×
$helper.renderConfluenceMacro('{bmc-global-announcement:$space.key}')
 
 
  •  

Phased rollout

 

This version of the software is currently available only to early adopter SaaS customers as the first step in our phased rollout. Click here to view an earlier version.

BMC Helix Virtual Agent 21.02

Planning and deploying chatbots

Before implementing chatbots in your organization, you must plan and identify the use cases that you want to address by using chatbot. 

Typically, planning and deploying a chatbot includes the following stages: 


Best practices for planning, implementing, and operating chatbots

The following presentation explains the stages and best practices for planning, implementing, and operating BMC Helix Virtual Agent:


Additional information about IBM Watson Assistant capabilities

The following blog links provide more information about IBM Watson Assistant capabilities. BMC does not endorse the information in these external blog links. The information provided in these links should be used for reference purposes only.

Best practices for IBM Watson Assistant capabilities
Category

Reference in IBM Watson Assistant documentation

Blogs


  • Disambiguation
  • Self-learning from Disambiguation selections
  • Measure customer effort
  • Controlling the conversational flow

  • Enable your skill to improve itself with autolearning

  • Tracking the impact of autolearning
  • General Guidelines For Chatbot Scripts

  • Enable Your Chatbot To Disambiguate Intelligently With Automatic Learning

  • How To Measure Customer Effort With IBM Watson Assistant
Digression

Understanding dialog skill digressions

Why Your Chatbot Conversation Must Allow For Digression

Spelling correction (language dependent) and
Fuzzy marching

Correcting user input

How IBM Watson Assistant Is Correcting User Input For Chatbots

Irrelevancy detection

Defining what's irrelevant

Two Significant Enhancements Were Made To IBM Watson Assistant

Intent conflict resolution

Creating intents

How To Resolve Intent Conflicts With IBM Watson Assistant

Annotated Contextual Entities

Annotation-based method

Contextual Entities with IBM Watson Assistant

Handling compound intents

Tips for capturing information from user input

Dealing With Compound User Intents In IBM Watson Assistant

NLG (Random responses per node)

Adding variety

Chatbots: Creating Natural Language From Structured Data

  • Intent recommendations
  • Example utterances recommendation
  • Getting help with intents

  • Getting intent user example recommendations
  • Taking A Look at IBM Watson Assistant Intent Recommendations
Was this page helpful? Yes No Submitting... Thank you
Last modified by Aaditi Lakade on Mar 30, 2022
reference best_practices thirdpartylink externallink

Comments

Log in or register to comment.

Best practices for BMC Helix Virtual Agent
Submitting service requests or searching knowledge articles
© Copyright 2017 - 2021 BMC Software, Inc.
Legal notices

Powered by Atlassian Confluence and Scroll Viewport

© Copyright 2005-2023 BMC Software, Inc. Use of this site signifies your acceptance of BMC’s Terms of Use . BMC, the BMC logo, and other BMC marks are assets of BMC Software, Inc. These trademarks are registered and may be registered in the U.S. and in other countries.