Question Answering System Structured Unstructured Data Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional question answering systems are limited in their ability to effectively address questions that require information from both structured and unstructured data sources, as they often rely solely on one type of data source, which can lead to incomplete or inaccurate answers.

Innovation Solution

A method that analyzes user input questions to identify portions answerable from structured and unstructured data sources separately, constructs queries for each type of source, and merges the retrieved information to provide comprehensive answers, utilizing entailment analysis to identify supporting evidence from unstructured data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a QA system relies solely on structured data sources, then query processing is efficient and straightforward, but the system cannot answer questions requiring unstructured information

Engineering Contradiction:
Improveability to answer questions from multiple data sourcesVSAvoidsystem architecture complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system divides the question analysis process into segments: identifying structured data portions and unstructured data portions separately. This segmentation allows the system to process each type of data source appropriately while maintaining overall system manageability and avoiding overwhelming complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The QA system is designed with multi-functionality to handle both structured and unstructured data sources through a unified architecture. The system can adaptively select and process different data types based on question requirements, enhancing versatility without requiring entirely separate systems.

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

2Loss of information

If a QA system uses only unstructured data sources, then comprehensive information can be retrieved, but query processing becomes inefficient and less precise

Engineering Contradiction:
Improvecompleteness of answer informationVSAvoidquery processing efficiency
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The system applies different processing qualities to different portions of the question: structured data portions are processed with precise, efficient query methods, while unstructured data portions receive comprehensive text analysis. This local quality approach ensures optimal processing efficiency for each data type while maintaining complete information retrieval.

Inventive Principle:
Principle #3Local quality

3Reliability

If a QA system attempts to process both structured and unstructured data simultaneously, then complete answers can be provided, but the processing complexity and computational resources increase significantly

Engineering Contradiction:
Improveaccuracy of question answersVSAvoiddata processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the data processing pipeline into distinct pathways for structured and unstructured data, with separate processing logic for each. This segmentation maintains answer accuracy by applying appropriate processing methods to each data type while reducing overall processing complexity through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary analysis to identify which portions of the question require structured data and which require unstructured data before initiating full processing. This preliminary action allows the system to prepare appropriate processing strategies in advance, reducing computational complexity while ensuring accurate and complete answers.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10303798B2Question answering from structured and unstructured data sources
Publication Date: 2019.05.28 MICROSOFT TECHNOLOGY LICENSING LLC
  • US10303798B2 patent drawing
  • US10303798B2 patent drawing
  • US10303798B2 patent drawing

AI summary

Techniques for question answering involve receiving, from a user, a text input expressing a question in natural language. The text input may be analyzed, including identifying in the question at least one first portion answerable from at least one structured data source, and at least one second portion answerable from at least one unstructured data source. At least one first query configured for the structured data source(s) may be constructed from the at least one first portion of the question and applied to the structured data source(s) to retrieve first answer information for the at least one first portion of the question. At least one second query configured for the unstructured data source(s) may be constructed from the at least one second portion of the question and applied to the unstructured data source(s) to retrieve second answer information for the at least one second portion of the question.