US 11,714,841 B2
Systems and methods for processing a natural language query in data tables
Nikunj Agrawal, New Delhi (IN); Mukund Sundararajan, Sunnyvale, CA (US); Shrikant Ravindra Shanbhag, Jersey City, NJ (US); Kedar Dhamdhere, Sunnyvale, CA (US); Null Garima, Bengaluru (IN); Kevin Snow Mccurley, San Jose, CA (US); Rohit Ananthakrishna, Bangalore (IN); Daniel Adam Gundrum, New York, NY (US); Juyun June Song, Brooklyn, NY (US); and Rifat Ralfi Nahmias, Mountain View, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on May 3, 2021, as Appl. No. 17/306,666.
Application 17/306,666 is a continuation of application No. 15/408,664, filed on Jan. 18, 2017, granted, now 10,997,227.
Prior Publication US 2021/0271697 A1, Sep. 2, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/00 (2019.01); G06F 16/338 (2019.01); G06F 3/16 (2006.01); G06T 11/20 (2006.01); G06F 16/332 (2019.01); G06F 16/33 (2019.01); G06F 40/18 (2020.01); G06F 40/58 (2020.01); G06F 40/205 (2020.01)
CPC G06F 16/338 (2019.01) [G06F 3/167 (2013.01); G06F 16/3326 (2019.01); G06F 16/3337 (2019.01); G06F 40/18 (2020.01); G06F 40/58 (2020.01); G06T 11/206 (2013.01); G06F 40/205 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for processing a natural language query, the method comprising:
obtaining a natural language query;
parsing the natural language query to obtain a query term;
identifying a grid range in a data table as relevant to the query term;
preparing a table summary by extracting a plurality of characteristics from the grid range in the data table;
determining a logic operation to apply on the plurality of characteristics to derive a result corresponding to the query term;
translating the logic operation into a formula executable on the data in the data table;
applying the formula to the data in the data table to generate the result in response to the natural language query;
responsive to receiving negative feedback to the result, automatically processing the negative feedback and preparing a new table summary based on the query term, wherein automatically processing the negative feedback comprises disassociating one or more formula building objects with the query term;
generating an alternative formula of the natural language query based on the new table summary; and
generating an alternative result based on the alternative formula.