25 results about "Authoring system" patented technology

The invention, which relates to the technical field of artificial intelligence, discloses a full-process AI short episode creation system comprising an AI assistant core module, a script generation module, a vision generation module, a post optimization module and a data support module, the script generation module, the vision generation module, the post optimization module and the data support module are scheduled by the AI assistant core module, and the AI assistant core module is used to create a short episode. Real-time linkage is realized, and a closed-loop creation link is formed. According to the full-process AI short drama creation system, an intelligent assistant constructed by an AI intelligent agent serves as a center, a linear creation process is reconstructed, and seamless circulation of data in all links and AI collaborative decision making are achieved.

Taxonomy driven multi-system networking and content delivery systems and methods are provided herein. An example systems includes a website authoring platform generating a taxonomy structure for a webpage, the taxonomy structure indicating assets to be included in the webpage a layout for the assets, a technical documentation authoring system for creating technical documents related to the assets, and a metadata binder providing the technical documentation authoring system with access to the taxonomy structure of the website authoring platform so that technical document authors are provided with the taxonomy structure to guide creation and structuring of the technical documents so that the technical documents comprise data that corresponds to the assets.

The invention discloses an AI-based script creation system and method, and the method comprises the steps: receiving an initial cue word, and carrying out the recognition and extraction of script core elements of the initial cue word; inputting the script core elements into a pre-trained script generation model, and generating an initial script by the script generation model; performing text similarity, plot structure similarity and character relationship similarity calculation on the initial script and copyright scripts in a script database, and outputting the initial script only when the similarities are smaller than a preset percentage; according to the method, the overall creation period is shortened, the cost is reduced, the integrity of the script and the copyright security are both considered, and the copyright risk of the script is reduced while the script creation efficiency and quality are improved.

The invention discloses a multi-mode interactive creation system based on a movie and television knowledge graph, and particularly relates to the technical field of multi-mode interactive creation systems, which comprises an AI analysis module, a LoRA fine tuning module, a sub-mirror generation module, a multi-mode conversion module, a user interaction module, a data storage module and a security authentication module. According to the multi-mode interactive creation system based on the movie and television knowledge graph, an AI model is finely tuned through an over-low rank adaptation LoRA, the GPU video memory occupation is reduced from 24 GB to 8 GB, the amplitude is reduced by 66.7%, meanwhile, a single machine is supported to process 100 thousand concurrent WebSocket connection epoll I / O multiplexing, the resource utilization rate is remarkably increased, the real-time processing capacity can be achieved, 100 thousand files are processed every day, the average 10 MB / file is processed, the transmission speed reaches 1 MB / s, and the real-time processing capacity is achieved. The split mirror generation response time is less than or equal to 2 seconds, and the efficient creation requirement of the movie and television industry is met.

The present invention relates to an AI-based real-time interactive media art system, which is a technology that provides an immersive art experience by having AI analyze a viewer's movements, facial expressions, colors, and voice to generate customized media content and outputting it in real time using a 3D game engine. The system includes cloud-based AI analysis and 3D environment integration, and has a function in which the background, colors, and sounds change dynamically according to the speed of the user's actions.

In variants, the method can include: displaying a low-fidelity version of an asset in an extended-reality (XR) interface on an authoring device; receiving transformations of the low-fidelity asset from the user; and rendering high fidelity content using the transformations and a high-fidelity version of the asset. In variants, the method can also include: sampling LDR data using a mobile device, generating HDR data from the LDR data at a remote computing system, convolving the HDR data into a set of preconvolved HDR maps at the remote computing system, sending the set of preconvolved HDR maps to the mobile device, and dynamically rendering an XR asset at the mobile device by sampling a preconvolved HDR map associated with a surface parameter of the asset.

An augmented reality (AR) interaction authoring system is described. The AR interaction authoring system is configured to support the real-time creation of AR applications to support AR-enhanced toys. The design of the AR interaction authoring system enables bidirectional interactions between the physical-virtual space of toys and AR. The AR interaction authoring system allows intuitive authoring of AR animations and toys actuations through programming by demonstration, while referring to the physical toy for a contextual reference. Using a visual programming interface, users can create bidirectional interactions by utilizing users' input on toys to trigger AR animations and vice versa. A plug-and-play IoT toolkit is also disclosed that includes hardware to actuate common toys. In this way, users can effortlessly integrate toys into the virtual world in an impromptu design process, without lengthy electronic prototyping.

The invention provides a content generation method and device based on a large model, an intelligent agent and a storage medium, and relates to the technical field of artificial intelligence such as user content generation and natural language processing. The specific implementation scheme is as follows: obtaining input information when the user request content is generated; based on the input information, adopting a pre-trained content creation system to identify a target intention of the user; the content creation system is realized based on a large language model; based on the target intention, obtaining target tool arrangement information by adopting a content creation system; the target tool arrangement information comprises an arrangement process of the adopted target tool; the target tool is a tool in a tool library of the content creation system; based on the target tool arrangement information and the input information, using the content creation system to generate content; the generated content comprises information of at least one mode of a text, a picture and a video. According to the technology disclosed by the invention, the content generation efficiency can be effectively improved.

The application relates to the technical field of extended reality, and discloses an XR content creation method, an XR content creation system, an electronic device and a medium. The XR content creation method is applied to an XR content creation system, the XR content creation system comprises a terminal device, an edge computing device and a server; and the method comprises the following steps: the terminal device acquires identity feature data of a user, and generates operation action feature data according to the operation of the user on the terminal device; when the edge computing device detects that the identity feature data of the user sent by the terminal device matches the identity feature data stored in the server, and the operation data meets a preset condition, the edge computing device acquires historical creation content from the server, and sends the historical creation content to the terminal device; and the terminal device displays the historical creation content. Based on the above scheme, the storage of XR content, the creation of an XR content creation space and the mobile creation of XR content are more convenient and simple, and the user experience is improved.

The invention relates to a generative AI multi-mode collaborative creation system for artistic design, and belongs to the technical field of AI artistic design. The system runs on a hardware processor and comprises a multi-mode input processing module; the cross-modal fusion and intention understanding module is connected with the multi-modal input processing module; the multi-model generation engine module is connected with the cross-modal fusion and intention understanding module and used for receiving the fusion intention vector and driving at least one pre-trained generative model based on the vector to generate or modify the digital art works in an iterative mode; according to the method, the intuition and expressive power of interaction are improved, and complex creative ideas can be more intuitively and accurately conveyed to the AI; efficient team collaborative creation and multi-person real-time online editing and discussion are realized; the controllability of the creation process is enhanced, and an interactive iteration mechanism allows a designer to carry out fine and controllable local modification on the content generated by the AI instead of one-way instruction issuing.

The invention discloses an AIGC interactive story creation system, method and device and a medium. The system comprises a role definition module which generates a role drawing, sets role attributes and creates sound reference according to user-defined role parameters; the story construction module generates a story process based on a multi-node branch according to user-defined story basic information; the interaction module sets an interaction task of any node in the story process according to user-defined interaction; the visual content generation module generates corresponding visual content for any node in the story process according to a user-defined visual generation demand; according to the method, a structured creation process is constructed, role definition, story design, interactive setting and visual generation are disassembled into independent and linked modules, and a creator can intuitively construct complex branch logic in cooperation with a visual story flow chart and can complete high-interactivity content design without professional development ability.

An augmented reality (AR) interaction authoring system is described. The AR interaction authoring system is configured to support the real-time creation of AR applications to support AR-enhanced toys. The design of the AR interaction authoring system enables bidirectional interactions between the physical-virtual space of toys and AR. The AR interaction authoring system allows intuitive authoring of AR animations and toys actuations through programming by demonstration, while referring to the physical toy for a contextual reference. Using a visual programming interface, users can create bidirectional interactions by utilizing users' input on toys to trigger AR animations and vice versa. A plug-and-play IoT toolkit is also disclosed that includes hardware to actuate common toys. In this way, users can effortlessly integrate toys into the virtual world in an impromptu design process, without lengthy electronic prototyping.

The invention relates to the technical field of large language model application and personalized content generation, and discloses a large language model creation system for personalized content generation, which comprises a large language model creation system. The large language model creation system comprises a user mental model, a multi-mode perception and input module, a personalized generation engine, an interactive co-creation and calibration module and an asset management and evolution module. The user mental model comprises a dynamic portrait, interactive memory and a situation state. According to the large language model creation system for personalized content generation, by carrying a dynamic portrait and a user mental model module and combining interactive memory and situational state perception ability, demand changes and preference characteristics of a user in different creation scenes can be captured in real time, accurate understanding of user intentions is realized, and user experience is improved. The generated content better meets the personalized requirements of the user, and the problem that a traditional system is difficult to adapt to the dynamic requirements of the user is solved.

The invention discloses an intelligent compiling system and method for a technical publication maintenance program, and aims to compile technical publications and formulate corresponding templates according to different types of data modules, so that a first draft of the data modules is quickly compiled according to the selected specific type of data module templates. Meanwhile, a digital model library is established for parts and tools used in the data module maintenance step, corresponding names or part numbers can be backfilled into a first draft of the data module by calling a part digital model and a tool digital model in the model library, and a data module process draft is formed. And then, an intelligent simulation verification function is introduced to perform simulation verification on the data module process draft, so that interference risks are found in time, and synchronous verification of data module writing is realized.

[Problem] To provide a system capable of automatically creating a scenario (script) related to a presentation. [Solution] A scenario creation system according to the present invention includes a speech analysis unit 3 for analyzing speech, a presentation material related information storage unit 5 for storing information related to presentation material, a keyword storage unit 7, a key phrase storage unit 9, a presentation evaluation unit 11, and a scenario creation unit 13. The presentation evaluation unit 11: finds one or a plurality of keywords related to the presentation material on the basis of a plurality of presentations related to the presentation material, updates one or a plurality of the keywords stored in the keyword storage unit 7, and stores the updated keywords in the keyword storage unit 7; finds one or a plurality of key phrases related to the presentation material, updates one or a plurality of the key phrases stored in the key phrase storage unit 9, and stores the updated key phrases in the key phrase storage unit 9; and selects a presentation out of the plurality of presentations that has a greater count of one or both of the updated keywords and the updated key phrases, as a presentation that is highly evaluated. The scenario creation unit 13 creates a scenario related to the presentation material on the basis of the presentation that is highly evaluated.

A media creation system is provided for creating photographs and videos that include assets sourced from different geographic locations. The media creation system may perform parsing media, transposition the media, and / or perform additional modifications to the media. A method for creating photographs, videos, and live streams of one or more assets sourced from different geographic locations using the audiovisual media composition system is also provided. Communication, chat, and rating features are also provided.

A system and method for multi-media instruction authoring is disclosed. The multi-media instruction authoring system and method provide a unified and efficient system that supports the simultaneous creation of instructional media in AR, VR, and video-based media formats by subject matter experts. The multi-media instruction authoring system and method require only a single demonstration of the task by the subject matter expert and does not require any technical expertise of the subject matter expert. The multi-media instruction authoring system and method incorporate a 3D editing interface for free hand, in-headset interaction to create 2D videos from 3D recordings, by exploring novel virtual camera interactions.

The present disclosure relates to a method and apparatus for a metaverse performance contents authoring system. A method according to an embodiment of the present disclosure may comprise generating one or more assets related to performance authoring on a metaverse-based platform; and registering the generated one or more assets in a management server linked with the metaverse-based performance authoring system. The one or more assets may be shared on the metaverse-based platform and applied to the performance authoring. The one or more assets may include at least one of the following assets. The following assets include performance prop assets related to objects, performance effect assets related to special effects, or performance environment assets related to an overall configuration used in a performance.

Aspects of the present disclosure relate to generating bridge artifacts for computing environments. Embodiments include receiving a natural language prompt that indicates a type of bridge artifact to create and a target computing environment. Embodiments further include determining data retrieval tools relevant to the natural language prompt. Embodiments further include invoking the one or more data retrieval tools, wherein the one or more data retrieval tools are configured to retrieve data that is relevant to the natural language prompt and that is associated with the target computing environment. Embodiments further include invoking a bridge artifact creation tool based on the natural language prompt and the data retrieved by the one or more data retrieval tools. Embodiments further include generating a bridge artifact of the type indicated in the natural language prompt.

The present application provides a kind of script outline creation system based on artificial intelligence, it includes: information identification module is through the preliminary analysis of the identification of the attribute of the information of the person, object and background in picture in convolutional neural network;Comprehensive analysis module is the in-depth analysis of the story type, main character and supporting actor and their interests of script outline;Result output module is through the word coding of the relevant information of picture analysis by recurrent neural network, then the relevant words are decoded and output script outline.The above-mentioned method applies artificial intelligence technology to the field of script outline creation, so as to assist the creator to create or provide them with inspiration.

To appropriately create a training content for a trainee.SOLUTION: A training content creation system 1 creates training content for a trainee who responds to a report. The training content creation system includes a learning objective storage unit 11 and a training content creation unit 17. The learning objective storage unit stores a plurality of learning objectives and training content generation requirements for each of the plurality of learning objectives. The training content creation unit creates training content including the training content generation requirements on the basis of a learning objective selected by a creator from among the plurality of learning objectives.SELECTED DRAWING: Figure 1

This invention discloses a standard digital writing system driven by online document collaborative editing, belonging to the field of computer software application technology. It includes: a document initialization module for obtaining the writing document; a collaborative session management module for acquiring document data and generating a collaborative session identifier by combining pre-acquired user data and a random entropy factor, constructing a permission context object; a permission management module for performing rule matching on the permission context object using a dynamic permission reasoning mechanism based on a preset rule set, controlling writing permissions and recording permission judgments for the writing document; and a collaborative editing management module for acquiring user collaborative writing operation data in real time, and performing collaborative operation broadcasting and operation merging processing using a dual-mode collaborative model to obtain the latest document view. This invention enables multiple users to simultaneously edit, proofread, and supplement the same standard document, significantly improving the collaborative efficiency and response speed of the standard writing process.

A multimedia template creating computer system having a digital video production software application residing thereon. A media library resides on a computing device. A server has a master database for holding a data model having a plurality of video recipients and a list of custom multimedia tags for each of the plurality of video recipients and a cloud storage container. A video rendering computer system has a media compression and encoding software application residing thereon. The server connects to the multimedia template creating computer system and the video rendering computer system over a network. A multimedia template is sent from the multimedia template creating computer system to the server over the network. The media compression and encoding software application accesses the media library and the master database to convert the multimedia template into a plurality of customized videos with each customized video having a unique identifier corresponding to one of the plurality of video recipients. The media compression and encoding software application sends the plurality of customized videos to the server for storage in the cloud storage container. The server distributes each of the plurality of customized videos from the cloud storage container.

This invention relates to the field of machine learning computing systems, and more particularly to a machine learning-based gamified creation system and method, including a sensor data acquisition module, a gamified data recognition module, a machine learning creation module, a game creation output module, and a real-time feedback optimization module. This invention generates personalized game characters based on gamified data, supports style transfer and detail enhancement, introduces network latency monitoring and device computing power margin assessment, dynamically adjusts creation parameters, reduces model resolution or enables local caching to ensure smooth creation, and improves the efficiency of virtual character gamification creation. It identifies highly popular public characters through traffic analysis, corrects output results using similarity coefficients to avoid overlap between characters and public characters, and improves the efficiency and effectiveness of virtual character gamification creation by forming a "data-creation-feedback" closed loop.

1. The name of the design product: pattern creation system graphical user interface (design module) for electronic equipment. 2. The use of the design product: the design product is used in the running program of the pattern creation system (design module), and the graphical user interface is used in an electronic device. 3. The design points of the design product: the content of the graphical user interface. 4. The picture or photo that best indicates the design points: front view. 5. The design product is a flat product, and the rear view, left view, right view, top view and bottom view are omitted. 6. The use of the graphical user interface: the design is based on a pattern creation system (design module) developed for an electronic device, and is used for the operation interface of the pattern creation system (design module). The human-computer interaction mode of the graphical user interface: (1) the front view is the main interface, and the front view clicks 【Sign Up】 to enter the interface change state diagram.