Visualization of Potential Technical Solutions by Self-Organizing Maps and Co-Cluster Extraction
Yasushi Nishida, Katsuhiro Honda · 2018
This paper proposes a novel approach for supporting inspiration of potential technical solutions through visualization of solving means varied in patent documents. The data sets to be analyzed by SOM are constructed in two different schemes. In the first scheme, representative words are extracted to generate word level co-occurrence probability vectors. Then, in the second scheme, correlation coefficients of the generated co-occurrence probability vectors are merged into correlation coefficient vectors. Comparing the two SOMs derived with the above schemes, the potential of the method is shown in supporting innovation acceleration through extraction of important pairs of related factors in new technology development. Additionally, co-cluster structures are utilized for emphasizing field-related solutions by constructing multiple SOMs after co-clustering, in which document-keyword co-occurrences are partitioned into co-clusters consisting of mutually related pairs in particular fields.