entry point 111. (See also...) Figure 12 In Figure (b), in response to a user's click on the AI ​​Notes Assistant entry 111, the electronic device displays a second AI dialog box 112 in a second designated area. The second AI dialog box 112 can be displayed side-by-side with the text content of the opened note text. The second AI dialog box 112 includes prompts such as "AI Notes Assistant" and also includes a command input box 113, in which the user can input commands. Accordingly, the electronic device performs corresponding operations on the opened note text based on the commands input by the user in the command input box 113.

[0114] For example, in one instance, a user can enter a note summary command in the command input box 113 to trigger the electronic device to summarize the opened note text using AI functionality. For instance, the user can enter a summary command such as "Generate summary" or "What is the content of this note?" in the command input box 113, and then click the command confirmation control 114 in the command input box 113. Upon receiving the user's click on the command confirmation control 114, in response to the note summary command, the electronic device can summarize the opened note text using an AI model, and then display the summary result in the second AI dialog box 112. See also... Figure 13The content summary results can include a summary of the opened note text, which briefly describes what the opened note text is about, allowing users to quickly understand the relevant content of the note text. Optionally, the content summary results may also include statistical information about the opened note text, such as... Figure 13 As shown. The statistical information includes, but is not limited to, the total number of words in the note text, the number of images included, and the suggested reading time. This statistical information helps users quickly understand the content complexity, length, image-to-text ratio, and reading time of the note text. Optionally, the content summary results can also display smart tags, which include key information related to the opened note text, such as the relevant fields, keywords, and topics.

[0115] As an example, users can also ask questions about the content of the opened note text through a second AI dialog box 112, and the electronic device will provide the answer in the second AI dialog box 112 accordingly. See, for example. Figure 13 Users can enter question 1 in the command input box 113 and then click the command confirmation control 114 in the command input box 113. Correspondingly, the electronic device can analyze the opened note text based on the AI ​​model to obtain answer 1 for question 1. The electronic device then displays answer 1 in the second AI dialog box 112, allowing users to quickly obtain the desired answer. Optionally, the electronic device supports users continuously asking questions through the second AI dialog box 112. For example, after asking question 1 and obtaining answer 1, the user can continue to enter question 2 in the command input box 113 and then click the command confirmation control 114 in the command input box 113. Correspondingly, the electronic device can analyze the opened note text based on the AI ​​model to obtain answer 2, and then display answer 2 in the second AI dialog box 112. Because it supports users asking questions continuously, it can efficiently assist users in answering questions about the opened note text.

[0116] Optionally, the answer determined by the electronic device through the AI ​​model can be the original statement in the opened note text, or it can be a conclusion obtained by summarizing the text content in the opened note text.

[0117] As an example of this application, after each answer is displayed, the electronic device can recommend at least one question similar to the previous question below the answer. The user can click on any of the recommended questions. Accordingly, the electronic device uses an AI model to analyze the question clicked by the user based on the opened note text to determine the answer corresponding to that question, and then displays the answer corresponding to that question in a second AI dialog box 112. For example, see [link to example]. Figure 13, after the electronic device displays the answer 1, the electronic device can recommend two questions below the answer 1, the two questions are similar to the question 1 but have different ways of asking, and the user can click any one of the two questions to trigger the electronic device to determine and display the corresponding answer through the AI model. Similarly, after displaying the answer 2, questions similar to the answer 2 can also be recommended. In this way, through the recommended questions, the user can trigger the electronic device to continue searching and displaying answers without obtaining the desired answer, improving the answer search efficiency.

[0118] As an example of the present application, the AI function embedded in the multi-functional office platform also supports assisting writing of note text. For example, during the office or study process, when the user needs to generate a note text with strong readability and regular format from the opened note text, the user can input a layout instruction (which can be set according to the needs, for example, it can be a "help me with intelligent layout" instruction) in the instruction input box 113 in the second AI dialog box 112. Correspondingly, in response to the layout instruction, the electronic device calls the AI model to format the opened note text, and generates a note text with strong readability and regular format, and then the newly generated note text can be used to replace the opened note text. For example, see Figure 14 When the user wants to layout the opened note text, the user can input the "help me with intelligent layout" instruction in the instruction input box 113 in the second AI dialog box 112, and then click the instruction confirmation control 114 in the instruction input box 113. Correspondingly, the electronic device automatically layouts the opened note text through the AI model, see Figure 14 After the layout is completed, the electronic device displays the note text processed by the layout in the second AI dialog box 112, and the electronic device can provide a replacement control 1400 in the second AI dialog box 112, the replacement control 1400 is used to trigger the use of the note text processed by the layout to replace the original note text (i.e. the opened note text). When the user wants to replace the opened note text with the note text processed by the layout, the user can click the replacement control 1400, and in response to the user's click operation on the replacement control 1400, the electronic device displays the replaced note text in the opened note text, that is, displays the note text processed by the layout.

[0119] As an example but not limited to, the layout operation includes but is not limited to one or more of adding numbering, adjusting position, alignment, font size uniformity, picture centering, line spacing adjustment.

[0120] Optionally, see Figure 14In addition, the second AI dialog box 112 can further provide a copy control and an export control after the opened note text is processed by the layout. The copy control is used to trigger a text copy function, and the export control is used to trigger a text export function. In the case that the user wants to copy the note text processed by the layout, the copy control can be clicked. In response to the click operation of the user on the copy control, the electronic device copies the note text processed by the layout, thereby realizing the copy operation. Alternatively, the electronic device also supports the user to copy part of the content in the note text processed by the layout. For example, the user can select part of the content in the note text processed by the layout displayed in the second AI dialog box 112, and then click the copy control. Correspondingly, the electronic device copies the part of the content selected by the user, so that the user can copy the required text content according to the actual demand. In addition, in the case that the user wants to export the note text processed by the layout, the export control can be clicked. In response to the click operation of the user on the export control, the electronic device can export the note text processed by the layout in the format of text, that is, store it as another note text.

[0121] It should be noted that the above is an example of triggering the electronic device to display the second AI dialog box by the user clicking the AI note assistant entrance, and then triggering the electronic device to execute the corresponding service by using the AI function by the user inputting the instruction in the second AI dialog box. In one example, during the process of opening the note text, the electronic device can also push at least one control according to the opened note text. For example, the electronic device can display the at least one control at a preset position of the note interface. Each control in the at least one control can be used to trigger the electronic device to execute the corresponding service by using the AI function. The service corresponding to any one control can be used to assist the user to read or edit the opened note text, etc.

[0122] The preset position can be set according to requirements. For example, the preset position can be a position near the AI note assistant entrance, and the embodiments of the present application do not limit this.

[0123] In one optional implementation, the electronic device can push at least one control based on the total number of words and / or layout of the note text. For example, upon receiving an open operation for a note text, the electronic device can count the number of words in the opened note text. If the total number of words in the note text exceeds a first word threshold, the electronic device opens the note text and pushes a content summary control and / or an auxiliary reading control into the note interface. The content summary control triggers a summary operation on the opened note text; the auxiliary reading control triggers the electronic device to push at least one question in a second AI dialog box based on the opened note text. When the user clicks on any question, the electronic device determines the corresponding answer based on the opened note text and displays the determined answer in the second AI dialog box. Furthermore, if the layout of the note text does not conform to a preset layout pattern, it can be determined that the layout of the note text is disordered. In this case, the electronic device can push a smart layout control into the note interface, which triggers an automatic layout operation on the opened note text.

[0124] The first character count threshold can be set according to requirements.

[0125] In addition, preset layout patterns can be set as needed. As an example and not a limitation, electronic devices can use a pre-trained layout pattern recognition model to perform layout pattern recognition to determine whether the opened note text conforms to the preset layout pattern. This application embodiment does not limit the layout pattern recognition method.

[0126] For example, see Figure 15 In Figure (a), upon receiving a user's open operation on a text note, the electronic device opens the text note in the note interface in response to the user's open operation. Furthermore, if the total number of characters in the text note exceeds a first character threshold, the electronic device displays a content summary control 151 and an auxiliary reading control 152 in the form of bubbles near the AI ​​note assistant entry point in the note interface. If the user wants to summarize the opened text note using the AI ​​function, they can click on the content summary control 151. (See Figure [link to figure]). Figure 15In Figure (b), in response to a user's click on the content summary control 151, the electronic device displays a second AI dialog box 112 in the note-taking interface, and displays the content summary result in the second AI dialog box 112. That is, upon receiving a user's click on the content summary control 151, the electronic device summarizes the opened note text using an AI model, and then displays the summary result in the second AI dialog box 112. This eliminates the need for the user to input a note summary command in the second AI dialog box 112; the user can trigger the electronic device to summarize the opened note text with a single click using the pushed content summary control 151, improving assisted reading efficiency. If the user wants to ask questions about the opened note text using the AI ​​function, they can click on the assisted reading control 152, see [link to assisted reading section]. Figure 15 In Figure (c), in response to a user's click on the auxiliary reading control 152, the electronic device displays a second AI dialog box 112 in the note-taking interface, and can display at least one question in the second AI dialog box 112. The user can click on any of the questions, and correspondingly, in response to the user's click on any question, the electronic device displays the corresponding answer in the second AI dialog box 112.

[0127] For example, see Figure 16 In Figure (a), upon receiving a user's open operation on a text note, the electronic device opens the text note in the note interface in response to the user's open operation. Furthermore, if the text note's layout does not conform to the preset layout pattern, the electronic device displays a smart layout control 153 as a bubble near the AI ​​note assistant entry point in the note interface. If the user wants to automatically format the opened text note using the AI ​​function, they can click on the smart layout control 153. (See Figure [link to figure]). Figure 16 In Figure (b), in response to a user's click on the intelligent layout control 153, the electronic device displays a second AI dialog box 112 in the note-taking interface, and displays the formatted note text in the second AI dialog box 112. That is, upon receiving a user's click on the intelligent layout control 153, the electronic device can automatically format the opened note text through the AI ​​model, and then display the formatted note text in the second AI dialog box 112. In this way, the user does not need to trigger the electronic device to display the second AI dialog box 112 through the AI ​​note assistant entry and input layout instructions in the second AI dialog box 112. The user can trigger the electronic device to format the opened note text with one click through the pushed intelligent layout control 153, which improves the efficiency of assisted editing.

[0128] It should be noted that the embodiments of the present application are described by taking the form of pushing at least one control in the form of a bubble as an example. In another example, at least one control can also be pushed in other forms, for example, it can also be pushed in the form of a pop-up floating menu, and the embodiments of the present application do not limit this.

[0129] In addition, it should be noted that the embodiments of the present application are described by taking the form of automatically pushing the content summary control 151, the auxiliary reading control 152 and the intelligent layout control 153 by the electronic device as an example. In another example, other controls can also be pushed, and the embodiments of the present application do not limit this.

[0130] It is worth mentioning that in the case of detecting that the user opens the note text, by pushing at least one related control, the user can trigger the electronic device to summarize or layout the opened note text through the AI model through the at least one pushed control without triggering the electronic device to display the second AI dialog box 112 and input instructions in the second AI dialog box 112, thereby improving the user operation efficiency, so as to improve the user experience.

[0131] As an example of the present application, after displaying the execution result corresponding to the instruction each time, the electronic device can also display the like control, such as like, share, copy, share, etc. in the second dialog box, for example, see Figure 14 . In this way, the user can further operate the execution result based on these controls. Further, during the display of the execution result, the electronic device can display a stop control in the second dialog box, so that when the user does not need to continue to display the execution result, the stop control can be triggered to stop the display of the electronic device. After displaying the execution result, the electronic device can also display a refresh control in the second dialog box, so that when the user is not satisfied with the execution result, the refresh control can be triggered to trigger the electronic device to determine and display the execution result again. For details, see the document application scenario in the foregoing.

[0132] In addition, the instruction input box 113 also includes an instruction template control, for example, as shown in 1411. Figure 14 After the user clicks the instruction template control 1411, in response to the triggering operation of the user on the instruction template control 1411, the electronic device displays an instruction template box in the vicinity of the instruction template control 1411, as an example, the instruction template box includes an instruction template, which can be directly used as an instruction. For example, the instruction template box includes instruction templates such as "summarize the left content" and "help me with intelligent layout".

[0133] As an example of the present application, in the process of opening a note text through the multi-functional office platform, the electronic device can provide the above services through the AI function, and can also cluster part or all of the notes in the multi-functional office platform through an AI model, and then display the clustering results in the form of a graph. In one example, in the case of displaying the platform interface (such as (a) in FIG. Figure 1 In one example, in the case of displaying the platform interface (such as (a) in FIG.

[0134] For example, in the case of displaying the platform interface shown in (a) in FIG. Figure 1 If the user wants to view the knowledge classification of the note texts in the multi-functional office platform, the user can click the knowledge classification view control. In response to the user's click operation on the knowledge classification view control, the electronic device displays a graph in the second area S12, for example, the graph describes the history, present and future of the development of automobiles, and the three stages are displayed through three nodes in the graph, that is, the clustering information in the multiple nodes is history, present and future respectively. The user can continue to click any node in the view, for example, click the node corresponding to history. In response to the user's click operation on the node, the electronic device displays the basic description information of the note texts related to the clustering information in the node, such as basic description information including note 1, note 2 and note 3, indicating that the note texts related to history include note 1, note 2 and note 3.

[0135] It should be noted that the above embodiments are described by taking the case that the electronic device displays a graph in the multi-functional office platform after clicking the knowledge classification view control. In another example, if there are multiple clustering results, the electronic device can display multiple graphs, each graph corresponding to a clustering result, and different graphs corresponding to different topics. The user can view multiple graphs according to needs, for example, one of the multiple graphs is related to the topic of automobiles, and the other graph is related to the topic of tourism.

[0136] It is worth mentioning that by providing the user with the knowledge classification view control, the user can quickly understand the content recorded in the note texts in the multi-functional office platform according to the knowledge classification view control, so as to facilitate the user to quickly find the required note texts, and improve the office efficiency.

[0137] As an example of this application, when displaying the interface corresponding to the note-taking function, if there are multiple note texts, and each of these multiple note texts records a small amount of text content, such as the total number of characters in the note texts being less than a second character threshold, then a prompt message for merging the note texts can be displayed in the second area S12. The user can trigger the electronic device to merge the multiple note texts through this prompt message to generate a new note text. This new note text may include all the content of each of the multiple note texts, or it may include the merged content after redundancy processing. In an optional implementation, after merging the new note text, the electronic device may delete the multiple note texts; that is, the multiple note texts will no longer be displayed in the second area S12, only the newly generated note text will be displayed. In another optional implementation, after merging the new note text, the multiple note texts may not be deleted, and the newly generated note text may be added; that is, the second area S12 will still include the multiple note texts, and also include the newly generated note text.

[0138] The second character count threshold can be set according to requirements.

[0139] It is worth mentioning that, in this way, when multiple notes containing scattered data are detected in the multifunctional office platform, by providing users with prompts to merge the notes, users can trigger the electronic device to merge multiple notes with one click, thus improving the efficiency of note merging.

[0140] It should be noted that the above example illustrates opening existing notes on an electronic device within a multi-functional office platform. In another example, the electronic device can also utilize AI features embedded in the multi-functional office platform to assist the user in creating notes. For example, see [link to example]. Figure 17 In Figure (a), when a user wants to create a note text, they can click... Figure 17 In Figure (a), the "Create Note" control 171, in response to a user's triggering action on the "Create Note" control 171, causes the electronic device to create a new note text. See Figure (b). Figure 17 Figure (b) shows the AI ​​note-taking assistant entry 172, displayed in the second area S12. If the user needs to use AI functionality to assist in creating notes, they can click on the AI ​​note-taking assistant entry 172. In response to the user's click on the AI ​​note-taking assistant entry 172, the electronic device displays an AI assistant floating window in the second area S12, as shown in Figure (b). Figure 17As shown in Figure (c) 173, the AI ​​assistant floating window 173 displays an AI input box 174. The AI ​​input box 174 can provide a prompt such as "Help me write..." to encourage the user to trigger the electronic device to create note text using AI functions by inputting a command. For example, a user can input "Help me write an advertising copy" in the AI ​​input box 174, and then trigger the electronic device to call the AI ​​model to write a note reference text by pressing the Enter key. Optionally, the AI ​​assistant floating window 173 can include controls for various themes, such as meeting minutes, meeting agendas, leave requests, project reports, weekly reports, interview outlines, advertising copy, and blogger copy. Users can select a theme control according to their needs, and then input the relevant command for the content to be written in the AI ​​input box to trigger the electronic device to call the AI ​​model to write a note reference text on that theme, thus making the written text more closely aligned with the user's actual needs.

[0141] Furthermore, as an optional example of this application, the electronic device displays the interface corresponding to the note-taking function (i.e., Figure 1 In the interface shown in Figure (a), if the user moves the cursor to the border of any note text identifier and clicks the right mouse button, the electronic device can display a "parsing control" near the identifier of that note text. When the user selects the "parsing control," in response to the user's selection, the electronic device can display a thumbnail of the note text and key note information in the rightmost area, so that the user can quickly see what is recorded in the note text without opening the note document. In this way, when the user needs to find the note text, they can quickly find the required note text based on the key note information. For the specific implementation, please refer to the previous section on the implementation method of displaying key document information. Optionally, if the user clicks the left mouse button while the cursor is on the border of any note text identifier, the electronic device can open that note text in the rightmost area.

[0142] It should be noted that the above application scenarios illustrate how electronic devices manipulate text content using AI functions based on instructions. In another example, AI functions can also be used to edit images, tables, flowcharts, etc., within text. For instance, AI can be used to extract text from images or edit tables within text.

[0143] It should be noted that in some embodiments, the electronic device may, in the process of opening the document text, assist the user in reading with the aid of other AI-enabled applications, such as in some embodiments, with the aid of the YoYo assistant (with AI function) to assist in reading. However, this requires switching between two applications (i.e., the multi-functional office platform and the YoYo assistant), which is less efficient. In the embodiments of the present application, since the AI function can be used directly in the document management interface, that is, the AI function is embedded in the multi-functional office platform, and no switching between applications is required when using, the operation efficiency is improved, thereby improving the user experience.

[0144] It should be noted that the above application scenarios are only exemplary, and in another example, they can also be applied to other application scenarios, such as being applied to a collection space scenario to assist the user in intelligent classification, material extraction and editing, thereby improving the efficiency of material collection and organization. For example, it can also be applied to a file management scenario to assist the user in intelligent classification and management, thereby improving the user's file management efficiency on the electronic device.

[0145] As an example of the present application, the electronic device can execute the corresponding operation through the AI model configured in the electronic device in response to the instruction issued by the user. In another example, the electronic device can also execute the corresponding operation through the AI model in the cloud. In order to facilitate understanding, the following will be described in combination with Figure 18 The specific implementation process of the text management method is introduced.

[0146] S1801: In response to a first operation, a first interface is displayed in the multi-functional office platform, the first interface being an interface corresponding to a document management function, and the first interface including a first identifier of a first document text and a second identifier of a second document text.

[0147] Referring to Figure 1 (b) of the figure, the first operation can be a click operation on the document management icon. Alternatively, the first operation can also be a click operation on the application icon of the multi-functional office platform.

[0148] Referring to Figure 1 (b) of the figure, the first interface is an interface corresponding to the document management function.

[0149] Referring to Figure 2 (a) of the figure, the first identifier of the first document text can be identifier 21, including a document icon and a document title of the first document text, and the document title is "Introduction to A University".

[0150] Referring to Figure 2The second identifier of the second document text can be identifier 22, including a document icon and a document title of the second document text, and the document title is "World Economics".

[0151] S1802: In response to the selection operation on the first identifier, display the document key information of the first document text in the first specified area in the first interface.

[0152] Referring to Figure 2 After the user selects the first identifier, the electronic device displays the document key information of the first document text in the rightmost area in the first interface. In one possible implementation, the electronic device can analyze and process the first document text by using a local AI model to obtain the document key information, and then the electronic device displays the document key information of the first document text in the rightmost area in the first interface. In another possible implementation, the electronic device can also send a document analysis request to the cloud, and the document analysis request can carry the first document text. The document analysis request is used to request to determine the document key information of the first document text. Correspondingly, the cloud can analyze and process the first document text by using an AI model to obtain the document key information, and then send the document key information to the electronic device. After the electronic device receives the document key information sent by the cloud, the electronic device displays the document key information of the first document text in the rightmost area in the first interface.

[0153] Optionally, the electronic device can call a local AI model to analyze and process the first document text, and at the same time, can send a document analysis request to the cloud. If the cloud returns the document key information within a preset time length, the electronic device displays the document key information returned by the cloud in the first specified area in the first interface. If the cloud fails to return the document key information within the preset time length, the electronic device displays the document key information determined by using the local AI model in the first specified area in the first interface, so as to improve the accuracy of the display of the document key information and at the same time, to ensure the timeliness of the display of the document key information as much as possible.

[0154] S1803: In response to the selection operation on the second identifier, display the document key information of the second document text in the first specified area.

[0155] The specific implementation can be referred to S1802.

[0156] In the embodiment of the present application, in response to the first operation, the first interface corresponding to the document management function is displayed on the multi-functional office platform, the first interface includes the first identifier of the first document text and the second identifier of the second document text. In response to the selection operation on the first identifier, the document key information of the first document text is displayed in the first specified area in the first interface, so that the user can quickly understand what the first document text is about. In response to the selection operation on the second identifier, the document key information of the second document text is displayed in the second specified area in the second interface, so that the user can quickly understand what the second document text is about. In this way, the user only needs to click the identifier of the document text to trigger the electronic device to display the document key information, so that the user can quickly understand the document, and then the user can quickly find the document text to be found, thereby improving the document text finding efficiency.

[0157] It should be noted that the present application only takes displaying the document key information as an example for illustration. In another example, when the user triggers the electronic device to use the AI function to assist reading and editing, the corresponding execution result can also be determined according to the above process.

[0158] The electronic device related to the embodiments of the present application can be a mobile phone, a motion camera (GoPro), a digital camera, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, a vehicle-mounted device, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) \ virtual reality (VR) device, etc., and the embodiments of the present application are not limited thereto. In this way, for multi-terminal devices, the AI capability is pulled up in the notes and documents, and the user can use the AI capability in the multi-functional office platform on different electronic devices, thereby realizing the effect of consistent multi-terminal experience.

[0159] Figure 19 is a structural schematic diagram of an electronic device 100 provided by the embodiments of the present application. Referring to Figure 19The electronic device 100 can include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headset interface 170D, a sensor module 180, a key 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 can include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0160] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 can include more or fewer components than illustrated, or combine certain components, or split certain components, or different arrangement of components. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0161] The processor 110 can include one or more processing units, such as: the processor 110 can include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units can be independent devices, or can be integrated in one or more processors.

[0162] The controller can be the nerve center and command center of the electronic device 100. The controller can generate operation control signals according to instruction operation codes and timing signals, and complete the control of fetching instructions and executing instructions.

[0163] The processor 110 can also have internal memory that is used to store instructions and data. In some embodiments, the internal memory of the processor 110 is a cache memory. The cache memory can hold instructions and data that the processor 110 has recently used or that are likely to be used. If the processor 110 needs to use the instructions or data again, it can be accessed directly from the cache memory. This avoids repeated accesses to the main memory, reducing the latency of the processor 110 and thus improving the efficiency of the system.

[0164] In some embodiments, the processor 110 can include one or more interfaces, such as an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0165] It can be understood that the interface connection relationship between the modules shown in the embodiments of the present application is only illustrative and does not constitute a structural limitation of the electronic device 100. In some other embodiments of the present application, the electronic device 100 can also use different interface connection methods or a combination of multiple interface connection methods in the above embodiments.

[0166] The charging management module 140 is configured to receive charging input from a charger. The charger can be a wireless charger or a wired charger. The charging management module 140 can charge the battery 142 and also supply power to the electronic device 100 through the power management module 141. The power management module 141 is configured to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140 to supply power to the processor 110, the internal memory 121, the external memory, the display 194, the camera 193 and the wireless communication module 160, etc.

[0167] The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor, and the baseband processor, etc.

[0168] The electronic device 100 implements the display function through the GPU, the display screen 194, and the application processor, etc. The GPU is a microprocessor for image processing, connecting the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 can include one or more GPUs that execute program instructions to generate or change display information.

[0169] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel can adopt a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a Miniled, a MicroLed, a Micro-oLed, a quantum dot light emitting diode (QLED), etc. In some embodiments, the electronic device 100 can include 1 or N display screens 194, and N is an integer greater than 1.

[0170] The electronic device 100 can implement the shooting function through the ISP, the camera 193, the video codec, the GPU, the display screen 194, and the application processor, etc.

[0171] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement the data storage function. For example, music, video, etc. Files are saved in the external memory card.

[0172] The internal memory 121 can be used to store computer executable program codes including instructions. The processor 110 performs various function applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 can include a program storage area and a data storage area. The program storage area can store an operating system, at least one application program (such as a sound playing function, an image playing function, etc.) required by a function, etc. The data storage area can store data (such as audio data, a phone book, etc.) created by the electronic device 100 during use, etc. In addition, the internal memory 121 can include a high-speed random access memory, and can further include a non-volatile memory such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0173] The electronic device 100 can implement an audio function such as music playing, recording, etc. through an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone interface 170D, an application processor, etc.

[0174] Next, the software system of the electronic device 100 is described.

[0175] The software system of the electronic device 100 can adopt a layered architecture, an event-driven architecture, a micro-kernel architecture, a micro-service architecture, or a cloud architecture. Embodiments of the present application take an Android system with a layered architecture as an example to exemplarily describe the software system of the electronic device 100.

[0176] Figure 20 is a block diagram of a software system of an electronic device 100 provided by an embodiment of the present application. Referring to Figure 20 , the layered architecture divides software into several layers, each of which has a clear role and division of labor. Layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom, an application layer, an application framework layer, an Android runtime and a system layer, and a kernel layer.

[0177] The application layer can include a series of application packages. As Figure 20 indicated, the application packages can include multi-functional office platforms, camera, gallery, calendar, call, map, navigation, Bluetooth, music, video, short message, etc.

[0178] The application framework layer provides application programming interfaces (APIs) and programming frameworks for the applications of the application layer. The application framework layer includes some pre-defined functions. AsFigure 20 As shown, the application framework layer can include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like. As an example and not a limitation, the AI model described in each of the above examples can be located at the application framework layer of the electronic device.

[0179] The Android Runtime includes a core library and a virtual machine. The Android runtime is responsible for the scheduling and management of the Android system. The core library contains two parts: one is the function function that the java language needs to call, and the other is the core library of Android. The application layer and the application framework layer run in the virtual machine. The virtual machine executes the java file of the application layer and the application framework layer into a binary file. The virtual machine is used to perform the management of the object life cycle, the management of the stack, the management of the thread, the management of the security and the exception, and the garbage collection and the like.

[0180] The system library can include a plurality of functional modules, such as: a surface manager, media libraries, a three-dimensional graphics processing library (such as: OpenGL ES), a 2D graphics engine (such as: SGL), and the like.

[0181] The kernel layer is the layer between hardware and software. The kernel layer at least contains display driver, camera driver, audio driver, sensor driver.

[0182] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network or other programmable apparatus. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, such as the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium accessible by a computer, or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as digital versatile disc (DVD)) or semiconductor media (such as solid state disk (SSD)) and the like.

[0183] The above is an optional embodiment provided by the present application, and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the technical scope disclosed by the present application shall be included in the protection scope of the present application.

Claims

1. A text management method, characterized in that, The method is applied to an electronic device, which includes a multi-functional office platform that provides various application functions, including document management functions. In response to the first operation, a first interface is displayed on the multi-functional office platform. The first interface is the interface corresponding to the document management function. The first interface includes a first identifier of the first document text and a second identifier of the second document text. In response to the selection operation of the first identifier, the document key information of the first document text is displayed in the first designated area of ​​the first interface; In response to the selection of the second identifier, the document key information of the second document text is displayed in the first designated area.

2. The method as described in claim 1, characterized in that, Before displaying the document key information of the second document text in the first designated area in response to the selection operation of the second identifier, the method further includes: If a selection operation is received for the second identifier, and the key document information of the second document text has not been displayed, then the first control is displayed on the first interface. The step of displaying key document information of the second document text in the first designated area in response to the selection operation of the second identifier includes: Upon receiving a trigger operation on the first control, in response to a selection operation on the second identifier, the document key information of the second document text is displayed in the first designated area.

3. The method as described in claim 1 or 2, characterized in that, The step of displaying key document information of the second document text in the first designated area in response to the selection operation of the second identifier includes: In response to the selection operation of the second identifier, the document key information of the first document text is de-displayed in the first designated area, and the document key information of the second document text is displayed in the first designated area.

4. The method as described in claim 3, characterized in that, The step of displaying key document information of the first document text in a first designated area of ​​the first interface in response to the selection operation of the first identifier includes: In response to the selection operation of the first identifier, a thumbnail corresponding to the first document text is displayed in the first designated area, and key document information of the first document text is displayed in the first designated area; The step of de-displaying the key document information of the first document text in the first designated area and displaying the key document information of the second document text in the first designated area in response to the selection operation of the second identifier includes: In response to the selection operation of the second identifier, the document key information of the first document text is de-displayed in the first designated area, and the thumbnail corresponding to the first document text is de-displayed in the first designated area; The document key information of the second document text is displayed in the first designated area, and the thumbnail corresponding to the second document text is displayed in the first designated area.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: In response to the opening operation of the second document text, a second interface is displayed, which includes the text content of the second document text and an entry point for the artificial intelligence document assistant; In response to a second operation on the AI ​​document assistant entry point, a first AI dialog box is displayed on the second interface, wherein the first AI dialog box is displayed side by side with the text content of the second document text; In response to a text addition operation triggered in the first AI dialog box, an identifier of the added target text is displayed in the first AI dialog box, the text addition operation being used to determine the target text to be compared; In response to a first comparison command entered in the first AI dialog box, a first comparison result is displayed below the identifier of the target text in the first AI dialog box. The first comparison result is a comparison result of the content of the target text and the second document text.

6. The method as described in claim 5, characterized in that, The number of target texts is multiple, and the method further includes: In response to a second comparison command entered in the first AI dialog box, a second comparison result is displayed in the first AI dialog box, the second comparison result being a content comparison result of the plurality of target texts.

7. The method as described in claim 5 or 6, characterized in that, The response to the second operation on the AI ​​document assistant entry point, after the first AI dialog box is displayed on the second interface, further includes: In response to a document content summary command entered in the first AI dialog box, the content summary result of the second document text is displayed in the first AI dialog box.

8. The method according to any one of claims 5-7, characterized in that, The response to the second operation on the AI ​​document assistant entry point, after the first AI dialog box is displayed on the second interface, further includes: In response to a first question instruction entered in the first AI dialog box, a first answer corresponding to the first question instruction is displayed in the first AI dialog box. The first question instruction is a question instruction for the second document text, and the first answer is an answer determined based on the second document text.

9. The method according to any one of claims 5-8, characterized in that, The response to the second operation on the AI ​​document assistant entry point, after the first AI dialog box is displayed on the second interface, further includes: Receive a selection operation on the content of the first document in the second document text; In response to a polishing instruction entered in the first AI dialog box, at least one editing operation is performed on the content of the first document, and the editing result is displayed in the first AI dialog box. The at least one editing operation includes expansion, abbreviation, synonym rewriting, language style rewriting, and error correction. In response to the result replacement operation, the content of the first document is replaced with the edited result.

10. The method according to any one of claims 5-9, characterized in that, The response to the second operation on the AI ​​document assistant entry point, after the first AI dialog box is displayed on the second interface, further includes: In response to a translation command entered in the first AI dialog box, the second document text is translated into the language indicated by the translation command, and the translation result is displayed in the first AI dialog box.

11. The method according to any one of claims 1-10, characterized in that, The various application functions include note-taking functionality, and the method further includes: Receive a third operation and display a third interface, which is the interface corresponding to the note function, and the third interface includes at least one note text; In response to the opening operation of the first note text in the at least one note text, the text content of the first note text is displayed in the second designated area of ​​the third interface, and the AI ​​note assistant entry is displayed; In response to a fourth operation on the AI ​​note-taking assistant entry point, a second AI dialog box is displayed in the second designated area, wherein the first note text is displayed side by side with the second AI dialog box; In response to a note summary command entered in the second AI dialog box, the summary result of the first note text is displayed in the second AI dialog box.

12. The method as described in claim 11, characterized in that, The fourth operation in response to the AI ​​note-taking assistant entry, after displaying the second AI dialog box in the second designated area, further includes: In response to a second question instruction entered in the second AI dialog box, a second answer is displayed in the second AI dialog box. The second question instruction is a question instruction for the first note text, and the second answer is an answer determined based on the first note text.

13. The method as described in claim 11 or 12, characterized in that, The fourth operation in response to the AI ​​note-taking assistant entry, after displaying the second AI dialog box in the second designated area, further includes: In response to a layout instruction entered in the second AI dialog box, the layout result of the first note text is displayed in the second AI dialog box, and a replacement control is displayed in the second AI dialog box; In response to the triggering operation of the replacement control, the text content in the first note text is replaced with the layout result.

14. The method as described in claim 13, characterized in that, The second AI dialog box also includes a copy control and an export control. The copy control is used to copy the layout result, and the export control is used to export the layout result.

15. The method according to any one of claims 11-14, characterized in that, The method further includes: If the total number of characters in the first note text exceeds the first character threshold, after displaying the text content of the first note text in the second designated area, a note summary control is displayed on the third interface. In response to a trigger operation on the note summary control, the second AI dialog box is displayed in the second designated area, and the content summary result is displayed in the second AI dialog box.

16. The method according to any one of claims 11-15, characterized in that, The method further includes: If the format of the first note text does not conform to the preset format, after displaying the text content of the first note text in the second designated area, the formatting control is displayed on the third interface. In response to a trigger operation on the layout control, the second AI dialog box is displayed in the second designated area, and the layout text content is displayed in the second AI dialog box.

17. The method according to any one of claims 11-15, characterized in that, After receiving the third operation and displaying the second interface, the process further includes: If there are multiple second note texts in the multi-functional office platform, and the total number of characters in each of the multiple second note texts is less than a second character count threshold, a merge control is displayed on the second interface. In response to the triggering operation of the merge control, the text content of the plurality of second note texts is merged into the third note text.

18. The method according to any one of claims 11-15, characterized in that, After receiving the third operation and displaying the second interface, the process further includes: The knowledge category view control is displayed in the second interface; In response to a trigger operation on the knowledge classification view control, a note text graph is displayed in the second specified area. The note text graph is generated by clustering multiple note texts in the multi-functional office platform, and the note text graph includes multiple nodes. In response to a trigger operation on any one of the multiple nodes, basic descriptive information of the note text associated with the node information of said node is displayed.

19. An electronic device, characterized in that, The electronic device includes one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, the computer program code including computer instructions, the one or more processors calling the computer instructions to cause the electronic device to perform the method as described in any one of claims 1 to 18.

20. A chip system, characterized in that, The chip system is applied to an electronic device, the chip system including one or more processors, the one or more processors being used to invoke computer instructions to cause the electronic device to perform the method as described in any one of claims 1 to 18.

21. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-18.

Images