Big data credibility measurement method based on layering model

Abstract

The invention pertains to the field of data credibility assessment of big data, in particular to a big data credibility measurement method based on a layering model. The method comprises following steps: calculating credibility of data sources and credibility of data on the basis of a conventional data creditability analysis theory by adding weight parameters such as a time factor and a penalty factor and dynamically creating a credible analysis network for layered big data. Compared with a conventional model, the big data credibility measurement method helps overcome the problem of a conventional credible analysis method including inadaptability of credible calculations of big data such that the factor of affecting credibility of big data from a more comprehensive level is analyzed. In the meanwhile, more accurate analyses can be made to credibility measurement of data provided with more data amount provided by data sources such that the credible requirement of big data can be well satisfied.

Description

technical field [0001] The invention belongs to the field of big data-oriented data trust assessment, and in particular relates to a hierarchical model-based big data credibility measurement method. Background technique [0002] In recent years, with the rapid development of technologies such as the Internet of Things and cloud computing, the ternary world of "human-machine-thing" has been highly integrated, which has resulted in explosive growth of data scale and high complexity of data models, prompting the current information society. Enter the era of Big Data. The generation of big data provides a rich data source foundation for the fields of information science and control and decision-making, but the authenticity of data plays an important role in information fusion and intelligent decision-making. [0003] At present, there are some research methods and classic algorithms for data credibility measurement and trust management, which are mainly divided into two categor...

AI Technical Summary

Problems solved by technology

Although these algorithms have made some contributions to the trusted measurement of ordinary data, in the era of big data, data has typical "4V" characteristics (that is, massive data scale (Volume), fast data flow (Velocity), Various data types (Variety), huge data value (Value)) and typical "HDC" attributes (that is, data heterogeneity (Heterogeneous), dynamic data system (Dynamic), data complexity (Complexity)), This determines that big data has the characteristics of multi-source distribution, heterogeneity, time-space correlation, sociality and high noise, which makes traditional data credible analysis methods unable to meet the needs of big data

Images