Linares-Garcia, D A and Roofigari-Esfahan, N (2024) Practical deployment of BIM-interoperable voice-based intelligent virtual agent support construction worker productivity. Journal of Construction Engineering and Management, 150(11): 04024153, ISSN 0733-9364
Abstract
The architecture, engineering, and construction (AEC) industry in the US faces increasing labor shortages while accumulating downward productivity trends. Previous research efforts have shown that lack of timely access to information is one of the main factors hindering construction workers' productivity, and prompt information extraction (IE) from BIM sources can help address this issue. This study develops a BIM-web interoperable system, featuring a voice-based intelligent virtual agent (VIVA), to provide workers with information on-demand when conducting their activities on the jobsite. VIVA integrates construction digital sources with web platforms to enable real-time data communication between the users, workers in this case, and BIM platforms. The voice interaction feature of VIVA provides an intuitive and safe tool that can easily be used by workers with varying ranges of experience, with minimal need for training. The responsiveness and accuracy of VIVA is evaluated through two proof-of-concept case studies. Results indicate that the BIM-VIVA link and underlying natural language understanding (NLU) algorithms in the Google Actions platform accurately understand user queries, with a performance of 97.50% correct responses. As a result, VIVA achieves superior performance compared with previous research works based on NLU algorithms with text-based queries. The developments made in this research not only contribute to improving the safety and productivity of construction workers but also can open the door for easier onboarding of less-experienced workers, thus addressing the industry's severe skilled labor shortage issue.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | cyber-physical systems; internet of things; productivity; system development; systems interoperability; virtual agent; voice-based; voice-based intelligent virtual agent; worker support |
| Index terms: | agent, face, accuracy, skilled labour, interaction, internet, construction worker, access to information, interoperability, labour shortage, productivity, real-time data, case study, platform |
| Subjects: | digital design, social equity, behavioral psychology, practitioner, psychology, professional development, management, economics, systems and processes, data management, computing systems, data collection methods |
| Topics: | Research Practice, Information Management, Business Strategy, Roles and Professions, Human Resources, Digital Applications, Organizational Design, Ethics, Supply Chain Management |
| Descriptive scope: | 3 PCE |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here