Steven K Herbert

US Patent:

20200073994, Mar 5, 2020

Filed:

Aug 30, 2018

Appl. No.:

16/117050

Inventors:

- Redmond WA, US
Guoyu HAO - Sammamish WA, US
Steven Peter HERBERT - Woodinville WA, US
Boris ASIPOV - Bellevue WA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G06F 17/30
G06N 99/00
G06N 3/08

Abstract:

Described herein is a system and method for utilizing data flow analysis to perform data classification with respect to a source dataset and a generated derived dataset. A flow confidence for a field is calculated using an adaptive algorithm in accordance with the action performed and the derived dataset. An associated derived confidence for a particular tag is calculated in accordance with an associated confidence and the flow confidence. When the associated derived confidence is greater than or equal to a first threshold, the particular tag is copied to the derived dataset. In some embodiments, when the associated derived confidence is less than or equal to a second threshold, the particular tag is not copied to the derived dataset. Otherwise an action to be taken is identified. A response to the action is received and the adaptive algorithm is modified in accordance with the received response.

US Patent:

20200026803, Jan 23, 2020

Filed:

Jul 23, 2018

Appl. No.:

16/043067

Inventors:

- Redmond WA, US
Saikat GUHA - Seattle WA, US
Steven Peter HERBERT - Woodinville WA, US
Boris ASIPOV - Bellevue WA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G06F 17/30
G06N 7/00

Abstract:

According to one aspect of the present disclosure, a computing device is provided, including non-volatile memory storing a database including a plurality of database entries. The computing device may further include a processor configured to sort the plurality of database entries into a plurality of database entry length sets. For each database entry length set, each database entry included in the database entry length set may be within a predefined length range. For each database entry length set, the processor may be further configured to generate a probabilistic data structure based on the one or more database entries included in the database entry length set.