Natural Language Question Translation to Database Queries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems cannot understand natural language questions and correlate data values in document tables without pre-formatted database queries, limiting their ability to provide answers to user inquiries.

Innovation Solution

A mechanism that translates natural language questions into database query format by identifying key terms and classifying them as variable names or operation names, allowing the system to generate answers by converting the question into a structured query that can be applied to a data table.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing systems use pre-formatted database queries to perform data table operations, then data processing accuracy is improved, but system complexity and user operation difficulty increase

Engineering Contradiction:

Improvedata processing accuracyVSAvoiduser operation difficulty

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent introduces a natural language processing intermediary layer between the user and the database query system. This intermediary translates user-friendly natural language questions into structured database queries automatically, eliminating the need for users to manually format complex SQL statements while maintaining query accuracy through systematic translation rules and semantic understanding

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If existing systems require manual input of formatted database queries, then query precision is improved, but productivity decreases

Engineering Contradiction:

Improvequery precisionVSAvoiddata retrieval efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system implements self-service by automatically generating and optimizing database queries based on natural language input. The natural language processing system autonomously performs query formulation, parameter extraction, and database operation selection without requiring manual intervention for query formatting, thereby maintaining precision while significantly improving productivity

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent applies preliminary action by pre-defining query templates and structured translation rules that map natural language patterns to database operations. This preparation work is done in advance, allowing the system to quickly translate user questions into precise queries without time-consuming manual formatting during actual data retrieval operations

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11243948B2System and method for generating answers to natural language questions based on document tables

Publication Date: 2022.02.08 SALESFORCE INC

AI summary

Embodiments described herein provide a mechanism that translates a natural language question to a database query format that may be applied to a data table to generate an answer to the natural language question. The system may identify key terms from a natural language question and classify the key terms as variable names or operation names. The natural language question is than translated into a format of question template containing variable names and operation names. In this way, the system may map the template question to a database query which can be applied to operate on a relational database to identify a cell value that represents an answer to the natural language question.