US 11,853,335 B1
Cooperative build and content annotation for conversational design of virtual assistants
Muhtar Burak Akbulut, Waban, MA (US); Pankaj Dhoolia, Ghaziabad (IN); Andy James Stoneberg, Clarksburg, MD (US); Dan O'Connor, Cambridge, MA (US); and Sachindra Joshi, Gurgaon (IN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jun. 13, 2022, as Appl. No. 17/806,559.
Int. Cl. G06F 16/332 (2019.01); G06F 16/31 (2019.01)
CPC G06F 16/332 (2019.01) [G06F 16/316 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
formulating, by one or more processors, a build context based on a build activity of a user;
formulating, by the one or more processors, one or more content queries based on the build context;
building, by the one or more processors, a content index for content and content-fragment texts by augmenting a text-search index with ability to handle conversational annotation schemes defined by a canonical representation according to a build environment of the build activity;
building, by the one or more processors, a neural Information Retrieval (IR) index on conversational content annotations;
searching, by the one or more processors, the content index and the neural IR index in parallel using the one or more content queries to identify content relevant to the build context;
determining, by the one or more processors, at least one recommendation for the user based on heuristic rules applied to the build context and the identified content, wherein each recommendation is a build suggestion or a content annotation suggestion.