Natural Language Interface for Database Search

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional database interfaces require users to have knowledge of formal syntax or underlying database structure, and maintaining large-scale ontologies for natural language searches in large databases is resource-intensive and time-consuming.

Innovation Solution

A natural language interface that identifies and ranks possible logical interpretations of user queries, eliminating irrelevant tokens and generating queries compatible with the database structure, allowing users to search databases without formal syntax knowledge and reducing the need for extensive ontologies through integration with in-memory relational engines.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional database interfaces with formal syntax are used, then search accuracy is maintained, but user accessibility deteriorates

Engineering Contradiction:

Improveuser accessibilityVSAvoidsyntax knowledge requirement

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces a natural language processing intermediary layer that translates user-friendly natural language queries into formal database query syntax. This mediator handles the complexity of syntax translation automatically, allowing users to interact with databases using natural language while maintaining the precision of formal query languages in the background.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system employs automated query generation and optimization capabilities that self-serve the translation from natural language to formal syntax without requiring user intervention. The system automatically understands intent, generates appropriate queries, and optimizes them for execution, eliminating the need for users to learn or manually construct formal syntax.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If large-scale ontologies are maintained for natural language searches, then search capability is improved, but resource consumption increases

Engineering Contradiction:

Improvenatural language search capabilityVSAvoidontology maintenance resources

Core Design Contradiction:

Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

Instead of maintaining comprehensive large-scale ontologies for all possible domains, the system applies partial action by focusing on context-relevant vocabulary and concepts specific to each database domain. The natural language processing is tailored to the specific data being queried, processing only the necessary linguistic patterns rather than maintaining exhaustive ontological knowledge bases.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent segments the ontology requirement into domain-specific, database-specific linguistic models rather than requiring a single large-scale universal ontology. Each database or data domain has its own tailored natural language processing configuration, dividing the overall system into independent, manageable segments that require fewer resources each.

Inventive Principle:

Principle #1Segmentation

3Measurement precision

If comprehensive ontology maintenance is performed, then natural language understanding is improved, but maintenance time increases

Engineering Contradiction:

Improvenatural language understanding accuracyVSAvoidontology maintenance time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system implements self-service through automated learning and adaptation mechanisms that continuously improve natural language understanding without manual ontology maintenance. The system automatically learns from query patterns, user feedback, and data characteristics, dynamically adjusting its linguistic models to maintain high accuracy without requiring ongoing manual ontology curation.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The natural language processing system is designed to be dynamic rather than static, automatically adapting to new vocabulary, query patterns, and data structures. This dynamic adaptation allows the system to maintain or improve understanding accuracy over time without the manual intervention required for static ontology updates.

Inventive Principle:

Principle #15Dynamics

4Ease of operation

If natural language processing is implemented without formal syntax knowledge, then ease of use is improved, but query accuracy may deteriorate

Engineering Contradiction:

Improvequery input simplicityVSAvoidquery interpretation accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system uses a sophisticated intermediary natural language processing layer that acts as a bridge between simple user input and precise query execution. This intermediary automatically disambiguates intent, selects appropriate interpretations, and translates natural language into accurate formal queries, maintaining precision without requiring users to understand or specify syntactic details.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS8862458B2Natural language interface

Publication Date: 2014.10.14 SAP SE

AI summary

The present disclosure involves systems, software, and computer implemented methods for providing a natural language interface for searching a database. One process includes operations for receiving a natural language query. One or more tokens contained in the natural language query are identified. A set of sentences is generated based on the identified tokens, each sentence representing a possible logical interpretation of the natural language query and including a combination of at least one of the identified tokens. At least one sentence in the set of sentences is selected for searching a database based on the identified tokens.