US Patent Application 18227450. SYSTEMS AND METHODS FOR PROCESSING A NATURAL LANGUAGE QUERY IN DATA TABLES simplified abstract

SYSTEMS AND METHODS FOR PROCESSING A NATURAL LANGUAGE QUERY IN DATA TABLES

Organization Name

GOOGLE LLC

Inventor(s)

Nikunj Agrawal of New Delhi (IN)

Mukund Sundararajan of Sunnyvale CA (US)

Shrikant Ravindra Shanbhag of Jersey City NJ (US)

Kedar Dhamdhere of Sunnyvale CA (US)

Garima of Bengaluru (IN)

Kevin Snow Mccurley of San Jose CA (US)

Rohit Ananthakrishna of Bangalore (IN)

Daniel Adam Gundrum of New York NY (US)

Juyun June Song of Brooklyn NY (US)

Rifat Ralfi Nahmias of Mountain View CA (US)

SYSTEMS AND METHODS FOR PROCESSING A NATURAL LANGUAGE QUERY IN DATA TABLES - A simplified explanation of the abstract

This abstract first appeared for US patent application 18227450 titled 'SYSTEMS AND METHODS FOR PROCESSING A NATURAL LANGUAGE QUERY IN DATA TABLES

Simplified Explanation

This patent application describes systems and methods for processing natural language queries on data tables. Here is a simplified explanation of the abstract:

• Obtaining a query term from a natural language query.
• Creating a table summary based on the query term.
• Generating a formula for the natural language query based on the table summary.
• Generating a result based on the formula.
• If negative feedback is received for the result, disassociating the table summary or formula from the query term.

Bullet points to explain the patent/innovation:

• The invention focuses on processing natural language queries on data tables.
• It involves obtaining a specific term from a natural language query.
• A table summary is prepared based on this term, providing an overview of the relevant data.
• A formula is generated based on the table summary, allowing for more accurate processing of the query.
• The formula is used to generate a result that best matches the query.
• If the result receives negative feedback, the system can disassociate the table summary or formula from the query term to improve future processing.

Original Abstract Submitted

Systems and methods are disclosed herein for processing a natural language query on data tables. According to some embodiments, a query term is obtained from a natural language query. A table summary is prepared based on the query term and a formula of the natural language query is generated based on the table summary. A result is generated based on the formula. Responsive to receiving negative feedback to the result, one or more of the table summary or the formula is disassociated from the query term.