Disney Enterprises, Inc.

Tony R Smith

Alexander C Chen

Mark Arana

Edward C Drake

Mehul Patel

Leon Silverman

Benjamin F Havey

Systems and methods are described for leveraging machine learning to deliver time-sensitive media content offers to a consumer over an optimal device and channel. In an implementation, a server system transmits media content offers over an optimal device and channel to a user. The server system captures metadata of at least one of: the user's use of multiple devices, the user's media content preferences, the user's preferred transmission channels for receiving media content offers over the multiple devices, and the user's preferred times for receiving media content offers. The server system prepares a media content offer for transmission to the user. Based on the captured metadata, the server system selects a user device of the multiple user devices and a transmission channel of multiple transmission channels to transmit the media content offer; and transmits the media content offer to the selected user device over the selected transmission channel.

System and method for leveraging machine learning to deliver time-sensitive content over optimal devices and channels

A system for identifying, tagging, and displaying one or more assets within an audio visual (AV) file includes an asset tagging server, an asset tag acquisition device, and a database, wherein the asset tag acquisition device includes an asset identification engine configured to receive an asset identification data set and generate an asset tag data file that includes an asset tag corresponding to each asset. The asset tagging server is configured to receive, from an AV capture device, an AV file that includes an AV representation of each asset and corresponding timestamp data, and store, in the database, an AV asset tag data file comprising the beginning timestamp, the ending time stamp, and the set of asset tags.

System and method for identifying and tagging assets within an AV file

A system for identifying, tagging, and displaying one or more assets within an audio visual (AV) file includes an asset tagging server, an asset tag acquisition device, and a database, wherein the asset tag acquisition device includes an asset identification engine configured to receive an asset identification data set and generate an asset tag data file that includes an asset tag corresponding to each asset. The asset tagging server is configured to receive, from an AV capture device, an AV file that includes an AV representation of each asset and corresponding timestamp data, and store, in the database, an AV asset tag data file comprising the beginning timestamp, the ending time stamp, and the set of asset tags. The system further includes a scene generation server configured to receive, from an editing display system, a set of asset parameters, search the database to identify one or more AV asset tag data files that correspond to the set of asset parameter, and display, on a user interface, the identified AV asset tag data files together with corresponding thumbnail images.

Systems and methods are described for linking and interacting between augmented reality (AR) and virtual reality (VR) environments. An AR host system may capture or retrieve data associated with an AR view of a first user's real-world environment. The data may include an audio-visual stream of the real-world view, digital object data associated with digital objects overlaid on the real-world view, and other data. The AR host system transmits the data to a VR system. The VR system may place a second user into a VR environment that is a representation of the AR view. The VR system may also generate additional digital object data associated with the AR view and transmit the generated digital object data to the AR host system. The AR host system receives the digital object data and modifies the AR view presented to the first user.

System and method for linking and interacting between augmented reality and virtual reality environments

There is provided a system comprising a non-transitory memory and a hardware processor configured to determine elements of a performance in a video, identify one or more people to feature in the video based on the elements of the performance in the video, receive a user input selecting a person from the one or more people to feature in the video, retrieve performance data for featuring the selected person in the video based on actions performed by the actor in the video, create a personalized video by featuring the selected person in the video using the performance data, and display the personalized video on a user device.

Systems and methods for featuring a person in a video using performance data associated with the person

Systems and methods for generating and outputting personalized content recommendations are provided. When it is determined that two or more users are in close proximity to each other, the two or more users' respective media content libraries may be compared. Commonalities or related aspects of the two or more users' respective media content libraries can be determined and leveraged to generated personalized content recommendations.

System and method for proximity-based personalized content recommendations

There is provided a system for use in an environment, the system comprising a microphone, a plurality of speakers, a memory storing an executable code, and a processor executing the executable code to receive a media content including an audio component, play the audio component of the media content over at least one of the plurality of speakers, detect, while playing the audio component, an ambient sound in the environment using the microphone, and adjust playing of the audio component of the media content for the at least one of the plurality of speakers based on the ambient sound in the environment.

Growing community of inventors

Sherman Oaks, CA, United States of America

Tony R Smith