Watson Assistant on Cloud Pak for Data as a Service
With Watson Assistant on IBM Cloud Pak for Data as a Service, you can use AI to build and deploy a branded assistant into any device, application, or channel. Connect your assistant to the customer support resources that you already use to deliver an engaging, unified problem-solving experience to your customers.
Your customers interact with a chatbot, which is also known as an assistant, through an existing social media channel or client user interface that you build. For example, you might implement a simple chat window or a mobile app, or even a robot with a voice interface. Use the Watson Assistant APIs to send messages from the user interface to the service. Your client interface application can be hosted either inside or outside the IBM Cloud Pak for Data infrastructure.
Use the intuitive graphical tools that are provided with the Watson Assistant service to develop training data that captures your unique customer needs and use cases. Watson Assistant uses the training data to generate a customized machine learning model for you. This model is what powers your assistant to understand requests from customers so it can answer them correctly.
After your assistant analyzes the message from a customer, it routes the message to the appropriate skill:
- The dialog skill interprets the user input further, then directs the flow of the conversation. The dialog gathers any information it needs to respond or perform a transaction on the user’s behalf. The skill can connect with other IBM services or interact with your own back-end systems to extract information or perform transactions that are based on the user’s intent or other information.
- The search skill routes complex customer inquiries to IBM Watson™ Discovery for IBM® Cloud Pak for Data. Discovery treats the user input as a search query. It finds information that is relevant to the query from the configured data sources and returns it so the assistant can share the information with the user as its response.
With the help of the skills that you build, your assistant can answer simple or complex questions, and even perform tasks, such as opening tickets, updating account information, or placing orders.
Watson Assistant requires these prerequisite services to be installed.
Use an AI-powered search engine to extract answers from complex business documents. Train AI for deep understanding of your content, including tables and images, to help you find business-value hidden in your enterprise.
These related services are often used with Watson Assistant and provide complementary features, but they are not required.
|Watson Language Translator||
Identify the language of text and translate it into different languages programmatically.
|Watson Knowledge Studio||
Create a machine learning model that understands the linguistic nuances, meaning, and relationships specific to your industry or create a rule-based model that finds entities in documents based on rules that you define.
|Watson Speech to Text||
Convert audio and voice to written text with speech recognition capabilities for your applications.
|Watson Text to Speech||
Convert written text to natural-sounding speech for your applications and stream the results back to the client with minimal delay.