At the IADC DEC Tech Conference in Houston, Fabio Concina from Kwantis presented a new approach to automating Daily Drilling Report (DDR) generation using generative AI. The solution addresses a longstanding inefficiency by reducing the manual workload associated with operational reporting. This functionality is available in ID3 Reporting and has been deployed in operational environments.
Hybrid Architecture: Deterministic Algorithms + LLMs
The system combines deterministic algorithms with Large Language Model (LLM) capabilities to automate DDR data capture and reporting. A segmentation algorithm analyzes stand detection patterns and sensor readings to identify intervals of similar drilling activities. This allows the system to automatically generate time logs while offering configurable granularity, enabling operators to adjust the resolution of activity tracking according to operational needs.
Template-Driven Activity Descriptions
Once activity segments are identified, descriptions are generated using customizable templates populated with parameters derived from rig sensor data. This approach ensures consistent reporting while still capturing the specific details of each drilling operation.
Retrieval-Augmented Code Assignment
To assign IADC activity codes, the system uses a Retrieval-Augmented Generation (RAG) pipeline built on historical operational data. The model retrieves relevant examples of user-assigned codes from previous operations and uses them to infer the most appropriate codes and subcodes. Each assignment is accompanied by a transparent justification, supporting both automation and auditability while maintaining compliance with International Association of Drilling Contractors reporting standards or other Company standards.
Proven Results in Field Deployment
The solution has been deployed across four rigs and has processed more than 150 rig-days of operational data. Results show a reduction of over 50% in report preparation time while maintaining full compliance with IADC reporting requirements, demonstrating the potential of generative AI to streamline operational workflows in drilling environments.