The Bank of New York Mellon Corporation

Deeya Patel

Matthew Champlin

Richard Joseph Comeau

Divek Patel

Karan Keerthy

Nitin Seshadri

Chaz Anthony Darvish

The disclosure relates to a multi-agent framework that includes a plurality of language model (LM) agents that each perform a respective Natural Language Processing (NLP) task to analyze content having natural language text. An LM agent may execute a language model to perform its respective NLP task. For example, to identify target information within content, a first LM agent in the multi-agent framework may generate a summary of the content along with the target information, a second LM agent may extract, independently from the first LM agent, the target information and output reasoning that explains why the target information was extracted, and a third LM agent may verify that the target information was correctly identified based on the output of the first and second LM agents.

Multi-agent framework for natural language processing

An eyesight device for the visually impaired comprises a case having a front, rear and side walls. An ultrasonic sensor is provided on at least the front wall although, preferably, ultrasonic sensors are provided on the front and side walls to provide a greater range of peripheral vision. A microcontroller within the case is coupled to the ultrasonic sensor. A power source energizes the microcontroller. An audible signal generating means is adapted to generate an audible signal. The microcontroller is programmed to receive the output of the ultrasonic sensor and computing the distance between the case and an obstacle spaced from the case and energize the audible signal generating means when the distance is less than a preselected threshold distance. Attaching means is provided for attaching the case to an item of clothing of the user to free the hands of the user.

Advanced eyesight device for visually impaired

Growing community of inventors

Ossining, NY, United States of America

Deeya Patel