Disney Patents
The Walt Disney Company is an entertainment company focused on media networks, parks and resorts, studio entertainment, consumer products and interactive games. The company's media holdings include ESPN (partial ownership), the Disney channels, ABC Family and A&E Television Networks (partial ownership). The company also operates Walt Disney World, Disneyland, Aulani, the Disney Cruise Line, and has partial ownership interests in Disneyland Paris, Hong Kong Disneyland, and Shanghai Disney. Tokyo Disneyland is operated by an independent company that licenses Disney intellectual property and pays royalties based on revenues. Disney also produces live-action and animated motion pictures, direct-to-video content, musical recordings and live stage plays, and distributes Walt Disney Pictures, Pixar, Marvel, Lucasfilm and Touchstone films.
Disney Patents by Type- Disney Patents Granted: Disney patents that have been granted by the United States Patent and Trademark Office (USPTO).
- Disney Patent Applications: Disney patent applications that are pending before the United States Patent and Trademark Office (USPTO).
-
Publication number: 20260267708Abstract: In some embodiments, a system receives usage data for content delivered by multiple content delivery network (CDN) entities during a last time interval. This usage data is based on delivering the content from servicing first requests. The system calculates ideal distribution weights from this usage data to allocate second requests to the CDN entities in a next time interval. It also calculates effective distribution weights from the usage data to allocate the second requests, where these effective weights are further based on a current network condition. A selection parameter is then generated based on correcting the effective distribution weights to be closer to the ideal distribution weights for the next time interval. The system outputs this selection parameter and uses it to select a particular CDN entity for a second request. This selection is performed according to a distribution for the next time interval that is closer to the ideal distribution than it is to the effective distribution.Type: ApplicationFiled: April 24, 2026Publication date: September 10, 2026Applicant: Disney Enterprises, Inc.Inventors: Thomas Howe, Mark Kegel, Edward Russell, Joseph Higgins, Daniel Spiewak, Matthias Sainz
-
Publication number: 20260268656Abstract: In some embodiments, a method receives an image to analyze for artifacts. Texture information that characterizes texture in the image is determined. The method merges the texture information with the image. The texture information is used to focus an analysis of artifacts more in a first region of the image and focus less in a second region of the image. The method outputs a score based on the processing of the image that assesses the artifacts in the image.Type: ApplicationFiled: April 24, 2026Publication date: September 10, 2026Applicants: Disney Enterprises, Inc., Beijing YoJaJa Software Technology Development Co., Ltd.Inventors: Xuchang Huangfu, Yuanyi Xue, Wenhao Zhang, Yang Zhang, Chen Liu, Xuewei Meng
-
Patent number: 12732654Abstract: The present disclosure provides for systems and methods for customizing channel programming. The disclosed methods and systems utilize various data inputs, including affirmative user inputs, non-affirmative user characteristics, environmental data and/or temporal data to customize channel programming for a particular user or group of users. In a further aspect, the disclosed methods and systems provide for various social sharing of viewing experiences and channels by coordinating, broadcasting and/or sharing channels or viewing schedules with other users.Type: GrantFiled: April 9, 2024Date of Patent: September 8, 2026Assignee: Disney Enterprises, Inc.Inventors: Josiah Eatedali, Mark Arana
-
Patent number: 12731056Abstract: A system includes a computing platform having a hardware processor and a memory storing software code, a memory data structure storing memory features for an artificial intelligence interactive character (AIIC), and a trained machine learning (ML) model. The software code is executed to elicit, using the AIIC, a reminiscence from a user, predict, using the trained ML model and the reminiscence, one or more user memory feature(s) of the reminiscence, identify, using the memory data structure, one or more of the memory features for the AIIC as corresponding to the user memory feature(s), and determine, using the user memory feature(s), a mood modifier for a creative composition. The software code is further executed to produce, based on the mood modifier and the corresponding one or more of the plurality of memory features for the AIIC, the creative composition, and provide the creative composition to the AIIC.Type: GrantFiled: March 9, 2023Date of Patent: September 8, 2026Assignee: Disney Enterprises, Inc.Inventors: James R. Kennedy, Douglas A. Fidaleo, Anthony P. Dohi, Komath Naveen Kumar, Prutsdom Jiarathanakul, Benjamin Hwang, Michael Barron
-
Patent number: 12731044Abstract: A system includes a computing platform having a hardware processor and a memory storing software code, a memory data structure storing memory features for an artificial intelligence interactive character (AIIC), and a trained machine learning (ML) model. The hardware processor executes the software code to receive interaction data describing a communication by a user with the AIIC, predict, using the trained ML model and the interaction data, at least one user memory feature(s) of the communication, and identify, using the memory data structure, one or more of the memory features for the AIIC as corresponding to the user memory feature(s). The software code also determines, using the user memory feature(s) and the corresponding one or more of the memory features for the AIIC, an interactive communication for execution by the AIIC in response to the communication by the user; and outputs the interactive communication to the AIIC.Type: GrantFiled: March 9, 2023Date of Patent: September 8, 2026Assignee: Disney Enterprises, Inc.Inventors: Douglas A. Fidaleo, James R. Kennedy, Michael Barron
-
Patent number: 12731567Abstract: A system for simulating operation of a stringed instrument using a combination of water and light steams. The system includes a nozzle configured for outputting a falling laminar water stream. The system includes a light transmitter configured to inject light into a first end of the water stream and a light receiver configured to receive the light injected into the water stream and, in response, generate a signal. The system includes a controller configured for processing the signal and, in response to a lack of the signal, for operating an audio system to play a musical note or audio file. The system may include an optical fiber with a first end proximate to the nozzle oriented to receive the light injected into the water stream at the second end of the water stream, and the light receiver can be a photodetector coupled to the second end of the optical fiber.Type: GrantFiled: March 29, 2023Date of Patent: September 8, 2026Assignee: Disney Enterprises, Inc.Inventors: Lanny S. Smoot, Robert J. Bristow, David James Myers, Gary A. Powell, Charles Jacob Sedor, Keith Jeffrey Mazzella, Steven I. Smith
-
Publication number: 20260261722Abstract: In some embodiments, a method receives a plurality of metric values for quality of service based on delivering content in a content delivery system. Respective metric values into a fuzzy value in a plurality of possible fuzzy values where a plurality of fuzzy values is determined. The method determines a plurality of fuzzy rules where a fuzzy rule is associated with a fuzzy value. Respective conditions for fuzzy rules are applied to the plurality of fuzzy values to determine fuzzy rules that have conditions met. A fuzzy rule applies when respective conditions for the fuzzy rule are met by one or more fuzzy values in the plurality of fuzzy values. A fuzzy output is determined from fuzzy values that are associated with the fuzzy rules that have conditions met. A unified quality score is calculated from the fuzzy output. The method outputs the unified quality score.Type: ApplicationFiled: February 28, 2025Publication date: September 3, 2026Applicants: Disney Enterprises, Inc., HULU, LLC, Beijing YoJaJa Software Technology Development Co., Ltd.Inventors: Si Chen, Wenhao Zhang, Tongyu Dai, Thomas Howe, Nicholas Brookins
-
Patent number: 12725289Abstract: One embodiment of the present invention sets forth a technique for generating a pose estimation model. The technique includes generating one or more trained components included in the pose estimation model based on a first set of training images and a first set of labeled poses associated with the first set of training images, wherein each labeled pose includes a first set of positions on a left side of an object and a second set of positions on a right side of the object. The technique also includes training the pose estimation model based on a set of reconstructions of a second set of training images, wherein the set of reconstructions is generated by the pose estimation model from a set of predicted poses outputted by the one or more trained components.Type: GrantFiled: May 19, 2022Date of Patent: September 1, 2026Assignees: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Martin Guay, Dominik Tobias Borer, Jakob Joachim Buhmann
-
Patent number: 12725320Abstract: Techniques for generating modified images using content information and style information are disclosed. First image data comprising image content information is received, and a content encoder generates a first embedding by extracting the image content information from the first image data. A second embedding generated by a style encoder is received, the second embedding comprising style information of second image data. The style information comprises color information and texture information. A decoder generates a modified image using the first embedding and the second embedding, the modified image comprising the image content information of the first image data and the style information of the second image data.Type: GrantFiled: January 29, 2024Date of Patent: September 1, 2026Assignee: DISNEY ENTERPRISES, INC.Inventors: Pablo Pernias Pascual de Pobil, Santiago Iglesias Navarro, Robert B. Moore, David N. Juboor
-
Patent number: 12725319Abstract: A system includes an augmented reality (AR) device having a first display, processing hardware, and a memory storing software code. The processing hardware is configured to execute the software code to monitor media content including a sequence of moving images displayed on a second display separate from the AR device and controlled by a media player device, detect, based on monitoring the media content, an image in the sequence of moving images for enhancement by one or more AR effects. The processing hardware further executes the software code to render the one or more AR effects on the first display, and transmit, contemporaneously with rendering the one or more AR effects on the first display, a signal configured to pause or loop the playing of the media content on the second display.Type: GrantFiled: September 10, 2024Date of Patent: September 1, 2026Assignee: Disney Enterprises, Inc.Inventors: Evan M. Goldberg, Alexandra Christiansen, Jackson Aaron Rogow, James Voris, Alice Jane Taylor
-
Patent number: 12724942Abstract: In some embodiments, a method receives a first value for a feature. The first value is associated with an entity. A cohort is determined for the entity where a cohort is associated with a dimension, and the entity is associated with a dimension value for the dimension. The method determines a normalization value for the cohort based on the dimension value for the entity. The normalization value is generated based on second values at the dimension value for the feature, and the second values are associated with entities in the cohort. A cohort-agnostic feature value is generated based on the first value and the normalization value. The cohort-agnostic feature value is input into a model to generate a prediction for the entity.Type: GrantFiled: April 7, 2023Date of Patent: September 1, 2026Assignee: Disney Enterprises, Inc.Inventor: Fabian Gallusser
-
Patent number: 12725039Abstract: In some embodiments, a method receives input data to calculate an effect of a variable on a group for a plurality of methods. Methods in the plurality of methods calculate the effect of the variable for the input data using different logic. A plurality of sub-weights for methods in the plurality of methods are generated. The sub-weights are generated based on a balance metric, a dissimilarity metric, and a reliability metric. The method combines the plurality of sub-weights for methods in the plurality of methods to generate a final weight for the methods. The respective final weight is applied to an intermediate result from a respective method in the plurality of methods to generate a weighted intermediate result for the method. The method combines weighted intermediate results for the plurality of methods to generate a final result for the effect of the variable.Type: GrantFiled: July 24, 2023Date of Patent: September 1, 2026Assignee: Disney Enterprises, Inc.Inventors: Fabian Gallusser, Corey Katz, Huancen Liu
-
Publication number: 20260253579Abstract: In some embodiments, a method inputs a first speech sample into a prosody encoder, wherein the prosody encoder is trained as part of a text-to-speech model. A second speech sample is input into the prosody encoder. The prosody encoder generates a first representation of the first speech sample and a second representation of the second speech sample. The method compares the first representation and the second representation to determine a metric value and determines an action to perform based on the metric value.Type: ApplicationFiled: February 24, 2025Publication date: August 27, 2026Applicant: Disney Enterprises, Inc.Inventors: Komath Naveen Kumar, Erika Doggett, SeYun UM
-
Patent number: 12715114Abstract: An encoder is trained to generate latent representations of kinematic motion from motion data and a control policy is trained to generate dynamics informed output for a robotic system based on the latent representations of kinematic motion. The encoder and the control policy are deployed in the robotic system to generate the dynamics informed output based on the motion data.Type: GrantFiled: May 10, 2024Date of Patent: August 25, 2026Assignee: Disney Enterprises, Inc.Inventors: Moritz Niklaus Bächer, Agon Serifi, Ruben Jelle Grandia, Lars Espen Knoop
-
Patent number: 12718450Abstract: One embodiment of the present invention sets forth a technique for training a neural motion controller. The technique includes determining a first set of features associated with a first control signal for a virtual character. The technique also includes matching the first set of features to a first sequence of motions included in a plurality of sequences of motions. The technique further includes training the neural motion controller based on one or more motions included in the first sequence of motions and the first control signal.Type: GrantFiled: February 21, 2023Date of Patent: August 25, 2026Assignees: Disney Enterprises, INC., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Martin Guay, Dhruv Agrawal, Dominik Tobias Borer, Jakob Joachim Buhmann, Mattia Gustavo Bruno Paolo Ryffel, Robert Walker Sumner
-
Patent number: 12718481Abstract: One embodiment of the present invention sets forth a technique for synthesizing an interaction with a virtual character. The technique includes matching a first message from a user to a first set of memories associated with the virtual character and determining at least a portion of the first set of memories based on a plurality of factors associated with the first set of memories. The technique also includes inputting a first prompt that includes (i) one or more instructions associated with the virtual character, (ii) the at least a portion of the first set of memories, and (iii) the first message into a machine learning model. The technique further includes generating, via execution of the machine learning model based on the first prompt, a first response by the virtual character to the first message, and causing the first response to be outputted to the user.Type: GrantFiled: May 22, 2024Date of Patent: August 25, 2026Assignees: Disney Enterprises, INC., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Erika Varis Doggett, Fabian Jonas Landwehr, Romann Matthew Weber
-
Patent number: 12715138Abstract: A system for performing surface maintenance based on one or more detected environmental factors for a surface monitored for maintenance. The system includes a surface monitoring assembly that monitors a surface for one or more environmental factors, such as a traffic pattern in a cleaning application, and the assembly may utilize one or more video cameras focused on a monitored surface along with video analytics software to process captured video to identify an environmental factor, such as heavy traffic, a spill, or the like. When an environmental factor is detected, the assembly passes this data to a maintenance control routine that processes the data to determine whether to vary the operations of an automated robot maintenance system provided in the system. The data can be used to define or modify a location, a time, and/or a parameter of a maintenance task or function (e.g., vacuuming versus wet mopping).Type: GrantFiled: October 11, 2022Date of Patent: August 25, 2026Assignee: Disney Enterprises, Inc.Inventor: Eric J. Moy
-
Patent number: 12717355Abstract: A ride system may include a track including uneven terrain, a plurality of ride vehicles positioned on the track, and a fleet controller (e.g., a wayside controller). The ride vehicles may be adapted to traverse the uneven terrain, such as along a respective chosen path of multiple paths based on respective user control. The user control may be configured to select the chosen path and adjust a speed and a direction of the ride vehicle along the chosen path. The fleet controller may provide an override control of the ride vehicles along the track based on the chosen path, the speed, and the direction of the ride vehicles. The fleet controller may define a default position and pacing for the ride vehicles. The user control may be configured to adjust the position and pacing of an associated ride vehicle from the default position and pacing, respectively.Type: GrantFiled: September 11, 2024Date of Patent: August 25, 2026Assignee: Disney Enterprises, Inc.Inventors: Derek Lee Howard, Edward Allen Nemeth
-
Patent number: 12711575Abstract: Techniques are disclosed for resampling images. In some embodiments, a resampling model includes (1) one or more feature extraction layers that extract features from an input image and a degradation map; (2) one or more resampling layers that generate warped features from the extracted features and a warp grid; and (3) one or more prediction layers that generate, from the warped features, an output image or resampling kernels that can be applied to the input image to generate an output image. In some embodiments, the resampling model can be trained by applying degradation maps to output images in a training data set to generate corresponding input images, and training the resampling model using the input images and the corresponding output images.Type: GrantFiled: May 19, 2023Date of Patent: August 18, 2026Assignees: Disney Enterprises, INC., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Abdelaziz Djelouah, Michael Yves Bernasconi, Farnood Salehi, Christopher Richard Schroers
-
Patent number: 12711439Abstract: A system includes a computing platform having processing hardware and a memory storing software code. The processing hardware executes the software code to receive content data identifying new content and a future release date for the new content, provide a prediction identifying a subset of the users likely to request the new content upon its release, and prioritize, based on the prediction, a schedule for pre-provisioning authentication data for accessing the new content to the subset of users. The processing hardware further executes the software code to pre-provision, using the prioritized schedule, the authentication data to the subset of users prior to the release of the new content.Type: GrantFiled: December 14, 2021Date of Patent: August 18, 2026Assignee: Disney Enterprises, Inc.Inventors: Hui Li, Chen Hu Wu
-
Patent number: 12711449Abstract: According to one implementation, a tagging performance evaluation system includes a computing platform having a hardware processor and a memory storing a software code. The hardware processor is configured to execute the software code to receive annotation data identifying content, annotation tags applied to the content, and one or more correction(s) to the annotation tags, to perform, using the annotation data, at least one of an evaluation of a tagging process resulting in application of the annotation tags to the content or an assessment of a correction process resulting in the correction(s), and to identify, based on the at least one of the evaluation or the assessment, one or more parameters for improving at least one of the tagging process or the correction process. At least one of the evaluation or the assessment is performed using a machine learning model of the tagging performance evaluation system.Type: GrantFiled: February 3, 2021Date of Patent: August 18, 2026Assignee: Disney Enterprises, Inc.Inventors: Miquel Angel Farre Guiu, Marcel Porta Valles, Marc Junyent Martin, Jordi Badia Pujol, Melina Ovanessian
-
Publication number: 20260222638Abstract: In some embodiments, a method determines an instance of content to be delivered to a client device. The instance of content includes a plurality of segments that is associated with a plurality of profiles. A target metric and a bandwidth distribution are determined. The method determines a performance of the target metric based on the bandwidth distribution and a model for selecting a top profile for the plurality of segments. The model includes a set of conditions. The method solves the model based on the performance of the target metric where solving the model provides a solution that meets the set of conditions and outputs the top profile for each segment. The top profile for each segment for delivery to the client device. The top profile for each segment is used to remove profiles when requesting segments in the plurality of segments during playback of the instance of content.Type: ApplicationFiled: January 28, 2025Publication date: July 30, 2026Applicants: Disney Enterprises, Inc., Beijing YoJaJa Software Technology Development Co., Ltd.Inventors: Lemei Huang, Tongyu Dai, Wenhao Zhang, Si Chen, Thomas Howe
-
Publication number: 20260219564Abstract: A system includes a light source configured to emit light; a lens assembly including an optical component and at least one lens; a fiber optic cable configured to transmit the light emitted from the light source to the lens assembly; an image forming layer; and a projection medium. The projection medium includes ulexite, selenite, or a combination thereof. The image forming layer is provided between the lens assembly and the projection medium.Type: ApplicationFiled: January 25, 2025Publication date: July 30, 2026Applicant: Disney Enterprises, Inc.Inventors: Jason William MONAHAN, Daniel Mark JOSEPH, Jessica Anne KLOUDA, Charles Jacob SEDOR
-
Patent number: 12694401Abstract: Systems and methods to produce a physical article that provides admission authorization to an event and correlated digital asset from a temporary wallet are disclosed. Exemplary implementations may: establish one or more temporary wallets; effectuate a smart contract that causes the temporary wallets to hold digital assets, where individual digital assets are correlated with event information; generate one or more wallet machine-readable mediums that represent the temporary wallets; generate one or more asset machine-readable mediums that represent the digital assets; cause an output device to output the wallet machine-readable mediums and the wallet machine-readable mediums on physical articles that provide admission authorizations events or locations; upon user devices scanning the wallet machine-readable mediums, the users may be enabled to establish digital wallets or access digital wallets such that the digital asset is transferred from the temporary wallets to the digital wallets.Type: GrantFiled: June 20, 2023Date of Patent: July 28, 2026Assignee: Disney Enterprises, Inc.Inventor: Jokton Mishael Strealy
-
Patent number: 12695879Abstract: In some embodiments, a method receives source content. A pre-processor pre-processes the source content to output pre-processed source content. The pre-processor includes a first parameter that is trained based on a differentiable proxy codec, and a calculated adjustment to a second parameter of the differentiable proxy codec is used to train the first parameter of the pre-processor. The method encodes the pre-processed source content into compressed pre-processed source content. The compressed pre-processed source content is output.Type: GrantFiled: March 21, 2025Date of Patent: July 28, 2026Assignees: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Yang Zhang, Mingyang Song, Christopher Richard Schroers, Tunc Ozan Aydin, Yuanyi Xue, Scott Labrozzi
-
Publication number: 20260212267Abstract: Methods and systems for performing novel view synthesis in addition to various image-to-image diffusion processes using machine learning models are disclosed. These include methods for performing inpainting-based novel view synthesis using depth maps and conditional models, video novel view synthesis using texture map inpainting, spatially consistent inpainting-based novel view synthesis using video diffusion models, and high-fidelity image-to-image diffusion using a texture conditional model. Further, methods for generating training data that can be used to train machine learning models to perform novel view synthesis are disclosed. These include symmetry exploiting methods of training data generation and methods using training pair alignment and splatting error simulations.Type: ApplicationFiled: July 15, 2025Publication date: July 23, 2026Applicants: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Xiang Zhang, Longxiang Jiao, Yang Zhang, Christopher Richard Schroers, Lukas Francesco Mehl
-
Publication number: 20260212560Abstract: Methods and systems for performing novel view synthesis in addition to various image-to-image diffusion processes using machine learning models are disclosed. These include methods for performing inpainting-based novel view synthesis using depth maps and conditional models, video novel view synthesis using texture map inpainting, spatially consistent inpainting-based novel view synthesis using video diffusion models, and high-fidelity image-to-image diffusion using a texture conditional model. Further, methods for generating training data that can be used to train machine learning models to perform novel view synthesis are disclosed. These include symmetry exploiting methods of training data generation and methods using training pair alignment and splatting error simulations.Type: ApplicationFiled: July 15, 2025Publication date: July 23, 2026Applicants: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Yang Zhang, Christopher Richard Schroers, Xiang Zhang, Lukas Francesco Mehl, Longxiang Jiao
-
Publication number: 20260212590Abstract: Methods and systems for performing novel view synthesis in addition to various image-to-image diffusion processes using machine learning models are disclosed. These include methods for performing inpainting-based novel view synthesis using depth maps and conditional models, video novel view synthesis using texture map inpainting, spatially consistent inpainting-based novel view synthesis using video diffusion models, and high-fidelity image-to-image diffusion using a texture conditional model. Further, methods for generating training data that can be used to train machine learning models to perform novel view synthesis are disclosed. These include symmetry exploiting methods of training data generation and methods using training pair alignment and splatting error simulations.Type: ApplicationFiled: July 15, 2025Publication date: July 23, 2026Applicants: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Christopher Richard Schroers, Yang Zhang, Xiang Zhang, Lukas Francesco Mehl
-
Publication number: 20260211762Abstract: In some embodiments, a method receives online quality of service (QoS) metric values for online logs of using a service. Synthetic QoS metric values that describe anomalies are added to the training dataset. A model predicts predicted QoS metric values in the online logs. A distribution of a difference between QoS metric values from the training dataset and the predicted QoS metric values is determined. The method uses the difference to adjust a parameter in the model to train the model to predict the predicted QoS metric values. The distribution is used to determine a dynamic threshold that is used to determine whether an anomaly occurs. The method determines whether an anomaly is detected in new online logs based on applying the dynamic threshold to a difference between online QoS metric values and predicted QoS metric values generated by the trained model. The dynamic threshold changes over the time series.Type: ApplicationFiled: January 17, 2025Publication date: July 23, 2026Applicants: Disney Enterprises, Inc., Beijing YoJaJa Software Technology Development Co., Ltd.Inventors: Junchao Yu, Chenyu Tian, Tongyu Dai, Thomas Howe
-
Patent number: 12688732Abstract: A guest assistance platform may analyze video data of an environment that includes a liquid substance. The video data is analyzed using a machine learning model trained to detect objects in the liquid substance. The guest assistance platform may detect an individual in the liquid substance based on analyzing the video data and may determine a measure of confidence associated with detecting the individual in the liquid substance. The guest assistance platform may determine one or more confidence factors associated with detecting the individual in the liquid substance. The guest assistance platform may modify the measure of confidence using the one or more confidence factors and may determine whether the modified measure of confidence satisfies a confidence threshold. The guest assistance platform may selectively cause assistance to be provided to the individual or continue analyzing the video data based on whether the modified measure of confidence satisfies the confidence threshold.Type: GrantFiled: November 9, 2023Date of Patent: July 21, 2026Assignee: Disney Enterprises, Inc.Inventors: Gregory Brooks Hale, Gary D. Markowitz, Clifford Aron Wilkinson, Ching-Chien Chen
-
Publication number: 20260205660Abstract: In some embodiments, a method determines a number of session types. Training data from sessions is analyzed to cluster the data in the number of session types. The method trains a model using the number of session types. Feature values for the session types are input into the model. The model generates an output based on the feature values. The output is compared to a reference output for the feature values. The method alters the number of session types based on comparing.Type: ApplicationFiled: February 27, 2026Publication date: July 16, 2026Applicant: Disney Enterprises, Inc.Inventor: Fabian Gallusser
-
Publication number: 20260195548Abstract: In some embodiments, a method receives a first translation for an instance of content. A first prompt is generated to refine the first translation. The first prompt includes instructions to refine the first translation and a scoring guide. The method inputs the first prompt into a large language model to generate a score for the first translation and suggestions for the first translation. The method evaluates the score to determine whether the first translation meets a threshold. When the score does not meet the threshold: the method generates a second prompt to refine the first translation, inputs the second prompt into the large language model to refine the first translation using one or more of the suggestions to generate a second translation, and provides feedback to the generate another first prompt to refine the second translation. When the score meets the threshold, the method outputs the first translation.Type: ApplicationFiled: January 6, 2025Publication date: July 9, 2026Applicant: Disney Enterprises, Inc.Inventors: Clifford Hilo, Guglielmo Camporese, Ana Jessica Payes, Shinobu Hattori, Mitsuaki Watanabe, Dan Sebastian Ruta
-
Patent number: 12675973Abstract: In some embodiments, a method selects first content and second content. The first content and the second content are configured to be delivered to clients. First labels are determined for categories for the first content. The first labels are based on an analysis of the first content. Second labels are determined for the categories for the second content. The second labels are based on an analysis of the second content. The method compares the first labels and the second labels to determine scores for the first labels. The scores is based on parameters of a matching tool that is configured to determine a match between instances of content. A weight of a category is used to adjust a score in the scores to generate an adjusted score. The score is for the label that is determined for the category. The method outputs information for the adjusted score and other scores.Type: GrantFiled: August 30, 2023Date of Patent: July 7, 2026Assignee: Disney Enterprises, Inc.Inventors: Lori Huck, Melissa Mirch, Scott Morehead, Mara Lucien, Alexander Niedt
-
Patent number: 12675917Abstract: One embodiment of the present invention sets forth a technique for performing identity-preserving image generation. The technique includes converting an identity image depicting a facial identity into an identity embedding. The technique further includes generating a combined embedding based on the identity embedding and a diffusion iteration identifier. The technique further includes converting, using a neural network and based on the combined embedding, a first input image that includes first noise into a first predicted image depicting one or more facial features that include one or more first facial identity features, wherein the one or more first facial identity features correspond to one or more respective second facial identity features of the identity image and are based at least on the identity embedding.Type: GrantFiled: May 19, 2023Date of Patent: July 7, 2026Assignees: Disney Enterprises, INC., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Manuel Jakob Kansy, Anton Julien Raël, Jacek Krzysztof Naruniec, Christopher Richard Schroers, Romann Matthew Weber
-
Patent number: 12675471Abstract: Techniques for generating a result for a search query. These techniques include identifying a complex search query including more than two parameters, dividing the complex search query into one or more components, and determining an intent for each of the one or more components using machine learning (ML), the ML including at least one of: a large language model (LLM) or natural language processing (NLP) neural network. The techniques further include generating a result for the search query based on routing each component through a pipeline using the respective intent, the pipeline including both a query against a graph database and a search against a vector database.Type: GrantFiled: July 31, 2024Date of Patent: July 7, 2026Assignee: Disney Enterprises, Inc.Inventors: David DeWet Raal, Jason Alexander Cox
-
Publication number: 20260185651Abstract: In some implementations, an assembly may comprise a ball comprising one or more first channels provided on an outer surface of the ball. The assembly may further comprise a material configured to harden or cure within a threshold amount of time. The assembly may further comprise a socket configured to receive the ball in an opening defined by an inner surface of the socket. The socket may comprise one or more second channels provided on the inner surface of the socket and an injection port configured to receive the material and distribute the material to the one or more first channels and the one or more second channels. After the material hardens or cures within the threshold amount of time, the ball may be permanently secured within the socket.Type: ApplicationFiled: December 31, 2024Publication date: July 2, 2026Applicant: Disney Enterprises, Inc.Inventor: Richard H. KIRCHHOFF
-
Patent number: 12669396Abstract: A system for adjusting torque value settings on click type torque wrenches. The system is configured to limit repetitive motions by an operator including limiting repetitive wrist movements to rotate a wrench handle, while also providing a very portable and easy to use system with built-in safety features. The system includes an electric motor or driver that is operable, e.g., by manual movement of a lever on a controller or control signals from a digital controller, to rotate the head of the wrench while the operator holds the wrench handle in an unlocked configuration. The operator inserts the head of the wrench into an adaptive, self-centering chuck provided at the output of the electric motor. A tool rest extends from a base of the system at an end opposite the mounting chuck, and this rest is configured to support the body of the wrench parallel to the motor shaft.Type: GrantFiled: February 9, 2023Date of Patent: June 30, 2026Assignee: Disney Enterprises, Inc.Inventor: Kenneth Wayne Culotta
-
Patent number: 12669747Abstract: A system may comprise a fog generating unit configured to generate fog; a fog distributing unit comprising: an intake component configured to receive the fog generated by the fog generating unit, a fog manifold configured to receive the fog from the intake component and separate the fog into a plurality of fog portions, a fog laminar assembly comprising a plurality of laminar portions configured to receive the plurality of fog portions and generate a plurality of laminar flows of fog using the plurality of fog portions; and a plurality of light sources configured to illuminate the plurality of laminar flows of fog to create a plurality of images, of an item, on the plurality of laminar flows of fog.Type: GrantFiled: November 8, 2023Date of Patent: June 30, 2026Assignee: Disney Enterprises, Inc.Inventors: Daniel M. Joseph, Jessica Klouda
-
Patent number: 12669235Abstract: A system, comprising: a first array of lasers; a first linear polarizer; a second array of lasers; a second linear polarizer provided at an angle with respect to the first linear polarizer; a first beamsplitter coupled to the first linear polarizer; a phosphor assembly; a collimator lens; a third linear polarizer; a second beamsplitter coupled to the third linear polarizer; and a telephoto lens.Type: GrantFiled: March 26, 2024Date of Patent: June 30, 2026Assignee: Disney Enterprises, Inc.Inventors: Daniel M. Joseph, Veronica Chen, Jessica Klouda
-
Publication number: 20260179202Abstract: Systems and methods are disclosed for automated video quality assessment using a hybrid neural network architecture. A sequence of video frames is received and partitioned into fragments, which are further subdivided into patches and encoded as tokens. The tokens are processed in parallel by a state space model, configured to extract temporal features, and by a convolutional neural network, configured to extract spatial features. The resulting feature representations are combined to form a unified embedding, which is input to a prediction head to generate local and overall quality scores indicative of the perceptual quality of the video. In some embodiments, frame-level supervision is employed during training by comparing predicted per-frame scores to reference scores, improving accuracy and granularity.Type: ApplicationFiled: November 26, 2025Publication date: June 25, 2026Applicants: Disney Enterprises, Inc., ETH Zürich (Eidgenössische Technische Hochschule Zürich)Inventors: Yang ZHANG, Felix YANG, Christopher Richard SCHROERS
-
Patent number: 12666002Abstract: A system and method for controlling and testing at least one remote media player device using a corresponding remote testing device and at least one user device not collocated with the remote testing device includes receiving from a user a selection of an available remote testing device, displaying on the user device a remote-control image or a list of automated tests, receiving from the user a selection of one of a remote-control command or an automated test as the selected remote command, sending the selected remote command to the selected remote testing device, receiving from the selected remote testing device a video output signal indicative of a medial player video output signal from the media player device in response to the selected remote command, and displaying the received video output signal on the user device simultaneously with the displaying of the remote-control image, while simultaneously performing the receiving and the sending of the selected remote commands.Type: GrantFiled: May 30, 2024Date of Patent: June 23, 2026Assignee: DISNEY ENTERPRISES, INC.Inventors: Jeffrey Hollis, Roman Bediner, Jeffrey Eggert, Taylor White, Gavin Haynes, Andrew Pritykin
-
Patent number: 12664618Abstract: Techniques are disclosed for denoising videos. In some embodiments, video frames are denoised using a denoising model that includes an encoder-decoder architecture and attention modules. During training of the denoising model, the attention modules learn weightings to upweight certain dimensions of input features to help pixel registration, remove ghosting artifacts, and improve temporal consistency when the frames of a video are being denoised. The denoising model can also be used to train a student denoising model that has a same architecture as, but is smaller and faster than, the denoising model. After training, noisy video frames can be input into the denoising model and/or the student denoising model to generate corresponding denoised video frames.Type: GrantFiled: April 14, 2022Date of Patent: June 23, 2026Assignee: DISNEY ENTERPRISES, INC.Inventors: Yang Zhang, Tunc Ozan Aydin, Christopher Richard Schroers
-
Patent number: 12664986Abstract: A system includes a hardware processor, a memory storing software code, and a machine learning (ML) model trained to detect an interruption to a conversation. The system detects, during a conversational turn by an artificial intelligence (AI) character in interaction with a human and/or another AI character, sound produced by the human and/or the other AI character, classifies, using the ML model, the sound as an interruption or irrelevant to the interaction. When the sound is irrelevant to the interaction, the conversational turn of the AI character continues. When the sound is an interruption, the system identifies a response strategy for continuing the interaction, and executes the response strategy including at least one of: (i) retention of the conversational turn, (ii) relinquishment of the conversational turn, or (iii) a negotiation, with the human and/or the other AI character, to determine the retention or the relinquishment of the conversational turn.Type: GrantFiled: January 4, 2024Date of Patent: June 23, 2026Assignee: Disney Enterprises, Inc.Inventors: James R. Kennedy, Reshmashree Bangalore Kantharaju, Maike Paetzel-Pruesmann, Ronald Cumbal, Komath Naveen Kumar
-
Patent number: 12656784Abstract: A method may include comparing, using a virtual map, a position of a ride vehicle to a position of an obstacle in an operating environment; and querying a virtual map of an operating environment, the virtual map including a characteristic for an object within the operating environment; and maintaining, by a ride vehicle, a clearance envelope with respect to the object based on the object characteristic. Additional methods and associated systems are also disclosed.Type: GrantFiled: July 1, 2024Date of Patent: June 16, 2026Assignee: DISNEY ENTERPRISES, INC.Inventors: Bradley A. Pease, Kevin T. Parent, Frank D. Mezzatesta, III, Andrew Jesse Milluzzi, William Bennett Hogue, Jr., Allan Bloemsma, Youssef Safwat Rokes, Selina L. Herman, Bryant D. Boyle
-
Publication number: 20260161746Abstract: A traffic-overload protected content-sharing system, includes a content-providing device; a server in communication with the content providing device, wherein a processor of the server executes instructions that cause the processor to: receive content from the content-providing device; store the content on a memory component in communication with the server; set a geographic boundary on access to the content; receive a plurality of requests to access the content from one or more content-consuming devices; identify respective geographical locations of the one or more content-consuming devices; deny at least one of the plurality of requests based on the respective geographical location of the one or more content-consuming devices being outside the geographic boundary; and expand the geographic boundary based on the denial of the at least one of the plurality of requests.Type: ApplicationFiled: April 15, 2025Publication date: June 11, 2026Applicant: DISNEY ENTERPRISES, INC.Inventors: Steven Makofsky, Nitzan Katz, Michael David Smith
-
Patent number: 12651318Abstract: A system includes a hardware processor and a memory storing software code. The hardware processor executes the software code to receive a three-dimensional (3-D) image including a plurality of pixels each having a plurality of bins with respective depth values, select, for a first bin of the plurality of bins of a first pixel, a second bin in each of one or more nearest neighbor pixels of the first pixel, the second bin in each of the one or more nearest neighbor pixels having a most similar depth value to a depth value of the first bin. The hardware processor further executes the software code to generate a first depth-aware bin group including the first bin and the second bin in each of the one or more nearest neighbor pixels, and process, using the first depth-aware bin group, the 3-D image to produce a corresponding 3-D output image.Type: GrantFiled: May 21, 2024Date of Patent: June 9, 2026Assignees: Disney Enterprises, Inc., ETH ZURICH (EIDGENÖSSISCHE TECHNISCHE HOCHSCHULE ZÜRICH)Inventors: Marios Papas, Gerhard Roethlin, Tunc Ozan Aydin, Xianyao Zhang, Farnood Salehi, Shilin Zhu
-
Patent number: 12651397Abstract: The present invention sets forth a technique for simulating wrinkles under dynamic facial expression. The technique includes receiving a wrinkle graph, including a plurality of nodes associated with a plurality of pores included in a three-dimensional (3D) representation of a facial structure and a plurality of edges associated with a plurality of wrinkles included in the 3D representation of a facial structure. The technique also includes assigning one or more of the plurality of wrinkles associated with edges in the wrinkle graph to one of a plurality of bins and generating, for each of the bins, a plurality of pre-computed displacement texture maps. The technique further includes generating a per-frame displacement texture map and modifying an animation frame based on the per-frame displacement texture map, such that the modified animation frame depicts the plurality of pores and the plurality of wrinkles included in the 3D representation of the facial structure.Type: GrantFiled: April 5, 2024Date of Patent: June 9, 2026Assignee: DISNEY ENTERPRISES, INC.Inventors: Derek Edward Bradley, Prashanth Chandran, Sebastian Klaus Weiss, Gaspard Zoss
-
Patent number: 12645791Abstract: The present invention sets forth a technique for performing automated application security onboarding. The technique includes receiving, via an interactive dashboard, a designation associated with a software application and one or more items of application information associated with the software application. The technique also includes determining, in real-time and based on one or more schemas, that that the one or more items of application information are sufficient for executing one or more of a plurality of software scanning tools. The technique further includes transmitting the designation and the one or more items of application information to the plurality of software scanning tools, analyzing the software application via the plurality of software scanning tools, receiving, from the plurality of software scanning tools, one or more scan results based on the analysis, and displaying the one or more scan results via the interactive dashboard.Type: GrantFiled: October 8, 2024Date of Patent: June 2, 2026Assignee: DISNEY ENTERPRISES, INC.Inventors: Truong Tuan Nguyen, Christian Matthew Gustafson, Daniel Micah Babb, Kenneth William De Hoop, Danielle Kish
-
Patent number: 12639127Abstract: In some embodiments, a method receives usage data that is based on a delivery of content by a plurality of content delivery network entities. A first value of a selection parameter is used to determine whether to select a content delivery network entity from the plurality of content delivery network entities to process a first request for content. The method allocates the usage data in a first distribution to the plurality of content delivery network entities. The allocating does not use a condition to determine the first distribution. The usage data is allocated in a second distribution to the plurality of content delivery network entities. The allocating uses the condition to determine the second distribution. The method adjusts the first value of the selection parameter to a second value based on the first distribution and the second distribution.Type: GrantFiled: June 27, 2022Date of Patent: May 26, 2026Assignee: Disney Enterprises, Inc.Inventors: Thomas Howe, Mark Kegel, Edward Russell, Joseph Higgins, Daniel Spiewak, Matthias Sainz
-
Patent number: 12639627Abstract: A method for training a control system model includes introducing a simulated fault into a software simulation of a physical system and generating emulated sensor data based on the simulated fault, where the emulated sensor data emulates output from one or more sensors of the physical system. The method further includes obtaining output data from a test control system provided with the emulated sensor data, where the test control system emulates a control system of the physical system and tagging the output data with the simulated fault to create training data. The method further includes utilizing the training data to train the control system model, where the control system model is a machine learning model for use with the control system of the physical system during operation of the physical system.Type: GrantFiled: September 1, 2022Date of Patent: May 26, 2026Assignee: DISNEY ENTERPRISES, INC.Inventors: Andrew Jesse Milluzzi, Faith Elizabeth Smith Haslebacher
