استخراج خودکار و کشف هوش فنی
Abstract
1. Introduction
2. Literature review
3. Proposed methodology
4. Experiments
5. Discussion
6. Conclusions
Acknowledgement
References
Abstract
It is imperative and arduous to acquire product and business intelligence of global technical market. In this paper, a deep learning methodology is proposed to automatically extract and discover vital technical information from large-scale news dataset. More specifically, six kinds of technical elements are first defined to provide the concrete syntax information. Next, the CRF-BiLSTM approach is used to automatically extract technical entities, in which a conditional random field (CRF) layer is added on top of bidirectional long short-term memory (BiLSTM) layer. Then, three indicators including timeliness, influence and innovativeness are designed to evaluate the value of intelligence comprehensively. Finally, as a case study, technical news on three militaryrelated websites is utilized to illustrate the efficiency and effectiveness of the foregoing methodology with the result of 80.82 (F-score) in comparison to four other models. In more detail, data on unmanned systems are extracted to summarize the state-of-the-art, and track up-to-the-minute innovations and developments in this field.
Introduction
Science and technology (S&T) has emerged from simple to complex over the past century. New initiatives such as Industry 4.0, Reindustrialization, Smart Manufacturing and Super Smart Society 5.0 are proposed in succession, and thus the size of technologies is rapidly expanding. Meanwhile, technologies are no longer independent individuals, but networked with each other in regard to their relationships of coordination and interdependence. In military, technical Intelligence (TECHINT) is intelligence about weapons and equipment used by foreign nations. In a broader social context, TECHINT refers to all technical information to promote the awareness of technical threats and opportunities in global (Ma et al., 2017). To keep or gain competitive edge in the business, it is always necessary for a company to take proactive measures to detect, track and predict emerging technologies or innovative combination of currently-existing technologies (Clauset et al., 2017). The companies should be aware of the products and business information of global technical market. Such intelligence is of great significance for them to expand market, promote new products and develop new areas (Huang et al., 2016). Typically, the TECHINT process is divided into collection, exploitation and production. There are two basic tasks to exploit TECHINT. On one hand, it tries to answer existing questions with available intelligence. On the other hand, it is more challenging to answer questions by capturing new information rapidly.