US 12,462,110 B2
Natural language generation system for automated translation of digital multimedia
George Anthony Albero, Charlotte, NC (US); Maharaj Mukherjee, Poughkeepsie, NY (US); and Prashant Thakur, Gujarat (IN)
Assigned to BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed by BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed on Apr. 18, 2023, as Appl. No. 18/135,800.
Prior Publication US 2024/0355317 A1, Oct. 24, 2024
Int. Cl. G06F 40/40 (2020.01); G10L 13/08 (2013.01); H04N 21/43 (2011.01); H04N 21/439 (2011.01)
CPC G06F 40/40 (2020.01) [G10L 13/086 (2013.01); H04N 21/4307 (2013.01); H04N 21/4396 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A natural language generation system for automated translation of digital multimedia, the system comprising:
a processing device;
a non-transitory storage device containing instructions when executed by the processing device, causes the processing device to perform the steps of:
receive, from a user input device, a search request, wherein the search request comprises a search query and a preferred natural language for a response to the search query;
determine the response for the search query in a first natural language, wherein the response comprises digital multimedia;
reconfigure the response for display on the user input device in the preferred natural language, wherein reconfiguring further comprises:
determining an intermediate natural language based on a lexical similarity with the preferred natural language;
translating, using a first natural language translation subsystem, the response from the first natural language to the intermediate language;
determining that only a portion of the response is applicable to the search query; and
translating, using a second natural language translation subsystem, the portion of the response from the intermediate language to the preferred natural language while retaining a remaining portion of the response in the intermediate language; and
transmit the reconfigured response to be displayed on the user input device, wherein the portion of the reconfigured response is displayed in the preferred natural language.