US 12,086,117 B2
Combining user feedback with an automated entity-resolution process executed on a computer system
Nicholas Akbar Ablitt, Putney (GB)
Assigned to SAS INSTITUTE INC., Cary, NC (US)
Filed by SAS Institute Inc., Cary, NC (US)
Filed on Jun. 22, 2023, as Appl. No. 18/212,832.
Application 18/212,832 is a continuation of application No. 18/299,973, filed on Apr. 13, 2023.
Claims priority of provisional application 63/416,450, filed on Oct. 14, 2022.
Prior Publication US 2024/0126731 A1, Apr. 18, 2024
Int. Cl. G06F 16/00 (2019.01); G06F 16/215 (2019.01); G06F 16/23 (2019.01)
CPC G06F 16/215 (2019.01) [G06F 16/2365 (2019.01)] 30 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium comprising program code that is executable by one or more processors for causing the one or more processors to:
receive a set of data records;
execute an automated entity resolution (AER) process configured to assign the set of data records to a set of entities;
for each entity in the set of entities:
generate a respective consistency score for the entity, the respective consistency score indicating a level of consistency among a respective group of data records assigned to the entity, wherein generating the respective consistency score for the entity involves comparing a first set of attributes in a first data record of the respective group of data records to a second set of attributes in a second data record of the respective group of data records;
determine whether one or more data records in the respective group of data records have been validated by a user;
generate a respective confidence score for the entity based on the respective consistency score for the entity and based on whether the one or more data records have been validated by the user, the respective confidence score indicating a probability that the respective group of data records is correctly assigned to the entity;
determine a respective visual indicator based on the respective confidence score for the entity, the respective visual indicator being configured to indicate a risk of record misassignment; and
generate a graphical user interface that includes the respective visual indicator for each of the entities.