Table Attribute Complementer for Relationship Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Automatically detecting corresponding relationships between tables with varying structures in documents is challenging due to missing attribute names and differing heading arrangements, leading to incorrect identification of table relationships.

Innovation Solution

An information processing apparatus that includes a complementer to add missing attributes to tables, a converter to standardize table structures, and a determiner to accurately identify corresponding relationships by analyzing and comparing the attributes and subjects across tables.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automatic detection methods are used to identify corresponding relationships between tables, then detection speed is improved, but detection accuracy deteriorates due to varying table structures and missing attributes

Engineering Contradiction:

Improvedetection speedVSAvoiddetection accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The complementer performs preliminary action by adding missing attribute names to tables before the determiner attempts to detect corresponding relationships. This pre-processing step ensures that all necessary information is available upfront, enabling accurate automatic detection without requiring manual verification later.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The complementer acts as an intermediary between the raw table data and the determiner. It mediates the detection process by supplementing incomplete table structures with inferred attribute names, thereby bridging the gap between varying table formats and the requirements for accurate relationship detection.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual verification is used to check corresponding relationships between tables, then detection accuracy is improved, but time consumption increases significantly

Engineering Contradiction:

Improvedetection accuracyVSAvoidchecking time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically detecting and correcting its own deficiencies. The complementer autonomously identifies missing attributes and adds them without human intervention, and the determiner automatically detects corresponding relationships, eliminating the need for manual verification while maintaining high accuracy.

Inventive Principle:

Principle #25Self-service

3Device complexity

If tables with varying structures are directly compared, then processing simplicity is maintained, but detection reliability deteriorates due to missing attributes and differing heading arrangements

Engineering Contradiction:

Improveprocessing simplicityVSAvoiddetection reliability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The complementer applies local quality by adding attributes specifically where they are missing in each table, rather than requiring complete standardization of the entire table structure. This targeted approach maintains the original simplicity of each table's local structure while ensuring that all necessary information is present for reliable comparison.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS11526660B2Information processing apparatus for complementing a heading of a table

Publication Date: 2022.12.13 KK TOSHIBA

AI summary

An embodiment of the present invention provides an information processing apparatus capable of complementarily adding an attribute not included in a table in order to detect tables having a corresponding relationship. An information processing apparatus as an embodiment of the present invention includes a complementer. The complementer complementarily adds an attribute not included in a first table based on a content of at least one of the first table and an electronic document including the first table.