The objective of the TMM project is to identify, at an early stage, the risks associated with new technologies and develop solutions to ward off such threats. It also aims to assess existing products and applications to pinpoint vulnerabilities. In that process, artificial intelligence and machine learning will play an important part. The main goal of this project is to automatically identify technology offerings of Swiss companies especially in the cyber security domain. This also includes identifying key stakeholders in these companies, possible patents, published scientific papers.
In particular, a user of our system would be interested in retrieving technologies related to a company, identifying companies associated with a technology and retrieving similar companies to a company according to their technology offering. As such, our system involves two main components: technology extraction and technology retrieval.
For technology extraction, we leverage state-of-the-art techniques in natural language processing to automatically identifying technological terms in plain texts. These texts are collected from company websites, public patents, and public job offerings. This involves identifying key entities and whether they are related to technology.
For technology retrieval, we intend to create embedding representations for entities and concepts that support diverse search and inference tasks. The embedding models are inferred from currently available and future heterogeneous data collections related to technology, research, innovation, and companies from Swiss and global sources. In order to tackle the heterogeneity of the data considered, we will employ recent advances in heterogeneous network representation learning.