Selection Question
A decision model that selects one option from a predefined set of categories and is used for multi-classification tasks such as ticket routing and intent recognition.
Timeline (last 90 days)
The questioning approaches corresponding to decision models can be summarized into three types: predicate questions, choice questions, and score questions.
A choice question requires the model to pick one answer from preset categories; it is a many-to-one classification task, suitable for scenarios such as customer service ticket routing, content tagging, and intent recognition.
Choice questions correspond to single-label multi-class classification in machine learning, whose output space is a set of mutually exclusive categories.
The key engineering constraint of choice questions is that the category system must be closed and complete; if a new category not covered by the training set appears, the model can only force it into a known class, causing misrouting.
All Facts (4)
The questioning approaches corresponding to decision models can be summarized into three types: predicate questions, choice questions, and score questions.
50%UnverifiedA choice question requires the model to pick one answer from preset categories; it is a many-to-one classification task, suitable for scenarios such as customer service ticket routing, content tagging, and intent recognition.
50%UnverifiedChoice questions correspond to single-label multi-class classification in machine learning, whose output space is a set of mutually exclusive categories.
50%UnverifiedThe key engineering constraint of choice questions is that the category system must be closed and complete; if a new category not covered by the training set appears, the model can only force it into a known class, causing misrouting.
50%