Reputation sharing dual-stage data quality evaluation method based on block chain

Abstract

The invention discloses a reputation sharing double-stage data quality evaluation method based on a block chain, and the method comprises the steps: storing the historical data of task participants through a reputation sharing mechanism based on the block chain; and for the task participant who does not participate in the task, using the reputation value of the task participant in other fields as a judgment basis of the reliability of the task participant, so that the selection quality of the task participant can be improved, and the problems of storage and cold start of historical data in a dynamic environment can be solved. Aiming at a true phase estimation problem in an initial stage in a true phase discovery algorithm, a machine learning-based true phase discovery algorithm is provided, data collected from task participants is firstly preliminarily pre-judged through a machine learning model, and an estimated value which is more accurate than a randomly determined pre-true phase is obtained as an initial value; and the deviation with a correct answer is reduced, and the execution efficiency of a true phase discovery algorithm and the accuracy of a perception result can be effectively improved.

Description

technical field [0001] The invention relates to the field of crowd sensing technology, in particular to a blockchain-based two-stage data quality evaluation method for reputation sharing. Background technique [0002] With the rapid development of embedded devices, wireless sensor networks, and intelligent mobile terminals of the Internet of Things, pervasive intelligent systems integrating perception, computing, and communication capabilities are being widely deployed and gradually integrated into people's daily life environment. A new data collection and processing mode called CrowdSensing has become a research hotspot in recent years and has been applied in many fields, such as environmental monitoring, indoor positioning, public safety, personalized recommendation, traffic planning, etc. . [0003] The basic idea of ​​group intelligence sensing is to use group intelligence to solve various complex problems. Its system model is mainly composed of: task issuer, perception...

AI Technical Summary

Problems solved by technology

[0005] What the present invention aims to solve is the problem of low quality of perception data existing in the current crowd sensing, and provides a two-stage data quality evaluation method based on blockchain reputation sharing

Images