JPMorgan Chase Bank Patent for Intent Prediction and Usage

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted a patent to JPMorgan Chase Bank, N.A. for systems and methods related to intent prediction and usage. The patent describes a process using machine learning to predict user intent from text and retrieve relevant artifacts from a content repository.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12586572B2 to JPMorgan Chase Bank, N.A. The patent covers systems and methods for intent prediction and usage, specifically detailing a process that involves tokenizing text, vectorizing tokens, using a machine learning model to predict intent, formatting a query based on that intent, retrieving an artifact from a content repository, and displaying it via an interface.

This patent grant is primarily an intellectual property development for JPMorgan Chase Bank and does not impose new regulatory obligations on other entities. However, it signifies advancements in AI and machine learning applications within the financial sector, particularly for enhancing customer interaction and content retrieval systems. Compliance officers in financial institutions may note this as an example of technological innovation in AI-driven services.

Source document (simplified)

← USPTO Patent Grants

Systems and methods for intent prediction and usage

Grant US12586572B2 Kind: B2 Mar 24, 2026

Assignee

JPMORGAN CHASE BANK, N.A.

Inventors

Sai Chaitanya Darla, Owen Churchill, Vlad Tyshkevich, Oluwaseye Adekanye, Jose Burgos, Siva Tanuku, Rudolph L. Mappus, IV

Abstract

In some aspects, the techniques described herein relate to a method including: tokenizing a text string into utterance tokens; vectorizing the utterance tokens; providing the utterance tokens to a machine learning model as input to the machine learning model; receiving, as output from the machine learning model, a predicted intent; formatting a query of a content repository, wherein the query includes the predicted intent; receiving, based on the query, an artifact from the content repository; and displaying the artifact via an interface.