US 12,189,691 B2
Natural language question answering systems
Amit Prakash, Saratoga, CA (US); Ravi Tandon, San Jose, CA (US); Manikanta Venkata Rahul Balakavi, Mountain View, CA (US); Pavan Ram Piratla, Campbell, CA (US); Ashish Shubham, Mountain View, CA (US); Alonzo Canada, Menlo Park, CA (US); Rakesh Kothari, San Jose, CA (US); Maneesh Apte, Redwood City, CA (US); Amitabh Singhal, Palo Alto, CA (US); Aditya Viswanathan, Redwood City, CA (US); and Ajeet Singh, Saratoga, CA (US)
Assigned to ThoughtSpot, Inc., Mountain View, CA (US)
Filed by ThoughtSpot, Inc., Mountain View, CA (US)
Filed on Sep. 1, 2023, as Appl. No. 18/459,887.
Application 18/459,887 is a continuation of application No. 17/506,819, filed on Oct. 21, 2021, granted, now 11,790,006.
Application 17/506,819 is a continuation of application No. 16/262,796, filed on Jan. 30, 2019, granted, now 11,157,564, issued on Oct. 26, 2021.
Claims priority of provisional application 62/760,563, filed on Nov. 13, 2018.
Claims priority of provisional application 62/637,823, filed on Mar. 2, 2018.
Prior Publication US 2024/0070204 A1, Feb. 29, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 17/30 (2006.01); G06F 16/242 (2019.01); G06F 16/2453 (2019.01); G06F 16/903 (2019.01); G06N 5/04 (2023.01); G06N 7/01 (2023.01)
CPC G06F 16/90335 (2019.01) [G06F 16/243 (2019.01); G06F 16/24534 (2019.01); G06N 5/04 (2013.01); G06N 7/01 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
identifying a current set of context features for a database query that is associated with a string, wherein the database query includes a sequence of tokens of a database syntax, and the current set of context features includes words from the string and tokens from the database query;
selecting an inference record from an inference store based on a comparison of the current set of context features to context features of inference records in the inference store,
wherein the inference record includes a set of context features, a corresponding resolution, and an inference type selected from a set comprising superlative disambiguation and date disambiguation, and
wherein the inference record is learned based on user selections and feedback during query formulations;
modifying the database query using a resolution of the inference record to obtain an inferred database query, wherein the resolution includes one or more tokens of the database syntax; and
invoking a search of a database using a query based on the inferred database query to obtain search results.