Interaction method and device, storage medium and program product
By combining dialogue and editing areas on the same display interface and generating editing instructions based on user input, the problem of difficulty in editing multi-genre information in the prior art is solved, and a more efficient and flexible creative experience is achieved.
Patent Information
- Application Number
- CN202510300021.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-13
- Publication Date
- 2025-05-13
AI Technical Summary
The prior art is difficult to edit multi-genre information in a complex scenario of dialogue and editing, resulting in limited flexibility and efficiency in the creation process.
An interactive method is provided to generate editing instructions to edit content by displaying a dialogue area and an editing area on the same display interface and according to user input and operations. The method includes generating content in response to user instructions, displaying editing areas of matching genres, determining and performing editing operations, and providing corresponding editing tools based on content genres.
It realizes multi-genre information editing in dialogue and editing scenarios, improves user creative efficiency and experience, and allows users to flexibly conceive and edit different types of content.
Smart Images

Figure CN119987606A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer technology, and in particular to an interaction method, device, storage medium and program product. Background Art
[0002] With the development of artificial intelligence technology, users can communicate with intelligent agents to efficiently obtain information, and users can also use intelligent agents to create. Summary of the invention
[0003] According to some embodiments of the present disclosure, an interaction method is provided, comprising: in response to a user inputting an instruction to generate first content in a dialogue area, generating the first content; displaying an editing area matching the genre of the first content, and displaying the first content in the editing area, the editing area and the dialogue area being located on the same display interface; in response to the user triggering an editing operation in the dialogue area or the editing area, determining an editing instruction for the first content based on the first content and the genre of the first content; and editing the first content in the editing area based on the editing instruction.
[0004] According to some other embodiments of the present disclosure, an interactive device is provided, including: a generation module, configured to generate the first content in response to a user inputting an instruction to generate the first content in a dialogue area; a display module, configured to display an editing area matching the genre of the first content, and display the first content in the editing area, the editing area and the dialogue area being located on the same display interface; a determination module, configured to determine an editing instruction for the first content based on the first content and the genre of the first content in response to the user triggering an editing operation in the dialogue area or the editing area; and an editing module, configured to edit the first content in the editing area based on the editing instruction.
[0005] According to some embodiments of the present disclosure, an interaction device is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the interaction method of any embodiment described in the present disclosure based on instructions stored in the memory.
[0006] According to some embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the method of any embodiment described in the present disclosure is implemented.
[0007] According to some embodiments of the present disclosure, a computer program product is provided, comprising: computer instructions, which, when executed by a processor, implement the method of any embodiment described in the present disclosure.
[0008] Other features, aspects and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] The following is an explanation of the embodiments of the present disclosure with reference to the accompanying drawings. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation to the present disclosure. In the accompanying drawings:
[0010] Figure 1 A schematic diagram showing a flow chart of an interaction method according to some embodiments of the present disclosure;
[0011] Figure 2 A schematic diagram showing a flow chart of determining an editing instruction for a first content according to some embodiments of the present disclosure;
[0012] Figure 3A A schematic diagram showing a display interface related to writing genres according to some embodiments of the present disclosure;
[0013] Figure 3B A schematic diagram showing a display interface related to writing genre according to other embodiments of the present disclosure;
[0014] Figure 3C A schematic diagram showing a display interface related to image genres according to some embodiments of the present disclosure;
[0015] Figure 3D A schematic diagram showing a display interface related to image genres according to other embodiments of the present disclosure;
[0016] Figure 3E A schematic diagram showing a display interface related to programming genres according to some embodiments of the present disclosure;
[0017] Figure 3F A schematic diagram showing a display interface related to programming genres according to other embodiments of the present disclosure;
[0018] Figure 4A A schematic diagram showing a display interface related to writing genre according to yet other embodiments of the present disclosure;
[0019] Figure 4B Schematic diagram showing a display interface related to writing genre according to other embodiments of the present disclosure
[0020] Figure 4C A schematic diagram showing a display interface related to image genres according to yet other embodiments of the present disclosure;
[0021] Figure 4D A schematic diagram showing a display interface related to image genres according to yet other embodiments of the present disclosure;
[0022] Figure 5 A schematic diagram showing a flow chart of determining an editing instruction for a first content according to some other embodiments of the present disclosure;
[0023] Fig. 6A A schematic diagram showing a display interface related to writing genres according to some further embodiments of the present disclosure;
[0024] Figure 6B A schematic diagram showing a display interface related to image genres according to some further embodiments of the present disclosure;
[0025] Figure 7 A schematic diagram showing a flow chart of determining an editing instruction for a first content according to some further embodiments of the present disclosure;
[0026] Figure 8 A schematic diagram showing a display interface related to writing genres according to some further embodiments of the present disclosure;
[0027] Fig. 9 A schematic diagram showing a flow chart of determining an editing instruction for a first content according to some further embodiments of the present disclosure;
[0028] Fig. 10A A schematic diagram showing proactive provision of content suggestions according to some embodiments of the present disclosure;
[0029] Fig. 10B A schematic diagram showing a user accepting a content suggestion according to some embodiments of the present disclosure;
[0030] Fig.11A A schematic diagram showing how to obtain improvement suggestions through dialogue with an intelligent agent according to some embodiments of the present disclosure;
[0031] Fig. 11B A schematic diagram showing how to obtain improvement suggestions through dialogue with an intelligent agent according to other embodiments of the present disclosure;
[0032] Fig.12 A block diagram showing an interaction device according to some embodiments of the present disclosure;
[0033] Fig.13 A block diagram showing an interaction device according to some other embodiments of the present disclosure;
[0034] Fig.14 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.
[0035] It should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportional relationship. The same or similar reference numerals are used in the various drawings to represent the same or similar parts. Therefore, once an item is defined in one drawing, it may not be further discussed in subsequent drawings. DETAILED DESCRIPTION
[0036] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present disclosure. It should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein.
[0037] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be performed in different orders, and / or performed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown in the execution. The scope of the present disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values of the parts and steps set forth in these embodiments should be interpreted as being merely exemplary and do not limit the scope of the present disclosure.
[0038] The term “including” and its variations used in the present disclosure are intended to be open terms that include at least the following elements / features but do not exclude other elements / features, that is, “including but not limited to.” The term “based on” means “at least partly based on.”
[0039] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. Unless otherwise specified, the concepts of "first", "second", etc. are not intended to imply that the objects described in this way must be in a given order in time, space, ranking, or any other manner.
[0040] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0041] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0042] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0043] The embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined in any suitable manner that will be clear from the present disclosure by a person of ordinary skill in the art.
[0044] In the related art, the information replied by the agent is presented in the dialogue interface in the form of a dialogue, and the user cannot edit the information replied by the agent. The present disclosure provides an interactive method, which can be applied to edit multi-genre information in a complex dialogue and editing scenario, helping users to quickly complete creation and improve the user experience of using the agent.
[0045] Figure 1 A flowchart of an interaction method according to some embodiments of the present disclosure is shown.
[0046] like Figure 1 The interaction method includes: step S11, in response to the user inputting an instruction to generate the first content in the dialogue area, generating the first content; step S12, displaying an editing area matching the genre of the first content, and displaying the first content in the editing area, the editing area and the dialogue area being located on the same display interface; step S13, in response to the user triggering an editing operation in the dialogue area or the editing area, determining an editing instruction for the first content based on the first content and the genre of the first content; step S14, editing the first content in the editing area based on the editing instruction.
[0047] When users are creating content, for example, in order to conceive articles more flexibly, they can choose to create a new blank document. In the dialogue area, the agent can provide users with some writing guidance, for example, by telling the agent their identity and writing requirements to further discuss the topic selection, or directly enter the topic of the writing. Users can also write the document content directly in the editing area, or use AI (Artificial Intelligence) to help me write, write an outline first, import documents, and select templates to add content.
[0048] The display interface of the agent includes a conversation area and an editing area. In some embodiments, the conversation area is displayed first on the display interface, and then the editing area is displayed, and finally the conversation area and the editing area are simultaneously presented on the display interface. In other embodiments, the conversation area and the editing area are simultaneously displayed on the display interface.
[0049] The genre of the first content can also be called a type, for example, the genres include writing, programming, images, or reading, etc. Correspondingly, the editing area supports multi-genre editing, for example, the editing area can be a text editing area, a code editing area, an image editing area, a reader area, etc. This embodiment can achieve linkage with the editing area based on the dialogue in the dialogue area. For example, when a user interacts with an intelligent agent, the intelligent agent can identify the genre of the first content indicated by the user, and then call the editing area corresponding to the genre. The editing area can also be called an editing page. The editing area can be a freely editable editing page, and the user can freely modify the content of the editing area, and the editing results will be automatically saved to the latest version.
[0050] The user can trigger an editing operation in the dialogue area or the editing area. The agent determines the editing instructions for the first content based on the specific information and genre of the first content. The editing instructions can also be called editing tools. The editing instructions include various instructions such as continuation instructions, help writing instructions, erasure instructions, batch processing instructions, programming instructions, and translation instructions. The agent can provide different editing instructions for different genres and specific content. The editing instructions are configured to edit, modify, or optimize the first content, so as to help the user improve the content through the agent.
[0051] In this embodiment, the conversation area and the editing area are displayed in the same display interface, and the editing area matches the genre of the generated content, so as to facilitate the editing of the generated content. Since the editing instructions are determined based on the generated content and the genre of the generated content, the intelligent agent can perform targeted editing on the generated content of any genre, which can improve the user's creative efficiency and thus enhance the user experience.
[0052] The following will be combined Figures 2 to 11B , the interactive methods based on different editing methods are introduced.
[0053] Figure 2 A schematic diagram showing a flow chart of determining an editing instruction for a first content according to some embodiments of the present disclosure is shown.
[0054] like Figure 2As shown, step S13 includes step S131, in response to the user's triggering operation on the target content in the first content in the editing area, determining editing instructions related to the genre and the first content, wherein the triggering operation includes at least one of selection, staying for a specified time, and triggering a control displayed in association with the target content, and the editing instructions are configured to generate a second content corresponding to the target content.
[0055] For example, the first content is displayed in the editing area, and the user selects the target content in the first content by making a selection, or by keeping the mouse or other operating components on the target content for 3 seconds, or by clicking or double-clicking the cursor associated with the target content, etc., to trigger the target content, and then generate the second content corresponding to the target content, thereby editing the target content. Those skilled in the art should understand that 3 seconds is only used as an example, and the time can be set according to actual conditions. The target content can be part of the first content, or the entire first content.
[0056] The editing instructions are related to the genre of the first content and the first content. For example, if the genre of the first content is writing, and the first content is related to children's stories, the agent can provide instructions for continuing writing, helping writing, polishing, etc. If the genre of the first content is writing, and the first content is related to news reports, the agent can provide instructions for word order detection, typos detection, etc. If the genre of the first content is writing, and the first content is related to academic papers, the agent can provide logical judgment instructions, data verification instructions, rewriting instructions, etc. If the genre of the first content is image, and the first content is related to a picture, the agent can provide instructions for expanding the picture, erasing, etc. If the genre of the first content is image, and the first content is related to multiple pictures, the agent can provide batch repair instructions. The image can include dynamic images such as videos, and can also include static images. If the genre of the first content is programming, and the first content is related to Python code, the agent can provide function call instructions, etc. If the genre of the first content is programming, and the first content is related to JavaScript code, the agent can provide array operation instructions, etc. Those skilled in the art should understand that the above-mentioned genres, contents, and editing instructions are only used as examples, and more genres, contents, and editing instructions can be set according to actual conditions.
[0057] For example, when a user interacts with an intelligent agent, the intelligent agent recognizes the user's creative intention. For example, the user enters a creative demand in the dialogue area: "Help me write an article related to ***". The intelligent agent recognizes that the user's writing demand is related to timeliness hotspots, so the intelligent agent matches the ability to search for information on the Internet and automatically match pictures (online picture search, AI image), and quickly generates a first draft, including title, paragraph framework and specific content. Of course, users can also choose whether to upload or search for information on the Internet, as well as use a variety of writing tools. The intelligent agent calls the editor related to writing, and the article is displayed in the editing area. If the user's cursor stays on a certain paragraph for 3 seconds or the user clicks the cursor on a certain paragraph, the user does not need to enter an instruction. The intelligent agent recognizes that the user wants to continue writing the paragraph, and generates a continuation instruction to continue writing the content of the paragraph, thereby improving the user's writing efficiency.
[0058] After generating the second content corresponding to the target content, the agent can optimize the first content, for example, output the second content; in response to the user's confirmation operation on the second content, replace the target content with the second content, and / or add the second content to the area related to the target content.
[0059] For example, the second content is displayed in the editing area in the form of a floating window, etc. If the generated second content meets the user's expectations, the user can confirm the second content, and the agent replaces the target content with the second content or inserts the newly generated second content based on the first content. In some embodiments, the target content originally selected by the user is replaced with the newly generated second content, thereby realizing the editing of the first content. In other embodiments, for example, if the target content needs to be continued, the second content can be added below the target content, thereby realizing the optimization of the first content.
[0060] In some embodiments of the present disclosure, in response to the user's triggering operation on the target content in the first content in the editing area, determining the editing instructions related to the genre and the first content includes: in response to the user's triggering operation on the target content in the first content in the editing area, recommending multiple candidate instructions related to the genre and the first content to the user for selection; and using the instructions selected by the user from the multiple candidate instructions as the editing instructions related to the genre and the first content.
[0061] Combine the following Figures 3A to 3F Take the above embodiment as an example to introduce the above embodiment.
[0062] Figure 3A Schematic diagram showing a display interface related to writing genre according to some embodiments of the present disclosure. Figure 3A As shown, Figure 3A As an example for writing genres, the display interface 3 includes a dialogue area 31 and an editing area 32. The user can input information in the dialogue control 311 of the dialogue area 31, and the generated text content 321 can be displayed in the editing area 32. The user selects a part of the text content 321 321. A plurality of candidate instructions are displayed in the editing area 32, for example, including polishing instructions, expansion instructions, abbreviation instructions, tone adjustment instructions, etc. The tone adjustment instructions can include more professional, more lively, more straightforward, more confident, more friendly, etc.
[0063] The user selects an instruction from the candidate instructions as an editing instruction, and edits the partial content 3211 through the editing instruction. Figure 3B As shown, Figure 3B Schematic diagrams of display interfaces related to writing genres according to other embodiments of the present disclosure are shown. Related content 3212 corresponding to the partial content 3211 is output in the form of a floating window. The user can click a replace control or an insert control to update the partial content 3211 based on the related content 3212, thereby completing the editing of the text content 321.
[0064] Figure 3C Schematic diagram of a display interface related to image genre according to some embodiments of the present disclosure is shown. Figure 3C As shown, Figure 3C As an example for image genre, the display interface 3 includes a dialogue area 31 and an editing area 32. The user can input information in the dialogue control 311 of the dialogue area 31, and the generated image content 322 can be displayed in the editing area 32. The user selects a partial image 3221 in the image content 322. A plurality of candidate instructions are displayed in the editing area 32, for example, including a rotation instruction, a color adjustment instruction, a watermark removal instruction, a filter instruction, a channel operation instruction, and the like.
[0065] The user selects an instruction from the candidate instructions as an editing instruction, and edits the partial image 3221 through the editing instruction. Figure 3D As shown, Figure 3D Schematic diagrams of display interfaces related to image genres according to other embodiments of the present disclosure are shown. Related images 3222 corresponding to the partial image 3221 are displayed. The user can click a replace control or an insert control to update the partial image 3221 based on the related image 3222, thereby completing the editing of the image content 322.
[0066] Figure 3E Schematic diagram of a display interface related to programming genres according to some embodiments of the present disclosure is shown. Figure 3E As shown, Figure 3EAs an example for programming genre, the display interface 3 includes a dialogue area 31 and an editing area 32. The user can enter instructions in the dialogue control 311 of the dialogue area 31, and the generated code content 323 can be displayed in the editing area 32. The user selects a part of the code 3231 in the code content 323. A plurality of candidate instructions are displayed in the editing area 32, for example, including instructions such as code explanation and code repair.
[0067] The user selects an instruction from the candidate instructions as an editing instruction, and edits the partial program 3231 through the editing instruction. Figure 3F As shown, Figure 3F Schematic diagrams of display interfaces related to programming genres according to other embodiments of the present disclosure are shown. If the user selects a code repair instruction, the editing area 32 displays the related code 3232 corresponding to the partial code 3231. The user clicks the related code 3232, and the partial code 3231 is replaced with the related code 3232, thereby optimizing the code content 323.
[0068] In some embodiments of the present disclosure, in response to the user's triggering operation on the target content in the first content in the editing area, determining the editing instructions related to the genre and the first content includes: in response to the user's triggering operation on the target content in the first content in the editing area, displaying a first dialog control related to the target content; in response to the user inputting first information in the first dialog control, determining the editing instructions related to the genre and the first content, the editing instructions being configured to generate second content corresponding to the target content based on the first information.
[0069] Combine the following Figures 4A to 4D Take the above embodiment as an example to introduce the above embodiment.
[0070] Figure 4A Schematic diagrams showing display interfaces related to writing genres according to some other embodiments of the present disclosure. Figure 4A As shown, the display interface 4 includes a dialogue area 41 and an editing area 42. The user can enter information in the dialogue control 411 of the dialogue area 41, and the generated text content 421 can be displayed in the editing area 42. The user selects a part of the text content 4211, and a first dialogue control 43 related to the part of the content 4211 is displayed. The user enters the first information in the first dialogue control 43, for example, please help me rewrite this paragraph. The intelligent agent automatically generates a rewriting instruction, and based on the rewriting instruction, generates related content 4212 corresponding to the part of the content 4211. Figure 4B As shown, Figure 3BSimilarly, the agent can output the related content 4212 corresponding to the partial content 4211 in the form of a floating window. The user can click the replace control or insert control to update the partial content 4211 based on the related content 4212, thereby completing the editing of the text content 421.
[0071] Figure 4C Schematic diagrams showing display interfaces related to image genres according to some other embodiments of the present disclosure. Figure 4C As shown, the display interface 4 includes a dialogue area 41 and an editing area 42. The user can input information in the dialogue control 411 of the dialogue area 41, and the generated image content 422 can be displayed in the editing area 42. The user selects a partial image 4221 in the image content 422, and the editing area 42 displays a first dialogue control 43 related to the partial image 4221. The user inputs first information in the first dialogue control 43, for example, please help me change the mouse to a fish. The intelligent agent automatically generates a picture editing instruction, and generates a related image 4222 corresponding to the partial image 4221 based on the picture editing instruction. Figure 4D and Figure 3D Similarly, the editing area 42 displays a related image 4222 corresponding to the partial image 4221. The user can click on the replacement control to update the partial image 4221 based on the related image 4222, thereby completing the editing of the image content 422.
[0072] Figure 5 A schematic diagram showing a flow chart of determining an editing instruction for a first content according to some other embodiments of the present disclosure.
[0073] like Figure 5 As shown, step S13 includes step S132, in response to the user entering second information in the second dialogue control in the dialogue area, determining editing instructions related to the genre and the first content, and the editing instructions are configured to edit the target content related to the second information.
[0074] The target content may be part of the first content or the entire first content. By means of editing instructions related to the genre and the first content, the target content related to the second information can be edited, thereby helping the user optimize the first content and improve editing efficiency.
[0075] Combine the following FIG. 6A to FIG. 6B Take the above embodiment as an example to introduce the above embodiment.
[0076] Fig. 6A Schematic diagrams showing display interfaces related to writing genres according to some further embodiments of the present disclosure. Fig. 6A As shown, Fig. 6AAs an example for writing genres, the display interface 6 includes a dialogue area 61 and an editing area 62 , and the user can input second information in a second dialogue control 611 of the dialogue area 61 , so that the agent edits the target content related to the second information in the editing area 62 .
[0077] For example, the agent helps the user write an article, and the user enters "Help me add / rewrite a more attractive title" in the second dialogue control. The agent generates an instruction to modify the title, thereby generating a corresponding title for the article.
[0078] For another example, the article contains multiple "you" characters, and the user enters "Help me change all "you" to "I"" in the second dialogue control. The agent generates a global matching replacement instruction, thereby changing the "you" in the article to "I".
[0079] For another example, if the user enters "help me add more **details" in the second dialogue control, the agent will generate instructions to add details and rewrite, thereby adding **details to the article.
[0080] For another example, the user enters "help me translate the full text into English" in the second dialogue control, and the agent generates a translation instruction to complete the translation of the full text of the article.
[0081] Figure 6B Schematic diagrams showing display interfaces related to image genres according to some further embodiments of the present disclosure. Figure 6B As shown, in the editing area 62, a rectangular image is generated. The user enters "content adjusted to 1:1 square size" in the second dialogue control 611, and the intelligent agent modifies the rectangular image into a square image in the editing area.
[0082] In the above embodiment, the first content is edited through free dialogue.
[0083] When the user inputs information in the dialogue area, the agent needs to locate the first content. Therefore, in some embodiments, editing the first content in the editing area based on the editing instruction includes: locating the target content related to the second information in the first content; and editing the target content based on the editing instruction.
[0084] For example, when the user inputs "Please continue writing the second paragraph" in the second dialogue control, the agent needs to first locate the position of the second paragraph in the second information in the article, and then the editing instruction can edit the content of the second paragraph.
[0085] In some embodiments, locating the target content related to the second information in the first content includes: acquiring an image of the editing area; visually understanding the image; and determining the target content in the first content based on the visual understanding result and the second information.
[0086] For example, the agent takes a screenshot of the editing area, and through visual understanding, can determine the content in the image, thereby parsing the target content corresponding to the second information. Then, based on the editing instruction, the target content related to the second information is edited, thereby optimizing the first content.
[0087] Figure 7 A schematic diagram showing a flow chart of determining an editing instruction for a first content according to some further embodiments of the present disclosure is shown.
[0088] like Figure 7 As shown, step S13 includes step S133 and step S134. In step S133, in response to the user's triggering operation on the first content, multiple candidate instructions related to the genre and the first content are recommended to the user for selection by the user; in step S134, the instruction selected by the user from the multiple candidate instructions is used as an editing instruction related to the genre and the first content, and the editing instruction is configured to perform global editing on the first content.
[0089] For example, the user moves the cursor to the editing area, and the multiple candidate instructions related to the genre and the first content are displayed in the editing area for the user to select. The multiple candidate instructions can be pre-packaged global shortcut processing instructions to help the user quickly complete global editing.
[0090] For example, Figure 8 As shown, Figure 8 A schematic diagram showing a display interface related to writing genre according to some further embodiments of the present disclosure. Figure 8As an example for writing genres, the display interface 8 includes a dialogue area 81 and an editing area 82. The user can enter information in the dialogue control 811 of the dialogue area 81, and the generated text content 821 can be displayed in the editing area 82. Multiple candidate instructions 822 are, for example, full-text polishing instructions, length adjustment instructions, intelligent typesetting instructions, reading level instructions, one-key picture matching instructions, editing and rewriting instructions, and reference generation instructions. For creative articles, full-text polishing instructions are used to improve literary talent and rhetoric. For efficiency articles, full-text polishing instructions are used to improve the professionalism of articles. The length adjustment instructions can also include expansion instructions and abbreviation instructions. Intelligent typesetting instructions can optimize typesetting in one step for different genres. Reading level instructions can also include elementary school reading level instructions, junior high school reading level instructions, high school reading level instructions, or university reading level instructions. Generate reference instructions are used to provide real reference source information for content, especially data results. The user selects an instruction as an editor from multiple candidate instructions, so as to achieve global editing of the first content.
[0091] For another example, the multiple candidate instructions may also be located in the dialog area. The user selects an instruction from the multiple candidate instructions in the dialog area as editing, thereby enabling global editing of the first content.
[0092] In the above embodiment, global editing of generated content can be achieved through global instructions.
[0093] Fig. 9 A schematic diagram showing a flow chart of determining an editing instruction for a first content according to some further embodiments of the present disclosure is shown.
[0094] like Fig. 9 As shown, step S13 includes steps S135 to S138. In step S135, the first content is understood; in step S136, based on the understanding result of the genre and the first content, at least one editing suggestion matching the first content is determined; in step S137, the at least one editing suggestion is recommended to the user in the conversation area or the editing area; in step S138, in response to the user's confirmation operation on the target suggestion in the at least one editing suggestion, an editing instruction related to the genre and the first content is determined, and the editing instruction is configured to edit the first content based on the target suggestion.
[0095] For example, the agent understands the first content, determines the specific information and genre in the first content, and then actively gives some creative suggestions, which can be displayed in the dialogue area or in the editing area. After the user selects the creative suggestion, the agent generates an editing instruction to edit the first content based on the creative suggestion.
[0096] Below Fig. 10A and Fig. 10B Take the above embodiment as an example to introduce the above embodiment.
[0097] Fig. 10A A schematic diagram showing active provision of content suggestions according to some embodiments of the present disclosure is shown. Fig. 10B A schematic diagram showing a user accepting content suggestions according to some embodiments of the present disclosure. In this embodiment, after the intelligent agent understands the text content, it gives optimization suggestions in the dialogue area 101, for example, adding a brief introduction to the opening game so that non-game players can also quickly understand the game background. If the user clicks the control to accept the suggestion, an editing instruction is generated, and corresponding content 103 is generated in the editing area 102 based on the editing instruction.
[0098] In the above embodiment, the intelligent agent actively provides creation suggestions during the creation process, and edits the generated content based on the target suggestions through editing instructions, thereby improving the optimization efficiency of the generated content.
[0099] In some embodiments, the understanding of the first content includes: in response to the user instructing the agent to give editing suggestions in the dialogue area, understanding the first content.
[0100] For example, if the user enters the instruction "Please give optimization suggestions" in the dialogue area, the intelligent agent will understand the first content, determine the specific information and genre in the first content, and then actively give some creation suggestions, which can be displayed in the dialogue area or in the editing area. After the user selects the creation suggestion, an editing instruction is generated so that the first content can be edited based on the creation suggestion.
[0101] Below Fig.11A and Fig. 11B Take the above embodiment as an example to introduce the above embodiment.
[0102] Fig.11A A schematic diagram showing how to obtain improvement suggestions through dialogue with an intelligent agent according to some embodiments of the present disclosure, Fig. 11B Schematic diagram showing how to obtain improvement suggestions through dialogue with an agent according to other embodiments of the present disclosure. The user enters the message "propose specific optimization suggestions" in the dialogue area 1101. The agent gives some optimization suggestions in the editing area 1102. If the user adopts the optimization suggestions, the agent edits the content in the editing area 1102 through editing instructions to quickly improve the quality of the article.
[0103] In the above embodiment, the user obtains improvement suggestions provided by the intelligent agent through dialogue with the intelligent agent, and then edits the generated content, thereby improving editing efficiency and editing quality.
[0104] In some embodiments, in the conversation area, a conversation sent by the agent is displayed, and the sent conversation includes the at least one editing suggestion.
[0105] For example, Fig. 10A As shown, the intelligent agent displays editing suggestions in the dialogue area through dialogue, so that the user can determine whether to adopt the suggestion in time.
[0106] In some other embodiments, an annotation is displayed in the editing area, and the annotation includes the at least one editing suggestion.
[0107] For example, Fig.11A As shown, the agent comments in the form of annotations, thereby supporting users to quickly apply optimization suggestions.
[0108] In some embodiments of the present disclosure, in response to the user inputting an instruction in the dialogue area to generate a third content, the editing area that matches the genre of the first content is switched to an editing area that matches the genre of the third content, wherein the genres of the first content and the third content are different.
[0109] For example, the genre of the first content is writing, and the genre of the third content is programming. The editing area that matches the genre of the first content is the text editing area. When the agent generates the third content, it calls the program editing area and displays the third content in the program editing area. This realizes the linkage of editing areas of multiple genres.
[0110] For another example, the user first inputs image information in the dialogue area, and the agent calls the image editing area to edit the image content in the image editing area. Subsequently, the user inputs the creation article information in the dialogue area, and the agent calls the text editing area to edit the created article in the text editing area.
[0111] In other embodiments of the present disclosure, the fourth content is displayed in an editing area that matches the genre of the fourth content; in response to the user inputting an instruction in the dialogue area to generate the first content, the editing area that matches the genre of the fourth content is switched to an editing area that matches the genre of the first content.
[0112] For example, the agent obtains the interaction intention with the user. If the user wants to read text, the reading editor is called. Then, if the user wants to create based on the reading article, the agent calls the text editor, thereby switching the reading editor to the text editor, realizing the linkage of editors of multiple genres.
[0113] Through the introduction of the above embodiments, the agent can freely switch editors of various genres based on the user's intention. For example, for various scenarios such as reading before writing, drawing before writing, writing before drawing, etc., the editor that matches the generated content is called to improve the user's creation efficiency.
[0114] In some other embodiments of the present disclosure, one or more folders are displayed, where the folders are used to store edited content corresponding to the first content.
[0115] For example, after completing a creation, the user stores the creation content in a folder, such as a cloud disk folder, to facilitate subsequent users to retrieve related materials and integrate them.
[0116] In some other embodiments of the present disclosure, a sharing link of the edited version of the content corresponding to the first content is generated to facilitate collaborative editing.
[0117] For example, after completing a creation, the user can share the creation with team members and invite them to collaborate online to modify it. During the collaboration process, the team can discuss details in the conversation area and directly edit the creation. This embodiment can realize creation sharing and multi-person online editing.
[0118] In addition, users can also export the created content into a predetermined format and send the created content to other users.
[0119] The above is the interactive method provided by the embodiment of the present disclosure. Figure 12-14 An interaction device according to an embodiment of the present disclosure is described, which is used to execute any embodiment of the above-mentioned interaction method.
[0120] Fig.12 A block diagram of an interaction device according to some embodiments of the present disclosure is shown.
[0121] like Fig.12 As shown, the interaction device 12 includes a generation module 1210 , a display module 1220 , a determination module 1230 and an editing module 1240 .
[0122] The generation module 1210 is configured to generate the first content in response to a user inputting an instruction to generate the first content in the dialogue area; the display module 1220 is configured to display an editing area matching the genre of the first content, and display the first content in the editing area, and the editing area and the dialogue area are located in the same display interface; the determination module 1230 is configured to determine the editing instructions for the first content based on the first content and the genre of the first content in response to the user triggering an editing operation in the dialogue area or the editing area; the editing module 1240 is configured to edit the first content in the editing area based on the editing instructions.
[0123] In some embodiments, the determination module 1230 is configured to determine editing instructions related to the genre and the first content in response to the user's triggering operation on the target content in the first content in the editing area, wherein the triggering operation includes at least one of selection, staying for a specified time, and triggering of a control displayed in association with the target content, and the editing instructions are configured to generate second content corresponding to the target content.
[0124] In some embodiments, the determination module 1230 is configured to recommend a plurality of candidate instructions related to the genre and the first content to the user for selection in response to the user's triggering operation on the target content in the first content in the editing area; and use the instruction selected by the user from the plurality of candidate instructions as the editing instruction related to the genre and the first content.
[0125] In some embodiments, the determination module 1230 is configured to display a first dialogue control related to the target content in response to the user triggering an operation on the target content in the first content in the editing area; and to determine the editing instructions related to the genre and the first content in response to the user inputting first information in the first dialogue control, and the editing instructions are configured to generate second content corresponding to the target content based on the first information.
[0126] In some embodiments, the editing module 1240 is configured to output the second content; in response to the user's confirmation operation on the second content, replace the target content with the second content, and / or add the second content to an area related to the target content.
[0127] In some embodiments, the determination module 1230 is configured to determine editing instructions related to the genre and the first content in response to the user entering second information in a second dialogue control in the dialogue area, and the editing instructions are configured to edit target content related to the second information.
[0128] In some embodiments, the editing module 1240 is configured to locate target content related to the second information in the first content; and edit the target content based on the editing instruction.
[0129] In some embodiments, the editing module 1240 is configured to obtain an image of the editing area; perform visual understanding on the image; and determine the target content in the first content based on the visual understanding result and the second information.
[0130] In some embodiments, the determination module 1230 is configured to recommend the multiple candidate instructions related to the genre and the first content to the user for selection in response to the user's triggering operation on the first content; and use the instructions selected by the user from the multiple candidate instructions as editing instructions related to the genre and the first content, and the editing instructions are configured to perform global editing on the first content.
[0131] In some embodiments, the determination module 1230 is configured to understand the first content; based on the understanding results of the genre and the first content, determine at least one editing suggestion matching the first content; recommend the at least one editing suggestion to the user in the dialogue area or the editing area; in response to the user's confirmation operation on the target suggestion in the at least one editing suggestion, determine editing instructions related to the genre and the first content, and the editing instructions are configured to edit the first content based on the target suggestion.
[0132] In some embodiments, the determination module 1230 is configured to understand the first content in response to the user instructing the agent to give editing suggestions in the dialogue area.
[0133] In some embodiments, the determination module 1230 is configured to display a conversation sent by the agent in the conversation area, wherein the sent conversation includes the at least one editing suggestion; and / or display an annotation in the editing area, wherein the annotation includes the at least one editing suggestion.
[0134] In some embodiments, the interactive device also includes a switching module (not shown), which is configured to switch an editing area matching the genre of the first content to an editing area matching the genre of the third content in response to the user inputting an indication in the dialogue area to generate third content, wherein the genres of the first content and the third content are different.
[0135] In some embodiments, the display module is further configured to display the fourth content in an editing area that matches the genre of the fourth content; the switching module is configured to switch the editing area that matches the genre of the fourth content to an editing area that matches the genre of the first content in response to the user inputting an instruction in the dialogue area to generate the first content.
[0136] In some embodiments, the display module is further configured to display one or more folders, where the folders are used to store edited versions of content corresponding to the first content.
[0137] In some embodiments, the generation module is further configured to generate a sharing link of the edited version of the content corresponding to the first content to facilitate collaborative editing.
[0138] In the above embodiment, the conversation area and the editing area are displayed in the same display interface, and the editing area matches the genre of the generated content, which facilitates the editing of the generated content. Since the editing instructions are determined based on the generated content and the genre of the generated content, the intelligent agent can perform targeted editing on the generated content of any genre, which can improve the user's creative efficiency and thus enhance the user experience.
[0139] It should be noted that the above-mentioned units are only logical modules divided according to the specific functions they implement, and are not used to limit the specific implementation methods. For example, they can be implemented in software, hardware, or a combination of software and hardware. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned units are shown with dotted lines in the accompanying drawings to indicate that these units may not actually exist, and the operations / functions they implement can be implemented by the processing circuit itself.
[0140] Fig.13 A block diagram showing an interaction device according to some other embodiments of the present disclosure.
[0141] like Fig.13 As shown, the interaction device includes a memory 131; and a processor 132 coupled to the memory, wherein the processor is configured to execute the above-mentioned interaction method based on instructions stored in the memory.
[0142] The memory 131 is used to store one or more computer-readable instructions. The memory 131 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), flash memory. The memory 131 may store, for example, an operating system, an application, a boot loader (BootLoader), a database, and other programs, and may also store various applications and various data.
[0143] The processor 132 is used to run computer-readable instructions to implement the interaction method described in any of the above embodiments or the interaction method described in any of the above embodiments. The specific implementation of each step of the method can refer to the above embodiments, and the repeated parts are not repeated here.
[0144] The processor 132 may be configured to execute Figures 1 to 11BThe processor 132 may be embodied as various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The central processing unit (CPU) may be an X86 or ARM architecture, etc.
[0145] The processor 132 and the memory 131 may communicate with each other directly or indirectly. For example, the processor 132 and the memory 131 may communicate with each other via a network. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 132 and the memory 131 may also communicate with each other via a system bus, which is not limited in the present disclosure.
[0146] It should be noted that Fig.13 The components of the interactive device 13 shown are only exemplary and non-restrictive. The interactive device 13 may also have other components according to actual application requirements. The processor 132 may control other components in the electronic device 13 to perform desired functions.
[0147] In the above embodiment, by storing data instructions in a memory and then processing the instructions through a processor, generated content of any genre can be edited in a targeted manner, which can improve user creation efficiency and further enhance user experience.
[0148] The interaction device 13 may be implemented by software, firmware and / or hardware, and may be integrated into a device installed with relevant application programs.
[0149] Fig.14 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.
[0150] Fig.14 The electronic device 14 shown may be a computer system with a dedicated hardware structure, which can execute corresponding functions when a relevant application program is installed.
[0151] Electronic devices include, but are not limited to, mobile terminals such as smart phones, laptops, personal digital assistants (PDA), tablet personal computers (Tablet PC), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., and fixed terminals such as digital televisions, desktop computers, etc.
[0152] like Fig.14As shown, the central processing unit (CPU) 141 performs various processes according to the program stored in the read-only memory (ROM) 142 or the program loaded from the storage part 148 to the random access memory (RAM) 143. In the RAM 143, data required when the CPU 141 performs various processes, etc. is stored as needed. The central processing unit is only exemplary, and it can also be other types of processors, such as the various processors described above. The ROM 142, the RAM 143 and the storage part 148 can be various forms of computer-readable storage media. It should be noted that although Fig.14 ROM 142, RAM 143 and storage section 148 are shown separately in FIG. 1 , but one or more of them may be combined or located in the same or different memory or storage modules.
[0153] The CPU 141, the ROM 142, and the RAM 143 are connected to one another via a bus 144. To the bus 144, an input / output interface 145 is also connected.
[0154] The following components are connected to the input / output interface 145: an input portion 146, such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output portion 147, including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage portion 148, including a hard disk, a magnetic tape, etc.; and a communication portion 149, including a network interface card such as a LAN card, a modem, etc. The communication portion 149 allows communication processing to be performed via a network such as the Internet. It is easy to understand that although Fig.14 Some of the electronic devices 14 are shown to communicate via the bus 144, but they may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless networks and wired networks.
[0155] A drive 1410 is also connected to the input / output interface 145 as needed. A removable medium 1411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 1410 as needed so that a computer program read therefrom is installed into the storage section 148 as needed.
[0156] When the above-described series of processing is realized by software, a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 1411 .
[0157] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which computer instructions are stored, wherein the instructions implement the above-mentioned interaction method when executed by a processor.
[0158] The computer-readable storage medium can improve the user's creative efficiency.
[0159] According to one aspect of the present disclosure, a computer program product is provided, comprising: computer instructions, wherein the computer instructions implement the above interaction method when executed by a processor.
[0160] This computer program product can improve user creation efficiency and enhance user experience.
[0161] According to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which, when running on a computer, enables the computer to implement the method described in any of the aforementioned embodiments. The computer program product includes a computer instruction carried on a computer-readable medium, containing a program code for executing the method shown in the flowchart. In such an embodiment, the computer instruction can be downloaded and installed from a network through the communication part 149, or installed from the storage part 148, or installed from the ROM 142. When the computer program is executed by the CPU 141, the method of the embodiment of the present disclosure is executed.
[0162] It should be noted that, in the context of the present disclosure, a computer-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, apparatus, or device or for use in conjunction with an instruction execution system, apparatus, or device.
[0163] The computer-readable medium may be a computer-readable storage medium, or a computer-readable signal medium, or any combination of the two. The computer-readable storage medium is a non-transitory computer storage medium.
[0164] Computer-readable storage media include, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device. Computer instructions are stored on a computer-readable storage medium, and when the instructions are executed by a processor, the method described in any of the foregoing embodiments is implemented.
[0165] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer readable program codes. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0166] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0167] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to execute the method described in any of the above embodiments. For example, the instructions may be embodied as computer program codes.
[0168] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In situations 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).
[0169] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0170] The functions described above may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0171] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims
1. An interactive method, comprising: In response to a user inputting an instruction to generate first content in the dialogue area, generating the first content; Displaying an editing area that matches the genre of the first content, and displaying the first content in the editing area, wherein the editing area and the conversation area are located on the same display interface; In response to the user triggering an editing operation in the conversation area or the editing area, determining an editing instruction for the first content based on the first content and the genre of the first content; Based on the editing instruction, the first content is edited in the editing area.
2. The interactive method according to claim 1, wherein: The determining, based on the first content and the genre of the first content, an editing instruction for the first content includes: In response to the user's triggering operation on the target content in the first content in the editing area, the editing instruction related to the genre and the first content is determined, wherein the triggering operation includes at least one of selection, staying for a specified time, and triggering of a control displayed in association with the target content, and the editing instruction is configured to generate a second content corresponding to the target content.
3. The interactive method according to claim 2, wherein: In response to the user's triggering operation on target content in the first content in the editing area, determining the editing instruction related to the genre and the first content includes: In response to a trigger operation of the user on a target content in the first content in the editing area, recommending a plurality of candidate instructions related to the genre and the first content to the user for selection by the user; An instruction selected by the user from the plurality of candidate instructions is used as the editing instruction related to the genre and the first content.
4. The interactive method according to claim 2, wherein: In response to the user's triggering operation on target content in the first content in the editing area, determining the editing instruction related to the genre and the first content includes: In response to the user triggering an operation on a target content in the first content in the editing area, displaying a first dialog control related to the target content; In response to the user inputting first information in the first dialogue control, the editing instruction related to the genre and the first content is determined, and the editing instruction is configured to generate second content corresponding to the target content based on the first information.
5. The interactive method according to claim 2, wherein: The editing of the first content in the editing area based on the editing instruction includes: outputting the second content; In response to the user's confirmation operation on the second content, the target content is replaced with the second content, and / or the second content is added to an area related to the target content.
6. The interactive method according to claim 1, wherein: The determining, based on the first content and the genre of the first content, an editing instruction for the first content includes: In response to the user inputting second information in a second dialogue control in the dialogue area, the editing instruction related to the genre and the first content is determined, and the editing instruction is configured to edit the target content related to the second information.
7. The interactive method according to claim 6, wherein: The editing of the first content in the editing area based on the editing instruction includes: Locating target content related to the second information in the first content; Based on the editing instruction, the target content is edited.
8. The interactive method according to claim 7, wherein: The locating the target content related to the second information in the first content includes: Acquire an image of the editing area; performing visual understanding of the image; The target content in the first content is determined based on the visual understanding result and the second information.
9. The interactive method according to claim 1, wherein: The determining, based on the first content and the genre of the first content, an editing instruction for the first content includes: In response to a triggering operation of the user on the first content, recommending a plurality of candidate instructions related to the genre and the first content to the user for selection by the user; An instruction selected by the user from the plurality of candidate instructions is used as an editing instruction related to the genre and the first content, and the editing instruction is configured to perform global editing on the first content.
10. The interactive method according to claim 1, wherein: The determining, based on the first content and the genre of the first content, an editing instruction for the first content includes: Understand the first content; Based on the understanding results of the genre and the first content, determining at least one editing suggestion matching the first content; recommending the at least one editing suggestion to the user in the conversation area or the editing area; In response to a confirmation operation of the user on a target suggestion in the at least one editing suggestion, the editing instruction related to the genre and the first content is determined, and the editing instruction is configured to edit the first content based on the target suggestion.
11. The interactive method according to claim 10, wherein: The understanding of the first content includes: In response to the user instructing the agent to give editing suggestions in the dialogue area, the first content is understood.
12. The interactive method according to claim 10, wherein: The displaying of the at least one editing suggestion comprises: In the conversation area, displaying a conversation sent by an agent, wherein the sent conversation includes the at least one editing suggestion; and / or An annotation is displayed in the editing area, wherein the annotation includes the at least one editing suggestion.
13. The interactive method according to any one of claims 1 to 12, further comprising: In response to the user inputting an instruction to generate a third content in the dialogue area, the editing area matching the genre of the first content is switched to an editing area matching the genre of the third content, wherein the genres of the first content and the third content are different.
14. The interactive method according to any one of claims 1 to 12, further comprising: Displaying the fourth content in an editing area matching the genre of the fourth content; In response to the user inputting an instruction to generate the first content in the dialogue area, the editing area matching the genre of the fourth content is switched to the editing area matching the genre of the first content.
15. The interactive method according to any one of claims 1 to 12, further comprising at least one of the following: Displaying one or more folders, where the folders are used to store edited content corresponding to the first content; Generate a sharing link of the edited version of the content corresponding to the first content to facilitate collaborative editing.
16. An interactive device, comprising: A generating module, configured to generate the first content in response to a user inputting an instruction to generate the first content in the dialogue area; A display module, configured to display an editing area matching the genre of the first content, and to display the first content in the editing area, wherein the editing area and the conversation area are located on the same display interface; a determination module configured to determine, in response to the user triggering an editing operation in the conversation area or the editing area, an editing instruction for the first content based on the first content and the genre of the first content; The editing module is configured to edit the first content in the editing area based on the editing instruction.
17. An interactive device, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the interaction method according to any one of claims 1 to 15 based on instructions stored in the memory.
18. A computer-readable storage medium having computer instructions stored thereon, wherein: When the instruction is executed by a processor, the interactive method described in any one of claims 1 to 15 is implemented.
19. A computer program product comprising: The method comprises computer instructions, which, when executed by a processor, implement the interaction method according to any one of claims 1 to 15.
Citation Information
Patent Citations
Image generation method and device, electronic equipment and storage medium
CN116543075A
Interaction method and device, electronic equipment and storage medium
CN116795261A
Interaction method and device for multimedia content, medium and program product
CN119256289A
Media content processing method and device, storage medium and program product
CN119496957A
Image editing
US20250078369A1
Cited By
Information processing method and device, equipment and storage medium
CN120764682A
Image generation method, image generation device, and computer readable storage medium
CN121600117A
Content adjustment interaction method and device, electronic equipment and readable storage medium
CN122195296A