Matching system examples

Check out the following examples to understand the differences between keywords and User says matching systems.

Example 1

The bot can enter one of the following user inputs.

All examples are calculated with the default confidence score (0.7).

All examples are calculated with the default confidence score (0.7).

• User Input A uses Machine Learning matching system: The section User Says is filled with: Tell me more about your payments policy.

• User Input B uses Keywords matching system: The section User Says is filled with one word payments.

Now let’s see the bot’s behavior with three different user inputs.

• payments - would trigger User Input B.

  • Matching score: ML < 70%; Keywords = 100%.

  • Explanation: The matching score for User Input B equals 100% while for User Input A the matching score is less than 70% (below the confidence score).

• tell me about payments policy would trigger User Input A.

  • Matching score: ML => 70% but it’s < 100%; Keywords: 100%

  • Explanation: Even though the matching score for the User Input A is lower, ML has preference and will be executed.

• payments policy: would trigger User Input B

  • Matching score: ML < 70%, Keywords = 100%;

  • Explanation: The matching score for machine learning is below the required threshold. User Input A won’t be considered so the bot will go for the User Input B.

Even though ML matching system has a preference, it won’t be selected when the matching score Is lower than the confidence score.

Even though ML matching system has a preference, it won’t be selected when the matching score Is lower than the confidence score.

Example 2

We’ve got two following user inputs:

• User Input A - based on ML matching engine. User Says section is filled with sys.any system entity {{ sys.any:any }}.

• User Input B - based on keywords matching engine. User Says section is filled with a user entity named Movies. The entity has two values: Star Wars and Punisher.

Now let’s check how is our bot going to behave after the following user input is added:

• something

  • Matching score: ML = 100%, Keywords = 0%; triggered User Input A

  • Explanation: sys.any Is the only possible entity what won’t have preference while powered by the ML matching system. User Input B matching score equals 0%. The bot selects User Input A as this is the only possible variant.

• Punisher

  • Matching score: ML = 100%, Keywords = 100%; triggered User Input B

  • Explanation: Having in mind that sys.any Is never prioritized, the bot will follow User Input B which has matching score 100%.

Machine Learning matching system isn’t prioritized when User Says field is filled with the system entity sys.any.

Machine Learning matching system isn’t prioritized when User Says field is filled with the system entity sys.any.

Example 3

Let’s see the last example. We’ve got two user inputs:

• User Input A - based on ML matching system. User Says filled with a phrase payments.

• User Input B - based on Keywords matching system. User says filled with a phrase payments.

Both User Inputs have identical User Says field. Let’s check how will this scenario go.

• payments

  • Matching score: ML > 70%, Keywords = 100%; triggers User Input A

  • Explanation: ML User Input A is prioritized as it’s ML > 70%.

• transfers

  • Matching score: ML = 0%, Keywords = 0%; triggers Fallback User Input If ON.

  • Explanation: No condition has been met.

User Input can have vary matching systems. Use the one that is more relevant and gives bigger chances to be selected by the bot.