Multi-source unstructured data cleaning method for discrete intelligent manufacturing application

Abstract

The invention discloses a multi-source unstructured data cleaning method for discrete intelligent manufacturing application, and the method comprises the steps: carrying out the characterization analysis of multi-source unstructured data in a discrete intelligent manufacturing application environment, and classifying the cleaning types; and carrying out data cleaning on the to-be-cleaned multi-source unstructured data according to the data cleaning strategy corresponding to the cleaning type. The problem of unified description of the multi-source unstructured data and the problem of complexity of data classification processing are solved; cleaning type classification processing of multi-source unstructured data applied to discrete intelligent manufacturing by means of a computer becomes possible, computer processing is short in time consumption and has certain high efficiency, the cleaning types of the multi-source unstructured data are reflected by adopting the cloud model, the problems of unclear expression of fuzzy cleaning types and the like are avoided, therefore, the classification result of the cleaning types is more reliable, and a new technical solution is provided for multi-source unstructured data cleaning of discrete intelligent manufacturing application.

Description

technical field [0001] The invention relates to the fields of big data technology and data cleaning technology, in particular to a multi-source unstructured data cleaning method for discrete intelligent manufacturing applications. Background technique [0002] In the current discrete intelligent manufacturing environment, the gradual development of big data has led to the collection of massive data. It is very important to clean these massive data and extract meaningful information from them. After years of exploration and time, the majority of scientific research institutes and enterprises have carried out a lot of exploration and application in data cleaning for discrete intelligent manufacturing environments, but how to clean unstructured data in discrete manufacturing environments to support subsequent data The development of mining has always been a technical bottleneck that enterprises urgently need to solve. There are many reasons for this. Among them, as the core of ...

AI Technical Summary

Problems solved by technology

[0005] However, the multi-source unstructured data generated in the application environment of discrete intelligent production lines mainly include video data, picture data, audio data, text data and other production line equipment operation status data, such as inspection documents generated by production line quality inspection equipment. , tool cutting state image, production equipment running vibration, production line monitoring video, etc., these data have problems such as irregular data structure or inconsistent format, which cannot be directly expressed by two-dimensional logical data tables; and discrete intelligent manufacturing applications There are many types of equipment in the scene, and the data information generated by each mechanical equipment resource is complex and changeable. As a result, most studies at this stage have limited general guiding significance in supporting multi-source unstructured data cleaning under discrete manufacturing applications.

The reason is that: under the application of discrete intelligent manufacturing, multi-source unstructured data has a wide range of data sources, lacks a unified data format and standard, and data storage is often stored by computer in binary, which makes the classification and processing of data in different formats very complicated; at the same time , the discrete manufacturing application environment is a dynamically changing industrial activity environment, and the multi-source unstructured data generated by mechanical equipment often contains time series information, which increases data classification and information dimensions; these factors have led to the application of discrete intelligent manufacturing. The difficulty of determining the cleaning type of multi-source unstructured data has increased significantly, which has increased the difficulty of data classification and cleaning

Images