US 11,755,582 B2
Adaptive field-level matching
Arun Kumar Jagota, Sunnyvale, CA (US); Ajitesh Jain, San Mateo, CA (US); Rahul Mathias Madan, Sunnyvale, CA (US); and Shravani Madhavaram, Mountain View, CA (US)
Assigned to Salesforce, Inc., San Francisco, CA (US)
Filed by salesforce.com, inc., San Francisco, CA (US)
Filed on Apr. 30, 2020, as Appl. No. 16/862,667.
Prior Publication US 2021/0342353 A1, Nov. 4, 2021
Int. Cl. G06F 7/00 (2006.01); G06F 16/2455 (2019.01); G06N 20/00 (2019.01)
CPC G06F 16/24558 (2019.01) [G06F 16/24564 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system for adaptive field-level matching, the system comprising:
one or more processors; and
a non-transitory computer readable medium storing a plurality of instructions, which when executed, cause the one or more processors to:
identify first elements in a field of a prospective record for a database, and second elements in the field of a candidate record, in the database, for matching the prospective record;
identify features corresponding to any of the first elements that are identical to any of the second elements, any of the first elements that are absent from the second elements, and any of the second elements that are absent from the first elements;
determine, by a machine-learning model, a field match score, based on the features, for the second elements in the field of the candidate record;
determine, by another machine-learning model, a record match score, based on weighing the field match score and weighing another field match score for another field of the candidate record, for the candidate record;
determine whether the record match score satisfies a threshold; and
identify the candidate record as matching the prospective record, in response to a determination that the record match score satisfies the threshold.