US 12,413,664 B2
Identification and prevention of sensitive information exposure in telephonic conversations
Manu K M, Bangalore (IN); Balaji Sankar Kumar, Bangalore (IN); Vidya Chandrashekar, Bangalore (IN); vamshi dondapati, Hyderabad (IN); Arun Aravind, Mahe (IN); Akshat Dixit, Lucknow (IN); and Arun Sabaresh Anantha Narayanan, Bangalore (IN)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jul. 19, 2023, as Appl. No. 18/223,815.
Prior Publication US 2025/0030795 A1, Jan. 23, 2025
Int. Cl. H04M 3/22 (2006.01); G10L 15/18 (2013.01); H04L 9/08 (2006.01); H04L 9/30 (2006.01)
CPC H04M 3/2281 (2013.01) [G10L 15/1815 (2013.01); H04L 9/088 (2013.01); H04L 9/30 (2013.01); H04M 3/2218 (2013.01); H04M 2201/40 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
converting to text data in real-time, by a voice-to-text converter, voice data of a conversation occurring in real-time between a first party and a second party;
extracting, by an extractor, an intent and an entity from the text data, wherein the intent comprises a request by the first party to the second party, and wherein the entity comprises a category of information being requested;
predicting, by a predictor, based on the request and the category of information being requested, a sensitive information that is likely to be disclosed in the real-time conversation;
comparing, by an intersector, the text data in real-time to the predicted sensitive information;
determining, by the intersector, responsive to the comparing, whether the text data includes the predicted sensitive information; and
intersecting, by the intersector, responsive to a determination that the text data includes the predicted sensitive information, the voice data.