Sunya | Energy AI Observatory · Open the interactive dossier
3 AI initiative profiles for PetroChina across 3 departments, with evidence grades and source links. Strongest evidence: A · Operator filing — Kunlun large model with value-chain applications.
crude purchase evaluation cycle: 5 minutes vs hours or days (Company-reported); deployed scenarios: 152 (Company-reported)
CNPC article reports that forecast accuracy “improved by 15%” (预测准确率提升15%). The comparison baseline, calculation, validation set, forecast horizon, and whether this is a relative improvement or percentage-point change are unspecified; it is not an absolute 15% accuracy score.
Company reports average condition-diagnosis accuracy above 90%, abnormal-well discovery moving from days to minutes, and wells managed per person increasing from 3.5 to 11.5. It also reports usable data rising from 40% to above 95%. Validation definitions, samples, observation periods and staffing populations are not supplied.