An automated method for identifying TRIZ evolution trends from patents

Trend analysis of the Theory of Inventive Problem Solving (Russian acronym: TRIZ) identifies the evolutionary status of systems to seek directions for further improvement of technology by relating properties and functions obtained from patents to TRIZ trends. The property, which is a specific characteristic of a system, is usually described using adjectives; the function, which is an action that changes a feature of an object, is usually described using verbs. Methods exist to facilitate identification of TRIZ trends, but they rely heavily on human intervention to identify specific trends and trend phases. Therefore, this paper proposes a method that automates identification of TRIZ trends. The proposed method consists of (1) extracting binary relations of the 'adjective+noun' or 'verb+noun' forms from patents using natural language processing, (2) defining a 'reasons for jumps' rule base that arranges trend-specific binary relations for trend identification, and (3) determining specific trends and trend phases by measuring semantic sentence similarity between the binary relations from patents and the binary relations in the rule base. The final output of the method depicts the evolutionary potential as a normalized radar plot, which can be used as input for technology forecasting based on TRIZ trends.

[1]  Darrell Mann,et al.  Hands-on systematic innovation , 2002 .

[2]  M. F. Porter,et al.  An algorithm for suffix stripping , 1997 .

[3]  Michael E. Lesk,et al.  Automatic sense disambiguation using machine readable dictionaries: how to tell a pine cone from an ice cream cone , 1986, SIGDOC '86.

[4]  G. Altshuller.  Creativity as an exact science : the theory of the solution of inventive problems , 1984 .

[5]  Han Tong Loh,et al.  Automatic classification of patent documents for TRIZ users , 2006 .

[6]  Eric Brill,et al.  A Simple Rule-Based Part of Speech Tagger , 1992, HLT.

[7]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[8]  Semyon Savransky,et al.  Engineering of Creativity: Introduction to TRIZ Methodology of Inventive Problem Solving , 2000 .

[9]  Byungun Yoon,et al.  A systematic approach for identifying technology opportunities: Keyword-based morphology analysis , 2005 .

[10]  Liang Chen,et al.  A Patent Document Retrieval System Addressing Both Semantic and Syntactic Properties , 2003, ACL 2003.

[11]  Joost Duflou,et al.  Relating properties and functions from patents to TRIZ trends , 2008 .

[12]  Thorsten Brants,et al.  TnT – A Statistical Part-of-Speech Tagger , 2000, ANLP.

[13]  Ted Pedersen,et al.  Extended Gloss Overlaps as a Measure of Semantic Relatedness , 2003, IJCAI.

[14]  Yongtae Park,et al.  Development of New Technology Forecasting Algorithm: Hybrid Approach for Morphology Analysis and Conjoint Analysis of Patent Information , 2007, IEEE Transactions on Engineering Management.

[15]  Adwait Ratnaparkhi,et al.  A Maximum Entropy Model for Part-Of-Speech Tagging , 1996, EMNLP.

[16]  Gaetano Cascini,et al.  Measuring patent similarity by comparing inventions functional trees , 2008, IFIP CAI.

[17]  Davide Russo,et al.  Computer-aided analysis of patents and search for TRIZ contradictions , 2007 .

[18]  Christopher D. Manning,et al.  Stanford typed dependencies manual , 2010 .

[19]  Dan Klein,et al.  Fast Exact Inference with a Factored Model for Natural Language Parsing , 2002, NIPS.

[20]  Denis Cavallucci,et al.  Integrating Altshuller's development laws for technical systems into the design process , 2001 .

[21]  Loh Han Tong,et al.  Grouping of TRIZ Inventive Principles to facilitate automatic patent classification , 2008 .

[22]  Runhua Tan,et al.  A Text-Mining-based Patent Analysis in Product Innovative Process , 2007, IFIP CAI.

[23]  Simon Dewulf,et al.  Directed variation of properties for new or improved function product DNA – A base for connect and develop , 2011 .