Edge intelligent data classification storage method

Abstract

The invention relates to an edge intelligent data classification storage method, and belongs to the field of Internet of Things. The method comprises the following steps: firstly, designing a data preprocessing method, abstracting an intelligent entity state data sequence, and converting the intelligent entity state data sequence into a quantitative intelligent entity state sequence and a qualitative intelligent entity state sequence; then, performing feature extraction based on DSAE; then, outputting the extracted features to an SVM, and distinguishing of a transient intelligent entity and aslow-varying intelligent entity is achieved; and finally, storing the transient smart entity state data with relatively strong time-varying property at the edge, and storing the slow-varying smart entity state data with relatively weak time-varying property at the cloud center. According to the method, the state time-varying characteristics of the qualitative and quantitative state intelligent entities are mined, the intelligent entities are classified according to the time-varying degree, so that the state data of the intelligent entities are distinguished and cached according to the categorydifference, the search result accuracy of the Internet of Things search system is remarkably improved, and the search time delay for massive state time-varying intelligent entities is reduced.

Description

technical field [0001] The invention belongs to the field of the Internet of Things and relates to a method for classifying and storing edge intelligent data. Background technique [0002] With the development and popularization of the Internet of Things (IoT), more and more sensing devices with sensing functions such as massive sensors and RFID are connected to the Internet. In the next 20 years, trillions of IoT sensing devices will appear in our lives, realizing information sharing and interconnection of all things. Among them, the rapid development of low-cost sensors, communication protocols, embedded systems, actuators and miniaturized hardware has promoted the rapid growth of the Internet of Things, which can collect, process and transmit data without human intervention, and also provide new services And the development of applications, such as indoor public safety monitoring, telemedicine and environmental pollution management. [0003] In recent years, the applica...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the purpose of the present invention is to solve the problem of poor search accuracy and high search delay caused by centralized storage to the cl

Images