WO2025244580A1

WO2025244580A1 - Artificial intelligence (ai)-assisted post editing

Info

Publication number: WO2025244580A1
Application number: PCT/SG2025/050332
Authority: WO
Inventors: Linlin Chen; Tianhao HE; Angel JIN; Mengyin LU
Original assignee: Lemon Inc Cayman Island
Current assignee: Lemon Inc Cayman Island
Priority date: 2024-05-23
Filing date: 2025-05-15
Publication date: 2025-11-27
Anticipated expiration: 2026-11-23
Also published as: US20250363289A1

Abstract

Method, apparatus, and user interfaces for editing posts are described In one example, an electronic device receives user input of at least a part of content of a post on a post editing page of an application on the electronic device. A suggested title of the post is generated based on the at least a part of content of the post. The suggested title of the post is provided on the post editing page. In response to receiving a user confirmation of the suggested title, the suggested title of the post is displayed on the post editing page.

Description

ARTIFICIAL INTELLIGENCE (Al)- ASSISTED POST EDITING

Cross-Reference to Related Application(s)

[0001] This application claims priority to US Application No. 18/672,420 filed in May 23, 2024, the disclosure of which is incorporated herein by reference in its entirety.

TECHNICAL FIELD

[0002] The present disclosure generally relates to post editing, and more specifically, to artificial intelligence (Al)-assisted post editing.

BACKGROUND

[0003] Al-assisted editing refers to the use of artificial intelligence technology to help with editing text, images, video, or audio. This can include, for example, correcting grammar and spelling in text, enhancing images or improving the clarity and quality of audio recordings.

SUMMARY

[0004] The present disclosure describes methods, apparatus, and user interfaces for editing a post.

[0005] In one aspect, the present disclosure describes a method. The method includes the following operations: receiving, by an electronic device, user input of at least a part of content of a post on a post editing page of an application on the electronic device; generating, based on the at least a part of content of the post, a suggested title of the post; providing, on the post editing page, the suggested title of the post; receiving a user confirmation of the suggested title of the post; and in response to receiving the user confirmation, displaying the suggested title of the post on the post editing page.

[0006] In another aspect, the present disclosure describes an apparatus including one or more processors and one or more computer-readable memories coupled to the one or more processors. The one or more computer -readable memories store instructions that are executable by the one or more processors to perform the above-described operations.

[0007] In still another aspect, the present disclosure describes a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium stores programing instructions executable by one or more processors to perform the above-described operations.

[0008] In some implementations, these general and specific aspects may be implemented using a system, a method, or a computer program, or any combination of systems, methods, and computer programs. The foregoing and other described aspects can each, optionally, include one or more of the following aspects.

[0009] In some implementations, generating, based on the at least a part of content of the post, the suggested title of the post includes: sending the at least the part of content of the post to one or more pre-trained generative artificial intelligence (GenAI) models; and receiving the suggested title of the post outputted by the one or more pretrained GenAT models. [0010] In some implementations, the one or more pre-trained GenAI models are executed in a remote server.

[0011] In some implementations, the one or more pre-trained GenAI models are executed in the electronic device.

[0012] In some implementations, the at least a part of content of the post comprises at least one of graphical content items or textual content items.

[0013] In some implementations, the at least a part of content of the post comprises one or more graphical content items. In such implementations, the method includes: receiving, by the electronic device, the one or more graphical content items at the post editing page of the application on the electronic device; generating, based on the one or more graphical content items, a textual description of the one or more graphical content items using a first model; and generating, based on the textual description of the graphical content items, the suggested title of the post using a second model.

[0014] In some implementations, the at least a part of content of the post comprises one or more graphical content items and one or more textual content items. In such implementations, the method includes: receiving, by the electronic device, tire one or more graphical content items and the one or more textual content items at the post editing page of the application on the electronic device; generating, based on the one or more graphical content items, a textual description of the one or more graphical content items using a third model; and generating, based on the one or more textual content items and the textual description of the one or more graphical content items, the suggested title of the post using a fourth model.

[0015] In some implementations, the method includes: generating, based on the at least a part of content of the post, a plurality of titles of the post; and providing, on the post editing page, a suggestion of the plurality of titles of the post.

[0016] In some implementations, the method includes: receiving a user instruction to continue drafting the post; in response to receiving the user instruction, generating, based on existing content of the post, additional textual content; and inserting the additional textual content in the post.

|0017| In some implementations, the method includes: receiving, as a selected portion of textual content, a first user selection of a portion of textual content of the post; in response to receiving the first user selection, displaying, on the post editing page, one or more editing options; receiving, as a selected editing option, a second user selection of one of the one or more editing options; and in response to the second user selection, performing an editing operation corresponding to the selected editing option on the selection portion of textual content.

[0018] In some implementations, the method includes: providing, on the post editing page, one or more interactive elements for switching between multiple versions of user-confirmed post content; and in response to a user interaction with one of the one or more interactive elements, replacing current content of the post with one of the multiple versions of user-confirmed post content.

[0019] In some implementations, die mediod includes: receiving a user instruction to change a tone of textual content of the post; in response to receiving the user instruction, providing one or more tone options on the post editing page; receiving, as a selected tone option, a user selection of one of the one or more tone options; and generating new textual content of the post that corresponds to the selected tone option.

100201 In some implementations, the method includes: providing, on the post editing page, a first interactive element to exit an Al-assisted editing mode; receiving a first user interaction with the first interactive element; in response to receiving the first user interaction with the first interactive element, providing, on the post editing page, a second interactive clement for prompting user feedback in a nondisruptivc manner.

[0021] In some implementations, die method include: receiving a second user interaction with the second interactive element; and in response to receiving the second user interaction, providing a feedback page.

[0022] In some implementations, the method includes: in response to determining that no user interaction with the second interactive element is received within a threshold duration, dismissing the second user interaction, from displaying on the post editing page.

100231 The details of one or more implementations of the subject matter of this disclosure are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages of the subject matter will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figures 1A-1K illustrate an example user interface (UI) for editing a post, according to one or more implementations of the disclosure.

[0025] Figures 2A-2F illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0026] Figures 3A-3E illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0027] Figures 4A-4H illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0028] Figures 5 A-5I illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0029] Figures 6A-6G illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0030] Figures 7A-7C illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

100311 Figures 8A-8D illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0032] Figures 9A-9I illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0033] Figures 10A-10H illustrate an example UI for editing a post, according to one or more implementations of the disclosure. [0034] Figures 11A-11D illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0035] Figures 12A-12E illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0036] Figures 13 A-l 3D illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0037] Figures 14A-14D illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[ 00381 Figures 15A-15D illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0039] Figures 16A-16D illustrate an example UI for editing a post, according to one or more implementations of the disclosure

[0040] Figures 17A-17D illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0041] Figures 18A-18B illustrate an example UI for editing a post, according to one or more implementations of the disclosure

[0042] Figures 19A-19B illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0043] Figures 20A-20B illustrate an example UI for editing a post, according to one or more implementations of the disclosure.

[0044] Figure 21 illustrates a block diagram of an example process of editing a post, according to one or more implementations of the disclosure.

100451 Figure 22 illustrates a block diagram of an example computer system, according to one or more implementations of the disclosure.

[0046] Like reference numbers and designations in the various drawings indicate like elements.

DETAILED DESCRIPTION

[0047] Example techniques arc described for leveraging artificial intelligence (Al) for post editing in one or more applications/programs of an electronic device. For example, the applications/programs can include one or more of a social networking application, a photo/video posting/sharing application, a web-browsing application, or integrate functionalities of one or more of these and other applications/programs. An example application can be a video sharing application that allows a user to create content, for example, by uploading and editing media such as text, image, video, and/or audio, and sharing the created content publicly or within one or more groups, for example, in the form of a post. The application can also include social networking features or services that allow other users to interact, through the application, with the user who uploads or create the post. [0048] A post can include graphics, e.g., image and/or video, text, and/or audio, A post can have different viewing permissions, such as viewing permissions based on the creator’s approval, and/or viewing time limits from a creation time for the post. As an example, a post can include a temporary story that is available for viewing for a limited amount of time, a post that is available for viewing for a longer period of time, a sound, a product or promotion, or a livestream.

[0049] Users can view posts and interact with posts in different viewing modes. For example, die system can provide a feed mode that presents a stream of posts to the user. In some examples, the posts presented to the user are personalized, i.e., the posts are curated based on the user’s interests, prior interactions, and viewing habits. The system can also provide a full post mode that presents each post in a larger portion of the screen and displays more information about the post such as comments, likes, and shares for the post. The full post mode can also support enhanced user interaction with the content, allowing for actions like liking, commenting, sharing, and exploring the content creator’s profile. Additional interactive features in the full post mode may include the ability to create duets or stitches with the media, provided these functionalities are enabled by the content creator.

100501 The described techniques provide example user interfaces that can provide media items, such as images or videos, for display and that can allow a user to create a new media item more easily, such as a title and/or textual description, related to the media items provided for display. In some implementations, a user interface can include everything from the layout of the screen, the design of the buttons and icons, to the responsiveness of the electronic device when a user interacts with it. For an electronic device that includes a display or screen such as a touchscreen, the user interface can include a graphical user interface (GUI). In some implementations, the user interacts with the GUI, for example, through finger contacts and/or gestures on or in front of the touchscreen.

[0051] The user interfaces can be provided for display by a system implemented as computer programs on one or more computers in one or more locations. The system can include an electronic device such as smart phones, pads, tablets, TVs, or other computer devices or terminals. In some implementations, the system can also include one or more servers that are remote from the electronic device.

100521 Example techniques are described that provide solutions to integrate Al into post editing functionalities of the application, allowing editing across multiple mediums, and offering sophisticated tools with enhanced efficiency and quality. In text editing, Al provides advanced grammar correction, style optimization, and content personalization, improving readability and engagement. For image editing, Al capabilities include automatic photo enhancements, object removal, and complex manipulative tasks that traditionally require extensive manual effort. In video editing, Al facilitates automated clip selection, seamless transitions, and color correction, streamlining postproduction workflows. Furthermore, AT can enhance audio editing by offering noise reduction, speech clarity enhancement, and even tone adjustment.

[0053] In some examples, the described techniques can leverage Al to automatically generate caption ideas from user-provided prompts and photos, continue adding to existing text input by a user, alter the tone of descriptions, summarize content, and suggest appropriate titles for a post. The title of a post can include, for example, a caption, a headline, a header, a summary, a synopsis, an abstract or another name tiiat describes a content of die of detailed text and multimedia. The expanded view facilitates a more focused and immersive user experience, allowing for deeper engagement with the content creation process.

100581 In some implementations, an initial interaction of a user with the interactive element 106 on the post editing page triggers the display of a disclaimer page 108, as depicted in Figure 1C. The disclaimer page 108 informs the user that activation of the Al-assisted editing functionality is contingent upon their consent. If the user opts to gain further understanding of this functionality by tapping on the “Learn More” element, represented by interactive element 110, a more detailed disclaimer or explanation about the Al-assisted editing features is then presented, as depicted in Figure ID. This can ensure that users are fully informed about the nature and implications of tire Al tools at their disposal, promoting transparency and informed consent in the utilization of Al technology within die application.

[0059] In some implementations, the disclaimer page 108 includes additional interactive elements to facilitate user control over the activation of Al-assisted editing features. In the shown example of Figure 1C, interactive element 112 is provided to allow users to decline die activation of the Al-assisted editing functionality. Interactive element 114 is included to permit users to consent to enabling die Al-assisted editing functionality. This configuration can ensure that users have clear options to either accept or refuse the use of Al technologies, thereby enhancing user autonomy and consent in the application’s operation. These interactive elements are designed to make the decision process straightforward and user-friendly, promoting a transparent interaction model within the application.

[0060] In the illustrated embodiment, when a user engages with interactive element 114 to authorize the activation of Al-assisted editing functionality, interactive element 1 14 transitions its label from an initial state, such as “Get Started,” to a subsequent label tiiat indicates die activation process as demonstrated in Figure IE. Following this label change, the Al-assisted editing panel 116 becomes visible, presenting a variety of Al-assisted editing options. As shown in Figure IF, these options include, but are not limited to, “Suggest more,” “Longer,” and “Change tone,” allowing users to tailor their content dynamically according to their needs.

[0061] In some implementations, when (he user engages with interactive element 112 to decline the Al-assisted editing functionality, interactive element 106, which is used to activate die Al-assisted editing features, becomes greyed out, as illustrated in Figure 1G. This visual change serves as an indication drat the Al-assisted editing functionality has been disabled. When the user subsequently taps interactive element 106, a notification 118 appears, informing the user that the Al-assisted editing functionality is set to be activated, as show n in Figure 1H. Following this interaction, interactive element 106 reverts from being greyed out, signaling that the Al-assisted editing functionality has been reactivated, as depicted m Figure 11. This sequence allows users to visually and interactively manage the enabling and disabling of Al editing features, enhancing user control and clarity in the application interface.

[0062] In some implementations, when a system malfunction occurs, such as a failure in uploading, the interactive element 106, which is designated for activating the Al-assisted editing functionality, will automatically become greyed out, as depicted m Figure 1J. This change visually communicates to the user that the Al-assisted editing functionality is temporarily disabled. If the user attempts to engage with the greyed-out interactive element 106, a notification 120 will be presented, informing the user that the Al-assisted editing functionality is currently unavailable, as shown in Figure IK. This feature ensures that users are promptly made aware of any disruptions in service, maintaining transparency and managing user expectations effectively.

[0063] Figures 2A-2F illustrate an example UI 200 for editing a post, according to one or more implementations of the disclosure.

[0064] Figure 2A illustrates Ul 200 configured as a post editing page, including multiple images 202 for user modification or arrangement, a post composing area 204 for text entry , and an interactive element 206 designed to activate Al-assisted editing functionalities. Upon user activation of element 206, an Al -assisted editing panel 208 is displayed, offering various editing options such as “Suggest more,” “Longer,” and “Change tone,” as shown in Figure 2B. In some examples, when no textual content is inputted by the user, only the “Suggest more” option is shown as available for user interaction, and the other options are greyed out, indicating that they are not currently available.

100651 In addition to the Al-assisted editing panel 208, one or more suggested content versions 210 for the post are also provided in the post editing page. In some examples, the suggested content versions 210 can be generated by an Al model based solely on the images 202. Each suggested content version includes an associated interactive clement labeled “Select,” enabling the user to choose their preferred content version.

[0066] Selecting a suggested content version 210 populates it into the post composing area 204, which includes fields for the title and description, as shown in Figure 2C. Users can terminate the Al-assisted editing session by tapping an interactive element 216, marked “X,” as depicted in Figures 2C and 2D. Subsequently, the Al-assisted editing panel 208 vanishes, and the element 206 for reactivating Al features becomes accessible again. Users may finalize their post edits by tapping the “Done” button 218, as indicated in Figure 2D.

[0067] In some implementations, users have the option to hide the suggested content 210 by tapping the “suggest more” button within panel 208 in Figure 2B or by interacting with the post composing area 204, as demonstrated in Figure 2E.

[0068] As shown in Figure 2B, when the user input fewer characters than a predetermined threshold (e.g., 30 characters), certain options within the Al-assisted editing panel 208 will be greyed out, signaling their deactivation. If a user attempts to select any disabled option from panel 208, a notification 220 will appear, advising that a minimum of the threshold character count is required to activate the disabled editing options, as illustrated in Figure 2F. This functionality ensures that the editing tools are only activated when there is sufficient text to support meaningful edits, thus maintaining the quality and relevance of the Al-assisted enhancements.

[0069] Figures 3A-3E illustrate an example UI 300 for editing a post, according to one or more implementations of the disclosure.

[0070] Figure 3A illustrates UI 300 configured as a post editing page, including multiple images 302 for user customization, a post composing area 304 for text entry, and an interactive element 306 designed to activate AI- assisted editing features. In the example shown, the user has already inputted some text into the post composing area 304. In scenarios where the user input exceeds a predefined threshold (e.g., 30 characters), tapping the interactive element 306 will reveal the Al-assisted editing panel 308, which offers a range of editing options including, but not limited to, “Suggest more,” “Longer,” and “Change tone,” as illustrated in Figure 3B. In the shown example, all options within the Al-assisted editing panel 308 are displayed as available for user interaction.

[0071] Upon selection of the “suggest more” option from the Al-assisted editing panel 308, multiple suggested content versions 310 for the post arc shown beneath the panel 308. Each version is accompanied by an interactive element labeled “Select,” which allows users to choose their preferred content version, as depicted in Figure 3C. If a user selects one of these content versions 310, an alert 312 is generated, prompting the user to decide whether to replace the existing post content with die chosen version 310 or to cancel die selection, as shown in Figure 3D. If the user opts to replace the existing content, the selected version 310 will update the text in the post composing area 304, as illustrated in Figure 3E. This feature enhances user control and flexibility, allowing for dynamic content updates based on Al-generated suggestions while respecting user decisions and existing content.

[0072] Figures 4A-4H illustrate an example UI 400 for editing a post, according to one or more implementations of die disclosure.

[0073] In some implementations, activating a post editing function within an application triggers the rendering of UI 400 as illustrated in Figure 4A, which depicts a post editing page. The post editing page includes multiple images 402 that users can edit or arrange, a post composing area 404 for text entry, and an interactive clement 406 for enabling Al-assisted editing features. Additionally, the post editing page includes various other interactive elements that enhance the functionality and user interaction, such as options for adding hashtags, ‘@’ mentions, tagging other users, inserting hyperlinks, and utilizing location services.

[0074] In some implementations, interacting with die post editing page, such as tapping the post composing area 404, initiates a transition to a full screen editing mode. The full screen editing mode enlarges the post composing area, enhancing the user’s ability to compose posts with increased visibility and minimal distractions, as shown in Figure 4B. The full-screen functionality is tailored to support extensive editing tasks, including tire integration of detailed text and multimedia content. The expanded view is designed to provide a more focused and immersive editing experience, fostering deeper user engagement with the content creation process.

[0075] Activation of the interactive clement 406 reveals the Al-assistcd editing panel 408, featuring options such as “Suggest more,” “Longer,” and “Change tone,” as depicted in Figure 4C. In scenarios where no text or insufficient text (below a specified threshold) is entered, only the “Suggest more” option is active, with other options in tire Al-assisted editing panel 408 being temporarily inaccessible (greyed out). The keyboard remains visible and accessible, enhancing user convenience. Additionally, multiple content versions 410 are displayed above the AT- assisted editing panel 408, each associated with an “Add” element that allows users to select and incorporate these versions into their posts.

[0076] Selecting a content version 410 via its associated “Add” element populates this version into the post composing area 404. As illustrated in Figure 4D, when the post composing area 404 contains text exceeding a certain threshold, all editing options in the Al-assisted editing panel 408 become accessible. An interactive exit element 412, marked as “X,” also appears, providing a straightforward method for users to exit Al -assisted editing. Tapping the “X” element makes the editing panel 412 disappear, restoring the visibility of the interactive element 406 for reactivating Al-assisted editing features, as shown in Figure 4E.

[0077] Further examples include scenarios depicted in Figures 4F and 4G, where entering text above a designated threshold and tapping the interactive element 406 brings forth the Al-assisted editing panel 408 with all editing options enabled. In some examples, as shown in Figure 4H, if the text entered is below the threshold and the user activates the Al-assisted editing panel 408 via element 406, only the “Suggest more” option will be available, reflecting adaptive functionality based on text input levels. This adaptive approach ensures that editing tools are appropriately matched to the content volume, optimizing die editing experience.

[0078] Figures 5 A-5I illustrate an example UI 500 for editing a post, according to one or more implementations of the disclosure.

[0079] Figure 5A illustrates UT 500 configured as a post editing page. The post editing page includes multiple images 502, a post composing area 504, and an Al-assisted editing panel 506. The editing panel 506 includes options such as “Suggest more,” “Longer,” and “Change tone.” In some implementations, when the number of characters entered by the user falls below a specified threshold, only the “Suggest more” option is made accessible, while the other options are temporarily disabled and displayed as greyed out.

[0080] In some implementations, when the character count in tire post composing area 504 exceeds the threshold, all options within the Al-assisted editing panel 506 become accessible, as depicted in Figure 5B. This feature ensures that more complex editing tools are only unlocked when sufficient text is present, enhancing their relevance and effectiveness.

[0081] In some implementations, post composing area 504 includes a title field and a description field. In some examples, when a user positions the cursor at a particular location within the description field and selects the “Longer” option from the Al-assisted editing panel 506, the system will automatically continue generating text based on tire content preceding the cursor position and the images 502, as shown in Figure 5C. Upon activation of this “Longer” option, the post composing area 504 is temporarily disabled, the editing panel 506 and keyboard are hidden, and a loading status is displayed, indicating ongoing content generation.

[0082] During the display of the loading status for the “Longer” option, an interactive element 508 is also presented, enabling the user to exit this editing mode. Tapping this element 508 concludes the extension process, revealing the Al-generated text at the previous cursor location. In some examples, without users terminating the generation process, and after the system completes the generation, tire post composing area 504 is subsequently reenabled, and the Al-assisted editing panel 506 becomes accessible again, as illustrated in Figure 5D. In some implementations, the newly added content is automatically highlighted, making it easy for users to review and modify as needed. This system can enhance user interaction by providing dynamic content generation tools while maintaining user control and flexibility.

[0083] In some implementations, as illustrated in Figure 5D, the post editing page features interactive elements 509 drat enables users to toggle between various versions of content previously generated via Al-assisted features and subsequently confirmed for inclusion in the post composing area 504. This version control functionality facilitates navigation among different revisions of the post content, allowing users to review and compare multiple iterations of their work seamlessly.

[0084] In some implementations, users are provided the capability to select a specific segment of text within the description field of the post composing area 504 and utilize the “Longer" option to extend the composition based on the selected text, as shown in Figure 5E. In some examples, the system not only considers the selected text but also integrates the preceding content and associated images 502 from the post to generate additional text. This functionality allows for contextual continuation of the post content, enhancing the coherence and relevance of the extended text in relation to the original content and visual elements. Ulis feature can be useful for users who wish to develop more detailed narratives or explanations seamlessly within their posts.

[0085] In some examples, the system is capable of automatically continuing the composition of a title within the title field of tire post composing area 504, based on the initial user input. In some examples, when users have entered a sufficient number of characters in the description field of the post composing area 504, exceeding a predetermined threshold, all available options can be unlocked in the Al-assisted editing panel 506, as illustrated in Figure 5F. When a user positions the cursor at the end of the existing title content and selects the “Longer” option from the editing panel 506, the system initiates the automatic generation of additional title content. As depicted in Figure 5G, upon activation of the “Longer” option, the post composing area 504 is temporarily disabled, and both the editing panel 506 and the keyboard are concealed to present a loading status. This status serves as an indicator of ongoing content generation, ensuring users arc aware of the system's active engagement in extending the title based on the context provided by the user.

[0086] During the display of the loading status for the “Longer” option, an interactive element 508 is also presented, enabling the user to exit this editing mode. Tapping this element 508 concludes the extension process, revealing the Al-generated text at the previous cursor location in the title field. In some examples, without users terminating the generation process, and after the system completes the generation, the post composing area 504 is subsequently rc-cnablcd, and the Al-assisted editing panel 506 becomes accessible again, as illustrated in Figure 5H. In some implementations, the newly added content in the title field is automatically highlighted, making it easy for users to review and modify as needed.

100871 In some examples, users can select either a portion or the entirety of the title within the post composing area 504 to facilitate the continuation of title composition, as demonstrated in Figure 51. In some implementations, the system utilizes the selected title segment, the content preceding the selected segment, and associated images from the post to generate additional title content. This feature can allow for a contextual and coherent extension of the title, ensuring that the additional content is seamlessly integrated and relevant to the existing title and visual elements. This capability can enhance the flexibility and creativity of title generation, providing users with powerful tools to refine and expand their post titles effectively.

[0088] Figures 6A-6G illustrate an example UI 600 for editing a post, according to one or more implementations of the disclosure. [0089] Figure 6A illustrates UI 600 configured as a post editing page. The post editing page includes multiple images 602, a post composing area 604, and an Al -assisted editing panel 606. The editing panel 606 includes options such as "‘Suggest more,” “Longer,” “Change tone,” and “Summarize title.” In some implementations, when the number of characters entered by the user falls below a specified threshold, only the “Suggest more” option is made accessible, while the other options are temporarily disabled and displayed as greyed out.

[0090] In some implementations, when the content entered by a user in the description field of the post composing area 604 exceeds a specified threshold and no title is provided in the title field, users may select the “Summarize title” option from the editing panel 606 to initiate automatic title generation, as depicted in Figure 6B.

[0091] Upon selection of the “Summarize title” option, the system begins the process of automatic title creation. As shown in Figure 6C, activating the “Summarize title” option results in the temporary disabling of the post composing area 604, and the concealment of both the editing panel 606 and the keyboard, with a loading status displayed to indicate ongoing title generation.

[0092] During the loading phase, an interactive element 608 is displayed, providing users with the option to exit this mode. Engaging this element 608 terminates the title generation process and reveals the Al-generated title in the title field. In some examples, without users terminating the generation process, and after the system completes the title generation, the post composing area 604 is subsequently reactivated, and access to the Al-assisted editing panel 606 is restored, as illustrated in Figure 6D. The newly generated title content can be highlighted automatically, facilitating easy review and potential modification by the user.

[0093] Additionally , users may select specific segments of the description and utilize the “Summarize title” option to generate a title, as shown in Figure 6E. In some examples, the system can disregard the selected description content and generate the title based on the entirety of the description and associated images 602, enhancing the flexibility of the title generation process.

[0094] In scenarios where a title is already present, and users activate the “Summarize title” option to request a new title, as illustrated in Figures 6F and 6G, the system will provide a notification 610, notifying users that the existing title will be replaced with the new one. Users arc then presented with options to cither confirm or decline this replacement, ensuring user control over the content modification process and maintaining clarity in content management.

100951 Figures 7A-7C illustrate an example UI 700 for editing a post, according to one or more implementations of the disclosure.

[0096] Figure 7A illustrates UI 700 configured as a post editing page. The post editing page includes multiple images 702, a post composing area 704, and an Al -assisted editing panel 706. The editing panel 706 includes options such as “Suggest more,” “Keep writing,” and “Change tone.” In some examples, as shown, when the number of characters in the description field of post composing area 704 exceed a specified threshold, all editing options in the editing panel 706 are made accessible.

[0097] In some examples, selecting the “Keep writing” option from the editing panel 706 enables (lie sy stem to automatically continue composing the post based on existing inputs in the post composing area 704 and associated images 702. For example, upon activation of this option, the system can commence the generation of additional content, taking into account the existing title, content prior to the cursor’s position, and the images 702.

100981 The activation of the “Keep writing” option leads to the temporary deactivation of the post composing area 704, and the concurrent concealment of the editing panel 706 and the keyboard. A loading status is displayed during this time to inform users of the ongoing content generation process, as depicted in Figure 7B.

[0099] An interactive element 708 is also presented during the loading phase, providing users with the ability to exit this automatic writing mode. Engaging this element 708 halts the content generation, revealing the newly created Al-generated content within the description field. If the generation process is not manually terminated by the user and completes successfully, the post composing area 704 is re-enabled, and access to the Al -assisted editing panel 706 is reinstated, as illustrated in Figure 7C.

[0100] Figures 8A-8D illustrate an example UI 800 for editing a post, according to one or more implementations of the disclosure.

[0101] Figure 8A illustrates UI 800 configured as a post editing page. The post editing page includes multiple images 802, a post composing area 804, and an Al -assisted editing panel 806. The editing panel 806 includes options such as “Longer,” “Shorter,” “Change tone,” and “Summarize title.” In some examples, as shown, when the number of characters in the description field of post composing area 804 exceed a specified threshold, all editing options in the editing panel 806 are made accessible.

[0102] In some examples, when users select the “Longer” option from the editing panel 806 to extend the description of a post, this selection triggers the system to automatically continue the composition based on inputs already present in the post composing area 804 and related images 802. For instance, upon activation, the system begins generating additional content that considers the current title, the content preceding the cursor’s location, and the images 802.

[0103] Activating the “Longer” option results in the temporary disabling of the post composing area 804, along with the concealment of both the editing panel 806 and the keyboard. During this period, a loading status is displayed to keep users informed about the active content generation process, as show n in Figures 8B and 8C.

[0104] As illustrated in Figures 8B and 8C, while the loading status is visible, the system may also display the progression of content generation on the post editing page. This feature provides users with real-time feedback on the content being generated, enhancing transparency and engagement during the automatic composition process.

[0105] In some examples, users are afforded the flexibility to terminate the generation process at any point. By lapping an interactive element 808, users can halt the process, and the Al-generated content will then be displayed. Tn some examples, if the generation process concludes without manual interruption and is successful, the post composing area 804 is reactivated, and access to the Al-assisted editing panel 806 is restored, as depicted in Figure 8D. This approach ensures that users maintain control over the content generation, allowing for dynamic interaction with the editing process.

[0106] Figures 9A-9I illustrate an example UI 900 for editing a post, according to one or more implementations of the disclosure [0107] Figure 9A illustrates UI 900 configured as a post editing page. The post editing page includes multiple images 902, a post composing area 904, and an Al-assisted editing panel 906. The Al-assisted editing panel 906 includes various editing options like “Suggest more,” “Longer,” and “Change tone.” In some examples, when the character count in the description field of the post composing area 904 falls below a designated threshold, only the “Suggest more” option is activated, while other options remain inaccessible.

[0108] In some examples, when the text entered by users exceeds the threshold, all functionalities within die editing panel 906 become available, as depicted in Figure 9B. Selecting the “Change tone” option prompts the display of a tonal panel 908, which lists various tonal choices such as “Professional,” “Casual,” “Funny,” etc., as shown in Figure 9C.

[0109] In some examples, when the cursor is placed at certain place in the post composing area 904, and upon selecting a tone, such as the “Casual” option, the system initiates the transformation of the post’s content to reflect the chosen tone, integrating both existing text and images 902 to generate content that aligns with the selected style, as indicated in Figure 9D.

[0110] The activation of the “Casual” tone temporarily disables the post composing area 904 and conceals both the tonal panel 908 and the keyboard. A loading status is displayed during this time to inform users of the ongoing content adaptation process, as shown in Figure 9D.

|0111| An interactive element 910 is also introduced during the loading phase, allowing users the option to exit this mode. Engaging this element 910 stops the content generation, revealing the Al-generated content in the description field. If the generation process is not manually halted and successfully concludes, the post composing area 904 is reactivated, and the Al-assisted editing panel 906 becomes accessible again, as demonstrated in Figure 9E. In some examples, the newly generated content automatically replaces the previous content, with the new additions being highlighted for review and further modification.

[0112] In some implementations, users have the capability to select a segment of the description within the post composing area 904 for tonal modification. As depicted in Figure 9F, users can select a portion of the description when all options in the editing panel 906 arc available.

[0113] Selecting the “Change tone” option triggers the display of tonal panel 908, which lists various tonal choices such as “Professional,” “Casual,” “Funny,” etc., as illustrated in Figure 9G. Upon choosing a tone, like the “Casual” option, the system begins adapting the selected text to reflect the new tone. In some examples, the system may also incorporate elements from the associated images 902 to enhance the tonal conversion of the text.

[0114] Activating a specific tone, such as “Casual,” leads to the temporary deactivation of the post composing area 904 and the concealment of both the panel 908 and the keyboard. During this period, a loading status is shown, updating users on the progress of the content adaptation process, as shown in Figure 9H.

[0115] Upon manual termination of the content generation by the user, or upon successful conclusion of the process, the post composing area 904 is reactivated, and access to the Al-assisted editing panel 906 is restored, as demonstrated in Figure 91. In some examples, the newly adapted content automatically replaces the originally selected text, with the fresh content highlighted for easy identification and potential further refinement. [0116] Figures 10A-10H illustrate an example UI 1000 for editing a post, according to one or more implementations of the disclosure.

[0117] Figure 10A illustrates UI 1000 configured as a post editing page. The post editing page includes multiple images 1002, a post composing area 1004, and an Al-assistcd editing panel 1006. The Al-assistcd editing panel 1006 includes various editing options like “Suggest more,” “Longer,” and “Change tone.”

|0118| In some examples, when the text entered by users exceeds a threshold, all functionalities within the editing panel 1006 become available, as depicted in Figure 10A. Selecting the “Change tone” option prompts the display of a tonal panel 1008, which lists various tonal choices such as “Professional,” “Casual,” “Funny,” etc., as shown in Figure 10B.

[0119] In some examples, when the cursor is placed at a certain place in the title field in the post composing area 1004, and upon selecting a tone, such as the “Casual” option, the system initiates the transformation of the post's title to reflect the chosen tone, integrating both existing text and images 1002 to generate a title that aligns with the selected style, as indicated in Figure 10C.

[0120] The activation of the “Casual” lone temporarily disables the post composing area 1004 and conceals both the tonal panel 1008 and the keyboard. A loading status is displayed during this time to inform users of the ongoing content adaptation process, as shown in Figure 10C.

[0121] An interactive clement 1010 is also introduced during the loading phase, allowing users the option to exit this mode. Engaging this element 1010 stops the content generation, revealing the ALgenerated title in the title field. If the generation process is not manually halted and successfully concludes, the post composing area 1004 is reactivated, and the Al-assisted editing panel 1006 becomes accessible again, as demonstrated in Figure 10D. In some examples, the newly generated title automatically replaces the previous title, with the new title being highlighted for review and further modification.

[0122] In some implementations, users have the capability to select a segment of the title within title field of the post composing area 1004 for tonal modification. As depicted in Figure 10E, users can select a portion of the title when all options in the editing panel 1006 are available.

101231 Selecting the “Change tone” option triggers the display of a tonal panel 1008, which lists various tonal choices such as “Professional,” “Casual,” “Funny,” etc., as illustrated in Figure 10F. Upon choosing a tone, like the “Casual” option, the system begins adapting the selected portion of title to reflect the new tone. In some examples, the system may also incorporate elements from the associated images 1002 to enhance the tonal conversion of the text.

[ 01241 Activating a specific tone, such as “Casual,” leads to the temporary deactivation of the post composing area 1004 and the concealment of both the tonal panel 1008 and the keyboard. During this period, a loading status is shown, updating users on the progress of the content adaptation process, as shown in Figure 10G.

[0125] Upon manual termination of the content generation by the user, or upon successful conclusion of the process, the post composing area 1004 is reactivated, and access to the Al -assisted editing panel 1006 is restored, as demonstrated in Figure 10EL In some examples, the newly adapted content automatically replaces the originally selected text of the title, with the fresh content highlighted for easy identification and potential further refinement.

|0126| Figures 11A-11D illustrate an example UI 1100 for editing a post, according to one or more implementations of the disclosure.

[0127] Figure 11 A presents UI 1100 configured as a post editing page. The post editing page includes multiple images 1102, a post composing area 1104, and an Al-assisted editing panel 1106. The editing panel 1106 includes options such as “Suggest more,” “Keep writing,” and “Change tone.” In some examples, once the user has entered a number of characters exceeding a preset threshold, all options within the editing panel 1106 become available.

[0128] Selecting the “Change tone” option from the editing panel 1106 reveals a tonal panel 1108 that displays multiple tonal choices, including “Professional,” “Casual,” “Funny ,” and “Educational,” as illustrated m Figure 1 IB. Additionally, an element 1110 appears, signaling that the “Change tone” option is active.

|0129| When a user chooses a tonal option, such as “Casual” from panel 1108, the system initiates the adaptation of the post's content to the selected tone. Activating this particular tone results in the temporary deactivation of the post composing area 1104 and the concealment of the tonal panel 1108, the element 1110, and the keyboard. A loading status is also displayed during this phase, providing updates to the user about the ongoing content adaptation process, as shown in Figure 11C.

|0130| If the user manually terminates the content generation or if the process concludes successfully, the post composing area 1104 is reactivated, and access to the Al-assisted editing panel 1106 is reinstated, as depicted in Figure 1 ID. In some examples, the content that has been newly adapted automatically replaces the original text in the post composing area 1104.

[0131] Figures 12A-12E illustrate an example UI 1200 for editing a post, according to one or more implementations of the disclosure.

[0132] Figure 12A presents UI 1200 configured as a post editing page. The post editing page includes multiple images 1202, a post composing area 1204, and an Al-assisted editing panel 1206. The editing panel 1206 includes options such as “Longer,” “Shorter,” “Change tone,” and “Summarize title.” In some examples, once the user has entered a number of characters exceeding a preset threshold, all options within the editing panel 1206 become available.

[0133] Selecting the “Change tone” option from the editing panel 1206 reveals a tonal panel 1208 that displays multiple tonal choices, including “Professional,” “Casual,” “Funny,” and “Educational,” as illustrated m Figure 12B. Additionally, an element 1210 appears, signaling dial the “Change tone” option is active.

|0134| When a user selects a tonal option, such as “Casual” from panel 1208, the tonal panel 1208 vanishes, and the display element 1210 updates its text to indicate that the system is adapting the post content to the chosen tone, as illustrated in Figure 12C. Following this selection, the system commences the adaptation process. Activating this tone leads to the temporary deactivation of the post composing area 1204 and the concealment of both the display element 1210 and the keyboard. Throughout this phase, a loading status is presented, which keeps the user informed about the progress of the content adaptation, as shown in Figure 12D. [0135] If the user manually stops the content generation or if the process completes successfully, the post composing area 1204 is reactivated, and access to the Al -assisted editing panel 1206 is restored, as depicted in Figure 12E. In some examples, the newly adapted content automatically replaces the original text within the post composing area 1204.

[0136] Figures 13A-13D illustrate an example UI 1300 for editing a post, according to one or more implementations of the disclosure.

[0137] Figure 13 A depicts UI 1300 configured as a post editing page. The post editing page includes multiple images 1302, a post composing area 1304, and an interactive element 1306 designed to activate Al-assisted editing features.

[0138] In some implementations, when users highlight a specific segment of the description within the post composing area 1304, a side menu, such as the editing panel 1308, becomes active, presenting Al-assisted editing options such as “Keep writing"’ and “Change tone,” as shown in Figure 13B. In some examples, the editing panel 1308 can selectively display options that are appropriate for the highlighted text segment.

[0139] Selecting an editing option, such as the “Keep writing” option, prompts the system to continue generating content based on the highlighted text and associated images 1302.

[0140] The activation of an editing option results in the temporary deactivation of the post composing area 1304, and the concealment of both the editing panel 1308 and the keyboard. A loading status is also displayed during this phase, providing ongoing updates to the user about the progress of the content generation, as illustrated in Figure 13C.

|0141| If the content generation is manually terminated by the user or concludes successfully, the post composing area 1304 is reactivated, and access to the Al-assisted editing panel 1308 is reinstated, as depicted in Figure 13D.

[0142] In some examples, the newly generated content automatically replaces the originally selected text, with the new content being automatically selected and highlighted for easy review and further modifications. In some examples, the editing panel 1308 can show additional editing options, based on the newly selected portion of description.

[0143] Figures 14A-14D illustrate an example UI 1400 for editing a post, according to one or more implementations of the disclosure.

[0144] Figure 14A depicts UI 1400 configured as a post editing page. The post editing page includes multiple images 1402, a post composing area 1404, and an interactive element 1406 designed to activate Al-assisted editing features.

[0145] In some implementations, when users highlight a specific segment of the description within the post composing area 1404, a side menu, such as the editing panel 1408, becomes active, presenting Al-assisted editing options such as “Longer,” “Shorter,” and “Change tone,” as shown in Figure 14B. In some examples, the editing panel 1408 can selectively display options that are appropriate for the highlighted text segment. [0146] Selecting an editing option, such as the “Longer" option, prompts tire system to continue generating content based on the highlighted text and associated images 1402.

[0147] The activation of an editing option results in the temporary' deactivation of the post composing area 1404, and the concealment of both the editing panel 1408 and the keyboard. A loading status is also displayed during this phase, providing ongoing updates to the user about the progress of the content generation, as illustrated in Figure 14C.

[ 01581 Activating die interactive element 1608 transitions UI 1600 to a feedback page, where users are invited to submit their feedback, as shown in Figure 16D. In some implementations, the feedback is collected and used to refine or train the GcnAl models to improve on the Al-assistcd content generation. This transition facilitates a seamless feedback collection process, enhancing the user’s interaction with the system and providing valuable insights for future improvements.

[0159| Figures 17A-17D illustrate an example UI 1700 for editing a post, according to one or more implementations of the disclosure.

[0160] Figure 17A presents UI 1700, configured as a post editing page that includes images 1702, a post composing area 1704, an interactive element 1706 for reverting to a previous stage or page, an Al-assisted editing panel 1707, and an element 1708 to exit Al-assisted editing features.

[0161] In some implementations, when users interact with clement 1708 to exit the editing features, the editing panel 1707 vanishes. Simultaneously, an clement 1709 for reactivating the Al-assistcd editing features is displayed alongside an element 1710 that prompts users to provide feedback, as depicted m Figure 17B.

[ 01621 Activating element 1710 prompts UI 1700 to transition to a feedback page, facilitating the collection of user feedback on their editing experience, as illustrated in Figure 17C.

[0163] In some implementations, when users engage element 1706 to return to a prior stage or page, the editing panel 1707 vanishes, and both elements 1709 and 1710 become visible at that stage or page, as shown in Figure 17D. Selecting element 1710 in Figure 17D also directs users to the feedback page depicted in Figure 17C, thus maintaining a consistent method for gathering user insights across different stages of the editing process.

|0164| Figures 18A-18B illustrate an example UI 1800 for editing a post, according to one or more implementations of the disclosure.

[0165] Figure 18A displays UI 1800 configured as a post editing page that includes images 1802 and a post composing area 1804. In some implementations, if the title field within the post composing area 1804 already contains text, users have the option to activate an Al-assisted editing feature to generate new title content and insert the new content in the middle of the title content. In scenarios where the character count in the title field, including the newly generated content, exceeds a predetermined threshold, only a portion of this new content will be retained in the title field to keep the character count within the limit. Concurrently, a notification 1806 will be provided, informing users that the inclusion of the new content has resulted in the title’s character count exceeding the allowable Emit.

[0166] Figures 19A-19B illustrate an example UI 1900 for editing a post, according to one or more implementations of the disclosure.

[0167] Figure 19A displays UI 1900 configured as a post editing page that includes images 1902 and a post composing area 1904. In some implementations, if the title field within the post composing area 1904 already contains text, users have the option to activate an Al-assisted editing feature to generate new title content and insert the new content at the end of the title content. Tn scenarios where the character count in the title field, including the newly generated content, exceeds a predetermined threshold, only a portion of this new content will be retained in the title field to keep the character count within the limit. Concurrently, a notification 1906 will be provided, informing users that the inclusion of the new content has resulted in the title’s character count exceeding the allowable Emit.

[0168] Figures 20A-20B illustrate an example UI 2000 for editing a post, according to one or more implementations of tlie disclosure.

[0169] In some implementations, the system may experience operational difficulties, resulting in a failure to produce results in response to a user’s activation of an Al-assisted editing feature, or user input may be restricted due to specific requirements. Under these circumstances, a notification (examples of which include notifications 2002 and 2004 depicted in Figures 20A and 20B) may be issued to inform users that their requests could not be processed. The notification advises users that they may either attempt the request again later or submit a new request, thereby keeping users informed and providing guidance on next steps.

[0170] Figure 21 illustrates a block diagram of an example process 2100 of editing a post, according to one or more implementations of the disclosure. Process 2100 will be described with reference to elements as illustrated in one or more of Figures 1 -20. It should be noted that while the elements in one or more of Figures 1 -20 are described herein as examples, these are not meant to be limiting, process 2100 can be performed with respect to any suitable elements. The operations shown in process 2100 may not be exhaustive and that other operations can be performed as well before, after, or in between any of the illustrated operations. Further, some of the operations may be performed simultaneously, or in a different order than shown in FIG. 21.

|0171| An electronic device receives user input (e.g., images 202) of at least a part of content of a post on a post editing page (e.g., UI 200 of Figure 2A) of an application on the electronic device (2102). In some examples, the user input can include textual descriptions, photographic images, or video clips that a user selects or captures to compile a social media post, blog entry, or news article directly within the application. For example, a user might type a detailed accormt of their recent vacation, add a selection of photos from the trip, and possibly include a video clip of a scenic view. This input can be then processed on the post editing page, where the user can also access tools for formatting the text, editing the images, or trimming the video, to enhance the presentation of the final post before it is published or shared through tire application.

[0172] A suggested title (e.g., the suggested title of Figure 6D) of the post is generated based on the at least a part of content of the post (2104). In some implementations, the electronic device generates, based on the at least the part of content of the post, the suggested title of the post using one or more pre-trained GenAI models. For example, the at least the part of content of the post is sent to one or more pre-trained generative artificial intelligence (GenAI) models, and the suggested title of the post is outputted by the one or more pre-trained GenAI models. In some examples, the one or more GenAI models are capable of generating new content, such as text, images, music, or other media, based on learned patterns and data. The GenAI models can use algorithms to analyze and process large datasets, identifying underlying structures and features that define the input data. The GenAI models can then utilizes this understanding to generate new, similar instances of data that retain the characteristics of the original dataset.

[0173] In some implementations, the one or more pre-trained GenAI models are executed in a remote server. In some examples, user input on the electronic device can be prepared for secure transmission via encryption and serialized into a suitable format. The input data can be compressed to optimize transmission speed and reduce bandwidth usage. The processed data then can be sent over the internet using secure transfer protocols to a remote server equipped with generative Al (GenAI) models. Upon receipt, the server can process the data, which may involve decoding and tokenization, to ready it for the GenAI models. These models then analyze and generate new content based on the input. The generated content is subsequently post-processed into a user-friendly format, packaged into a response, and securely transmitted back to the user’s device using similar secure protocols. The user device receives and verifies the integrity of the data before rendering the generated content for user interaction, completing a secure and efficient cycle of content generation and delivery.

[0174] In some implementations, the one or more pre-trained GenAI models are implemented locally on the electronic device. This local implementation can allow for real-time data processing and generation without the latency associated with data transmission over die internet. For example, the user inputs content into the device, which is then processed by the on-device GenAI models. These models analyze the input, generate new content, and immediately display this content on die user device. Or in some other implementations, some of one or more pretrained GenAI are implemented locally on the electronic device while some of one or more pre-trained GenAI are implemented on a remote server, and the suggested title of the post is generated using die one or more pre-trained GenAI models in a hybrid mode.

|0175| In some implementations, the at least a part of content of a post comprises at least one of graphical content items or textual content items, and the suggested title of the post is generated based on the at least a part of content of the post.

[0176] In some implementations, die at least a part of content of a post includes one or more graphical content items. Tn such implementations, the electronic device receives the one or more graphical content items at the post editing page of the application on the electronic device. A textual description of the one or more graphical content items is generated based on the one or more graphical content items using a first model. The suggested title of the post is generated based on the textual description of the graphical content items using a second model. In some implementations, the first model can be a model that can convert or otherwise transform the one or more graphical content items to obtain the texdial description of the one or more graphical content items. For example, the first model can be a transcription model that obtain text from a photo or video content items. In some examples, the first and second model are GenAI models.

[0177] In some examples, the one or more GenAI models can employ computer vision techniques to analyze graphical content, detecting objects, recognizing paterns, and understanding the scene composition of graphical input, such as images, videos, or designs, of a post. Techniques such as object detection, segmentation, and feature extraction can be utilized to deconstruct graphical content into comprehensible elements. Once the visual elements are identified, the GenAI models can employ a pre-trained language generation module to transform these visual insights into coherent textual descriptions. In some examples, this transforming process involves synthesizing the recognized elements, their relationships, and contextual cues to produce accurate and relevant descriptions, with natural language processing (NLP) techniques ensuring grammatical correctness and logical structure. Following the creation of a detailed textual description, another Al -driven linguistic model can extract key themes and details from the text to generate a title. By analyzing the semantic content, the model can generate a concise and informative title that encapsulates the main message or the most striking elements of the textual content, thus ensuring the title is both engaging and descriptive.

|0178| In some implementations, prompt engineering techniques are employed to design and refine the inputs (prompts) provided to Al models to elicit optimal or preferred outputs. The prompt engineering can be pertinent in the context of large language models and other generative models, where it serves to enhance the quality and specificity of the inputs. Such improvements can impact the accuracy, relevance, and practicality of the outputs generated by these models.

[0179] In some implementations, a collection of prompts can be systematically crafted to activate the generative function of an Al model. In some examples, depending on the particular requirements of a use case, this collection of prompts can be curated, augmented, or modified in response to user interactions, such as textual inputs and selections made on interface clement 116. Subsequently, these tailored prompts arc fed into the generative Al model. [0180] In some examples, prompts can be configured to reduce potential misinterpretations by the Al system. In some examples, prompts can incorporate essential context to direct tire Al towards producing relevant responses. Prompts can be tailored to correspond with specified outcomes or tasks, which may include generating textual content, code, images, or making predictive assessments. Furthermore, prompts can be optimized to achieve targeted outputs with reduced input, thereby enhancing efficiency in terms of computational resources and processing time. [0181] Furthermore, an application, along with its corresponding server infrastructure, can be configured to generate, append, eliminate, modify, or otherwise manage a repository of these prompts. This dynamic adjustment of the prompt library can be driven by user feedback, facilitating the continuous refinement of the prompts to enhance performance and relevance.

[0182] In some implementations, the at least a part of content of a post includes one or more graphical content items and one or more textual content items. In such implementations, the electronic device receives the one or more graphical content items and the one or more textual content items at the post editing page of the application on the electronic device. A textual description of the one or more graphical content items is generated based on the one or more graphical content items using a third model. The suggested title of the post is generated based on the one or more textual content items and the textual description of the one or more graphical content items using a fourth model. In some examples, the third and fourth models are GenAI models. In some examples, user input can include both graphical and textual content. In such examples, one model can be used to generate a textual description of the graphical input. Subsequently, another model can utilize both the newly generated textual description and any additional textual input provided by the user to create a title for the post.

|0183| In some implementations, the at least a part of content of a post includes one or more textual content items. In such implementations, the suggested title of the post is generated based on the at the one or more textual content items.

[0184] In some implementations, a plurality of titles of the post are generated based on the at least a part of content of the post. In such implementations, a suggestion of the plurality of titles of the post (e.g., the content versions 210 of Figure 2B) is provided on the post editing page.

[0185] The suggested title of the post is provided on the post editing page (2106). In some examples, the generated title(s) can be transmitted from the backend sy stem, either on the local device or a remote server, to the electronic device. In some examples, to display a suggested title on a user device, a distinct section of the user interface on the electronic device, such as a dialog box or overlay, can be designed to use a unique style to differentiate the suggestion.

[0186] A user confirmation of the suggested title of the post is received (2108). For example, user can tap a “Select” button associated with one of the suggested titles to confirm selection of the title.

|0187| In response to receiving the user confinnation, the suggested title of die post is displayed on the post editing page (2110). For example, the user-approved title can populate a title field (e.g., title field 212 of Figure 2C) of the post upon user’s confirmation. [0188] In some implementations, a user instruction (e.g., user taps tire “Longer” option in editing panel 506 of Figure 5B) is received to continue drafting the post. In response to receiving die user instruction, additional textual content is generated based on existing content of the post, and the additional textual content is inserted in the post.

[0189] In some implementations, a first user selection (e.g., the selected portion of text in Figure 13B) of a portion of textual content of the post is received as a selected portion of textual content. In response to the first user selection, one or more editing options (e g., die editing options in editing panel 1308 of Figure 13B) are displayed on the post editing page. A second user selection of one of the one or more editing options is received as a selected editing option. In response to the second user selection, an editing operation corresponding to the selected editing option is performed on the selection portion of textual content.

[0190] In some implementations, one or more interactive elements (e.g., elements 509 of Figure 5D) for switching between multiple versions of user-confirmed post content, such as titles and/or descriptions previously populated in a post composing area for a post, are provided on the post editing page. In response to a user interaction with one of the one or more interactive elements, current content of the post is replaced with one of the multiple versions of user-confirmed post content. In some implementations, the recent M (e.g., 20) versions of user-confirmed post content are stored. In some implementations, the version control elements 509 can include one element (e.g., a “<” or undo symbol) to resume to the last version, discard changes happen after the last version. In some implementations, the version control elements 509 can include one clement (e.g., a “>” or redo symbol) to resume to the current version, discard changes happen between the last version and the current version. In some implementations, users make changes, but no Al-assisted content is generated, the version control may not store those versions that does not include the Al-assisted content and the version control elements 509 cannot undo/redo only based on the user input.

[0191] In some implementations, a user instruction (e.g., user taps the “Change tone” option in the editing panel 906 of Figure 9B) to change a tone of textual content of the post is received. In response to the user instruction, one or more tone options (e.g., the tonal options in tonal panel 908 of Figure 9C) are provided on tire post editing page. A user selection of one of the one or more lone options is received as a selected tone option. New textual content of the post that corresponds to the selected tone option is generated.

[0192] In some implementations, a first interactive clement (e.g., clement 1606 of Figure 16A) to exit an Al- assisted editing mode is displayed on the post editing page. A first user interaction with the first interactive element is received. In response to the first interactive elements, a second interactive element (e.g., element 1608 of Figure 16B) for providing user feedback is provided on the post editing page. A second user interaction with the second interactive element is received. A feedback page (e.g., the feedback page of Figure 16D) is provided in response to the second user interaction.

[0193] Figure 22 illustrates a block diagram of an example computer system 2200 used to provide computational functionalities associated with described algorithms, methods, functions, processes, flows, and procedures, as described in the disclosure, according to one or more implementations. The example computer system 2200 can include an electronic device 2202 and a network 2230. The computer system 2200 can include additional or different components, such as, one or more remote servers that are communicatively linked with the electronic device 2202.

|0194| The electronic device 2002 can include a digital TV, a desktop computer, a work station, a smart appliance, or another stationary terminal. In some implementations, the electronic device 2202 is a portable device, such as, a notebook computer, a digital broadcast receiver, a handheld device, a portable multimedia player (PMP), an in-vchiclc terminal, an Internet of Things (loT) device. For example, the electronic device 2202 can be a phone, a smartphone, a pad (tablet computer), a digital assistant device (e.g., a PDA (personal digital assistant)), or another handheld device.

[0195] In some aspects, the electronic device 2202 may include a computer that includes a user interface 2215. The user interface 2215 can include an input device, such as a keypad, keyboard, touch screen/touch display, camera, microphone, accelerometer, gyroscope, AR/VR sensors, or other device that can accept user information, and an output device that conveys information associated with the operation of the electronic device 2202, including digital data, visual, or audio information (or a combination of information), or a graphical user interface (GUI). In some implementations, the user interacts with the GUI, for example, through contacts and/or gestures on or in front of the touch screen, for example, to implement the functions such as digital photographing/videoing, instant messaging, social network interacting, image/video editing, drawing, presenting, word/text processing, website creating, game playing, telephoning, video conferencing, e-mailing, web browsing, digital music/digital video playing, etc.

[0196] The electronic device 2202 can serve in a role as a client, network component, a server, a database or other persistency, or any other component (or a combination of roles) of a computer system for performing the subject matter described in the instant disclosure. The illustrated electronic device 2202 is communicably coupled with a network 2230. In some implementations, one or more components of the electronic device 2202 may be configured to operate within environments, including cloud-computing-based, local, global, or other environment (or a combination of environments).

[0197] At a high level, the electronic device 2202 is an electronic computing device operable to receive, transmit, process, store, or manage data and information associated with tire described subject matter. According to some implementations, the electronic deGee 2202 may also include, or be communicably coupled with, an application server, e-mail server, web server, caching server, streaming data server, or other server (or a combination of servers).

[0198] The electronic device 2202 can receive requests over network 2230 from a client application (for example, executing on another electronic device 2202) and respond to the received requests by processing the received requests using an appropriate software application(s). In addition, requests may also be sent to the electronic device 2202 from internal users (for example, from a command console or by other appropriate access methods), external or third-parties, other automated applications, as well as any other appropriate entities, individuals, systems, or computers.

[0199] Each of the components of the electronic device 2202 can commimicate using a system bus. In some implementations, any or all of the components of die electronic device 2202, hardware or software (or a combination of both hardware and software), may interface with each other or the interface 2204 (or a combination of both), over the system bus using an application programming interface (API) 2212 or a service layer 2213 (or a combination of the API 2212 and service layer 2213). The API 2212 may include specifications for routines, data structures, and object classes. The API 2212 may be either computer-language independent or dependent and refer to a complete interface, a single function, or even a set of APIs. The service layer 2213 provides software services to the electronic device 2202 or other components (whether or not illustrated) that are communicably coupled to the electronic device 2202. The functionality of the electronic device 2202 may be accessible for all service consumers using this service layer. Software services, such as those provided by the service layer 2213, provide reusable, defined functionalities through a defined interface. For example, the interface may be software written in JAVA, C++, or other suitable language providing data in extensible markup language (XML) format or other suitable formats. While illustrated as an integrated component of the electronic device 2202, alternative implementations may illustrate the API 2212 or the service layer 2213 as stand-alone components in relation to other components of the electronic device 2202 or other components (whether or not illustrated) that are communicably coupled to the electronic device 2202. Moreover, any or all parts of the API 2212 or the service layer 2213 may be implemented as child or sub-modules of another softw are module, enterprise application, or hardware module without departing from the scope of this disclosure.

[0200] The electronic device 2202 includes an interface 2204. Although illustrated as a single interface 2204 in FIG. 22, two or more interfaces 2204 may be used according to particular needs, desires, or particular implementations of the electronic device 2202. The interface 2204 is used by the electronic device 2202 for communicating with other systems that are connected to the network 2030 (whether illustrated or not) in a distributed environment. Generally, the interface 2204 includes logic encoded in software or hardware (or a combination of software and hardw are) and is operable to communicate with the network 2230. In some implementations, interface 2204 includes input/output (I/O) interface and network interface. In some examples, the interface 2204 may include software supporting one or more communication protocols associated with communications such that the network 2230 or interface’s hardware is operable to communicate physical signals within and outside of the illustrated electronic device 2202.

[0201] The electronic device 2202 includes a processor 2205. Although illustrated as a single processor 2205 in FIG. 22, two or more processors may be used according to particular needs, desires, or particular implementations of the electronic device 2202. Generally, tire processor 2205 executes instructions and manipulates data to perform the operations of the electronic device 2202 and any algorithms, methods, functions, processes, flows, and procedures as described in the instant disclosure.

[0202] The electronic device 2202 also includes a database 2006 that can hold data for the electronic device 2202 or other components (or a combination of both) that can be connected to the network 2230 (whether illustrated or not). For example, database 2206 can be an in-memory, conventional, or other type of database storing data consistent with this disclosure. In some implementations, database 2206 can be a combination of two or more different database ty pes (for example, a hybrid in-memory and conventional database) according to particular needs, desires, or particular implementations of the electronic device 2202 and the described functionality. Although illustrated as a single database 2206 in FIG. 22, two or more databases (of the same or combination of types) can be used according to particular needs, desires, or particular implementations of the electronic device 2202 and the described functionality . While database 2206 is illustrated as an integral component of the electronic device 2202, in alternative implementations, database 2206 can be external to die electronic device 2202.

[0203] The electronic device 2202 also includes a memory 2207 that can hold data for the electronic device 2202 or other components (or a combination of both) that can be connected to the network 2230 (whether illustrated or not). For example, memory 2207 can include a non-transitory computer readable storage medium or other computer program product that store executable instructions configured for execution by one or more processors 2205 for performing the functionality described in this disclosure. Memory 2207 can be Random Access Memory (RAM), Read Only Memory (ROM), optical, magnetic, and the like, storing data consistent with this disclosure. In some implementations, memory 2207 can be a combination of two or more different t pes of memory (for example, a combination of RAM and magnetic storage) according to particular needs, desires, or particular implementations of the electronic device 2202 and the described functionality. Although illustrated as a single memory 2207 in FIG. 22, two or more memories 2207 (of the same or a combination of types) can be used according to particular needs, desires, or particular implementations of the electronic device 2202 and the described functionality. While memory 2207 is illustrated as an integral component of the electronic device 2202, in alternative implementations, memory 2207 can be external to the electronic device 2202.

[0204] The application 2208 is an algorithmic software engine providing functionality according to particular needs, desires, or particular implementations of the electronic device 2202, particularly with respect to functionality described in this disclosure. For example, application 2208 can include one or more of a social network application, image/video/audio editing/presentation application, etc. Application 2208 can serve as one or more components, modules, or applications. Further, although illustrated as a single application 2208, the application 2208 may be implemented as multiple applications 2208 on the electronic device 2202. In addition, although illustrated as integral to the electronic device 2202, in alternative implementations, the application 2208 can be external to tire electronic device 2202. For example, one or more programs of the application 2208 can execute on an application server remote to the electronic device 2202.

[0205] The electronic device 2202 can also include a power supply 2214. The power supply 2214 can include a rechargeable or non-rechargeable battery that can be configured to be either user- or non-user-replaceable. In some implementations, the power supply 2214 can include power-conversion or management circuits (including recharging, standby, or other power management functionality). In some implementations, the power supply 2214 can include a power plug to allow the electronic device 2202 to be plugged into a wall socket or other power source to, for example, power the electronic device 2202 or recharge a rechargeable battery.

[0206] There may be any number of computers 2202 associated with, or external to, a computer system containing electronic device 2202, each electronic device 2202 communicating over network 2230. Further, the term “client,” “user,” and other appropriate terminology may be used interchangeably, as appropriate, without departing from the scope of this disclosure. Moreover, this disclosure contemplates that many users may use one electronic device 2202, or that one user may use multiple computers 2202.

102071 Although specific configurations and arrangements are discussed, it should be understood that this is done for illustrative purposes only. As such, other configurations and arrangements can be used without departing from the scope of the present disclosure. Also, the present disclosure can also be employ ed in a variety of other applications. Functional and structural features as described in the present disclosures can be combined, adjusted, and modified with one another and in ways not specifically depicted in the drawings, such that these combinations, adjustments, and modifications are within the scope of the present disclosure.

[0208] In general, terminology may be understood at least in part from usage in context. For example, the term “one or more’" as used herein, depending at least in part upon context, may be used to describe any feature, structure, or characteristic in a singular sense or may be used to describe combinations of features, structures or characteristics in a plural sense. Similarly, terms, such as “a,” “an,” or “the,” again, may be understood to convey a singular usage or to convey a plural usage, depending at least in part upon context. In addition, the term “based on” may be understood as not necessarily intended to convey an exclusive set of factors and may, instead, allow for existence of additional factors not necessarily expressly described, again, depending at least in part on context.

[0209] The foregoing description of the specific implementations can be readily modified and/or adapted for various applications. Therefore, such adaptations and modifications arc intended to be within the meaning and range of equivalents of the disclosed implementations, based on the teaching and guidance presented herein.

|0210| The breadth and scope of the present disclosure should not be limited by any of the above-described example implementations, but should be defined only in accordance with the following claims and their equivalents. Accordingly, other implementations also are within the scope of the claims.

Claims

CLAIMS What is claimed is:

1 . A method, comprising: receiving, by an electronic device, user input of at least a part of content of a post on a post editing page of an application on the electronic device; generating, based on the at least a part of content of the post, a suggested title of the post; providing, on the post editing page, the suggested title of the post; receiving a user confirmation of the suggested title of the post; and in response to receiving the user confirmation, displaying the suggested title of the post on the post editing page.

2. The method of claim 1, wherein generating, based on the at least a part of content of the post, the suggested title of the post comprises: sending the at least the part of content of the post to one or more pre-trained generative artificial intelligence (GenAI) models; and receiving the suggested title of the post outputted by the one or more pre-trained GenAI models.

3. The method of claim 2, wherein die one or more pre-trained GenAI models are executed in a remote server.

4. The mediod of claim 2, wherein the one or more pre-trained GenAI models are executed in the electronic device.

5. The method of claim 1, wherein the at least a part of content of the post comprises at least one of graphical content items or textual content items.

6. The mediod of claim 5, wherein: the at least a part of content of the post comprises one or more graphical content items; and receiving, by the electronic device, the user input of at least a part of content of the post on die post editing page of the application on the electronic device comprises: receiving, by the electronic device, the one or more graphical content items at the post editing page of the application on the electronic device; and generating, based on die at least a part of content of the post, the suggested title of the post comprises: generating, based on the one or more graphical content items, a textual description of die one or more graphical content items using a first model; and generating, based on the textual description of the graphical content items, the suggested title of the post using a second model.

7. The method of claim 5, wherein: the al least a part of content of tire post comprises one or more graphical content items and one or more textual content items; receiving, by the electronic device, the user input of at least a part of content of the post on die post editing page of the application on the electronic device comprises: receiving, by the electronic device, the one or more graphical content items and the one or more textual content items at the post editing page of the application on the electronic device; and generating, based on die at least a part of content of the post, the suggested title of the post comprises: generating, based on the one or more graphical content items, a textual description of die one or more graphical content items using a third model; and generating, based on the one or more textual content items and the textual description of the one or more graphical content items, the suggested title of die post using a fourth model.

8. The method of claim 1, wherein: generating, based on die at least a part of content of the post, the suggested title of the post comprises: generating, based on the at least a part of content of the post, a plurality of titles of the post; and providing, on the post editing page, the suggested title of the post comprises: providing, on die post editing page, a suggestion of the plurality of tides of the post.

9. The method of claim 1, further comprising: receiving a user instruction to continue drafting the post; in response to receiving the user instruction, generating, based on existing content of the post, additional textual content; and inserting the additional textual content in the post.

10. The method of claim 1, further comprising: receiving, as a selected portion of textual content, a first user selection of a portion of textual content of the post; in response to receiving the first user selection, displaying, on the post editing page, one or more editing options; receiving, as a selected editing option, a second user selection of one of the one or more editing options; and in response to the second user selection, performing an editing operation corresponding to the selected editing option on the selection portion of textual content.

11. The metiiod of claim 1, further comprising: providing, on the post editing page, one or more interactive elements for switching between multiple versions of user-confirmed post content; and in response to a user interaction with one of the one or more interactive elements, replacing current content of the post with one of the multiple versions of user-confirmed post content.

12. The method of claim 1, further comprising: receiving a user instruction to change a tone of textual content of the post; in response to receiving the user instruction, providing one or more tone options on the post editing page; receiving, as a selected tone option, a user selection of one of the one or more tone options; and generating new textual content of the post that corresponds to the selected tone option.

13. The method of claim 1 , further comprising: providing, on the post editing page, a first interactive element to exit an Al-assisted editing mode; receiving a first user interaction with the first interactive element; and in response to receiving the first user interaction with the first interactive element, providing, on the post editing page, a second interactive element for prompting user feedback in a nondisruptive manner.

14. Tire method of claim 13, further comprising: receiving a second user interaction with the second interactive element; and in response to receiving the second user interaction, providing a feedback page.

15. The method of claim 14, further comprising: in response to determining that no user interaction with the second interactive element is received within a threshold duration, dismissing the second user interaction, from displaying on the post editing page.

16. An apparatus, comprising: one or more processors; and one or more computer-readable memories coupled to the one or more processors and having instructions stored thereon, wherein the instructions are executable by die one or more processors to perform operations comprising: receiving user input of at least a part of content of a post on a post editing page of an application on the apparatus; generating, based on the at least a part of content of the post, a suggested title of the post; providing, on tire post editing page, the suggested title of the post; receiving a user confirmation of the suggested title of the post; and in response to receiving the user confirmation, displaying the suggested title of the post on the post editing page.

17. A non -transitory computer readable storage medium, wherein the non-transitory computer readable storage medium stores programing instructions executable by one or more processors to perform operations comprising: receiving, by an electronic device, user input of at least a part of content of a post on a post editing page of an application on the electronic device; generating, based on the at least a part of content of the post, a suggested title of the post; providing, on the post editing page, the suggested title of the post; receiving a user confirmation of the suggested title of the post; and in response to receiving the user confirmation, displaying the suggested title of the post on the post editing page.

18. The non-transitory computer readable storage medium according to claim 17, wherein die non-transitory computer readable storage medium stores programing instructions executable by the one or more processors to perform operations comprising: sending the at least the part of content of the post to one or more pre-trained generative artificial intelligence (GenAI) models; and receiving the suggested title of the post outputted by the one or more pre-trained GenAI models.

19. Tire non-transitory computer readable storage medium according to claim 18, wherein the one or more pretrained GenAI models are executed in a remote server.

20. The non-transitory computer readable storage medium according to claim 18, wherein the non-transitory computer readable storage medium stores programing instructions executable by the one or more processors to perform operations comprising: generating, by the electronic device based on the at least the part of content of the post, the suggested title of the post using one or more pre-trained GenAI models.