Natural Language Query Restatements for Data Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The increasing complexity and cost of managing and storing large volumes of data across various storage systems pose challenges for organizations, as different data storage technologies offer varying performance benefits, leading to data dispersion across multiple locations and types of storage systems, making it difficult for users to interact with and understand the available data sets for business intelligence and analytics.

Innovation Solution

Implementing a natural language query processing system that allows users to submit queries without knowing the underlying data storage system interfaces, using query restatements to explain and improve query performance, and providing visualizations to verify results, while utilizing metadata to enhance data set management and processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If data is stored across multiple different storage systems to optimize performance and features, then data analysis capability is improved, but system complexity increases

Engineering Contradiction:
Improvedata analysis capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a unified data storage interface as an intermediary layer between users and multiple storage systems. This interface abstracts the complexity of different storage technologies while enabling access to diverse data sets, thus maintaining high adaptability without increasing user-facing system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The unified data storage interface provides universal access to multiple types of storage systems through a single interface. This multi-functional approach allows the system to work with various storage technologies (relational databases, object stores, data streams) without requiring separate interfaces for each, thereby improving versatility while managing complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Speed

If data is distributed across multiple storage locations to optimize performance, then data retrieval speed is improved, but ease of operation deteriorates

Engineering Contradiction:
Improvedata retrieval speedVSAvoidease of operation
Core Design Contradiction:
SpeedVSEase of operation

Solution Approach 1:

The unified data storage interface acts as a mediator that handles the complexity of accessing data distributed across multiple storage locations. Users interact with a single interface that automatically manages data retrieval from optimized locations, thus maintaining high retrieval speed while preserving ease of operation.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs self-service by automatically managing data distribution and retrieval optimization without requiring user intervention. The unified interface handles the complexity of locating and retrieving data from multiple storage systems, allowing users to operate the system easily while maintaining high performance.

Inventive Principle:
Principle #25Self-service

3Productivity

If specialized storage technologies are used for different data types, then data management performance is improved, but cost increases

Engineering Contradiction:
Improvedata management performanceVSAvoidcost
Core Design Contradiction:
ProductivityVSQuantity of substance

Solution Approach 1:

The unified data storage interface provides universal access to multiple specialized storage technologies through a single interface. This allows the system to leverage the performance benefits of different storage types for appropriate data while avoiding the cost of implementing and maintaining separate interface systems for each storage technology.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system changes the interface parameter from multiple specialized interfaces to a single unified interface, while maintaining the ability to access specialized storage technologies. This parameter change reduces the cost of system complexity while preserving the performance benefits of specialized storage for different data types.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11726994B1Providing query restatements for explaining natural language query results
Publication Date: 2023.08.15 AMAZON TECH INC
  • US11726994B1 patent drawing
  • US11726994B1 patent drawing
  • US11726994B1 patent drawing

AI summary

Query restatements may be provided for explaining natural language query results. A natural language query is received at a natural language query processing system. An intermediate representation of the natural language query is generated for executing the natural language query. The intermediate representation is translated into a natural language restatement of the natural language query. The natural language restatement is provided with a result of the natural language query via an interface of the natural language query processing system.