US 12,073,947 B1
Meta-learning for automated health scoring
Nazanin Zaker Habibabadi, Sunnyvale, CA (US); Makanjuola Adekunmi Ogunleye, Blacksburg, VA (US); Jeremy S. Krohn, Reno, NV (US); and Xue Han, Sunnyvale, CA (US)
Assigned to INTUIT INC., Mountain View, CA (US)
Filed by INTUIT INC., Mountain View, CA (US)
Filed on Mar. 27, 2023, as Appl. No. 18/190,529.
Int. Cl. G06Q 30/02 (2023.01); G06N 5/022 (2023.01); G06Q 10/06 (2023.01); G06Q 10/10 (2023.01); G06Q 30/0282 (2023.01); G06Q 30/06 (2023.01); G16H 50/30 (2018.01)
CPC G16H 50/30 (2018.01) [G06N 5/022 (2013.01); G06Q 30/0282 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for automated health scoring through meta-learning, comprising:
retrieving text data related to an entity that was provided by a user;
providing one or more first inputs to a first machine learning model based on a subset of the text data;
determining, based on an output from the first machine learning model in response to the one or more first inputs, that a first portion of the subset of the text data includes an address and a name;
discarding a second portion of the subset of the text data that does not include the address or the name;
determining, based on the address and the name, that one or more text results from one or more data sources relate to the entity;
providing one or more second inputs to a second machine learning model based on the one or more text results and based further on determining vector representations of each given text result in the one or more text results;
determining, based on an output from the second machine learning model in response to the one or more second inputs, a health score for the entity;
performing one or more actions based on the health score for the entity; and
receiving user feedback with respect to the health score determined for the entity, wherein the second machine learning model is re-trained based on the user feedback.