Gui Z, Freund M, Harth A (2024)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2024
Publisher: Association for Computing Machinery New York NY United States
Pages Range: 3
Conference Proceedings Title: IoT '23: Proceedings of the 13th International Conference on the Internet of Things
Event location: Nagoya Japan
ISBN: 979-8-4007-0854-1
We present a demo of a Natural Language Interface (NLI) for controlling Internet of Things (IoT) devices using the Web of Things (WoT) specification as an intermediate abstraction layer. All interaction information of a device is stored in a Knowledge Graph using the thing description ontology. The central component of the NLI is a sequence-to-sequence neural network model for text to code translation. We build a data corpus based on the functionalities of a Philips Hue smart lamp and use the corpus to train the text to code model. Our demonstration illustrates how to control the power state, the light colour, and the brightness of a Philips Hue smart lamp using natural language commands. The implementation of an NLI system based on the WoT specification represents an approach towards the development of easy-to-use and interoperable IoT systems.
APA:
Gui, Z., Freund, M., & Harth, A. (2024). A Natural Language Interface for IoT Systems Using the Web of Things Abstraction. In IoT '23: Proceedings of the 13th International Conference on the Internet of Things (pp. 3). Nagoya Japan: Association for Computing Machinery New York NY United States.
MLA:
Gui, Zhou, Michael Freund, and Andreas Harth. "A Natural Language Interface for IoT Systems Using the Web of Things Abstraction." Proceedings of the IoT 2023: The International Conference on the Internet of Things, Nagoya Japan Association for Computing Machinery New York NY United States, 2024. 3.
BibTeX: Download