Contextual image generation in messaging applications

Abstract

The invention relates to contextual image generation in messaging applications. A system or method for contextual image generation in a messaging application may include analyzing text input using natural language processing to determine an intent to generate an image without the need for explicit commands. An image may be generated based on the determined intent and dialog context, and then displayed within the messaging application. The system supports collaborative image refinement, allowing multiple users in a group chat to modify and animation the generated image through natural language interaction. A suggestion mechanism may be employed to maintain user control of image generation.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Provisional Patent Application No. 63 / 585,552, entitled “COMMAND TO IMAGE,” filed on September 26, 2023, and U.S. Non-Provisional Patent Application No. 18 / 890,451, filed on September 19, 2024, the entire contents of which are hereby incorporated by reference. Technical Field

[0003] Exemplary aspects of the present disclosure relate generally to artificial intelligence (AI) based image generation, and more particularly to systems and methods for contextually generating and manipulating images within messaging applications. Background Art

[0004] The rapid development of artificial intelligence and natural language processing has revolutionized digital communications. Messaging applications, which are ubiquitous in modern society, have become platforms for rich multimedia interactions. However, the integration of AI-driven content generation in these applications remains limited, often requiring users to switch between multiple tools or use complex commands to create and share visual content. Summary of the invention

[0005] The disclosed subject matter provides systems and methods for contextual image generation and manipulation within messaging applications. By leveraging natural language processing and advanced image generation models, the subject matter is able to create, modify, or animate custom visual content through natural conversational interactions.

[0006] In some example aspects, a method, apparatus, and / or computer-readable medium for generating an image based on contextual analysis of a messaging conversation may be provided. The method, apparatus, and / or computer-readable medium may facilitate receiving text input associated with a user device in a messaging application, analyzing the text input to determine an intent to generate an image, generating an image based on the determined intent and content of the text input, and displaying the generated image in the messaging application.

[0007] The method, apparatus, and / or computer-readable medium can help determine the intent to generate an image without requiring an explicit command from a user device. Alternatively, the method, apparatus, and / or computer-readable medium can help analyze conversation context and user input to infer when image generation can enhance communication (e.g., in instances where image generation can enhance communication). This can allow for a more natural integration of visual content creation within a messaging flow. After the initial image is generated, subsequent text input can be provided to modify various attributes of the image or create an animated version. This enables an iterative, conversation-driven approach to visual content creation that was not possible in previous messaging applications.

[0008] To further enhance the collaborative nature of various example aspects of the present disclosure, generated images can be shared and manipulated in a group chat environment. Multiple users can contribute to the refinement and evolution of generated images, thereby promoting a creative exchange and shared experience. Users gain the ability to express themselves visually without interrupting the flow of conversation, while also opening up the possibility of creative collaboration.

[0009] Additional advantages will be partially described in the following description or can be learned through practice. These advantages will be realized and obtained through the elements or combinations specifically pointed out in the appended claims. It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not restrictive as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 An exemplary system for contextually generating and manipulating images within a messaging application is shown.

[0011] Figure 2 Example application interfaces on a user device associated with the disclosed subject matter are shown.

[0012] Figure 3 Example application interfaces on a user device associated with the disclosed subject matter are shown.

[0013] Figure 4A Example application interfaces on a user device associated with the disclosed subject matter are shown.

[0014] Figure 4B Example application interfaces on a user device associated with the disclosed subject matter are shown.

[0015] Figure 4C Example application interfaces on a user device associated with the disclosed subject matter are shown.

[0016] Figure 4D Example application interfaces on a user device associated with the disclosed subject matter are shown.

[0017] Figure 5 An example user interface for implementing a contextual image generation system is shown.

[0018] Figure 6 An example method for generating an image based on a conversation context in a messaging application is shown.

[0019] Figure 7 An example method of collaborative image generation and manipulation in a group chat session is shown.

[0020] Figure 8 Machine learning and training models according to various examples of the present disclosure are shown.

[0021] Fig. 9 An example block diagram of an exemplary computing device suitable for implementing aspects of the disclosed subject matter is shown.

[0022] The accompanying drawings depict various embodiments for purposes of illustration only. Those skilled in the art will readily recognize from the following discussion that alternative embodiments of the structures and methods shown herein may be employed without departing from the principles described herein. DETAILED DESCRIPTION

[0023] Some embodiments of the present invention will be described more fully below with reference to the accompanying drawings, in which some, but not all, embodiments of the present invention are shown. Various embodiments of the present invention may be implemented in many different forms and should not be construed as being limited to the embodiments set forth herein. The same reference numerals always refer to the same elements.

[0024] It should be understood that the methods and systems described herein are not limited to specific methods, specific components or specific implementations. It should also be understood that the terminology used herein is only for describing specific embodiments and is not intended to be limiting.

[0025] Typically, messaging platforms can limit visual expression to predefined resources, such as emojis, stickers, or Graphics Interchange Format (GIF) images. These resources often become outdated quickly, present challenges to search or organize, or provide minimal opportunities for customization, creative control, or collaborative work. Users often find themselves constrained by the limited options available and unable to fully express their thoughts or emotions through visual means within the context of their conversations.

[0026] Additionally, some systems often require users to exit messaging apps or use separate tools to create custom visual content. This can disrupt the natural flow of conversation and create friction in the user experience. Further, the lack of integration between image creation tools and messaging platforms can hinder collaborative creativity and real-time visual communication.

[0027] By leveraging natural language processing and advanced image generation models, the disclosed subject matter is able to create, modify, or animate custom visual content through natural conversational interactions (e.g., voice or text). In one aspect, a method for generating an image based on contextual analysis of a messaging conversation is provided. The method includes receiving text input associated with a user in a messaging application, analyzing the text input to determine an intent to generate an image, generating an image based on the determined intent and content of the text input, and displaying the generated image in the messaging application.

[0028] Figure 1 An example system 100 for implementing the disclosed subject matter is shown. The system 100 may include a user device 102, a user device 103, a server 112 (e.g., a messaging server 112), an artificial intelligence (AI) processing system 114, a data repository 122 (e.g., a training data repository 122), or an image model repository 124 connected via a network 108. The messaging server 112 may be connected to the AI ​​processing system 114, wherein the AI ​​processing system 114 may be combined with a natural language processing module (NLM) 116, an intent detection module (IDM) 118, or an image generation module (IGM) 120. The AI ​​processing system 114 accesses the training data repository 122 and the image model repository 124. The user device 102 may be a smartphone, a tablet, a laptop, or other device that may allow text, voice, or other communications. It is contemplated that the components herein may be physical components or functional components.

[0029] The user device 102 may include a messaging application (App) 105. When the application 105 is used to collect media. In one example, the messaging application 105 may be an independent application (app) or integrated into a social media platform application. The messaging application 105 or the messaging application (App) 106 may provide a user interface for text-based communication or media content display. The messaging application 105 may be associated with a first user profile, and the messaging application 106 may be associated with a second user profile. It is expected that the capabilities or components of the user device 103 and the messaging application 106 may be similar or identical to the user device 102 and the messaging application 105, respectively.

[0030] The messaging server 112 can manage the functions of the messaging service, including message routing, user authentication, or conversation persistence. The messaging server 112 can also serve as an interface between the messaging client and the AI ​​processing system 114.

[0031] The AI ​​processing system 114 may include some components that enable contextual image generation and manipulation features. A natural language processing module (NLM) 116 may analyze input text messages to understand their semantic content and context. An intent detection module (IDM) 118 may use this analysis to determine when an input (e.g., text, image, or gesture) associated with a user profile expresses an intent (explicit or implicit) to generate or manipulate an image. An image generation module (IGM) 120 may create, modify, or animate an image based on the detected intent, which may be associated with a text description.

[0032] The training data repository 122 may include data sets used to train various AI models employed by the system 100. This may include conversation data, image-text pairing data, or labeled intent data, etc. The image model repository 124 may include trained image generation or manipulation models used by the system.

[0033] To improve performance or user experience, the system 100 may incorporate one or more optimization techniques as further disclosed herein. A first technique may include using progressive image loading, where generated images are initially transmitted as low-resolution previews and refined as higher-quality versions are processed. This may provide a fast initial display, thereby reducing wait time while full-quality images are rendered in the background. Another technique may include predictive pre-generation, where the system analyzes ongoing conversations to predict potential image generation requests. By pre-generating possible candidate images in the background, the perceived response time is reduced when a user requests specific visual material.

[0034] The system may use adaptive model selection techniques to dynamically select an appropriate image generation model based on factors including conversation context, user preferences, or current system load. This may enable efficient resource management while ensuring relevant outputs. Distributed caching techniques may improve performance by storing frequently used image elements and generation results across the system 100, allowing for fast retrieval in the case of similar or repeated requests.

[0035] For the user interface of the messaging application 105, suggestion bubbles may appear within the conversation interface when an image generation opportunity arises. These suggestion bubbles may allow the user to trigger the creation of visuals without interrupting their typing or conversation flow. The generated image may be displayed in an interactive canvas, enabling direct manipulation through gestures such as pinch-to-zoom or swipe-to-pan. Modifications may be requested or suggested through these gestures.

[0036] The system 100 can save a visual history in a data repository 122, saving generated and modified images so that users can revert to earlier versions or explore alternative branches of image processing. In a group conversation in a group chat session, the interface can support collaborative image refinement by providing contribution mechanisms for multiple participants, including voting systems and layer-based editing options. Personal style presets can be defined and stored for user profiles, which can be applied to generated images to quickly achieve a preferred visual aesthetic. These features can create a flexible and user-centric system that can help the technical performance and creative potential of the image generation process.

[0037] Figure 2 An exemplary application interface on a user device 102 associated with the disclosed subject matter is shown. In one example, Derrek (e.g., a second user profile associated with user device 103) and Alice (e.g., a first user profile associated with user device 102) are in a group chat session. Derrek sends a message via messaging application 106 at block 121 indicating that he might like to see a movie called The Scientist, and Alice conveys at block 127 that she might like to see the movie The Scientist and the movie Toys. An AI assistant (e.g., an AI chatbot) can be part of the group chat session and can generate and display media content 123 (e.g., images or videos) associated with Derrek and Alice's communication. As further described herein, media content 123 can be generated and displayed based on explicit instructions (e.g., Figure 3 , “@AI / / Imagine a cat wearing a strawberry hat”) or implicit instructions (e.g. Figure 2 (inferred from the dialogue shown). Figure 3An exemplary application interface on a user device 102 associated with the disclosed subject matter is shown. As shown, block 125 includes the command " / imagine a cat wearing a strawberry hat", and media content 126 is generated and displayed.

[0038] FIG. 4A to FIG. 4C An example application interface on a user device 102 associated with the disclosed subject matter is shown. In one example, Figure 4A As shown, Derrek and Alice are engaging in a group chat session with the AI ​​assistant. Derrek mentions in box 131 that he saw a movie and ate pizza (emoji pizza), and in box 132, Alice conveys how good the pizza tasted. The AI ​​assistant generates and displays media content 133 (e.g., an image or video) associated with Derrek and Alice's communication. Media content 133 happens to be an image of a baked pizza with vegetables and cheese, which may be based on preferences or other information provided in the current or previous chat session. As further described herein, media content 133 may be generated based on explicit instructions or implicit instructions (e.g., inferred from the current or previous conversation or preferences). Figure 4B In , Alice or Derreck can utilize one or more commands associated with the messaging application 105 (e.g., using one or more options of the menu 134) to further manipulate, share, or comment on the media content 133. Figure 4C In , Derreck attempts to further manipulate the media content 133 using one or more commands (e.g., @AI / imagine baking it) as shown in a text block 136 associated with the messaging application 105. Figure 4D , based on the command in text box 136, an image associated with a baked pizza is shown.

[0039] Figure 5 An example user interface of a messaging application 105 of a user device 102 implementing contextual image generation is shown. A bottom interface 141 can be presented based on a detected intent (e.g., implicit or explicit) to create media content and present example options for AI-assisted content creation, including "Create Image," "Create Group Photo," and "Write Group Description." The bottom interface 141 seamlessly integrates AI-generated visual content into the flow of conversation.

[0040] Figure 6An example method 300 for generating media content based on a conversation context in a messaging application is shown. At step 302, input (e.g., text or voice) associated with a user profile can be received in a messaging application. The input can be part of an ongoing conversation between multiple group members (e.g., a first user profile associated with a user device 102 (e.g., messaging application 105), a second user profile associated with a user device 103 (e.g., messaging application 106), or an AI assistant) in a group chat session.

[0041] In step 304, the input can be analyzed to determine the intent to generate media content (e.g., an image or animation). This analysis can go beyond simple keyword matching and can utilize natural language processing techniques to understand the conversation context and intent conveyed by the input. The intent detection process can consider factors such as the presence of words related to visual concepts or media content creation, analysis of previous messages in the conversation, historical patterns associated with user profiles requesting or interacting with visual content, or the current conversation topic and emotional tone. The intent detection process can be used to infer when media content generation can enhance communication without the need for explicit commands (e.g., explicit text input of "create an image"). For example, if a hypothetical scene or fantasy creature is described in the messaging application 105, it can be determined that generating a visual representation can increase the value of the conversation.

[0042] When an intent associated with media content generation is detected, the method may proceed to step 306, where media content may be generated based on the determined intent and the input content. The determination may be based on satisfying a threshold confidence score. The media content generation process may utilize one or more AI models capable of creating different media content from the description. Depending on the specific intent and content, multiple specialized media content generation models optimized for different types of output (e.g., photo-realistic scenes, cartoon-style illustrations, or abstract art) may be used.

[0043] The generated media content may be displayed in the messaging application at step 308. The media content may be inserted directly into the conversation thread, or presented as a suggestion to agree to before being shared in the group chat session, which may depend on the confidence of the intent detection and preference.

[0044] Step 310 may involve receiving feedback or additional input associated with one or more user profiles about the generated media content. This may include requests for modifications (e.g., color or style), animations, or entirely new media content based on the initial output.

[0045] At step 312, the feedback or additional input may be processed, which may produce modified or new media content. This step implements an iterative, dialogue-driven approach to visual content creation.

[0046] At step 314, the modified or new media content may be displayed within the messaging application, thereby continuing the visual conversation.

[0047] Figure 7 An example method 350 for collaborative media content generation and operation in a group chat session is shown. In step 351, a group chat session can be initiated within a messaging application. The group chat session involves multiple user profiles (e.g., a first user profile, a second user profile, and an AI assistant), which can be connected via a network using one or more types of computing devices (e.g., a smartphone, a tablet, or a computer). In step 352, text input can be received from a first user profile in the group chat session. The text input can include a general message, a description of the media content, or an explicit request to generate the media content.

[0048] At step 354, an intent to generate media content may be determined. The received text input may be analyzed (e.g., using natural language processing techniques) to determine if there is an intent to generate media content. The analysis may take into account the content of the message, the context of the conversation, or any explicit commands or keywords.

[0049] At step 356, based on the content of the text input and the determined intent, initial media content can be generated (e.g., displayed). The generation process can utilize one or more artificial intelligence models selected based on the specific requirements of the media content description. The generated media content can be displayed within the group chat interface. In addition, notifications can be sent to members of the group chat session to alert them to the newly generated media content and invite collaboration.

[0050] In step 358, feedback about the generated media content can be received from one or more group members. The feedback can include text comments, suggested modifications, or reactions. In step 360, feedback from one or more group members is determined to have a specific modification intention (e.g., a request) to the media content. The modification intention can include a request to change color, add or remove elements, adjust style, or create animations. For animations, an animation sequence (e.g., the desired type of motion or transformation) can be created based on the current media content and the animation request. The modification intention can be queued for processing. The queue can be sorted based on factors such as request time, requesting user permission, or complexity of the definition (e.g., threshold level) of the modification.

[0051] In step 362, the queued media content modification requests are processed. Based on the nature of the modification request, an appropriate AI model or technology may be selected to perform the modification. A preview of the modified media content may be displayed in the group chat session. Feedback may be collected from one or more group members regarding each proposed modification. The feedback may include a vote of approval, further suggestions, or a request to revert the change.

[0052] In step 364, based on the collected feedback, an indication of the completion of the modification of the media content can be provided. Modifications that receive positive feedback can be applied, while modifications with negative feedback can be restored or further refined. In step 366, the completed media content is displayed. Upon completion, the drawing layer can be merged with the main media content (e.g., image), or saved as a separate overlay, depending on preference. A version history of the finalized media content can be maintained, in which each important modification can be recorded. The version history can allow one or more group members to review the evolution of the media content (e.g., still image to animation to modified animation), and possibly revert to an earlier version. One or more group members can be allowed to create branches from a point in the version history of the finalized media content, which can enable exploration of different creative directions based on the same initial media content. In one example, in order to summarize the collaborative process, a visual timeline of the evolution of the media content can be generated following the history of editing and contributions, and a collaborative summary (which can include confirmation of contributors) can be displayed in the group chat session.

[0053] The functionality disclosed herein can be understood through practical examples that demonstrate features in real-world environments. The following example scenarios illustrate how the system can operate in a natural way to incorporate visual elements into conversations and support collaborative dynamic image creation.

[0054] In a first example of implicit image generation, a first user profile may discuss traveling, expressing a desire to visit a tropical beach, mentioning features such as "clear water and palm trees." In the absence of an explicit command, one or more devices of system 100 may interpret the descriptive content of the statement, recognizing its potential for visualization. One or more devices of system 100 may generate an image based on the user's description, and may present it as a suggestion: "I have created an image based on your description. Would you like to add it to the conversation?" This process illustrates how the disclosed subject matter can enhance a discussion by introducing visual elements without interrupting the flow of the conversation.

[0055] Another example illustrates the iterative refinement capability. An initial image depicting a future city skyline may be generated. Subsequently, a request may include, “This looks great, but can we turn it to night time with lots of neon lights?”. One or more devices of the system 100 may process the request, adjust the lighting, and merge neon elements into the existing image. This demonstrates the ability to perform complex image modifications based on natural language input, providing a smooth visual creation process for the user.

[0056] In a collaborative environment, group storytelling can be supported, as shown in a group chat session where users are creating a fantasy narrative. One participant describes a magical forest, prompting the system to generate an image. Another user suggests, “Let’s add a unicorn drinking from a sparkling stream,” and the system updates the image accordingly. A third user then asks, “Now make the unicorn’s mane flow as if there’s a breeze.” This example highlights the system’s ability to facilitate collaborative visual storytelling, where multiple users can contribute to and refine a shared creation.

[0057] The disclosed subject matter can enable animated responses, as shown in a conversation about pets. After one user generates an image of a playful dog, another participant comments, "It would be cute if this dog was wagging its tail!". The system may interpret this as an animation request, resulting in a short sequence of the dog wagging its tail. This dynamic feature expands the expressive potential of the conversation by allowing users to introduce animated visuals in response to text prompts.

[0058] Together, these examples highlight the system’s ability to interpret natural language, generate and modify images, facilitate collaborative communications, or promote multimodal communications.

[0059] The disclosed subject matter provides several different technical effects. First, the disclosed subject matter allows for the integration of image generation capabilities within a messaging platform. This can enable users (e.g., user devices 102) to create and share custom visual content while maintaining their conversations without having to switch to a separate application. The system can analyze the context of the ongoing conversation, allowing it to interpret image generation intent based on previous exchanges. This contextual understanding can simplify interactions by allowing users to express their visual ideas naturally without having to learn specific commands or follow strict grammar.

[0060] The disclosed subject matter may also facilitate collaborative image creation. Multiple participants in a conversation may contribute to and refine visual output, thereby fostering creativity and enhancing group communication. Real-time iterative feedback may allow users to modify and improve generated images through natural language input, which may enable efficient exploration of visual concepts.

[0061] The disclosed subject matter can enhance the usability and creative potential of messaging applications, providing a more intuitive and collaborative experience. The usefulness of contextual image generation can extend beyond informal communications, providing considerable value to professional and educational applications. In educational settings, teachers and students can generate illustrative visuals during discussions to aid understanding of complex topics. This functionality enhances the learning experience by integrating visual aids directly into ongoing conversations.

[0062] Design professionals can use the disclosed themes for rapid prototyping and iteration of visual concepts within the communication platform. This process can eliminate the need to switch between different tools, allowing ideas to be explored and refined more efficiently. Marketing teams can also use the system to collaboratively generate and visualize campaign strategies while remaining in the messaging platform, promoting creativity and accelerating the ideation process.

[0063] In a customer support scenario, a representative can use the system to create custom instructional visuals tailored to a specific customer inquiry. This capability improves the clarity of technical support and product-related guidance, thereby enhancing the customer experience and reducing the time to resolve issues. The disclosed subject matter can be used as a general tool to expand its utility in a variety of professional and educational fields, thereby increasing the efficiency and creativity of visual communication.

[0064] Disclosed herein are methods, systems, or devices related to contextual media content (e.g., images) generation in a messaging application. A method, system, or device may provide: receiving text input associated with a user in a messaging application; analyzing the text input to determine an intent to generate an image; generating an image based on the determined intent and the content of the text input; and displaying the generated image within the messaging application. Analyzing the text input may include detecting one or more keywords associated with image generation, or evaluating a conversation history between a user and an AI assistant. The intent to generate an image may be determined without an explicit command from the user to generate an image.

[0065] The method may also include receiving subsequent text input related to modifying the generated image; generating the modified image based on the subsequent text input; and displaying the modified image within the messaging application. Modifying the generated image may include changing one or more visual attributes of the generated image. The method may also include receiving subsequent text input related to animating the generated image; generating an animated version of the generated image based on the subsequent text input; and displaying the animated version within the messaging application. Generating the image may be performed using one of a plurality of image generation models that is selected based on the determined intent. Prior to displaying the generated image, the method may include providing a suggestion to the user to generate the image based on the conversation, and receiving user consent to generate and display the image.

[0066] Text input can be received in a group chat session, and the generated image can be displayed to multiple users in the group chat. Analyzing the text input to determine the intent to generate an image can be performed using a natural language processing model that is trained on a data set of text prompts labeled as image generation intent or non-image generation intent. The messaging application can support multiple forms of AI-generated content, and analyzing the text input can include determining which form of AI-generated content to generate. All combinations of this paragraph and the above paragraphs (including the removal or addition of each step) are considered in a manner consistent with other parts of the specific implementation.

[0067] Figure 8 A framework 600 associated with machine learning or artificial intelligence (AI) is shown. The framework 600 may be hosted remotely. Alternatively, the framework 600 may be located at Figure 1 In the system 100 shown, and can be implemented by one or more devices. In some examples, the machine learning model 610 (also referred to herein as the artificial intelligence model 610) can be implemented / executed by a network device (e.g., server 112). In other examples, the machine learning model 610 can be implemented / executed by other devices (e.g., user device 102 or user device 103). The machine learning model 610 can be operably coupled to the training data stored in the training database 603 (e.g., data repository 122 or image model repository 124). In some examples, the machine learning model 610 can be associated with other operations. The machine learning model 610 can be one or more machine learning models.

[0068] In another example, the training data 620 may include the attributes of thousands of objects. The attributes may include, but are not limited to, the size, shape, orientation, position, etc. of one or more objects. The training data 620 employed by the machine learning model 610 may be fixed or updated regularly. Alternatively, the training data 620 may be updated in real time based on the evaluation performed by the machine learning model 610 in a non-training mode. This is shown by the bidirectional arrow connecting the machine learning model 610 and the stored training data 620.

[0069] The machine learning model 610 can be designed to generate one or more portions of media content (e.g., images) associated with one or more received inputs based in part on utilizing determined contextual information. The information includes fields such as descriptions, defined variables, data categories associated with the variables and outputs (e.g., media content), and responses to generated prompts. The machine learning model 610 can be a large language model that is used to generate representations or embeddings of one or more of the received one or more inputs. These machine learning models 610 can be trained (e.g., pre-trained and / or real-time trained) on large amounts of textual data (e.g., textual data associated with one or more inputs), previous responses to one or more generated prompts, previously generated media content, or data collection of various language patterns and semantic meanings. The machine learning model 610 can understand and represent the context of words, terms, and / or phrases, etc., in a high-dimensional space, thereby effectively collecting or determining semantic similarities between different received inputs (including descriptions and responses to prompts), even when they are not exactly the same.

[0070] Typically, such determinations made by certain existing systems may require a large amount of manual annotation and / or brute force computer-based annotation to obtain training data in a supervised training framework. However, example aspects of the present disclosure may deploy one or more machine learning models (e.g., machine learning model 610) that may be flexible, adaptive, automated, temporary, fast-learning, and trainable. Due to the various learning framework aspects of the present disclosure implemented by the machine learning model 610, manual operation or brute force equipment operation may be unnecessary for the various examples of the present disclosure. In this way, this enables one or more user inputs, requests for media content to help solve one or more problems, or other aspects of the various examples of the present disclosure to be flexible and scalable.

[0071] Fig. 9 An example computer system 700 is shown. In an example, one or more computer systems 700 perform one or more steps of one or more methods described or shown herein. In an example, one or more computer systems 700 provide functionality described or shown herein. In an example, software running on one or more computer systems 700 performs one or more steps of one or more methods described or shown herein, or provides functionality described or shown herein. The example includes one or more portions of one or more computer systems 700. In this document, references to a computer system may encompass a computing device, and vice versa, where appropriate. In addition, references to a computer system may encompass one or more computer systems, where appropriate.

[0072] The present disclosure contemplates any suitable number of computer systems 700. The present disclosure contemplates computer systems 700 in any suitable physical form. By way of example and not limitation, computer system 700 may be an embedded computer system, a system-on-chip (SOC), a single-board computer system (SBC) (e.g., a computer-on-module (COM) or a system-on-module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive kiosk, a mainframe, a network of computer systems, a mobile phone, a personal digital assistant (PDA), a server, a tablet computer system, or a combination of two or more of these systems. Where appropriate, computer system 700 may include one or more computer systems 700; may be single or distributed; may span multiple locations; may span multiple machines; may span multiple data centers; or may be located in a cloud (which may include one or more cloud components in one or more networks). Where appropriate, one or more computer systems 700 may perform one or more steps of one or more methods described or shown herein without substantial spatial or temporal limitations. By way of example and not limitation, one or more computer systems 700 may perform one or more steps of one or more methods described or shown herein in real time or in batch processing mode. Where appropriate, one or more computer systems 700 may perform one or more steps of one or more methods described or shown herein at different times or at different locations.

[0073] In the example, computer system 700 includes a processor 702, memory 704, storage 706, an input / output (I / O) interface 708, a communication interface 710, and a bus 712. Although this disclosure describes and illustrates a particular computer system having particular numbers of particular components in a particular arrangement, this disclosure contemplates any suitable computer system having any suitable numbers of any suitable components in any suitable arrangement.

[0074] In an example, the processor 702 includes hardware for executing a plurality of instructions (e.g., those constituting a computer program). By way of example and not limitation, to execute a plurality of instructions, the processor 702 may retrieve (or fetch) these instructions from an internal register, an internal cache, a memory 704, or a storage 706; decode and execute these instructions; and then write one or more results to an internal register, an internal cache, a memory 704, or a storage 706. In a particular embodiment, the processor 702 may include one or more internal caches for data, instructions, or addresses. Where appropriate, the present disclosure contemplates a processor 702 that includes any suitable number of any suitable internal caches. By way of example and not limitation, the processor 702 may include one or more instruction caches, one or more data caches, and one or more translation lookaside buffers (TLBs). The instructions in the instruction cache may be copies of the instructions in the memory 704 or the storage 706, and the instruction cache may speed up the retrieval of these instructions by the processor 702. The data in the data cache may be a copy of the data in the memory 704 or storage 706 for the instruction operation executed at the processor 702; may be the result of the previous instruction executed at the processor 702, for access by the subsequent instruction executed at the processor 702, or for writing to the memory 704 or storage 706; or may be other suitable data. The data cache may accelerate the read operation or write operation of the processor 702. The TLB may accelerate the virtual address translation of the processor 702. In a particular embodiment, the processor 702 may include one or more internal registers for data, instructions, or addresses. Where appropriate, the present disclosure contemplates a processor 702 including any suitable number of any suitable internal registers. Where appropriate, the processor 702 may include one or more arithmetic logic units (ALUs); may be a multi-core processor; or may include one or more processors 702. Although the present disclosure describes and illustrates a particular processor, the present disclosure contemplates any suitable processor.

[0075] In the example, the memory 704 includes a main memory for storing instructions for execution by the processor 702 or data for operation by the processor 702. As an example and not a limitation, the computer system 700 can load instructions from the memory 706 or another source (e.g., another computer system 700) to the memory 704. Then, the processor 702 can load these instructions from the memory 704 to an internal register or an internal cache memory. In order to execute these instructions, the processor 702 can retrieve these instructions from the internal register or the internal cache memory and decode them. During or after executing these instructions, the processor 702 can write one or more results (the one or more results can be intermediate results or final results) to the internal register or the internal cache memory. Then, the processor 702 can write one or more of these results to the memory 704. In the example, the processor 702 only executes instructions in one or more internal registers or in the internal cache memory, or in the memory 704 (rather than the memory 706 or elsewhere), and only operates data in one or more internal registers or in the internal cache memory, or in the memory 704 (rather than the memory 706 or elsewhere). One or more memory buses (each memory bus may include an address bus and a data bus) may couple the processor 702 to the memory 704. As described below, the bus 712 may include one or more memory buses. In a particular embodiment, one or more memory management units (MMUs) are located between the processor 702 and the memory 704 and facilitate access to the memory 704 requested by the processor 702. In a particular embodiment, the memory 704 includes a random access memory (RAM). Where appropriate, the RAM may be a volatile memory. Where appropriate, the RAM may be a dynamic RAM (DRAM) or a static RAM (SRAM). In addition, where appropriate, the RAM may be a single-port RAM or a multi-port RAM. The present disclosure contemplates any suitable RAM. Where appropriate, the memory 704 may include one or more memories 704. Although the present disclosure describes and illustrates a specific memory, the present disclosure contemplates any suitable memory.

[0076] In an example, the memory 706 includes a large capacity memory for data or instructions. As an example and not limitation, the memory 706 may include a hard disk drive (HDD), a floppy disk drive (FDD), a flash memory, an optical disk, a magneto-optical disk, a tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these memories. Where appropriate, the memory 706 may include a removable medium or a non-removable (or fixed) medium. Where appropriate, the memory 706 may be inside or outside the computer system 700. In a specific embodiment, the memory 706 is a non-volatile solid-state memory. In an example, the memory 706 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory, or a combination of two or more of these ROMs. The present disclosure contemplates mass storage 706 taking any suitable physical form. Where appropriate, storage 706 may include one or more storage control units that facilitate communication between processor 702 and storage 706. Where appropriate, storage 706 may include one or more memories 706. Although the present disclosure describes and illustrates particular memories, the present disclosure contemplates any suitable memories.

[0077] In an example, the I / O interface 708 includes such hardware, software, or both: the hardware, software, or both provide one or more interfaces for communication between the computer system 700 and one or more I / O devices. Where appropriate, the computer system 700 may include one or more of these I / O devices. One or more of these I / O devices can implement communication between a person and the computer system 700. As an example and not limitation, the I / O device may include a keyboard, a keypad, a microphone, a monitor, a mouse, a printer, a scanner, a speaker, a still camera, a stylus, a tablet computer, a touch screen, a tracking ball, a camera, another suitable I / O device, or a combination of two or more of these I / O devices. The I / O device may include one or more sensors. The present disclosure contemplates any suitable I / O device and any suitable I / O interface 708 for the I / O device. Where appropriate, the I / O interface 708 may include one or more devices or software drivers that enable the processor 702 to drive one or more of these I / O devices. Where appropriate, I / O interface 708 may include one or more I / O interfaces 708. Although this disclosure describes and illustrates a particular I / O interface, this disclosure contemplates any suitable I / O interface.

[0078] In an example, the communication interface 710 includes hardware, software, or both that provide one or more interfaces for communication (e.g., data packet-based communication) between the computer system 700 and one or more other computer systems 700 or one or more networks. By way of example and not limitation, the communication interface 710 may include a network interface controller (NIC) or a network adapter for communicating with an Ethernet or other wired network, or a wireless NIC (WNIC) or a wireless adapter for communicating with a wireless network (e.g., a Wi-Fi network). The present disclosure contemplates any suitable network and any suitable communication interface 710 for the network. By way of example and not limitation, the computer system 700 may communicate with one or more portions of an ad hoc network, a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), or the Internet, or a combination of two or more of these networks. One or more portions of one or more of these networks may be wired or wireless. As an example, the computer system 700 can communicate with the following networks: a wireless PAN (WPAN) (e.g., a BLUETOOTH WPAN), a WI-FI network, a WI-MAX network, a cellular telephone network (e.g., a Global System for Mobile Communications (GSM) network), or other suitable wireless networks, or a combination of two or more of these networks. Where appropriate, the computer system 700 may include any suitable communication interface 710 for any of these networks. Where appropriate, the communication interface 710 may include one or more communication interfaces 710. Although the present disclosure describes and illustrates particular communication interfaces, the present disclosure contemplates any suitable communication interface.

[0079] In particular embodiments, bus 712 includes hardware, software, or both that couples the various components of computer system 700 to each other. By way of example and not limitation, bus 712 may include: an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a front-side bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBAND interconnect, a low-pin-count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCIe) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus, or a combination of two or more of these buses. Where appropriate, bus 712 may include one or more buses 712. Although this disclosure describes and illustrates a particular bus, this disclosure contemplates any suitable bus or interconnect.

[0080] In this document, where appropriate, one or more computer-readable non-transitory storage media may include: one or more semiconductor-based integrated circuits (integrated circuits, ICs) or other integrated circuits (e.g., field-programmable gate arrays (FPGAs) or application-specific ICs (ASICs)), hard disk drives (HDDs), hybrid hard disk drives (HHDs), optical disks, optical disk drives (ODDs), magneto-optical disks, magneto-optical drives, floppy disks, floppy disk drives (FDDs), magnetic tapes, solid-state drives (SSDs), RAM drives, secure digital cards (SECURE DIGITAL cards) or secure digital drives, any other suitable computer-readable non-transitory storage media, computer-readable media, or any suitable combination of two or more of these storage media. Where appropriate, computer-readable non-transitory storage media may be volatile, non-volatile, or a combination of volatile and non-volatile.

[0081] As used herein, "or" is inclusive and not exclusive, unless expressly stated otherwise or the context indicates otherwise. Thus, as used herein, "A or B" means "A, B, or both," unless expressly stated otherwise or the context indicates otherwise. Furthermore, "and" is joint and several, unless expressly stated otherwise or the context indicates otherwise. Thus, as used herein, "A and B" means "A and B, jointly or severally," unless expressly stated otherwise or the context indicates otherwise.

[0082] Although the disclosed system has been described in conjunction with various examples of the accompanying drawings, it should be understood that other similar embodiments may be used or modifications and additions may be made to the various described examples of the robotic skin or AI robotic platform in addition to the other contents disclosed herein. For example, those skilled in the art will recognize that, in addition to the other contents disclosed in this application, the robotic skin or AI robotic platform can be applied to any environment, whether wired or wireless, and can be applied to any number of such devices connected via a communication network and interacting across the network. Therefore, the disclosed system described herein should not be limited to any single example, but should be interpreted according to the breadth and scope of the appended claims.

[0083] In describing the preferred methods, systems or apparatus of the subject matter of the present disclosure - shielding high security information on a companion device - as illustrated in the accompanying drawings, specific terminology is employed for the sake of clarity. However, the claimed subject matter is not intended to be limited to the specific terminology so selected.

[0084] In addition, unless the context clearly dictates otherwise, the singular forms "a", "an" and "the" used in the specification, including the appended claims, include plural forms, including at least that specific value when referring to a specific value. The term "plurality" as used herein means more than one. When expressing a range of values, another embodiment includes from one specific value to another specific value. Similarly, when a value is expressed as an approximation by using the antecedent "about", it will be understood that the specific value forms another embodiment. All ranges are inclusive and combinable. It should be understood that the terms used herein are only for describing specific aspects and are not intended to be limiting.

[0085] This written description uses examples to enable any person skilled in the art to practice the claimed subject matter, including making and using any device or system, and performing any incorporated method. Other variations of each example are contemplated herein. It should be understood that certain features of the disclosed subject matter described herein in the context of multiple separate embodiments for clarity may also be provided in combination in a single embodiment. Conversely, the various features of the disclosed subject matter described in the context of a single embodiment for brevity may also be provided separately or in any sub-combination. In addition, any reference to a value described in a range includes each value within that range. For any and all purposes, any document cited herein is incorporated herein by reference in its entirety.

[0086] The scope of the present disclosure covers all changes, substitutions, variations, alterations and modifications to the example embodiments described or shown herein, and those skilled in the art will understand these changes, substitutions, variations, alterations and modifications. The scope of the present disclosure is not limited to the examples described or shown herein. In addition, although the present disclosure describes and illustrates the various embodiments herein as including specific parts, elements, features, functions, operations, or steps, any embodiment in these embodiments may include any combination or arrangement of any of the parts, elements, features, functions, operations, or steps described or shown anywhere herein as understood by those of ordinary skill in the art. In addition, references to devices or systems that are suitable for, arranged to, capable of, configured to, enabled to, can be operated, or can be operated to perform a specific function, or components in a device or system in the appended claims include the device, system, component, regardless of whether the device, system, component or the specific function is activated, turned on or unlocked, as long as the device, system or component is so suitable for, arranged to, capable of, configured to, enabled to, can be operated or can be operated. Additionally, although this disclosure may describe or illustrate a particular embodiment as providing particular advantages, that particular embodiment may not provide these advantages, or may provide some or all of these advantages.

Claims

1. A method comprising: receiving text input associated with a user profile in a messaging application; analyzing the text input to determine an intent to generate media content; generating the media content based on the determined intent and the content of the text input; as well as The generated media content is displayed within the messaging application.

2. The method according to claim 1, wherein: Analyzing the text input includes evaluating a conversation history between the user profile and the artificial intelligence assistant.

3. The method according to claim 1, wherein: The intent to generate the media content is determined without requiring an explicit command from a user to generate the media content.

4. The method according to claim 1, wherein: Analyzing the text input includes determining one or more keywords associated with media content generation.

5. The method according to claim 1, further comprising: receiving subsequent text input associated with animating the generated media content; generating an animated version of the generated media content based on the subsequent text input; as well as The animated version is displayed within the messaging application.

6. The method according to claim 5, further comprising: The generated media content is modified based on changing one or more visual attributes of the generated media content.

7. The method according to claim 1, further comprising: receiving subsequent text input associated with modifying the generated media content; generating modified media content based on the subsequent text input; as well as The modified media content is displayed within the messaging application.

8. The method according to claim 1, wherein: Generating the media content is performed using one or more multimedia content generation models selected based on the determined intent.

9. The method according to claim 1, further comprising: providing one or more suggestion messages prior to displaying the generated media content, the one or more suggestion messages indicating suggestions for generating media content based on the text input in the messaging application; as well as Receiving user consent to generate and display the media content.

10. The method according to claim 9, wherein: The user consent includes receiving two or more consent votes.

11. The method according to claim 1, wherein: The text input is received in a group chat session, and wherein the generated media content is displayed to a plurality of users in the group chat session.

12. An apparatus comprising: one or more processors; as well as at least one memory, wherein the one or more memories store instructions that, when executed by the one or more processors, cause the apparatus to: receiving text input associated with a user profile in a messaging application; analyzing the text input to determine an intent to generate media content; generating the media content based on the determined intent and the content of the text input; as well as The generated media content is displayed within the messaging application.

13. The device according to claim 12, wherein: When the one or more processors further execute the instructions, the apparatus is configured to: In response to analyzing the text input, one or more keywords associated with media content generation are detected.

14. The device according to claim 12, wherein: When the one or more processors further execute the instructions, the apparatus is configured to: In response to analyzing the text input, a conversation history between the user profile and the artificial intelligence assistant is evaluated.

15. The device according to claim 12, wherein: When the one or more processors further execute the instructions, the apparatus is configured to: receiving subsequent text input associated with animating the generated media content; generating an animated version of the generated media content based on the subsequent text input; and The animated version is displayed within the messaging application.

16. The device according to claim 12, wherein: Generating the media content is performed using one or more multimedia content generation models selected based on the determined intent.

17. The device according to claim 12, wherein: When the one or more processors further execute the instructions, the apparatus is configured to: providing one or more suggestion messages prior to displaying the generated media content, the one or more suggestion messages indicating suggestions for generating media content based on the text input in the messaging application; as well as Receiving user consent to generate and display the media content.

18. A non-transitory computer readable medium storing instructions which, when executed, cause: receiving text input associated with a user profile in a messaging application; analyzing the text input to determine an intent to generate media content; generating the media content based on the determined intent and the content of the text input; as well as The generated media content is displayed within the messaging application.

19. The non-transitory computer readable medium of claim 18, wherein: The instructions, when executed, further cause: Generating the media content is performed using one or more multimedia content generation models selected based on the determined intent.

20. The non-transitory computer readable medium of claim 18, wherein: The instructions, when executed, also cause: providing one or more suggestion messages prior to displaying the generated media content, the one or more suggestion messages indicating suggestions for generating media content based on the text input in the messaging application; as well as Receiving user consent to generate and display the media content.

Images