Natural Language Query System for Database Autocomplete

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Typical database management systems require users to have knowledge of data parameters and query languages, making it difficult and time-consuming to query complex data effectively, especially for business users who are not database administrators.

Innovation Solution

Natural Language Query (NLQ) allows users to ask questions in a conversational manner, using templates to parse and autocomplete queries, enabling users to interact with databases without needing to know specific measures, dimensions, or filters, and providing feedback for invalid queries.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional database management systems are used, then data can be stored and retrieved, but users require extensive knowledge of data parameters and query languages making operation difficult

Engineering Contradiction:

Improveease of querying dataVSAvoidcomplexity of query language requirements

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces a natural language processing intermediary layer between the user and the database management system. This intermediary translates conversational user input into formal query language, eliminating the need for users to learn complex query syntax while maintaining full database functionality. The system acts as a mediator that handles the complexity internally while presenting a simple interface to users.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical system of manual query construction with an automated natural language processing system. Instead of requiring users to manually assemble complex queries according to strict syntax rules, the system automatically parses and translates natural language input into executable database queries, substituting automated intelligence for manual mechanical operations.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If complex queries are set up and stored by database administrators, then query results can be obtained, but it requires significant training and user effort

Engineering Contradiction:

Improvequery result efficiencyVSAvoidtime for learning query languages

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent enables users to perform database querying themselves using natural language without requiring training from database administrators. The system provides self-service capabilities where users can independently construct and execute queries through conversational input, eliminating the time investment required for formal training while maintaining query effectiveness.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary translation and parsing of natural language input into executable query format before execution. This preliminary processing step converts user-friendly language into the structured format required by the database system, preparing the query in advance without requiring the user to perform the complex transformation manually.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If various query languages are used across databases, then data can be accessed, but processing power is consumed to parse query inputs

Engineering Contradiction:

Improvecompatibility with different databasesVSAvoidprocessing power for query parsing

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The natural language processing system serves as a universal intermediary that translates diverse natural language inputs into database-specific query formats. Rather than requiring the database system to parse multiple query language variations, the intermediary handles the translation work, converting user input into the appropriate format for each database type, thereby reducing the processing burden on the database engine.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11055353B2Typeahead and autocomplete for natural language queries

Publication Date: 2021.07.06 SALESFORCE INC

AI summary

Embodiments are described for enabling a user to query a database using natural language and receive results without requiring the user to manipulate or know details of the database contents. The user is guided in the creation of the natural language query by suggested predetermined queries from a template. Natural language is parsed using the template. The approach allows a user's query words to be completed automatically from the template as the user inputs the words. The approach further allows the next suggested parts of the query to be automatically typed from the template ahead of the user's cursor. Other features provide feedback to the user for invalid or irrelevant queries that cannot be parsed, including suggesting complete predetermined queries from the template. The approach helps the user focus the query on exactly what the user seeks to learn from the database without complex, process-intensive parsing.