The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jan. 27, 2026

Filed:

Apr. 30, 2025
Applicant:

Intuit Inc., Mountain View, CA (US);

Inventors:

Shutendra Kirty Harsola, Bangalore, IN;

Deepak Gujraniya, Bangalore, IN;

Aniruddha Bardhan, Bengaluru, IN;

Vikas Raturi, Bangalore, IN;

Mohammad Saman Tamkeen, Bangalore, IN;

Arkadeep Banerjee, Bangalore, IN;

Assignee:

Intuit Inc., Mountain View, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 17/28 (2006.01); G06F 16/2452 (2019.01); G06F 16/383 (2019.01); G06F 17/20 (2006.01);
U.S. Cl.
CPC ...
G06F 16/24522 (2019.01); G06F 16/383 (2019.01);
Abstract

A method including receiving a training dataset including instance data structures storing natural language queries in a domain-specific language. The domain-specific language includes predefined terms representable in a predefined data structure. The natural language queries corresponds to the instance data structures. The method also includes training, until convergence, a ranking model on the training dataset using a pairwise ranking loss function that modifies a sequence of layers of the ranking model to maximize a score output by the ranking model. The score represents a probability that a combination of an instance data structure and a corresponding natural language query, when inserted into a conversion prompt of a conversion model, increases a performance of the conversion model when converting a new natural language query into a new instance data structure. After convergence, the ranking model is returned as a trained ranking model.


Find Patent Forward Citations

Loading…