public float ClassificationThreshold { get; set; }
To filter out false positive results and still get variety in matched
natural language inputs for your agent, you can tune the machine learning
classification threshold. If the returned score value is less than the
threshold value, then a no-match event will be triggered. The score values
range from 0.0 (completely uncertain) to 1.0 (completely certain). If set
to 0.0, the default of 0.3 is used.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[[["\u003cp\u003eThe page provides a comprehensive list of versions for \u003ccode\u003eNluSettings\u003c/code\u003e within the \u003ccode\u003eGoogle.Cloud.Dialogflow.Cx.V3\u003c/code\u003e namespace, ranging from the latest version 2.23.0 down to version 1.0.0.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eNluSettings\u003c/code\u003e is a class related to settings for Natural Language Understanding (NLU) within Dialogflow CX, and it implements interfaces such as \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eNluSettings\u003c/code\u003e class includes properties such as \u003ccode\u003eClassificationThreshold\u003c/code\u003e, \u003ccode\u003eModelTrainingMode\u003c/code\u003e, and \u003ccode\u003eModelType\u003c/code\u003e, which allow for customization of NLU behavior and model selection.\u003c/p\u003e\n"],["\u003cp\u003eThe Class has a public constructor \u003ccode\u003eNluSettings()\u003c/code\u003e and a second constructor that takes in a \u003ccode\u003eNluSettings\u003c/code\u003e object as a parameter, called \u003ccode\u003eNluSettings(NluSettings other)\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eClassificationThreshold\u003c/code\u003e property allows users to tune the machine learning classification threshold to filter out false positives, with values ranging from 0.0 to 1.0, and a default of 0.3.\u003c/p\u003e\n"]]],[],null,[]]
