CPC H04L 63/0892 (2013.01) [G06F 11/1464 (2013.01); H04L 65/765 (2022.05)] | 20 Claims |
1. A method for processing video data, the method comprising:
obtaining, by a data processing unit (DPU) of an edge device, video data;
processing the video data to obtain video data chunks and video processing engine outcomes using data analytics models, wherein the video processing engine outcomes comprise facial recognitions and fraud detections generated by the data analytics models;
generating authentication and authorization (AA) metadata comprising first AA metadata and second AA metadata, wherein the first AA metadata is associated with a facial recognition of the facial recognitions and the second AA metadata associated with a fraud detection of the fraud detections based on the video data chunks, the facial recognition, and the fraud detection, wherein:
the first AA metadata specifies first user identifiers, first group identifiers, a full access type, and a first authorization associated with the facial recognition; and
the second AA metadata specifies second user identifiers, second group identifiers, a legal hold access type, and a second authorization associated with the fraud detection;
associating the first AA metadata with a first portion of the video data chunks corresponding to the facial recognition and associating the second AA metadata to a second portion of the video data chunks corresponding to the fraud detection, and
storing the AA metadata and the video data chunks.
|