Abstract: A system and method are provided for predicting gift preferences using a person's social media data. For example, natural language processing, image recognition, and machine learning models can be used by a recommender system to generate personalized gift recommendations based on a person's behaviors and interests extracted from their social media activity. The recommender system can use a machine learning (ML) model for text-and image-based analysis to distill semantic content from social media data of the gift recipient, generating a profile from the semantic content. A prediction model predicts gift preferences based on the profile, and gift recommendations are made based on the gift preferences. The recommender system includes features to adhere to the user's data-privacy selections.

Abstract: A computing device may receive interaction data characterizing an interaction between a client device and a media element. The computing device may generate a training dataset using the interaction dataset and characteristics associated with the client device. A machine-learning model may execute using a feature vector derived from the training dataset. The machine-learning model defines a context associated with the interaction with the media element and generates an interaction response based on the context. The interaction response may be presented by the client device. Upon receiving subsequent interaction data associated with the interaction response may cause the machine-learning model to define a new context associated with the subsequent interaction data and the interaction response. The computing device may update the update the training dataset using the new context. The updated training dataset can cause a subsequent execution of the machine-learning model to generate modified media elements.

Abstract: A media generator may generate media based on a canon associated with a media asset in a style of the media asset. The media generator may receive an identification of a media asset representing a set of related media. The media generator may generate a training dataset based on the identification of the media asset. The training dataset may include a subset of the set of related media. The media generator may train a machine-learning model using the training dataset. The machine-learning model may be configured to generate media associated with the media asset. The media generator may then receive a request to generate media representing the media asset. The media generator may generate media by executing the machine-learning model based on the request. The media generator may facilitate a presentation of at least a portion of the media.

Abstract: Write protection can be provided in mixed-media datasets. Contextual details may be extracted from a set of media to form a mixed-media dataset. The mixed-media dataset may be used to train a machine-learning model. A request to modify the mixed-media dataset may be received causing the machine-learning model to determine if implementing the request to modify the mixed-media dataset will introduce conflict or a deviation from the current mixed-media dataset. Upon confirming that implementing the request will not introduce a conflict or deviate from the from the current mixed-media, the mixed-media dataset may be modified according to the request and the machine-learning model may be retrained using the modified mixed-media dataset.

Abstract: A system and method are provided for generating a moving picture from a graphic narrative. Pages of a graphic narrative (e.g., comic book) are partitioned into panels, which are segmented into image segmented elements and text elements. The segmented elements are applied to a machine learning (ML) method that labels/identifies the segmented elements. Prompts based on the labels are then applied to a second ML model that outputs a moving picture representing one or more of the panels. The prompts can include script information, such as a script, storyboard, or a scene (e.g., keyframes). Thus, the comic book is effectively a movie storyboard that is automatically converted into full-motion rendered graphics by treating each combination of text and graphics as a unique prompt for a generative ML model.

Abstract: A system and method are provided for automating the reformatting of graphic narratives (e.g., comic books, manga, etc.) to a digital format. An artificial intelligence (AI) based method identifies panels within the pages, and, based on the relative positions of the panels and the contextual content represented in segmented image and textual elements, the AI-based method predicts a narrative flow among the panels (and within some of the respective panels). Editors either approve or modify the predicted narrative flow. Using the narrative flow, a dynamic path is created to guide the reader's attention through the graphic narrative (e.g., using visual cues and/or an order in which the panels are displayed on a digital device (e.g., an e-reader). The narrative flow can also be used to make the reader's experience more engaging and immersive.

Abstract: Methods and systems are provided for automatic, adaptive navigation of digital comic book frames. A frame image of a comic book may include one or more discrete panels. The frame image can be parsed using a first machine-learning model to derive visual features associated with the frame image and a second machine-learning model to derive contextual information associated with words appearing in each panel. A frame configuration can be defined that defines a transition for navigating between a sequence of views of the frame image, where each view corresponds to a panel or a portion thereof.

Abstract: A system and method are provided for modifying a graphic narrative to feature select products/services. Panels of the graphic narrative are segmented into elements (e.g., using semantic segmentation models like Fully Convolutional Networks), which are then identified as backgrounds, foregrounds, text bubbles, objects, characters etc. (e.g., using artificial intelligence (AI) classifiers like K-means classifiers). The identified elements are compared to a product database to select products suitable to be promoted by modifying selected elements, resulting in a version of the graphic narrative having modified panels in which the selected element(s) are changed to feature the selected products. For example, generative AI methods can redraw image elements or redraft text to place the selected products within the context of the graphic narrative. Links or watermarks can be placed in the modified panels to provide users with access to interact with or purchase the promoted products.

Abstract: A system and method are provided for generating a costume corresponding to graphic narrative (e.g., based, in part, on costumes depicted in images of a digital graphic narrative). Panels of the digital graphic narrative are segmented into elements (e.g., using semantic segmentation models like Fully Convolutional Networks), and clothing elements are identified as outfits/costumes worn by the characters. Based on multiple viewing angles provided by a plurality of images, data such as color and texture of the outfits/costumes is extracted and a digital costume model is created. The digital costume model can include animated and real-life components for rendering realistic and animated representations of the digital costume model. The digital costume model can be customized, shared on social media, used to help render a virtual environment, and used to fabricate a physical costume.

Abstract: A method for using the screen names of users are used to appropriately tailor a service for the users. If the service is a restricted service, then the screen name is used as the basis for deciding whether access should be granted to ensure that access is granted to a limited set of users. Alternatively, if the service is comprised of several component sub-services, and some of those sub-services are restricted, then the screen name is used as the basis for deciding whether access should be granted to the relevant sub-service.

Abstract: A method for using the screen names of users are used to appropriately tailor a service for the users. If the service is a restricted service, then the screen name is used as the basis for deciding whether access should be granted to ensure that access is granted to a limited set of users. Alternatively, if the service is comprised of several component sub-services, and some of those sub-services are restricted, then the screen name is used as the basis for deciding whether access should be granted to the relevant sub-service.

Abstract: A method for using the screen names of users are used to appropriately tailor a service for the users. If the service is a restricted service, then the screen name is used as the basis for deciding whether access should be granted to ensure that access is granted to a limited set of users. Alternatively, if the service is comprised of several component sub-services, and some of those sub-services are restricted, then the screen name is used as the basis for deciding whether access should be granted to the relevant sub-service.

Abstract: A method and system for interactively responding to queries from a user sending messages through an instant messaging network. The query or request is interpreted and appropriate action is taken, such as accessing a local or remote data resource and generating an answer to the user's query. The answer is formatted as appropriate and returned to the user as an instant message or via another route specified by the user. A method and system of providing authenticated access to a given web page via instant messaging is also disclosed.

Abstract: A method for using the screen names of users are used to appropriately tailor a service for the users. If the service is a restricted service, then the screen name is used as the basis for deciding whether access should be granted to ensure that access is granted to a limited set of users. Alternatively, if the service is comprised of several component sub-services, and some of those sub-services are restricted, then the screen name is used as the basis for deciding whether access should be granted to the relevant sub-service.

Abstract: A method and system for interactively responding to queries from a remotely located user includes a computer server system configured to receiving an instant message query or request from the user over the Internet. The query or request is interpreted and appropriate action is taken, such as accessing a local or remote data resource and formulating an answer to the user's query. The answer is formatted as appropriate and returned to the user as an instant message or via another route specified by the user. A method and system of providing authenticated access to a given web page via instant messaging is also disclosed.

Abstract: A method and system for interactively responding to queries from a user sending messages through an instant messaging network. The query or request is interpreted and appropriate action is taken, such as accessing a local or remote data resource and generating an answer to the user's query. The answer is formatted as appropriate and returned to the user as an instant message or via another route specified by the user. A method and system of providing authenticated access to a given web page via instant messaging is also disclosed.