US 12,412,027 B1
Machine learning model automated data extraction and prediction
Chandrashekhar Jha, Bengaluru (IN); Bharath G R, Bengaluru (IN); Pallenavya Manishankar, Bengaluru (IN); Sourodeep Chatterjee, Bengaluru (IN); Abhinesh, Bengaluru (IN); Vishal Babani, Bengaluru (IN); Prateek Mukhija, Bengaluru (IN); Harshitha Srikanth, Bengaluru (IN); Shivam Sharma, Bengaluru (IN); and Pushpavathi K N, Bengaluru (IN)
Assigned to INTUIT INC., Mountain View, CA (US)
Filed by INTUIT INC., Mountain View, CA (US)
Filed on Apr. 30, 2025, as Appl. No. 19/194,795.
Int. Cl. G06F 16/00 (2019.01); G06F 16/35 (2019.01); G06F 21/62 (2013.01); G06F 40/166 (2020.01); G06F 40/205 (2020.01); G06F 40/279 (2020.01); G06V 30/41 (2022.01)
CPC G06F 40/166 (2020.01) [G06F 16/35 (2019.01); G06F 21/6254 (2013.01); G06F 40/205 (2020.01); G06F 40/279 (2020.01); G06V 30/41 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for automated data extraction and prediction using machine learning models, comprising:
providing one or more documents to a text extraction engine;
extracting, by the text extraction engine, a set of data from each document of the one or more documents;
instructing a machine learning model, via a prompt, to parse the set of data from each document of the one or more documents and identify one or more protected entities contained in the set of data from each document of the one or more documents;
instructing the machine learning model, via the prompt, to classify each protected entity of the one or more protected entities identified by the machine learning model in the set of data from each document of the one or more documents;
instructing the machine learning model, via the prompt, to generate, for each protected entity of the one or more protected entities identified in the set of data from each document of the one or more documents, a corresponding unprotected entity;
instructing the machine learning model, via the prompt, to replace each protected entity of the one or more protected entities identified in the set of data from each document of the one or more documents with the corresponding unprotected entity;
receiving an output from the machine learning model in response to the prompt; and
performing an action based on the output.