Amazon Technologies, Inc.

Harshal Dilip Wanjari

Hooman Mahyar

Thomas Albert Faulhaber, Jr

Vimal Bhat

Sanjeev Kumar

Ayman Mahfouz

Pratik GuhaRay

Ramasubramanian Balagurunathan

Hsuan-Cheng Lai

Muhammad Yahia

Robert Eicher Simmering

Juan Martin Borgnino

Jon Robert Ducrou

Douglas James Herrington

Mohammad Naghshvar

Arjun Cholkar

Paul Warren Smart

Sushanta Das

Prashant Hegde

Deepak Maini

Ankit Kumar Yadav

Maksym Kovalenko

Bhupinder Singh Sidana

Shai Ben Nun

Noam Katz

Matthew David Sandler

Hannah Elizabeth McClellan

Sandeep Rao

Josiah William Jordan

Dennis Antonio Jumaquio

Neha Aggarwal

Kenneth Hale Montanez

Ajay Mohan

Mark Steven Mastandrea

Advertisements for brands that are to be aired during media programs are selected based on similarities between the brands and creators of the media programs. As a media program is being aired, data representing content of a media program is processed to identify words being spoken or sung during the media program and sentiments associated with the media program. The media program is classified based on the words and sentiments, and a classification of the media program is compared to attributes of advertisements to determine which of the advertisements is best suited for airing during the media program. Additionally, a set of words that, if spoken or sung during a media program would establish conditions favorable to a given advertisement may be identified and provided to a creator.

Selecting advertisements for media programs and establishing favorable conditions for advertisements

Summaries of media programs that are in progress are generated based on content of the media programs that has already been transmitted to listeners or viewers. The content is transcribed into text, and contextual features regarding the media program such as topics, identities of speakers or interactions received from listeners are identified. The transcribed content and the contextual features are provided as multi-modal inputs to a model that is trained to generate a summary of the media program in response to such inputs. Summaries of media programs that are then in progress are transmitted to devices of listeners who may be interested in joining one of the media programs and displayed in a menu or user interface or announced to the listeners.

Summarizing content of live media programs

A creator establishes a media program including a plurality of media files or content in accordance with a broadcast plan. Mixing systems establish connections with a mobile device of the creator, and with sources of the audio files or content, either manually or automatically in response to instructions of the creator. Broadcast systems establish connections with computer devices of listeners and a mixing system. Conference systems establish connections with the mobile device of the creator and a mixing system. The connections established may be one-way or two-way channels. The media program may include live or previously recorded audio content including words or sounds of the creator, as well as advertisements, music, news, sports, weather, or other programming. The media program may also include live or previously recorded interviews or other conversations with guests, including but not limited to one or more listeners.

Synchronizing media content streams for live broadcasts and listener interactivity

Selecting advertisements for media programs by matching brands to creators

Systems, methods, and computer-readable media are disclosed for systems and methods for automated selection of color palettes for video content. Example methods may include determining, by one or more computer processors coupled to memory, a first segment of video content, the first segment comprising a first set of frames, determining, using a first video processing algorithm, a first object that is present in the first set of frames, and determining, using a second video processing algorithm, a first semantic characteristic of the first segment. Some example methods may include generating a first vector representing the first object and the first semantic characteristic, and generating, using a first neural network and the first vector, a first color palette recommendation for the first segment. Selection of the first color palette recommendation may cause a color filter to be applied to the first set of frames.

Automated selection of color palettes for video content using artificial intelligence

Systems, methods, and computer-readable media are disclosed for systems and methods for intelligent content rating determination. Example methods include determining presence of a first feature in a first frame of a video using an object recognition algorithm, determining presence of a second feature in an audio file associated with the video using an audio processing algorithm, and determining presence of a third feature in a text file associated with the video using a natural language processing algorithm. Certain embodiments may include generating a predicted content rating for the video using a machine learning model, where the predicted content rating is based at least in part on the first feature, the second feature, and the third feature, and using feedback data for the predicted content rating to retrain the machine learning model.

Intelligent content rating determination using multi-tiered machine learning

Techniques are described for detecting and replacing burned-in subtitles in image and video content.

Detection and replacement of burned-in subtitles

A user may indicate an interest relating to events such as objects, persons, or activities, where the events included in content depicted in a video. The user may also indicate a configurable action associated with the user interest, including receiving a notification via an electronic device. A video item, for example a live-streaming sporting event, may be broken into frames and analyzed frame-by-frame to determine a region of interest. The region of interest is then analyzed to identify objects, persons, or activities depicted in the frame. In particular, the region of interest is compared to stored images that are known to depict different objects, persons, or activities. When a region of interest is determined to be associated with the user interest, the configurable action is triggered.

Customized action based on video item events

A user may order items that may be made available at a facility such as a pickup facility. Described are techniques for preparing and expediting an order for pick up by the user. In one implementation, geolocation data acquired from a user device may be used to determine when the user has entered a geofence associated with the facility. Based on this geolocation data and sensor data from sensors at the facility, a system may automatically identify the user. Once identified, the items in the order may be delivered to the user in a parking area of the pickup facility, who may then depart the pickup facility.

System for expediting delivery of items

Systems, methods, and computer-readable media are disclosed for systems and methods for customized video content summary generation. Example methods may include determining a first segment of digital content including a first set of frames, first textual content, and first audio content. Example methods may include determining a first event that occurs in the first set of frames, determining a first theme of the first event, generating first metadata indicative of the first theme, and determining a meaning of a first sentence that occurs in the first textual content. Some methods may include determining a second theme of the first sentence, generating second metadata indicative of the second theme, determining that user preference data associated with an active user profile includes the first theme and the second theme, generating a video summary that includes a portion of the first segment of digital content, and presenting the video summary.

Customized video content summary generation and presentation

This disclosure describes systems and methods for dynamically and automatically adapting the level of data logging that occurs within a network of nodes, identifying causes of exceptions that occur within the network and resolving those causes to ensure that the network continues operating efficiently. A monitoring service may automatically increase/decrease data logging of various nodes within the network as it progresses through levels of a network searching for a node that is the source of a cause of an exception. Once identified, the monitoring service may process the logged data and either automatically resolve the cause of the exception or provide information to an operator for resolution.

Real time adaptive monitoring

Growing community of inventors

Issaquah, WA, United States of America

Harshal Dilip Wanjari