Keyword Derivation from Technical Document Fields
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing technology trends, such as the Delphi technique, have low accuracy, and using abstract keywords from news and public announcements is inadequate for defining technical trends and deriving detailed technologies.
Innovation Solution
A method and apparatus that search technical documents using data fields like titles, summaries, and keywords to generate and score keyword sets, re-search documents, and derive representative keywords and documents, improving the accuracy of trend analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the Delphi technique is used to analyze technology trends by examining expert opinions, then comprehensive technology trend analysis can be achieved, but the accuracy is low (about 30%)
Solution Approach 1:
The patent replaces the manual expert opinion-based Delphi technique with an automated data mining system that processes technical documents, keywords, and citations computationally to derive technology trends, thereby improving accuracy while reducing methodological complexity
Solution Approach 2:
The patent introduces an intermediary keyword derivation system that acts as a bridge between raw technical documents and technology trend analysis, using automated keyword extraction and document scoring to objectively identify technology trends without relying on subjective expert opinions
2Adaptability or versatility
If abstract keywords from news and public announcements are used to define technical trends, then broad coverage can be achieved, but the ability to define detailed technologies is inadequate
Solution Approach 1:
The patent segments the analysis into multiple levels: first extracting keywords from technical documents, then using those keywords to search and score documents, and finally deriving detailed technology definitions from the scored documents, thereby achieving both broad coverage and precise technology definition
Solution Approach 2:
The patent adds a new dimension of analysis by using citation data and document scoring based on multiple data fields (title, summary, keywords) to transform abstract keyword matching into a multi-dimensional technology trend analysis that captures both breadth and depth
3Measurement precision
If multiple data fields (title, summary, keywords) are used to generate and score keyword sets, then representative keywords can be derived, but the processing complexity increases
Solution Approach 1:
The patent performs preliminary actions by first extracting keywords from multiple data fields (title, summary, keywords) to generate an initial keyword set, which is then scored and refined before being used for document searching and technology trend derivation, thereby managing complexity through staged processing
Data Source
AI summary
A method includes searching a technical document including a first, second, and third data fields based on search terms and search year ranges related to a technical field, generating a keyword set using the first, second, and third data fields of the searched technical document, scoring a plurality of keywords included in the keyword set, and selecting some of the plurality of keywords, re-searching the technical document related to the technical field, using the selected keywords, scoring the re-searched technical document to derive a representative document representing the technical field, and deriving a representative keyword representing the technical field, using the second data field included in the representative document, wherein the first data field includes a title of the technical document, the second data field includes a summary of the technical document, and the third data field includes keywords of the technical document.