Waston Strengths and investigation
- With the release of Watson Conversation Service, developers can now partner with businesses to build out conversation applications with simplified tooling.
- Watson Engagement Advisor provides enterprise level support and needs including data isolation, end-to-end encryption, personally identifiable information (PII) support (coming in September).
- Using the Watson Conversation Service, developers have the ability to deploy a range of bots via many channels from simple, narrowly focused bots to much more sophisticated, full-blown virtual agents across mobile devices, messaging platforms like Slack, or even through a physical robot.
- Starting this fall, we will begin offering industry specific offerings for the enterprise via Watson Engagement Advisor including a trained corpus, with intents. For example, in the telco industry this would include things like common questions about wireless services.
- Complementary APIs like Retrieve and Rank and Tone Analyzer that make our bots more comprehensive.
Both Watson Conversation Service and Watson Engagement Advisor
How conversation service and engagement service works?
We built our robot over NLP classifier and Alchemy language beofore.
According to practice on API, Watson Conversation service sample code. In my eyes, Watson dialog and NLP classifier extract the intent and entities to build the accurate model for question and answer system for individual question, conversation beyond that and it allow developers to extract context of previous Q/A to make an smart conversation.
See detail in source of Demo app
Watson engagement advisor looks industry solution to integrate most capabilities of Waston API to determine users intent thru extracting entities, tone(sentiment), and context, then response appropriate answer NLP classifier by text or voice.