Bank of America Corporation

Nizar Naitlho

Yvonne Y Li

Zhexiao Zhang

Yipeng Zhu

Debra A Holder

Sushant Hanmant Gosavi

Juned Gulabkhan Inamdar

Megan Lynn Mcguire

Min Kyung Kim

Makesh Krishnan

Systems, computer program products, and methods are described herein for query interface response synthesis via machine learning and progressive query data decomposition. The present disclosure includes receiving a document, parsing retrievable text in the document to identify a query in the retrievable text, decomposing the query, using a generative AI model comprising a large language model, into a sub-query sequence, wherein the sub-query sequence comprises a plurality of sub-queries, the plurality of sub-queries within the sub-query sequence successively increasing in complexity, retrieving, using a retriever, data records corresponding with a user identifier, transmitting the data records to the generative AI model, generating, within a first persistent dialogue session of the generative AI model, successive responses according to the sub-query sequence, and collating the successive responses into collated response data.

System and method for query interface response synthesis via machine learning and progressive query data decomposition

Systems, computer program products, and methods are described herein for automatically building dynamic queries for identifying data in unstructured datasets. The present disclosure is configured to receive a plurality of pre-defined query templates associated with an alert type(s); dynamically filter the plurality of pre-defined query templates based on the alert type(s); identify an unstructured database note(s) based on a user identifier; apply the unstructured database note(s) and the filtered plurality of pre-defined query templates to an unstructured notes search engine; generate, by the unstructured notes search engine, at least one raw score for the at least one unstructured database note and for each alert type(s); transform, by the unstructured notes search engine, the at least one raw score to a relevancy score using a quantile transformation; and determine a highest relevancy score for each of the at least one unstructured database note for the user identifier.

Systems and methods for automatically building dynamic queries for identifying data in unstructured datasets

Growing community of inventors

Jersey City, NJ, United States of America

Nizar Naitlho