sn_nlu_workbench.glide.nlu.conflict.critical_threshold Sets the score threshold for classifying an NLU conflict as critical. The default is 0.95; keep it above the moderate threshold so critical conflicts use a stricter cutoff.
0.95The answers below summarize the purpose, scope, default effect, and review scenarios for this property.
| What does it do? | This property defines the critical threshold value for detecting conflicts in NLU processing, influencing how the system responds to ambiguous inputs. |
|---|---|
| What area does it affect? | NLU Workbench - Advanced Features |
| What does the default mean? | The default value is "0.95", which is the baseline setting used unless it is changed. |
| When should you review it? | Review this property when adjusting NLU performance settings or troubleshooting conflict detection issues. |
Raw metadata from the property record.
| Property name | sn_nlu_workbench.glide.nlu.conflict.critical_threshold |
|---|---|
| Sys ID | b658183b0724201028ef0a701ad30096 |
| Type | string |
| Application | NLU Workbench - Advanced Features |
| Default value | 0.95 |
| Description | NLU Conflict Detection - Critical Threshold |
| Updated | 2024-05-25 03:56:12 |
Official references and nearby text excerpts where this property appears.
sn_nlu_workbenchOther properties in the same namespace.
sn_nlu_workbench.glide.nlu.batch_test.max_import_rows
This property defines the upper limit for the number of rows that can be included in a batch test import file,
sn_nlu_workbench.glide.nlu.batchtest.max_runs
This property limits the number of execution runs for an NLU definition to a specified integer value, enhancin
sn_nlu_workbench.glide.nlu.conflict.moderate_threshold
This property specifies the threshold value for identifying moderate conflicts in NLU processing, influencing
sn_nlu_workbench.glide.nlu.migration_completed
It serves as a boolean flag to signify the completion status of the NLU Model group migration process.
sn_nlu_workbench.glide.nlu.optimize.min_labeled_data
It sets the minimum count of labeled utterances required for effective model tuning in the NLU Workbench.
sn_nlu_workbench.glide.nlu.performance.min_clustering_records
It defines the threshold of records necessary for conducting performance analysis in the NLU Workbench.