Objectives
Aiming at the problems such as simple integration method and insufficient data value depth mining involved in practical application, combined with the relatively mature relevant knowledge in machine learning, Big data, automation and other fields, corresponding improvement and improvement strategies are proposed to improve the efficiency of drainage data integration, improve the availability of data, fully tap the hidden value of drainage data, and better serve the research on water resource recycling, Serving higher-level data applications and providing new solutions for data integration.
Conclusions
This article explores the data value behind using drainage data through some mathematical methods, explores the application fields of using drainage data, provides basic data support for upper level data analysis work, and provides corresponding analysis ideas and methods for data analysis work at the same level. In the future, the analysis work can be completed by automated programs, which process based on realtime updated data, and the processing efficiency is much higher than manual calculations. This article aims to provide reference ideas for the integration of drainage data, help improve the quality of water data application, and expand the application direction.