Determining areas of interest in video based at least on a user's interactions with the video
AssigneeThe ADT Security Corporation
InventorShy Ward
Life of this patent
Estimating the term…
Abstract
According to one or more embodiments, an interaction device is provided. The interaction device includes processing circuitry configured to render for display a first premises security video comprising a plurality of frames, determine a user interaction with a playback of the first premises security video, determine a plurality of logical weights associated with the plurality of frames based at least on the user interaction, train a machine learning model based at least on the plurality of logical weights, and perform a premises security system action based at least on the trained machine learning model.
Claims20
A system comprising:
- at least one device comprising processing circuitry configured to:
- render for display a premises security video comprising a plurality of frames;
- monitor a user interaction with a playback of the premises security video;
- for each of the plurality of frames, determine a ranking for the frame based at least on an amount of the user interaction with the frame;
- and
- train a machine learning model based at least on at least one ranking of the plurality of rankings for the plurality of frames to generate a trained machine learning model;
- and;
- perform a premises security system action based at least on the trained machine learning model.
A method implemented by a system, the method comprising:
- rendering for display a premises security video comprising a plurality of frames;
- monitoring a user interaction with a playback of the premises security video;
- for each of the plurality of frames, determining a ranking for the frame based at least on an amount of the user interaction with the frame;
- and
- training a machine learning model based at least on at least one ranking of the plurality of rankings for the plurality of frames to generate a trained machine learning model;
- and
- performing a premises security system action based at least on the trained machine learning model.
A non-transitory, computer-readable storage medium comprising instructions configured to cause a system to:
- render for display a premises security video comprising a plurality of frames;
- monitor a user interaction with a playback of the premises security video;
- for each of the plurality of frames, determine a ranking for the frame based at least on an amount of the user interaction with the frame;
- train a machine learning model based at least on at least one ranking of the plurality of rankings for the plurality of frames to generate a trained machine learning model;
- and
- perform a premises security system action based at least on the trained machine learning model.
Dependencies are inferred from the claim text.