Early screening of potential breakthrough technologies with enhanced interpretability: A patent-specific hierarchical attention network model
Authors:
Preprint
Abstract
Despite the usefulness of machine learning approaches for the early screening of potential breakthrough technologies, their practicality is often hindered by opaque models. To address this, we propose an interpretable machine learning approach to predicting future citation counts from patent texts using a patent-specific hierarchical attention network (PatentHAN) model. Central to this approach are (1) a patent-specific pre-trained language model, capturing the meanings of technical words in patent claims, (2) a hierarchical network structure, enabling detailed analysis at the claim level, and (3) a claim-wise self-attention mechanism, revealing pivotal claims during the screening process. A case study of 35,376 pharmaceutical patents demonstrates the effectiveness of our approach in early screening of potential breakthrough technologies while ensuring interpretability. Furthermore, we conduct additional analyses using different language models and claim types to examine the robustness of the approach. It is expected that the proposed approach will enhance expert-machine collaboration in identifying breakthrough technologies, providing new insight derived from text mining into technological value.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- Prediction of patent grant and interpreting the key determinants: an application of interpretable machine learning approachScientometrics, 2023
- Identification of emerging business areas for business opportunity analysis: An approach based on language model and local outlier factorComputers in Industry, 2022
- Measuring knowledge exploration distance at the patent level: Application of network embedding and citation analysisJournal of Informetrics, 2022
- Potential of patent image data as technology intelligence sourceJournal of Informetrics, 2022
- Anticipating promising services under technology capability for new product-service system strategies: An integrated use of patents and trademarksComputers in Industry, 2021
- Inventor profile mining approach for prospective human resource scoutingJournal of Informetrics, 2021
- Patent-trademark linking framework for business competition analysisComputers in Industry, 2020
- A novel approach to evaluating the business potential of intellectual properties: A machine learning-based predictive analysis of patent lifetimeComputers & Industrial Engineering, 2020
- A transferability evaluation model for intellectual propertyComputers & Industrial Engineering, 2019
- Hawkes process-based technology impact analysisJournal of Informetrics, 2017