Knowledge management (KM) in the Architecture, Engineering and Construction (AEC) industry is hampered by the overload and fragmentation of heterogenous data, information and knowledge. This has led to an inability to identify, capture, manage and reuse the large amount of potential knowledge generated by AEC organizations, underpinned fundamentally by the tacit nature of AEC knowledge, as well as the lack of interoperability of information systems. We address these challenges by evaluating a computational machine learning technique known as Latent Semantic Analysis (LSA) in real world AEC contexts, with reference to KM and knowledge creation theory. Specifically, we investigate whether and how LSA can be used to infer insights from abundant unstructured natural language textual material, that would otherwise have required expert tacit knowledge to achieve. Our investigations are rooted in various AEC domain problem contexts, applicable across the lifecycle: 1) Mapping of Communities of Practice via modelling of personnel knowledge, skills and competences, 2) Management of constructability knowledge and inference of domain topical relationships, and 3) Extraction and processing of change issues from a BIM-based renovation project. For each, we articulate the respective domain problems through the lenses of KM and align LSA to address them. Our principle results demonstrate that valuable insights, traditionally dependant on domain-specific human reasoning, can indeed be inferred from readily accessible textual documentation (be it passively or actively generated) in each AEC context. As such, LSA can help to give quantitative substance to many conceptual KM conjectures and contribute to developing both practical and philosophical elements of KM in AEC. We demonstrate that LSA has a clear role in advancing domain-specific applications of information retrieval and case-based reasoning systems, ontological mediation between data models as a matter of interoperability, as well as reconciliation between the social-technical, the tacit-explicit, and the qualitative-quantitative relationships of KM in AEC. Additionally, we highlight the contributions of our results with respect to the knowledge creation model – constituting processes of socialization, externalization, combination and internalization (SECI). Through demonstrating LSA's capabilities in the AEC context, we hope that this research opens new perspectives on the role of KM in various AEC applications, and likewise, new perspectives in the role of artificial intelligence within KM.
|Tila||Julkaistu - 2019|
|OKM-julkaisutyyppi||G4 Tohtorinväitöskirja (monografia)|