US 12,229,151 B2
System and method for intelligent knowledge access
Peter Yeh, Milpitas, CA (US); Ezra Story, Seattle, WA (US); and Prateek Jain, San Jose, CA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jun. 21, 2022, as Appl. No. 17/845,982.
Application 17/845,982 is a continuation of application No. 15/785,354, filed on Oct. 16, 2017, granted, now 11,372,862.
Prior Publication US 2022/0318256 A1, Oct. 6, 2022
Int. Cl. G06F 16/2457 (2019.01); G06F 16/2452 (2019.01); G06F 16/2455 (2019.01); G06N 5/04 (2023.01); G10L 15/22 (2006.01)
CPC G06F 16/24578 (2019.01) [G06F 16/24522 (2019.01); G06F 16/2455 (2019.01); G06N 5/04 (2013.01); G10L 15/22 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a natural language query;
mapping the received natural language query to one or more providers of a plurality of providers using provider capability descriptions;
generating a plurality of candidate query plans based on the mapping;
executing a first query plan from the generated plurality of candidate query plans;
responsive to the executed first query plan returning no results, executing a next query plan from the generated plurality of candidate query plans; and
responsive to the executed first query plan returning results, combining the returned results, including:
applying hard constraints to generate filtered results; and
applying soft constraints to the filtered results to generate an answer.