An automatic semantic annotation method for IoT devices

Abstract

The invention discloses an automatic semantic annotation method for Internet-of-things equipment. The method comprises the following steps: depicting equipment in the Internet of things by adopting a depicting frame of the Internet-of-things equipment; screening and filtering the equipment information and dividing the same into equipment functional information and equipment non-functional information; and by adopting different sorting methods, screening an ontological concept URI based on semantic similarity from an equipment body to be used as an annotation for a semantic label after integrating sorting results of two components. By considering the expansibility of the method, the equipment body is expanded for expanding the equipment body, so that the accuracy of semantic label selection is ensured. The automatic semantic annotation method for Internet-of-things equipment, disclosed by the invention, can improve the automatic semantic annotation efficiency of massive equipment in the semantic Internet of things, so that the performance of a service finding system is further enhanced.

Description

Technical field [0001] The present invention belongs to the semantic network, and the automatic semantic labeling field is specifically related to the IoT device description framework, automatic semantic labeling, and device body extension method. Background technique [0002] Semantic technology is to solve key technologies of massive, heterogeneous, distributed physical information interaction in the Internet of Things, and sequentially labeze the entities and perceived information about information. The semantic label in the field of Internet of Things is to make a semantic labeling of the Internet of Things and the data, allowing the IoT entity to describe the unified semantic form to provide support for the semantic service discovery of the service layer. [0003] At present, there is a semantic label platform, including Aerodaml, SMT, MNM, Armadillo, etc. Or use the word similarity technology or natural language processing technology and TF-IDF based on Wikipedia Corps, or ...

AI Technical Summary

Problems solved by technology

[0004] However, most of the existing semantic annotation tools and platforms and semantic annotation of web documents focus on text annotation and web pages. Due to the physical characteristics of IoT devices, such as space, time, and environment, it provides new information for semantic annotation. requirements, the labeling results often cannot meet the requirements; and the existing semantic labeling in the IoT environment is mainly for sensor data, and is a manual semantic labeling method. However, facing a large number of IoT entities, especially the number is still In the rapidly growing Internet of Things devices, manual or semi-automatic semantic annotation seems to be unable to do what it wants. Devices are the main components of Internet of Things entities. Research on automatic semantic annotation methods for Internet of Things devices has become an urgent problem to be solved.

Therefore, none of the existing semantic annotation methods can meet the demand for semantic annotation of massive IoT devices.

Images