Apparatus and method for detecting suspicious content
AssigneeAT&T Intellectual Property I, L.P.
InventorsStephen J. Griesmer, James Gordon Beattie, Jr.
Life of this patent
Estimating the term…
Abstract
Aspects of the subject disclosure may include, for example, receiving data associated with a video, applying the data to a machine learning model to obtain a prediction regarding an accuracy of an assertion included in the video, responsive to the prediction indicating that the assertion is accurate, transmitting the video to a processing system including a processor, and responsive to the prediction indicating that the assertion in inaccurate, preventing a transmission of the video to the processing system. Other embodiments are disclosed.
Claims20
A device, comprising:
- a processing system including a processor;
- and
- a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:
- processing a digest to generate a cascade assembly, the digest comprising first video content data associated with a first video;
- processing the cascade assembly to generate a veracity indication that represents an accuracy of at least one subject matter included in the first video;
- generating a model in accordance with at least the veracity indication;
- and
- applying second video content data to the model to generate a prediction regarding a likelihood of whether a subject matter of a second video associated with the second video content data is accurate.
A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
- generating a digest in accordance with a processing of data associated with at least a first video;
- generating a cascade assembly based on a processing of the digest;
- generating a plurality of veracity indications associated with a first plurality of assertions included in the at least a first video in accordance with a processing of the cascade assembly;
- generating a model in accordance with the plurality of veracity indications;
- and
- utilizing the model to generate a plurality of predictions regarding an accuracy of a second plurality of assertions included in a plurality of videos.
A method, comprising:
- applying, by a first processing system including a first processor, data to a machine learning model to obtain a prediction regarding an accuracy of a subject matter assertion included in a video;
- responsive to the prediction indicating that the subject matter assertion is at least substantially accurate, enabling, by the first processing system, access to the video by a second processing system including a second processor;
- and
- responsive to the prediction indicating that the subject matter assertion is at least substantially inaccurate, disabling, by the first processing system, access to the video by the second processing system.
Dependencies are inferred from the claim text.