Translation Engine for Non-Natural Language Data Conversion

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional question-answering systems face difficulties in handling non-natural language data sources, limiting their generic applicability due to the need for specific programming and inability to support multiple database sources, especially when dealing with mixed data formats.

Innovation Solution

A method and system that translate non-natural language document data into natural language form by determining the data type from a detection and conversion database, applying appropriate conversion rules, and outputting the data in a consumable format for natural language engines, enabling the handling of diverse data types and formats.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional QA systems handle non-natural language data sources, then specific programming is required, but generic applicability deteriorates

Engineering Contradiction:

Improvehandling capabilityVSAvoidgeneric applicability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent introduces a translation engine as an intermediary component that converts non-natural language data from multiple sources into a unified natural language format. This mediator layer enables the QA system to handle diverse data sources (databases, flat files, XML, HTML, etc.) without requiring specific programming for each source type, thereby maintaining generic applicability while improving handling capability

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system segments the data processing workflow into distinct modules: data extraction modules for different source types, a translation engine for format conversion, and a QA processing module. This segmentation allows each component to handle its specific function independently, enabling the system to process multiple data types through a standardized pipeline without requiring overall system reprogramming

Inventive Principle:

Principle #1Segmentation

2Ease of manufacture

If mail merge technique is used to convert database data to natural language, then conversion is achieved, but support for multiple database sources is limited

Engineering Contradiction:

Improveconversion capabilityVSAvoidmulti-source support

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The translation engine is designed with universal functionality to handle multiple database sources and data formats through a single unified interface. It supports extraction from databases, flat files, XML, HTML, and other formats using the same conversion mechanism, eliminating the need for separate mail merge operations for each source type and enabling multi-source support while maintaining ease of conversion

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10169337B2Converting data into natural language form

Publication Date: 2019.01.01 KYNDRYL INC

AI summary

Converting technical data from field oriented electronic data sources into natural language form is disclosed. An approach includes obtaining document data from an input document, wherein the document data is in a non-natural language form. The approach includes determining a data type of the document data from one of a plurality of data types defined in a detection and conversion database. The approach includes translating the document data to a natural language form based on the determined data type. The approach additionally includes outputting the translated document data in natural language form to an output data stream.