Automated Well Record Data Gap Filling via ML Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Oil exploration and production companies face challenges in maintaining high data quality in their well header databases due to gaps in data, which are often caused by human errors or pre-existing gaps in original data sources. These gaps negatively affect the confidence of inferences drawn from the data and require manual, time-consuming processes to fill using unstructured data sources like well reports and logs.
Innovation Solution
A method that identifies entities and data gaps in a well record database, uses a machine learning model to extract relevant values from documents in a document database, aggregates these values to create a data gap filler, and inserts this filler into the well log database, thereby automating the process of filling data gaps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual processes are used to fill data gaps by searching unstructured data sources, then data quality can be improved, but the process becomes time-consuming and reduces productivity
Solution Approach 1:
The patent replaces the manual mechanical search process with an automated machine learning model that uses natural language processing to extract data from unstructured well reports and logs. The system automatically identifies and fills data gaps without human intervention, resolving the contradiction between maintaining data quality and reducing time consumption.
Solution Approach 2:
The system enables self-service by allowing the database to automatically identify its own data gaps and fill them using the machine learning model. The well record database autonomously searches unstructured data sources, extracts missing information, and populates gaps without requiring manual searching, thereby improving both data quality and productivity.
2Loss of time
If manual searching stops after finding the first datapoint, then the search process is faster, but data accuracy decreases due to potential contradictions with other well logs
Solution Approach 1:
The machine learning model implements feedback by continuously evaluating extracted datapoints against existing database records and other well logs. The system verifies consistency across multiple sources before finalizing data gap fillers, ensuring high data accuracy while maintaining efficient automated processing without manual intervention.
3Productivity
If automated machine learning models are used to extract values from documents, then productivity increases, but the system complexity increases
Solution Approach 1:
The patent introduces an intermediary layer between the unstructured data sources and the well record database. The machine learning model acts as a mediator that handles the complexity of natural language processing and data extraction, translating unstructured text into structured database entries while managing system complexity internally and presenting a simple interface for data gap filling.
Data Source
AI summary
A method includes identifying entities in a well record database comprising data representing a plurality of objects and attributes of the objects, determining a data gap for at least one attribute of an object of the objects in the well record database, identifying documents in a document database, wherein identifying the documents include determining that the documents are relevant to the object based at least in part on metadata of the documents, extracting values for the data gap from the documents using a machine learning model, determining a data gap filler by aggregating the extracted values, and inserting the data gap filler into the data gap in the well log database.