Semantic Analysis for Active Knowledge Guidance in Documents

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face information overload and poor user experience when searching for relevant information due to the limitations of traditional document-based systems, which offer lower information density and ease of use compared to structured data interfaces.

Innovation Solution

A knowledge handling system performs deep semantic analysis on documents, visually highlighting and providing active knowledge guidance through user interfaces, allowing users to interact with and navigate deeper knowledge layers beyond the surface text.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If traditional document-based systems are used to present information, then access to more information is provided, but information density and ease of use deteriorate

Engineering Contradiction:
Improveamount of informationVSAvoidease of use
Core Design Contradiction:
Quantity of substanceVSEase of operation

Solution Approach 1:

The patent segments information into structured data elements and unstructured document content, allowing each to be processed and presented through appropriate interfaces. Structured data is organized into searchable fields while document content is processed through semantic analysis, enabling users to access information in organized segments rather than overwhelming raw text.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a hybrid interface that acts as an intermediary between structured data systems and unstructured document systems. This intermediary processes both data types through semantic analysis and presents them through a unified interface, combining the information access capabilities of document systems with the ease of use of structured data interfaces.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Quantity of substance

If traditional document-based systems are used to present information, then access to more information is provided, but information density deteriorates

Engineering Contradiction:
Improveamount of informationVSAvoidinformation density
Core Design Contradiction:
Quantity of substanceVSLoss of information

Solution Approach 1:

The patent performs preliminary semantic analysis on document content before presentation, extracting key information, entities, and relationships in advance. This preprocessing creates structured representations of unstructured content, enabling high information density display without requiring users to wade through raw text, thus preserving information while enhancing accessibility.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent transforms unstructured document content into structured data representations through semantic analysis, changing the parameter of information organization from free-text format to structured fields and relationships. This transformation maintains the full information content while enabling dense, efficient presentation similar to structured data interfaces.

Inventive Principle:
Principle #35Parameter changes

3Loss of information

If semantic analysis is performed on documents to provide deeper insights, then knowledge availability is improved, but system complexity increases

Engineering Contradiction:
Improveknowledge availabilityVSAvoidsystem complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent implements a universal semantic analysis engine that processes both structured data and unstructured document content through the same analytical framework. This multi-functional system handles entity recognition, relationship extraction, and semantic querying across different data types, reducing overall system complexity by eliminating the need for separate processing pipelines for different data formats.

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

Data Source

PatentUS9824088B2Active knowledge guidance based on deep document analysis
Publication Date: 2017.11.21 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US9824088B2 patent drawing
  • US9824088B2 patent drawing
  • US9824088B2 patent drawing

AI summary

An approach is provided for an information handling system to present knowledge-based information. In the approach, a semantic analysis is performed on the document with the analysis resulting in various sets of semantic content. Each of the sets of semantic content corresponds to an area in the document. The areas of the document are visually highlighted using visual indicators that show the availability of the sets of semantic content to a user via a user interface. In response to a user selection, such as a selection using the user interface or a user specified configuration setting, a selected set of semantic content is displayed to the user using the interface.