US 12,131,228 B2
Method for accessing data records of a master data management system
Alexandre Luz Xavier Da Costa, Stuttgart (DE); Geetha Sravanthi Pulipaty, Bangalore (IN); Mohammad Khatibi, Richmond Hill (CA); Neeraj Ramkrishna Singh, Bangalore (IN); and Abhishek Seth, Deoband (IN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Feb. 26, 2020, as Appl. No. 16/801,241.
Claims priority of application No. 19166696 (EP), filed on Apr. 2, 2019.
Prior Publication US 2020/0320153 A1, Oct. 8, 2020
Int. Cl. G06F 16/9535 (2019.01); G06F 16/9538 (2019.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) [G06F 16/9535 (2019.01); G06F 16/9538 (2019.01); G06F 18/214 (2023.01)] 18 Claims
OG exemplary drawing
 
1. A method for accessing data records of a master data management system, the data records comprising multiple attributes, the method comprising:
enhancing the master data management system with one or more search engines for enabling access to the data records;
receiving at the master data management system a request of data;
identifying, by an entity identifier, a set of one or more attributes and one or more entity types associated with the one or more attributes, of the multiple attributes, which are referenced in the received request, wherein the entity identifier relies on machine learning (ML) model;
selecting a combination of one or more search engines, of the search engines of the master data management system, whose performances for searching values of at least part of the set of attributes and the one or more entity types fulfill a current selection rule;
editing a configuration of the master data management system to search with the combination of one or more search engines;
processing the request using the combination of search engines, wherein the master data management system accesses the search engines with interfaces comprising a structured search application programming interface (API) and a fuzzy search API;
providing, at least in part, results of the processing based on displaying the results of the processing in a browser;
inputting the set of attributes to a predefined machine learning model and receiving from the machine learning model one or more search engines that may be used for searching the set of attributes;
receiving a training set indicative of different sets of one or more training attributes, wherein each set of training attributes is labeled to indicate search engines that are suitable to perform the search of the set of training attributes; and
training a predefined machine learning algorithm using the training set, thereby generating the machine learning model.