Back to results
US 12,520,017 B2Granted
Tracking content with artifical intelligence as it is consumed
AssigneeSony Group Corporation
InventorBrant Candelore
Life of this patent
Estimating the term…
Abstract
A user starts playback of an audio or AV program, which starts up a large language model (LLM) such as a generative pre-trained transformer. The LLM follows the program with the user as the program is being watched. Audio is converted to text and video is converted to text-based description. The LLM essentially trains on the resulting “corpus” so that should the user subsequently want to access part of the program using a simple conversational query about the program, the LLM can provide the answer.
Claims20
An apparatus, comprising:
- at least one computer memory that is not a transitory signal and that comprises instructions executable by at least one processor assembly to:
- receive a command to present audio and/or audio video (AV) content on a display;
- responsive to the command, start to play the content;
- responsive to the command, start at least one machine learning (ML) model to receive audio and/or video being played in the content;
- use the audio and/or video in the content to train at least one large language model (LLM);
- receive a stop or pause command;
- responsive to receipt of the stop or pause command, stop training the LLM and stop playing the content;
- while content play is stopped, receive at least one query related to the content;
- input the query to the LLM;
- receive from ML model a response to the query, the response comprising content information only up to the point in the content at which play was stopped;
- and
- present the response on at least one output device.
9 more elements
A method, comprising:
- receiving a command to present content on a display;
- responsive to the command, playing the content using a content player;
- responsive to the command, starting at least one machine learning (ML) model to receive audio and/or video being played in the content;
- as the content is being played, using the content to train the ML model;
- receiving a stop or pause command;
- responsive to receipt of the stop or pause command, stopping training the ML model and stopping playing the content;
- while content play is stopped, receiving at least one query related to the content;
- and
- using the ML model to return at least one response to the at least one query about the content, the response comprising content information only up to the point in the content at which play was stopped.
6 more elements
An apparatus comprising:
- at least one processor assembly configured to:
- receive a command to present audio and/or video content on a display;
- responsive to the command, start to play the content;
- responsive to the command, invoke at least one machine learning (ML) model to consume information related to content as the content is being played on at least one output device to train the ML model;
- receive a stop or pause command;
- responsive to receipt of the stop or pause command, stop invoking the ML model to consume information related to the content and stop playing the content;
- while content play is stopped, receive at least one query related to the content;
- and
- use the ML model to provide a response to the at least one query about the content, the response comprising content information only up to the point in the content at which play was stopped.
6 more elements
Dependencies are inferred from the claim text.