You have a LUIS application.
You plan to define entities to provide hints to another entity or intent.
Given the requirement that you need to create an entity for credit cards, which entity type would you use amongst the following choices? (select one answer choice)
Click on the arrows to vote for the correct answer
A. B. C. D.Correct Answer: B.
Option A is incorrect because a list entity represents a fixed and closed set of related words along with their symptoms.
They are case sensitive and require an exact match.
Option B is correct because Regex entity type extracts entities based on the regular expressions.
They are not case sensitive.
They are best suited for credit cards as you can have predefined alphanumeric values in a certain format for the credit cards.
Option C is incorrect because prebuilt entities are commonly used for data like name, date and currency.
Option D is incorrect because ML based entity types use a context to extract entities.
As the name suggests they are machine learning based entities and rely on example labels to identify the data.
Reference:
To learn more about Entity types in LUIS application, use the link given below:
Based on the given requirement, that you need to create an entity for credit cards, the appropriate entity type to use in LUIS would be a prebuilt entity.
Prebuilt entities in LUIS are pre-defined entities provided by Microsoft for common scenarios, such as date/time, email, and currency. They are trained on large amounts of data and can recognize entities in a wide variety of formats, including different languages and regions.
The prebuilt entity for credit card information in LUIS is called "builtin.creditCard". By using this prebuilt entity, LUIS can automatically identify and extract credit card information from user input, without the need to define specific patterns or lists.
List entities are used when you have a fixed list of values for an entity, and Regex entities are used to extract values based on a regular expression pattern. While these entity types could potentially be used to extract credit card information, they would require defining specific patterns or lists, which could be time-consuming and may not capture all possible formats of credit card information.
ML entities are custom entities trained using machine learning algorithms. They can be used to extract entities for scenarios where prebuilt or list entities are not available or sufficient. However, for the given requirement of creating an entity for credit cards, a prebuilt entity is the most appropriate and efficient option.