128 results about "Picture books" patented technology

The invention discloses a multi-style picture book generation method based on a diffusion model. The method comprises the following steps: S1, constructing a data set; s2, constructing a picture book generation model; the preprocessing module encodes the picture book image and the story text to obtain text embedding, role mask and role image; s3, importing a style reference image to a style consistency module, and obtaining style feature embedding; s4, importing text embedding, role masks and role images to a role consistency module, and obtaining role embedding and layout embedding; s5, importing the picture book image, performing style feature embedding, role embedding and layout embedding into a Unet module to perform picture book image noise prediction, and obtaining a predicted picture book image; and S6, constructing a loss function. According to the method, a diffusion model and an image style migration algorithm in deep learning are combined, a coherent picture book scene with various artistic styles can be generated according to the input reference image, and the method can be widely applied to the fields of animation production, image creative design, digital content generation and the like.

The invention discloses an AI-based child story picture book generation method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: generating a narrative framework through employing a BPOT bidirectional pre-training model, carrying out the filling optimization of detailed text paragraphs through combining reinforcement learning and semantic mutual information, extracting dynamic features based on DCNN and SENet, and generating a child story picture book. And an interactive dynamic effect sequence is generated in combination with the preprocessed corpus, and finally, typesetting is optimized through a Wasserstein distance and a variational auto-encoder to generate a child story picture book. By using a BPOT bidirectional pre-training model, reinforcement learning and semantic mutual information to optimize a narrative framework, semantic age suitability and educational target integrating degree are remarkably improved, a DCNN is combined with SENet to generate an age-suitable interaction dynamic effect, interaction trigger point design is fused, immersion and user participation degree of the picture book are improved, and it is ensured that the picture book integrally presents high-quality narrative consistency.

The invention belongs to the technical field of artificial intelligence content generation, and discloses an AI GC-based multi-modal picture book material fusion and dynamic presentation method. The method comprises the following specific steps: S1, creating a picture book; s2, illustration matching generation; s3, audio production and addition; s4, preliminarily fusing the materials; s5, interactive logic design; s6, embedding AR elements; and S7, carrying out personalized customization recommendation. According to the method, knowledge picture books are generated by means of AI GC, multi-mode and AR assistance are achieved, abstraction is converted into images, learning potential is stimulated, and knowledge construction, personalized customization, special effect matching, AR and expansion imagination are assisted; a warm bridge is built with the parent-child, the parent-child explores the world together, multiple modes are achieved, AR rich interaction is achieved, the parent-child distance is shortened, the barrier is eliminated, and the parent-child is warm and sweet in light.

The invention relates to the field of video generation, and discloses a cartoon video generation method, cartoon video generation equipment and a storage medium. The method comprises the steps of receiving a text making instruction; judging whether the text making instruction is an instruction for making a specified neural network or not; if yes, inputting the theme content setting, the story background setting and the role information setting into a preset AI text generation model to generate a story text; judging whether the story text limits the image to maintain the original text; when the story text is not limited, performing scene division and retouching processing on the story text to generate scene description; when the story text is limited, performing division processing on the original story text to generate scene description; performing drawing processing on the scene description to generate image data; dubbing the story text to generate dubbing data; and combining the dubbing data and the image data to generate an audio cartoon video. In the embodiment of the invention, the neural network is utilized to draw images and make dubbles for the story text, and the picture book cartoon video is efficiently generated at low cost.

The invention provides a cartoon generation method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical fields of artificial intelligence, large language models, natural language processing and the like. The specific implementation scheme is as follows: acquiring a plurality of target split scripts; in response to the cartoon generation request processing operation, sending a cartoon generation request carrying a plurality of target split scripts to the first electronic equipment; wherein the first electronic equipment is used for generating a target cartoon picture book based on a plurality of target split scripts carried in a cartoon generation request, and dubbing the target cartoon picture book to obtain a first target voiced cartoon; and receiving and playing the first target audio cartoon.

To provide a computer program, an information processing device, and an information processing method capable of easily creating a storyboard.SOLUTION: A computer program causes a computer with a built-in touch panel display to perform processing for: arranging and displaying a plurality of objects corresponding to each of a plurality of frames constituting a storyboard in chronological order along with thumbnails of images drawn for each frame, on the display; accepting a selection of an object corresponding to a frame to be edited from among the plurality of objects displayed, on the display; displaying an editing screen of a frame corresponding to the selected object in the same screen together with the plurality of objects; accepting drawing edits to the frame on the editing screen; displaying a play button, which plays the plurality of frames as a video in accordance with the set timeline, in the same screen; and playing the plurality of frames as a video when the play button is selected on the display.SELECTED DRAWING: Figure 5

The invention relates to a children digital picture book reading system and method based on immersive interaction, and the system comprises a projection module, an interaction module, a voice playing module, a voice conversation module, a video record synthesis module, an intelligent evaluation module, and a digital resource module. The original picture book content of the digital resource module is projected to the wall surface and the ground through the projection module to create an immersive digital picture book reading scene; the child interacts with the original picture book content of the digital resource module in real time through the interaction module, the voice playing module and the voice dialogue module; the video recording and synthesizing module is used for creating an immersive story telling scene for children and recording story telling audios and videos of the children; and the intelligent evaluation module receives the audio and the video transmitted by the video record synthesis module, and outputs an evaluation report through intelligent analysis. The problems that in the prior art, a game form and an interaction form are single, an immersive reading scene and an intelligent evaluation system are lacked, and continuous reading interest and language ability development of children are not facilitated are solved.

The application provides a multimedia story generation method, a control device, an electronic device and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring characteristic data and story text of family members, wherein the characteristic data comprises appearance characteristic data and voice characteristic data; generating character illustrations and character voices corresponding to the story text based on the characteristic data; and generating a multimedia picture book based on the character illustrations and the character voices. The multimedia story generation method provided by the application generates character illustrations and character voices corresponding to the story text based on the characteristic data of the family members, and then generates a multimedia picture book based on the character illustrations and the character voices. The generated multimedia picture book has strong personalization and exclusivity. Children no longer see other people's stories, but see stories that may occur to themselves and their families, thereby improving the interest and sense of immersion of children.

1. Name of this design product: Intangible Cultural Heritage Picture Book (Lele's Lacquer Fan). 2. Purpose of this design: For children's reading, to help children understand knowledge related to intangible cultural heritage. 3. The key design features of this product are the combination of pattern and color. 4. Images or photographs that best illustrate the design's key points: Reference images. 5. The design for which protection is sought includes color. 6. The bottom view is the same as the top view, so the bottom view is omitted.

1. Name of the product in this design: Picture Book Shelf. 2. Application of this design: This design is intended for use as a picture book shelf. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

To provide a system for offering digital picture books tailored to children's interests and detecting emotional or physical problems of children.SOLUTION: A system includes means for providing picture books tailored to children's interests through a digital picture book provision method linked to a dialogue system; means for asking the children questions about emotions and physical conditions within the picture books to detect potential problems; and means for collecting information about the home environment through dialogue with the dialogue system.SELECTED DRAWING: Figure 1

The invention relates to a self-adaptive control method and device for a vehicle-mounted entertainment information system, and belongs to the technical field of vehicle control, and the self-adaptive control method for the vehicle-mounted entertainment information system comprises the steps: obtaining the video stream data of an area where a target child is located, determining the metadata of a target picture book based on the video stream data, the metadata comprises a picture book theme, a picture book name and a picture book tone, the efficiency value is used for representing the positive degree or negative degree of emotion, the wake-up degree is used for representing the intense degree of emotion, and the concentration degree is used for representing the cognitive input degree; based on the metadata of the target picture book, determining a first control instruction used for controlling a vehicle-mounted audio system and a second control instruction used for controlling a vehicle-mounted atmosphere lamp system; and adjusting the first control instruction and the second control instruction based on the efficiency value, the wake-up degree and the concentration degree of the target child. According to the invention, the riding experience and riding safety of children are effectively improved.

1. The name of the design product: picture book rack (file folder). 2. The use of the design product: for placing picture books or file folders. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The system according to this embodiment aims to recommend picture books that will interest children and to ensure that parents can have reading time with their children even when they are busy. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a recommendation unit, a generation unit, a narration unit, and a notification unit. The reception unit receives information about the child. The analysis unit analyzes the information entered by the reception unit. The recommendation unit recommends picture books based on the information analyzed by the analysis unit. The generation unit generates the content of the picture books recommended by the recommendation unit. The narration unit reads aloud the content of the picture books generated by the generation unit. The notification unit sends a notification to the child at a designated time to inform them of reading time.

The invention provides an intelligent interaction method and platform for bilingual non-abandoned voiced picture book creation, and relates to the technical field of creation interaction, and the method comprises the steps: 101, obtaining the creation content and creation state of a bilingual non-abandoned voiced picture book created by a user; 102, based on the creation content, determining creation optimization suggestions; 103, based on the creation state, determining the upper limit of the single-time assistance force; 104, performing successive creation optimization assistance on the user under the constraint of the upper limit of the single assistance force based on creation optimization suggestions; wherein the user feedback after each assistance is used for updating the creation state, so that a new single assistance force upper limit for the next assistance is determined based on the updated creation state. According to the method, the creation content and the creation state of the user are obtained, the experience of the reader is predicted, optimization suggestions are provided, and meanwhile, the auxiliary strength is dynamically adjusted according to the current cognitive load, willingness and the like of the user, so that the creation process is accurate, efficient and personalized.

1. The name of the product of this design: picture book stand. 2. Purpose of this design product: used to display picture books and books. 3. The design key point of this appearance design product lies in the shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The present application belongs to the technical field of teaching aids for teenagers, and relates to a sound picture matched with English teaching materials, comprising a picture main body, a plurality of function keys, a loudspeaker and a printed circuit layer arranged in the picture main body. The content of the picture layer is matched with the English teaching materials, and the function keys include language switching keys, cycle keys, point-reading keys, test keys and dictation keys. The present application can make the content of classroom learning appear in front of the user frequently and at any time. The reproduction of the sound of English words can be realized through the cycle playing function and the point-reading function, the reproduction of the meaning can be realized through the picture of the picture layer and the switching of the language to the English-Chinese translation mode, and the reproduction of the shape can be realized through the word of the picture layer. The test keys and the dictation keys arranged in the present application make the present application have all the functions of English listening, speaking, reading and writing, and the user can check his own mastery at any time and find the missing parts in time.

We provide the system. [Solution] A means of inputting a picture drawn by a child, A means for analyzing the aforementioned drawing and identifying the main objects, A means for automatically generating a story based on the analyzed object, A means for customizing the generated story based on the child's age, interests, and strengths, A means for generating a picture book containing the customized story, A system including means for providing the generated picture books online.

1. Name of the Design Product: Picture Book Rack (Dinosaur). 2. Use of the Design Product: For placing children's picture books. 3. Design Key Points of the Design Product: Lies in the shape. 4. Picture or Photograph that Best Illustrates the Design Key Points: Perspective view.

The utility model discloses a self-positioning child picture album edge cutting structure which comprises a base and a transmission assembly fixedly arranged on the base, an edge fixing plate is installed on the base in a sliding mode, a limiting block is fixedly installed on the edge fixing plate, a threaded sleeve fixing plate assembly is fixedly installed on the limiting block, meanwhile, a flow guide plate is fixedly installed on the edge fixing plate, and the transmission assembly is fixedly arranged on the base. A first bidirectional threaded rod is arranged on the threaded sleeve fixing plate assembly, the first bidirectional threaded rod is rotationally installed on the base, and a second bidirectional threaded rod is arranged on the threaded sleeve fixing plate assembly. According to the self-positioning child picture album edge cutting structure, the positions of the two sets of edge fixing plates are in butt joint through the edge fixing plates, the threaded sleeve fixing plate assemblies and the first two-way threaded rods for adjustment, so that the two sets of edge fixing plates can move on the base, and the distance between the two sets of edge fixing plates is adjusted to be suitable for the size of a child picture album needing to be machined; and the two sets of edge fixing plates can position the side faces of the child picture album needing to be processed.

1. Name of this design product: Picture Book (The Caterpillar Who Loves Playing with a Ball). 2. Purpose of this design product: This design product is used for children's early education and entertainment. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The invention provides a picture book generation method, system and device and a medium, and belongs to the technical field of artificial intelligence. The method comprises the steps that story conception information input by a user is acquired; inputting the story conception information into a content planning model to generate a standardized creation instruction; inputting the role description and the scene description corresponding to each sub-mirror into a multi-modal content generator, and generating an initial role image and an initial scene background corresponding to each sub-mirror; inputting the split script corresponding to each split into the content planning model, and generating an initial narrative text corresponding to the split; based on the role description, performing optimization processing according to the initial role image and the initial scene background, and generating a visual fusion coordination foreground image; and based on the image-text correspondence, generating a target picture book file according to the coordinated foreground image, the initial scene background and the initial narrative text corresponding to each sub-mirror. According to the method, the personalized picture book with consistent picture and text styles and high quality is automatically and efficiently generated, and the technical threshold and time cost of picture book creation are reduced.

An object of a system according to an embodiment is to enable a user to create an original novel or picture book only by selecting an option.SOLUTION: A system according to an embodiment includes an option presentation section, a story generation section, a character setting section, a scene drawing section, and a story output section. The option presentation unit presents a plurality of options to a user. The story generation unit generates a story on the basis of the options presented by the option presentation unit. The character setting unit sets a character on the basis of the story generated by the story generation unit. The scene rendering unit renders a scene based on the character set by the character setting unit. The story output section outputs a story including the scene rendered by the scene rendering section.SELECTED DRAWING: Figure 1

The application discloses a continuous children's picture book image generation method based on dynamic memory enhancement. The application firstly performs multi-stage cascading cleaning on original children's picture book images to construct a high-quality image-text pair dataset; inserts a consistency enhancement low-rank adapter into a pre-trained text conditional image generation base model to construct a dual-source dynamic feature memory bank; performs frequency domain decoupling processing on latent feature maps corresponding to reference images and historical images, extracts local edge, texture details and local structure information, and combines a time sequence attenuation bias to perform memory enhancement attention fusion; constructs an automatic preference sample based on a multi-modal visual evaluation model, trains a preference alignment low-rank adapter, and obtains a continuous picture book image generation model based on preference alignment. The application can improve the role appearance consistency, page coherence and visual structure rationality in the continuous picture book image generation process, and reduce the occurrence probability of role drift, style mutation and local structure anomaly in long sequence generation.

To provide a system.SOLUTION: A system is provided, comprising means for automatically generating a picture book that provides a different story every time the book is read, means for specifying a genre and age, and means for outputting a picture book in line with the specified genre and age.SELECTED DRAWING: Figure 1