|
|
Interpreting ResultsZeroTrain returns a structured response that includes the decision outcome, execution details, and system feedback. Response Structure{
"Header": { ... },
"Results": [ ... ],
"UsageInfo": { ... },
"BatchInfo": { ... },
"Errors": [ ... ],
"Warnings": [ ... ]
}
HeaderThe Header provides high-level information about the execution.
ResultsThe Results section contains the decision outcomes. Each entry represents a model evaluation result. {
"modelName": "CallCenterRoutingModel",
"decisionId": "CC-002",
"action": "RouteToTier2",
"confidenceScore": 0.5134,
"logicPassed": false
}
Key Fields
Compact Trace InformationTrace data provides visibility into how the decision was evaluated. "logicTrace": ["R1","C1:P","C2:F","C6:F"]
Detailed Trace InformationThe trace output may include additional context to improve readability. This format retains the compact structure while providing descriptive details for each evaluation step. [ "R1", "C1:P: CallIntent BillingDispute", "C2:F: SentimentScore (null) ", "C4:P: HasPaymentFailure True" ] Format
Additional text may be included to describe the evaluated value or condition. Matched RowThe matchedRow section shows values from the selected outcome. {
"HasPaymentFailure": "True",
"Weight": "0.75"
}
Usage InformationUsageInfo provides execution and consumption details.
WarningsWarnings indicate non-blocking issues encountered during evaluation. {
"code": 20084,
"message": "Null value encountered..."
}
ConsistencyFor the same input and model, the system will always return the same result. SummaryZeroTrain results provide a complete view of the decision, including outcome, traceability, and execution details. |