Train

1. Introduction 

According to juniper Analytics, there will be a three-fold rise in Conversational bots by 2023. The demand is high since these bots provide a communication experience that mimics the behavior of a human agent. These bots work on advance NLP and are trained on FAQs to provide relevant information for a user query,

Advanced NLP enables users to add entities to FAQs to improve the search capability and also remove redundancy from the bot. MyBOT NLP Engine e-sense processes the query asked by the user and covers spelling and grammatical mistakes that a user may make while asking a question to the bot. 

The system then sends a match percentage with an answer already defined and based on that provides an answer. 

Training a bot means in cases where a wrong answer is triggered or a default response is triggered can be remapped to correct answer which will return the desired output in the next attempt. For Instance, a user asks a ticket booking bot about available shows and the bot does not provide a valid answer the bot can be then trained with a new response or tagging it to an existing relevant response to provide the required if the same query is triggered again. 

2. Accessibility 

A user can train a selected bot by clicking on the train button on the left panel. This functionality is provided to all users.

3. Terms and Definitions 

Terms Definitions
NLPNatural Language Processing is the ability of a computer program to understand human language as it is spoken. NLP is a component of artificial intelligence (AI)
Entities It is a data point or value which you can extract from a conversation/user query. This helps you to customize what kind of information you are collecting or how you want to associate it or want to add some custom value to it. For more information on entities and intents click here.
FAQFrequently Asked Questions (FAQs) are the standard queries relevant to a product or a service. For more Information on FAQs click here.

4. Training Process 

  1. A user types in a query/question on your bot 
  2. Your bot gets the closest matching query saved by you in your FAQ module 
  3. Bot triggers an answer mapped to that query 
  4. You can monitor the responses under the training tab 
  5. For an unsatisfactory/no response situation, click Train to provide the right/improve answer for the given query. 

4.1 Steps to train a bot for an FAQ

Step 1: Click on Train button on the left panel on your MyBOT app page 

This tab will list all the queries with date and time information, that are asked on the bot. You can see the query asked by the user, closest matching query listed by the system and response provided for the same. 

Step 2: Click train for the FAQ response you want to train your bot for

Step 3: The modal that opens will show you the question and the closest matching answer.

What can be done here to Improve responses?

Solution 1: Add a new response to the question

  • Click on new 
  • Select  a response type as Message or path 
  • Add new answer 

Solution 2: Add more variations to the question so that points to the right answer

  • Click on (+) sign in front of questions tab and add more     

                                variations to the same question. 

Variations are added to inconsistencies in queries. A user may ask the same question in a different manner than the other. 

 Example:  U1: How can I book my ticket using your bot?

                   U2: Can I make a reservation on your bots?

                   U3: Can we reserve our seats on the bot?

Solution 3: Add Entities  

Entities are data points or values which you can extract from a conversation/user query. This workflow allows you to customize what kind of information you are collecting, how do you want to associate it and add your own custom set of values, if needed.

Example: Let’s consider a use case where you want to trigger a standard response for a set of values. In this case  Course enrolment process. We can create a custom entity named course which can trigger a standard response for all course-related queries.

4.2  Adding an entity 

  4.3 Tagging an entity in an faq 

 4.4 Query and its response 

4.5 Handling an important lead at a critical point in bot flow 

If a user is in a critical point in bot flow or the query asked is an important part of the user journey/ a client close to conversion a bot owner can Jump in by clicking the chat button on the training screen. This way bot owners can respond to customer queries manually and improve user experience.

Illustration: Train a bot to handle the variation of queries mentioned above 

4.5.1 Pre-training mode

FAQ added in the bot: How can I book my ticket using your bot?

Test Query1: How can I book my ticket using your bot?

Test Query2: Can I make a reservation on your bots?

Test Query3: Can we reserve our seats on the bot?

4.6 Training the bot

Click on Train on the left Panel

Click on train button of the query that we need to add variations for which we did not receive an answer

We can select the closest matching response if it is right or add a new response if no valid response exists. In this case, we can see that there is the closest matching response. Select it and save it.

4.7 Similarly training for other unanswered responses. 

Test Post-training 

Test Query1: How can I book my ticket using your bot?

Test Query2: Can I make a reservation on your bots?

Test Query3: Can we reserve our seats on the bot?

We can see that the bot returns the trained response now.

Was this article helpful?

Related Articles

Leave A Comment?