Automated Chemical Name Identification in Text Documents

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manually searching for chemical names in large documents is time-consuming and prone to overlooking relevant terms, as existing methods lack an efficient automated process for identification.

Innovation Solution

A method and software that compare words in documents against lists of non-chemical words, regular expressions for chemical prefixes and suffixes, and synonyms to distinguish and highlight chemical names, allowing for grouping and occurrence counting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If manual search is used to find chemical names in large documents, then accuracy can be maintained, but time consumption increases significantly

Engineering Contradiction:

Improvetime to search for chemical namesVSAvoidspeed of chemical name identification

Core Design Contradiction:

Loss of timeVSProductivity

Solution Approach 1:

The patent replaces manual mechanical search processes with an automated computer-based system that uses regular expressions and data structures to identify chemical names. The system processes documents electronically, comparing words against predefined patterns and chemical name databases, thereby eliminating the need for human readers to manually scan through large documents while maintaining identification accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically performing the search and identification tasks that would otherwise require manual human intervention. The automated algorithm processes the document independently, comparing each word against the list of chemical names and regular expressions without requiring user input or manual scanning, thus significantly reducing search time while maintaining comprehensive coverage.

Inventive Principle:

Principle #25Self-service

2Reliability

If manual review is performed thoroughly to avoid overlooking chemical names, then reliability improves, but time required increases

Engineering Contradiction:

Improvecompleteness of chemical name identificationVSAvoidtime for thorough document review

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-compiling comprehensive lists of chemical names, synonyms, and regular expressions before processing the document. These predefined patterns and databases are prepared in advance, allowing the system to immediately compare against them during document processing without requiring time-consuming on-the-fly analysis, thus ensuring complete coverage while reducing processing time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual thorough review with an automated systematic comparison process. The computer algorithm methodically compares each word in the document against the predefined list of chemical names and regular expressions, ensuring no potential matches are overlooked. This automated systematic approach maintains the reliability of thorough review while eliminating the time consumption associated with manual processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated processes are implemented to speed up chemical name identification, then productivity improves, but complexity of the system increases

Engineering Contradiction:

Improvespeed of chemical name locationVSAvoidcomplexity of automated identification system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing the complex task of chemical name identification into multiple simpler stages: (1) comparing words against a list of non-chemical words to filter them out, (2) comparing remaining words against a list of chemical names for exact matches, and (3) applying regular expressions to identify chemical terms with prefixes, suffixes, or combinations. This segmentation of the processing logic into discrete, manageable steps reduces overall system complexity while maintaining high productivity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system uses intermediary data structures including lists of non-chemical words, lists of chemical names, and regular expression patterns as mediators between the input text and the identification process. These intermediary structures serve as pre-processed reference materials that simplify the comparison operations, allowing the system to efficiently identify chemical names without requiring complex real-time analysis algorithms.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS8046212B1Identification of chemical names in text-containing documents

Publication Date: 2011.10.25 ACCESS INNOVATIONS

AI summary

A method and computer software for rapid searching of text-containing documents and identifying and isolating chemical names and common chemical expressions from surrounding text. The chemical names are returned to the user in a list which is arranged in descending order based on the number of occurrences of each chemical name. The list can also contain all synonyms for each chemical name found.