SMART ARCHIVING MECHANISMS FOR ENERGY AND PETROLEUM PROJECTS USING BIG DATA

Abstract

Complexity of the construction projects varies by the domain and type of the project. Due to the interaction between different disciplines and parties, EPP are considered among the most complex. This research proposes a framework that increases the efficiency of archiving of these accumulated data without affecting the normal workflow of companies, overcoming the man-hours expenditure, and reducing the time of archiving while not affecting the accuracy of the outcome. The proposed framework integrates four modules to provide a complete solution to the problem. The first module is responsible for image processing to enhance the quality of the images. Then, OCR module converts the images to text to be processed, this data is then processed; where text cleansing and preparation is performed using big data tools to allow for large scale real-time implementation. The following module performs text searching and results verification using regular expressions. The final module is responsible for archiving the verified data in a structured database to be available for users. The framework transforms the existent unstructured data into structured data which can be used in initial estimations and referencing