Cisco Technology, Inc.

Fangyan Ye

Plamen Nedeltchev

Dong Li

Cheng Pan

Qingliang Lin

Xuanbei Lu

In one embodiment, an illustrative method herein may comprise: recognizing, by a device, key entries within a textual data set having a plurality of files; forming, by the device, a group of files by selecting a subset of the plurality of files that are considered by the device to be similar according to a tolerance-based similarity metric and a bi-dimensional hierarchical multiclass classification; generating, by the device, a metadata profile for the group of files by aggregating metadata from its constituent files; and causing, by the device and based on the metadata profile, a risk identification or remediation action to be performed on the textual data set.

Growing community of inventors

Shanghai, China

Fangyan Ye