Semantic service matching method and device in Internet of Things and storage medium

Abstract

The invention belongs to the field of edge computing and the Internet of Things, and relates to a semantic service matching method and device in the Internet of Things and a storage medium. The method comprises the following steps: acquiring an initial interest of a user on an intelligent object from the use frequency and average use time of the user on the intelligent object; establishing a joint distribution model to extract the preference intensity of the user by utilizing the influence of the initial interest on the preference intensity and the influence of the preference intensity on the use event of the intelligent object; obtaining a dynamic relationship between the intelligent objects by utilizing a hyperplane time perception knowledge graph embedding model, and estimating social similarity between the intelligent objects; constructing a semantic service matching model according to the preference degree of the user and the social similarity between the intelligent objects; and receiving a service request from a user or an intelligent object, performing similarity matching based on the semantic service matching model, and outputting a service matching result between the user and the intelligent object. The effectiveness and expansibility of service discovery and the accuracy of a service matching result are guaranteed.

Description

technical field [0001] The invention belongs to the field of edge computing and the Internet of Things, and performs semantic service matching based on user time preference and item social relationship, and specifically relates to a semantic service matching method, device and storage medium in the Internet of Things. Background technique [0002] The Internet of Things is hailed as the future of the Internet, which will expand the current form of communication between people to people to people, people to things, and things to things. A smart space is the name given to a physical location where numerous devices interact with each other to provide relevant services to human users under given conditions. The functions of these objects can be called services, and they provide real-time status information of the physical world. In this environment, the task of how to provide suitable services faces many new challenges and requirements. Furthermore, the Internet of Things has ...

AI Technical Summary

Problems solved by technology

In addition, due to the characteristics of spontaneity, context dependence and monopoly of SIOT service discovery, it also brings a series of difficulties and challenges to SIOT service discovery:

[0004] 1) The user's preference for smart objects is usually implicit and difficult to measure: unlike social networks or evaluation sites, users' preferences for an object can be expressed by evaluation or comment sentences, and users' preferences for smart object services Usually hidden in SIOT, so the existing ways of service discovery and recommendation based on content and collaborative filtering are not applicable

[0005] 2) Smart objects in SIOT are usually heterogeneous, and their similarity is usually difficult to estimate: in SIOT, objects are heterogeneous in both functions and attributes, and cannot be represented in a unified feature space

Furthermore, the serving textual descriptions of objects are usually incomplete, thus neither feature-based nor text-based models can be used to estimate the similarity between objects

[0006] 3) The problem of data sparsity: Most IoT service discovery systems usually learn user preferences based on user history. When new smart objects are added and users use too few smart objects, due to privacy and security issues, users and When the historical data of interaction between objects is difficult to collect, it will lead to the problem of data sparseness, which will affect the accuracy of service matching and service discovery

Images