Invention Grant
- Patent Title: Automated learning of anomalies in media streams with external feed labels
-
Application No.: US15984052Application Date: 2018-05-18
-
Publication No.: US11157524B2Publication Date: 2021-10-26
- Inventor: Eric Zavesky , Lee Begeja , Raghuraman Gopalan , Bernard S. Renger , Behzad Shahraray , Zhu Liu
- Applicant: AT&T Intellectual Property I, L.P.
- Applicant Address: US GA Atlanta
- Assignee: AT&T Intellectual Property I, L.P.
- Current Assignee: AT&T Intellectual Property I, L.P.
- Current Assignee Address: US GA Atlanta
- Main IPC: G06F16/28
- IPC: G06F16/28 ; G06N3/08 ; G06F16/2457

Abstract:
Methods, computer-readable media, and devices are disclosed for providing a notification of an anomaly in a media content that is associated with an event type. For example, a method may include a processing system including at least one processor for detecting a first anomaly from a first media content, generating a first anomaly signature for the first anomaly, obtaining a notification of a first event, the notification including an event type, time information, and location information of the first event, correlating the first anomaly to the notification of the first event, and labeling the first anomaly signature with the event type. The processing system may further detect a second anomaly from a second media content that matches the first anomaly signature and transmit a notification of a second event of the event type when it is detected that the second anomaly matches the first anomaly signature.
Public/Granted literature
- US20190354629A1 AUTOMATED LEARNING OF ANOMALIES IN MEDIA STREAMS WITH EXTERNAL FEED LABELS Public/Granted day:2019-11-21
Information query