Technology Opportunity Analysis Based on Machine Learning
The sustainable growth of a company requires a differentiated research and development strategy through the discovery of technology opportunities. However, previous studies fell short of the need for utilizing outlier keywords, based on approaches from various perspectives, to discover technology op...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Axioms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1680/11/12/708 |
| _version_ | 1797461522994167808 |
|---|---|
| author | Junseok Lee Sangsung Park Juhyun Lee |
| author_facet | Junseok Lee Sangsung Park Juhyun Lee |
| author_sort | Junseok Lee |
| collection | DOAJ |
| description | The sustainable growth of a company requires a differentiated research and development strategy through the discovery of technology opportunities. However, previous studies fell short of the need for utilizing outlier keywords, based on approaches from various perspectives, to discover technology opportunities. In this study, a technology opportunity discovery method utilizing outlier keywords is proposed. First, the collected patent data are divided into several subsets, and outlier keywords are derived using the W2V and LOF. The derived keywords are clustered through the K-means algorithm. Finally, the similarity between the clusters is evaluated to determine the cluster with the most similarity as a potential technology. In this study, 5679 cases of unmanned aerial vehicle (UAV) patent data were utilized, from which three technology opportunities were derived: UAV defense technology, UAV charging station technology, and UAV measurement precision improvement technology. The proposed method will contribute to discovering differentiated technology fields in advance using technologies with semantic differences and outlier keywords, in which the meaning of words is considered through W2V application. |
| first_indexed | 2024-03-09T17:20:36Z |
| format | Article |
| id | doaj.art-e3dc01555e9141559c8bbad3ce8d3021 |
| institution | Directory Open Access Journal |
| issn | 2075-1680 |
| language | English |
| last_indexed | 2024-03-09T17:20:36Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Axioms |
| spelling | doaj.art-e3dc01555e9141559c8bbad3ce8d30212023-11-24T13:15:49ZengMDPI AGAxioms2075-16802022-12-01111270810.3390/axioms11120708Technology Opportunity Analysis Based on Machine LearningJunseok Lee0Sangsung Park1Juhyun Lee2Institute of Machine Learning and Big Data, Korea University, Seoul 02841, Republic of KoreaDepartment of Big Data Statistics, Cheongju University, Cheongju 28503, Republic of KoreaInstitute of Engineering Research, Korea University, Seoul 02841, Republic of KoreaThe sustainable growth of a company requires a differentiated research and development strategy through the discovery of technology opportunities. However, previous studies fell short of the need for utilizing outlier keywords, based on approaches from various perspectives, to discover technology opportunities. In this study, a technology opportunity discovery method utilizing outlier keywords is proposed. First, the collected patent data are divided into several subsets, and outlier keywords are derived using the W2V and LOF. The derived keywords are clustered through the K-means algorithm. Finally, the similarity between the clusters is evaluated to determine the cluster with the most similarity as a potential technology. In this study, 5679 cases of unmanned aerial vehicle (UAV) patent data were utilized, from which three technology opportunities were derived: UAV defense technology, UAV charging station technology, and UAV measurement precision improvement technology. The proposed method will contribute to discovering differentiated technology fields in advance using technologies with semantic differences and outlier keywords, in which the meaning of words is considered through W2V application.https://www.mdpi.com/2075-1680/11/12/708technology opportunity discoverypatentword2veclocal outlier factorUAV |
| spellingShingle | Junseok Lee Sangsung Park Juhyun Lee Technology Opportunity Analysis Based on Machine Learning Axioms technology opportunity discovery patent word2vec local outlier factor UAV |
| title | Technology Opportunity Analysis Based on Machine Learning |
| title_full | Technology Opportunity Analysis Based on Machine Learning |
| title_fullStr | Technology Opportunity Analysis Based on Machine Learning |
| title_full_unstemmed | Technology Opportunity Analysis Based on Machine Learning |
| title_short | Technology Opportunity Analysis Based on Machine Learning |
| title_sort | technology opportunity analysis based on machine learning |
| topic | technology opportunity discovery patent word2vec local outlier factor UAV |
| url | https://www.mdpi.com/2075-1680/11/12/708 |
| work_keys_str_mv | AT junseoklee technologyopportunityanalysisbasedonmachinelearning AT sangsungpark technologyopportunityanalysisbasedonmachinelearning AT juhyunlee technologyopportunityanalysisbasedonmachinelearning |