Document editing method and device, equipment, medium and product

Abstract

The invention relates to a document editing method and device, equipment, a medium and a product. The method comprises the following steps: determining a virtual object for collaboratively editing a document from a plurality of virtual objects, wherein the plurality of virtual objects are configured with different document editing attributes; generating editing suggestions for the document based on document editing attributes of the virtual object through interaction with the selected virtual object; and updating the document content based on the editing suggestion.

Description

Technical Field

[0001] This disclosure relates to the field of computers, and more specifically to methods, apparatus, computing devices, computer storage media, and computer program products for document editing. Background Technology

[0002] Online document collaboration technology refers to technologies that allow multiple users to create, edit, comment on, review, and manage the same document in real time via the internet. It primarily provides features such as simultaneous editing, commenting, and suggesting modifications by multiple users. However, existing online document collaboration technologies have limited intelligence; for example, they only offer basic functions like grammar checking and formatting adjustments, failing to meet users' needs for collaborative online document editing. Improving the intelligence level and the degree of artificial intelligence (AI) involvement in online document collaboration technology presents a challenge for relevant technical personnel. Summary of the Invention

[0003] In a first aspect of the embodiments of this disclosure, a document editing method is provided. The method includes: determining virtual objects for collaborative editing of a document from a plurality of virtual objects, the plurality of virtual objects being configured with different document editing attributes; generating editing suggestions for the document based on the document editing attributes of the virtual objects through interaction with the selected virtual objects; and updating the document content based on the editing suggestions.

[0004] In a second aspect of the embodiments of this disclosure, a document editing apparatus is provided. The apparatus includes: a determining unit configured to determine virtual objects for collaborative editing of a document from a plurality of virtual objects, the plurality of virtual objects being configured with different document editing attributes; a generating unit configured to generate editing suggestions for the document based on the document editing attributes of the selected virtual objects through interaction with the selected virtual objects; and an updating unit configured to update the document content based on the editing suggestions.

[0005] In a third aspect of embodiments of this disclosure, an electronic device is provided. It includes: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the computing device to perform the method as described in the first aspect of this disclosure.

[0006] In a fourth aspect of embodiments of this disclosure, a non-transient computer storage medium is provided. It includes machine-executable instructions that, when executed by a device, cause the device to perform the method as described in the first aspect of this disclosure.

[0007] In a fifth aspect of embodiments of this disclosure, a computer program product is provided. It includes machine-executable instructions that, when executed by a device, cause the device to perform the method as described in the first aspect of this disclosure.

[0008] The summary section is provided to present the chosen concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or principal features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Wherein:

[0010] Figure 1 A flowchart of a method for editing a document according to some embodiments of the present disclosure is shown;

[0011] Figures 2 to 3 A schematic diagram of a display interface for interacting with virtual objects according to some embodiments of the present disclosure is shown;

[0012] Figure 4 A flowchart illustrating a method for determining virtual objects for collaborative document editing according to some embodiments of the present disclosure is shown;

[0013] Figure 5 A block diagram of an apparatus for editing a document according to some embodiments of the present disclosure is shown; and

[0014] Figure 6 A block diagram of a device capable of implementing several embodiments of the present disclosure is shown.

[0015] In all the accompanying figures, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0016] It is understood that all user-related data involved in this technical solution should be obtained and used only after authorization from the user. This means that if it is necessary to use a user's personal information in this technical solution, the user's explicit consent and authorization are required before obtaining this data; otherwise, no related data collection and use will be carried out. It should also be understood that when implementing this technical solution, relevant laws and regulations should be strictly followed in the process of data collection, use, and storage, and necessary technical measures should be taken to protect user data security and ensure the secure use of data.

[0017] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0018] For example, upon receiving a user's proactive request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0019] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0020] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0021] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0022] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects unless explicitly stated. Other explicit and implicit definitions may also be included below.

[0023] The inventors noted that online document collaboration technology can provide features such as simultaneous editing by multiple users, commenting, suggesting modifications, and AI-assisted editing. However, the AI ​​tools configured in online document collaboration technology can only provide editing assistance and cannot deeply participate in document creation and review. Furthermore, users need to actively call upon the AI ​​tools to achieve these functions, making the process cumbersome. In addition, existing AI tools are usually general-purpose tools and cannot provide targeted suggestions for different documents, resulting in a poor user experience when collaboratively editing documents.

[0024] To address this, this disclosure provides a document editing method that utilizes configured virtual objects with different document editing attributes to assist in editing online documents. In this method, a virtual object for collaborative document editing is selected from multiple virtual objects. The virtual object can be a Large Language Model (LLM) or an intelligent agent built based on an LLM with different document editing attributes. These attributes are reflected through the professional background, review style, focus, and discourse characteristics configured for the virtual object. For example, a virtual object could be a boss whose specific personality is strict, whose professional background is managerial, whose document review style is rigorous, whose focus is on the coherence and logic of expression, and whose discourse characteristics are formal and serious. Users can interact with the selected virtual object to generate editing suggestions for the document based on the virtual object's document editing attributes. These suggestions refer to the modification opinions or annotations generated by the virtual object after analyzing the document. Users can then update the document content based on the editing suggestions generated by the selected virtual object.

[0025] This method offers several advantages. First, it allows for the generation of editing suggestions for documents by selecting different virtual objects. Compared to general-purpose AI tools, this method provides more targeted and professional editing advice. Second, through interaction with the selected virtual objects, these objects can be deeply involved in document creation and editing. Furthermore, the editing suggestions generated based on the virtual objects' document editing attributes are more relevant to the user's collaborative editing needs, thus improving the practicality and accuracy of the suggestions.

[0026] Figure 1 A flowchart of a method 100 for editing a document according to some embodiments of the present disclosure is shown. The method can be implemented by any electronic device with computing and display capabilities, including but not limited to mobile phones, tablets, wearable devices, in-vehicle devices, augmented reality / virtual reality devices, laptops, super mobile personal computers, netbooks, personal digital assistants, Internet of Things devices, industrial terminals, and various electronic devices with interface display functions. The embodiments of the present disclosure do not limit the specific type of electronic device.

[0027] For ease of understanding, it will be combined Figures 2 to 3The diagram illustrates the display interface for interacting with virtual objects. Figure 1 Method 100 is available, but it should be understood that... Figures 2 to 3 The exemplary display interface for interacting with virtual objects in the example is non-limiting.

[0028] like Figure 1 As shown in box 102, virtual objects for collaborative document editing are determined from a plurality of virtual objects, each configured with different document editing attributes. In some embodiments, at least one virtual object may be recommended from a virtual object library based on at least one of the document's content type and user editing behavior data. The document's content type includes at least one of text, tabular data, images, or code blocks. User editing behavior data refers to the user's operational behavior data during the document editing process, used to infer the user's editing intent, editing habits, and operational needs. For example, user editing behavior data may include the user's editing mode, pause time, and modification frequency. A virtual object library refers to a module or database that manages and provides multiple virtual objects, which can be described or defined using natural language.

[0029] Figure 2 A schematic diagram of a display interface 200 for interacting with virtual objects according to some embodiments of the present disclosure is shown. Figure 2 As shown, the display interface 200 includes an interaction area 201, a document editing area 202, and an annotation area 203. The interaction area 201 is used for user interaction with virtual objects, the document editing area 202 is used for editing documents, and the annotation area 203 is used to present editing suggestions generated by the virtual objects for the document. The virtual object selection window in the interaction area 201 displays selectable virtual objects. As an example, selectable virtual objects include a critical boss 204 and a data analyst 205. The critical boss 204 simulates the mindset and focus of a strict, detail-oriented, and results-driven manager when reviewing documents. The data analyst 205 simulates a professional data analyst who focuses on data-related content in the document, ensuring the accuracy and standardization of the data. It should be understood that the virtual object library may include more or fewer types of virtual objects, which is not limited here.

[0030] The document editing area 202 contains the document being edited by the user. The document's content type can include at least one of the following: text, tabular data, images, or code blocks. As an example, in document editing area 202, the document the user is editing is a "Third Quarter Work Report," which includes a summary of the quarter's work, key data performance, and plans for the next quarter. It should be understood that the text that the user can edit is not limited to work reports; it can also include academic papers, creative plans, data analysis reports, etc., without limitation. The annotation area 203 can display editing suggestions generated based on the document content from a virtual object selected by the user.

[0031] In some embodiments, at least one virtual object is recommended from a virtual object library based on at least one of the document's content type and user's document editing behavior data. The recommended virtual objects can be displayed in the interaction area 201 to help the user select a suitable virtual object to use. Based on the user's selection of one of the recommended virtual objects, a virtual object for collaborative document editing is determined. Exemplarily, one or more virtual objects are recommended from the virtual object library based on the content displayed in the document editing area 202 and / or user's document editing behavior data, and are presented at the top of the interaction area 201. By performing the above method, virtual objects can be intelligently recommended to the user based on the document's content type and the user's behavior patterns, without requiring manual configuration by the user.

[0032] In some embodiments, the user selects one virtual object from a plurality of virtual objects. For example, the user can choose a virtual object in the interaction area 201, such as a picky boss 204 or a data analyst 205. In some embodiments, a virtual object can be selected through interaction in the interaction area 201 of the display interface 200. A virtual object can also be selected through a virtual object selection window in the display interface 200. For example, the user can select a virtual object by clicking a virtual object option box, such as clicking a picky boss 204, or by entering the name of the desired virtual object in the dialog box 207. This disclosure does not limit the method by which the user actively selects a virtual object.

[0033] Back Figure 1Method 100 further includes generating editing suggestions for a document based on the document editing attributes of the selected virtual object through interaction with the virtual object. In some embodiments, editing suggestions are generated for the document using the selected virtual object based on the document's content type, structure, and input requirements. The document's content type refers to its content, purpose, and main elements; for example, the document's content type may include work reports, academic papers, creative plans, data analysis reports, technical documents, marketing posters, etc. The document structure refers to the document's organization, including chapter divisions, paragraph relationships, etc. Input requirements refer to the document modification goals actively provided by the user. For example, if a user wants to improve the document in terms of content richness, language fluency, or document structure optimization, they can enter corresponding natural language prompts in dialog box 207 to indicate in which aspect the virtual character should provide assistance. In some embodiments, editing suggestions may include language optimization, logical structure improvement, professionalism enhancement, format standardization, data supplementation, etc.

[0034] In some embodiments, editing comments on the text "Third Quarter Work Report" in the document editing area are generated based on the document editing attributes configured by the user through interaction with a selected virtual object, such as interacting with a user-selected "picky boss" 204. For example, the system receives the user's input in dialog box 207, "@picky boss, help me analyze the third quarter report," analyzes the content of the user-input text 206, confirms that the selected virtual object is "picky boss" 204, and that the user's interaction request is to help analyze the third quarter report. In annotation area 203, when it is determined that the user's interaction request is to analyze the third quarter report, the system waits for "picky boss" 204 to generate editing comments on the "Third Quarter Work Report" in the document editing area 202. By executing the above method, users can directly use virtual objects to generate editing comments on documents in the display interface, without having to switch between multiple interfaces to call AI tools, thus improving the convenience of using the intelligent agent.

[0035] Figure 3 A schematic diagram of a display interface 300 for interacting with virtual objects according to some embodiments of the present disclosure is shown. Figure 3 As shown, when the user inputs "@picky boss, help me analyze the third quarter report", the virtual object (picky boss 204) is used to review the work report and generate editing comments in the annotation area 203 on the right side of the display interface 300.

[0036] exist Figure 3In the document editing area 202, the text "Overall performance is good" in the "Quarterly Work Summary" section is highlighted, and the comment section 203 on the right adds the comment "The description is vague. What exactly is good? Provide data to support your points; avoid empty words." Furthermore, a revision icon 301, a reply icon 302, and a resolution icon 303 are displayed below this comment to allow users to choose whether to adjust the document based on their editing needs. Similarly, in the document editing area 202, the text "ROI performance is good" in the "Key Data Performance" section is highlighted, and the comment section 203 on the right adds the comment "What are the specific figures? How does it compare to the budget? How does it compare to the same period last year? Avoid vague descriptions." Furthermore, revision icons, reply icons, and resolution icons are also displayed below this comment.

[0037] In some embodiments, the virtual object can directly annotate editing suggestions within the document content, or it can display editing suggestions using a whole-paragraph comparison method; the display method of editing suggestions is not limited here. In some embodiments, through interaction with the virtual object, background knowledge related to the document is provided to the virtual object selected by the user, prompting the virtual object to generate editing suggestions based on the background knowledge related to the document. For example, through interaction with the demanding boss 204, background knowledge related to the document is provided to the demanding boss 204, such as indicators for evaluating the quality of work reports, prompting the demanding boss 204 to generate editing suggestions based on the aforementioned background knowledge. In some embodiments, the method of providing background knowledge to the demanding boss 204 can be, for example, providing additional documents related to the document; for example, documents related to the third-quarter work data analysis, such as historical data, can be provided to the demanding boss 204. In some embodiments, a background description input by the user in the interaction area 201 can be received; for example, background introduction content input by the user in the interaction area 201 can be received. In some embodiments, web page links or knowledge bases related to the document content can be provided to the demanding boss 204. For example, a knowledge base link could be provided to demanding bosses (like 204) to help generate more user-relevant editing suggestions for virtual objects. It should be understood that the above methods of providing background information to virtual objects are merely illustrative, and the methods used to provide background information may include at least one or more of these approaches, without limitation.

[0038] By implementing the methods described above, virtual objects can be selected to deeply participate in the document creation and review process, and targeted editing suggestions can be generated for the document. Furthermore, by displaying editing suggestions in other areas of the same interface as the document editing area, users can intuitively understand the document's shortcomings, enhancing the user experience of collaborative document editing.

[0039] Back Figure 1 Method 100 further includes: in box 106, updating document content based on editing suggestions. In some embodiments, a revision action generated by a selected virtual object in response to the editing suggestions is obtained, and the document content is updated based on the revision action. The revision action can edit the document content in a marked manner. For example, the editing suggestion generated for a critical boss 204 is "Overall performance is good, but what exactly makes it good? Provide data support, don't use empty words." Then, the user can click the revision icon 301 to prompt the virtual character to generate a corresponding revision action, such as adding data and relevant text content to the document as a response to the editing suggestion. In some embodiments, the user can select a specific virtual object to generate the revision action, for example, instructing a specific AI character, such as a data analyst, to provide relevant data and text content in the prompt, and adding the generated data and text content to the original text. The added data or text content is inserted into the document in a marked manner, and the user can choose to accept, reject, or further manually edit the document based on this.

[0040] In some embodiments, a response to an editing suggestion is received, wherein the response indicates collaborative editing of the document using a different virtual object than the virtual object selected by the user. In some embodiments, a response to an editing suggestion is generated by using a different virtual object associated with the editing suggestion. The document content is then updated based on this response. For example, in response to the editing suggestion "Overall performance is good, but what exactly makes it good? Provide data to support your points, don't use empty words" generated by a critical boss 204, the user can click the response icon 302 to respond. For instance, the user can enter "@Data Analyst, please retrieve data related to 'overall performance is good'" in the dialog box that pops up after clicking the response icon 302, generating a response to the editing suggestion by using a different virtual object (Data Analyst 205) associated with it. Based on the data retrieved by the Data Analyst, the document content can be updated using that data. It should be understood that users can use more virtual objects than the virtual object selected by the user to respond to editing suggestions, thereby generating more complete data and document modification suggestions. This disclosure does not limit the number of virtual objects used in the response.

[0041] In some embodiments, a response rejecting the edit suggestions generated for a user-selected virtual object is received, wherein the response includes a reason for rejection. For example, when rejecting an edit suggestion generated by the user-selected "picky boss 204," the response may include a reason for rejection, such as the inability to obtain accurate data or the lack of need to provide specific numerical values. By implementing the above method, based on the reason for rejection in the response, subsequent optimization and evolution of the virtual character can be facilitated.

[0042] In some embodiments, the system receives user actions to resolve editing suggestions, where the action indicates that the user can ignore or reject the editing feedback generated by the virtual object. For example, in response to the editing suggestion "Overall performance is good, but what makes it good? Provide data to support your claims, avoid vague terms," ​​generated by the critical boss 204, the user can click the resolution icon 303 to resolve the issue, keeping the document content unchanged. By implementing this method, the drawbacks of traditional AI tools directly revising documents are avoided, allowing users to independently decide whether to modify the document based on the editing suggestions.

[0043] In some embodiments, based on the document's editing results, the user can also select a virtual object to review the document again, generate further editing suggestions, and edit the document based on these suggestions. In some embodiments, the document editing attributes of the virtual object are optimized based on the document's update results. For example, based on the editing results of the document "Third Quarter Work Report" in the document editing area 202, such as receiving a revision operation, a reply operation, or a resolution operation, the document editing attributes of the "nitpicky boss" 204 are optimized. It should be understood that the above-mentioned optimization of the document editing attributes of the virtual object is not limited to the "nitpicky boss" virtual object, but can include more virtual objects, which are not limited here. It should also be understood that... Figures 2 to 3 An exemplary display interface for interacting with virtual objects may include at least one of an interaction area, a document editing area, and an annotation area. This disclosure does not limit the number or type of areas included in the display interface.

[0044] By implementing the above methods, on the one hand, users can use virtual objects to generate editing suggestions for documents within the same display interface, avoiding the traditional method of switching between interfaces to invoke AI tools, thus improving the collaborative editing experience. Furthermore, virtual objects can be deeply involved in document editing, providing more targeted editing suggestions. On the other hand, intelligently recommending virtual objects based on document content type and user behavior patterns enhances the ease of use of AI tools.

[0045] Figure 4 A flowchart is shown of a method 400 for determining virtual objects for collaborative editing of a document according to some embodiments of the present disclosure. The method 400 may be performed, for example, by an electronic device.

[0046] like Figure 4As shown, in box 401, the user enters document content. For example, the user can enter the document content "Third Quarter Work Report" in the document editing area 202. In box 402, the document content type is identified. For example, it can be determined that the document content type is a text-based work report. In box 403, scenario analysis is performed on the document. Scenario analysis refers to inferring the user's current specific work scenario and intentions by analyzing various information such as document content and user behavior data. In box 404, a virtual object is recommended. For example, based on the document content "Third Quarter Work Report" and at least one of the user's behavior data, a demanding boss 204 is recommended to the user. In box 405, the user's confirmation of the recommended virtual object is received. In box 406, based on the user's confirmation, the virtual object is used to collaboratively edit the document.

[0047] In some embodiments, when a user is creating a document, they can use a selected virtual object, such as a demanding boss (e.g., 204), to provide real-time editing suggestions. The selected virtual object may have multimodal analysis capabilities. For example, when the document to be reviewed includes text, the editing suggestions generated by the virtual object may include paragraph reorganization, language optimization, and logical improvement. When the document to be reviewed includes tabular data, the editing suggestions generated by the virtual object may include formatting, data validation, and icon suggestions. When the document to be reviewed includes images, the editing suggestions generated by the virtual object may include description generation, position adjustment, and image recommendations. When the document to be reviewed includes code blocks, the editing suggestions generated by the virtual object may include formatting, supplementary comments, and refactoring suggestions.

[0048] By implementing the above methods, suitable virtual objects for document editing can be intelligently recommended, and creative suggestions can be provided during the user's document creation stage and editing suggestions can be provided after the document is completed, thus improving the user's experience when collaboratively editing documents.

[0049] The above is for reference only. Figures 1 to 4 The described exemplary embodiments provide a method for editing documents. Compared to existing technologies, its advantages are: firstly, users can use virtual objects to generate editing suggestions for documents within the same display interface, avoiding the traditional method of switching between interfaces to invoke AI tools, thus improving the collaborative editing experience. Furthermore, virtual objects can be deeply involved in document editing, providing more targeted editing suggestions. Secondly, intelligently recommending virtual objects based on document content type and user behavior patterns enhances the convenience of using AI tools.

[0050] Figure 5 A block diagram of an apparatus 500 for editing a document according to some embodiments of the present disclosure is shown. Figure 5As shown, the apparatus 500 includes a determining unit 502 configured to determine virtual objects for collaborative document editing from a plurality of virtual objects, each virtual object having different document editing attributes. The apparatus 500 also includes a generating unit 504 configured to generate editing suggestions for the document based on the document editing attributes of the selected virtual objects through interaction with them. The apparatus 500 further includes an updating unit 506 configured to update the document content based on the editing suggestions.

[0051] In some embodiments, the device 500 may also be configured to provide a display interface for editing documents, the display interface including an interactive area and a document editing area, wherein the interactive area is used for users to interact with virtual objects, and the document editing area is used for editing documents.

[0052] In some embodiments, the display interface further includes an annotation area, wherein the annotation area is used to present editing suggestions for the document generated by the virtual object.

[0053] In some embodiments, the document editing attributes of a virtual object are determined based on at least one of the professional background, review style, focus, and discourse characteristics configured for the virtual object.

[0054] In some embodiments, the determining unit 502 may also be configured to: recommend at least one virtual object from a virtual object library, the virtual object library including multiple virtual objects, based on at least one of the document's content type and user editing behavior data; and select a virtual object from the at least one virtual object for collaborative editing of the document.

[0055] In some embodiments, the device 500 may also be configured to: select a virtual object by interacting with the interactive area of ​​the display interface; or select a virtual object by the virtual object selection window of the display interface.

[0056] In some embodiments, the generation unit 504 may also be configured to generate editing suggestions for a document using virtual objects based on the document's content type, structure, and input requirements.

[0057] In some embodiments, the generation unit 504 may also be configured to: provide the virtual object with background knowledge associated with the document through interaction with the virtual object; and prompt the virtual object to generate editing suggestions based on the background knowledge.

[0058] In some embodiments, the device 500 may also be configured to: provide additional files related to the document; provide background descriptions input by the user; and provide relevant web page links or knowledge bases.

[0059] In some embodiments, editorial suggestions include at least one of language optimization, logical structure improvement, professionalism enhancement, and formatting standardization.

[0060] In some embodiments, the update unit 506 may also be configured to: obtain a revision operation corresponding to the editing suggestion generated by the virtual object, wherein the revision operation edits the document content in a marked manner.

[0061] In some embodiments, the update unit 506 may also be configured to: receive a response to an editing suggestion, the response indicating the use of another virtual object different from the virtual object to collaboratively edit the document; and use the other virtual object to generate editing suggestions for the document.

[0062] In some embodiments, the update unit 506 may also be configured to receive a response to reject the editing suggestion, the response including a reason for rejection.

[0063] In some embodiments, the apparatus 500 may also be configured to optimize the document editing properties of virtual objects based on the document update results.

[0064] In some embodiments, the document content type includes at least one of text, tabular data, image, and code block, and the editing suggestions are associated with the document content type.

[0065] Figure 6 A block diagram of a device 600 capable of implementing various embodiments of the present disclosure is shown. (See diagram for example.) Figure 6 As shown, device 600 includes a computing unit 601, which may be a central processing unit (CPU) and / or a graphics processing unit (GPU). The computing unit 601 can execute various appropriate actions and processes based on computer program instructions stored in read-only memory (ROM) 602 or loaded from storage unit 608 into random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. An input / output (I / O) interface 605 is also connected to bus 604. Although not shown in... Figure 6 As shown, device 600 may also include a coprocessor.

[0066] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0067] The various methods or processes described above can be executed by computing unit 601. For example, in some embodiments, the methods can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by computing unit 601, one or more steps or actions of the methods or processes described above can be performed.

[0068] In some embodiments, the methods and processes described above can be implemented as a computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of this disclosure.

[0069] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0070] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, a local area network (LAN), a wide area network (WAN), and / or a wireless network, to an external computer or external storage device. The network may include copper cables, fiber optic cables, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0071] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​and conventional procedural programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to execute the computer-readable program instructions, thereby implementing various aspects of this disclosure.

[0072] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / poses specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / poses specified in one or more blocks of the flowchart and / or block diagram.

[0073] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to achieve the functions / poses specified in one or more boxes of a flowchart and / or block diagram.

[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0075] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A document editing method, comprising: A virtual object for collaborative document editing is determined from a plurality of virtual objects, wherein the plurality of virtual objects are configured with different document editing attributes; By interacting with the selected virtual object, editing suggestions for the document are generated based on the document editing attributes of the virtual object; and Based on the editorial suggestions, the document content has been updated.

2. The method according to claim 1, wherein, The method further includes: A display interface for editing the document is provided, the display interface including an interactive area and / or a document editing area, wherein the interactive area is used for the user to interact with the virtual object, and the document editing area is used for editing the document.

3. The method according to claim 2, wherein, The display interface also includes an annotation area, which is used to present the editing suggestions for the document generated by the virtual object.

4. The method according to claim 1, wherein, The document editing attributes of the virtual object are determined based on at least one of the professional background, review style, focus, and discourse characteristics configured for the virtual object.

5. The method according to claim 1, wherein, The virtual objects identified from a plurality of virtual objects for collaborative document editing include: Based on at least one of the document's content type and user editing behavior data, recommend at least one virtual object from a virtual object library, the virtual object library comprising multiple virtual objects; and Select the virtual object for collaborative document editing from the at least one virtual object.

6. The method according to claim 5, wherein, Selecting the virtual object for collaborative document editing from the at least one virtual object includes: The virtual object is selected by interacting with the interactive area of ​​the display interface; or Select the virtual object through the virtual object selection window on the display interface.

7. The method according to claim 1, wherein, Generating editing suggestions for the document based on the document editing attributes of the selected virtual object through interaction includes: Based on the document's content type, structure, and input requirements, the virtual object is used to generate the editing suggestions for the document.

8. The method according to claim 1, wherein, Using the virtual object to generate the editing suggestions for the document includes: By interacting with the virtual object, the virtual object is provided with background knowledge associated with the document; and The virtual object is prompted to generate the editing suggestions based on the background knowledge.

9. The method according to claim 8, wherein, Providing the virtual object with the background knowledge associated with the document includes at least one of the following methods: Provide additional files related to the document; Provide background descriptions input by the user; and Provide relevant web page links or knowledge bases.

10. The method according to claim 1, wherein, The editorial suggestions include at least one of the following: language optimization, logical structure improvement, professionalism enhancement, and formatting standardization.

11. The method according to claim 1, wherein, Based on the editorial suggestions, the document content was updated as follows: Obtain the revision operation corresponding to the editing suggestion generated by the virtual object, the revision operation editing the document content in a marked manner.

12. The method according to claim 1, wherein, Based on the editorial suggestions, the document content was updated as follows: Receive a response to the edit suggestion, the response indicating the use of a different virtual object than the virtual object to collaboratively edit the document; and Use the other virtual object to generate editing suggestions for the document.

13. The method according to claim 1, wherein, Based on the editorial suggestions, the document content was updated as follows: Receive a response rejecting the editorial suggestion, including the reason for rejection.

14. The method according to claim 1, wherein, The method further includes: Based on the updated document, the document editing properties of the virtual object are optimized.

15. The method according to claim 1, wherein, The document's content type includes at least one of text, tabular data, images, and code blocks, and the editing suggestions are associated with the document's content type.

16. A document editing device, comprising: The determining unit is configured to determine a virtual object for collaborative document editing from a plurality of virtual objects, the plurality of virtual objects being configured with different document editing attributes; The generation unit is configured to generate editing suggestions for the document based on the document editing attributes of the selected virtual object through interaction with the virtual object; as well as The update unit is configured to update the document content based on the edit suggestions.

17. An electronic device comprising: processor; as well as A memory coupled to the processor, the memory having instructions stored therein, which, when executed by the processor, cause the electronic device to perform the method according to any one of claims 1-15.

18. A computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of claims 1-15.

Images