US 12,190,250 B2
Contextual intelligence for unified data governance
Edward E. Seabolt, Williamson, TX (US); Eser Kandogan, Mountain View, CA (US); Mary A. Roth, San Jose, CA (US); and Harsha V. Krishnareddy, Sunnyvale, CA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Jun. 7, 2018, as Appl. No. 16/002,394.
Claims priority of provisional application 62/643,871, filed on Mar. 16, 2018.
Prior Publication US 2019/0287032 A1, Sep. 19, 2019
Int. Cl. G06N 5/022 (2023.01); G06F 16/23 (2019.01); G06F 16/901 (2019.01); G06N 3/08 (2023.01); G06N 5/025 (2023.01); G06N 20/00 (2019.01)
CPC G06N 5/022 (2013.01) [G06F 16/2379 (2019.01); G06N 3/08 (2013.01); G06N 5/025 (2013.01); G06F 16/9024 (2019.01); G06N 20/00 (2019.01)] 14 Claims
OG exemplary drawing
 
1. A computer system for unified data governance, comprising:
one or more computer devices each having one or more processors and one or more tangible storage devices; and
a program embodied on at least one of the one or more storage devices, the program having a plurality of program instructions for execution by the one or more processors, the program instructions comprising instructions for:
a machine learning framework in communication with a suite of enterprise application servers via one or more connector components, wherein the machine learning framework populates a context graph with to-be-governed data from the suite of enterprise application servers, trains a plurality of machine learning models based on user-defined parameters, persists properties of the plurality of machine learning models back to the context graph, and displays, via a graphical user interface, a generated recommendations panel based on contextual findings of the plurality of machine learning models, wherein the generated recommendations panel comprises recommended related database tables based on a context asset, natural language reasons as to why particular database tables were recommended, a number of queries a given recommended related database table was used in, and out of compliance recommendations, and wherein a natural language reason provides a shared context comprising a number of terms shared between a recommended related database table and the context asset and a listing of the terms, and wherein an out of compliance recommendation provides a warning when a table, of the recommended related database tables, has not been cataloged and is used within a query, and wherein the context graph comprises a schematic context which describes how data is structured, a semantic context which captures data meaning, a usage context which captures activity on data, a business context which captures practices of a business unit, and a social and organizational context which captures relationships between users comprising users following each other on a social network and organization membership, wherein the machine learning framework provides contextual governance intelligence via implementation of a declarative syntax based on human-optimized config object notation (HOCON) to construct machine learning pipelines.