Explainable Graph-based Search for Lessons-Learned Documents in the Semiconductor Industry
Industrial processes produce a considerable volume of data and thus information. Whether it is structured sensory data or semi- to unstructured textual data, the knowledge that can be derived from it is critical to the sustainable development of the industrial process. A key challenge of this sustainability is the intelligent management of the generated data, as well as the knowledge extracted from it, in order to utilize this knowledge for improving future procedures. This challenge is a result of the tailored documentation methods and domain-specific requirements, which include the need for quick visibility of the documented knowledge. In this paper, we utilize the expert knowledge documented in chip-design failure reports in supporting user access to information that is relevant to a current chip design. Unstructured, free, textual data in previous failure documentations provides a valuable source of lessons-learned, which expert design-engineers have experienced, solved and documented. To achieve a sustainable utilization of knowledge within the company, not only the inherent knowledge has to be mined from unstructured textual data, but also the relations between the lessons-learned, uncovering potentially unknown links. In this research, a knowledge graph is constructed, in order to represent and use the interconnections between reported design failures. A search engine is developed and applied onto the graph to answer queries. In contrast to mere keyword-based searching, the searchability of the knowledge graph offers enhanced search results beyond direct matches and acts as a mean for generating explainable results and result recommendations. Results are provided to the design engineer through an interactive search interface, in which, the feedback from the user is used to further optimize relations for future iterations of the knowledge graph.
Code (0)
등록된 구현이 없습니다.
Tasks
ManagementSimilar Papers 제목 키워드 기반
A Text Extraction-Based Smart Knowledge Graph Composition for Integrating Lessons Learned during the Microchip Design
The production of microchips is a complex and thus well documented process. Therefore, available textual data about the production can be overwhelming in terms of quantity. This affects the visibility and retrieval of a …
RetrievalSoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned
DARPA's AI Cyber Challenge (AIxCC, 2023--2025) is the largest competition to date for building fully autonomous cyber reasoning systems (CRSs) that leverage recent advances in AI -- particularly large language models (LL…
Lessons from Usable ML Deployments and Application to Wind Turbine Monitoring
Through past experiences deploying what we call usable ML (one step beyond explainable ML, including both explanations and other augmenting information) to real-world domains, we have learned three key lessons. First, ma…
Decision MakingOn Two XAI Cultures: A Case Study of Non-technical Explanations in Deployed AI System
Explainable AI (XAI) research has been booming, but the question "$\textbf{To whom}$ are we making AI explainable?" is yet to gain sufficient attention. Not much of XAI is comprehensible to non-AI experts, who nonetheles…
Explainable Artificial Intelligence (XAI)Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges
When 5G began its commercialisation journey around 2020, the discussion on the vision of 6G also surfaced. Researchers expect 6G to have higher bandwidth, coverage, reliability, energy efficiency, lower latency, and an i…
Collision AvoidanceDecision MakingExplainable Artificial Intelligence (XAI)Management+1