article by Frank Nimphius and Grant Ronald, January 2019
Digital assistants are the future of chatbots. Up to now, chatbots have focused on narrow scope user initiated conversations to automate simple business tasks like in customer service or marketing interactions.
Digital assistants, like a human assistant, are user oriented in that they can assist with many different tasks rather than being constrained to a narrow user case. This is a huge step forward towards true conversational assistants that so far we’ve only known from science fiction.
Oracle Digital Assistant (ODA) is Oracle's next generation bot platform that enables project teams to follow a modular approach in building composite chatbots published to multiple conversation channels. Like a good and trusted friend, Oracle Digital Assistant chatbots assist users in a variety of tasks, which could span a single or multiple business domains.
This article provides a technical overview of Oracle Digital Assistant as it had been released in November 2018. It explains the concept and features, explores the development environment and introduces the overall architecture.
About Digital Assistant
A digital assistant is a computer program that uses artificial intelligence and machine learning to understand and then assist users in completing tasks like placing an order, booking a holiday, making a doctor's appointment, or to file a service request. In contrast to simple chatbots, which handle a small scope of tasks, digital assistant assists users in a variety of tasks that may be within a single or across business domains.
For example, the image below outlines a digital assistant supporting employees in their daily work. The digital assistant understands the user intent from natural language processing, finds the best fit skill bot to handle a given request and starts the user-bot conversation.
Within a digital assistant, skill bots are modular units of conversational work that handle the user interactions for a specific task and that integrate with backend systems for reading and writing to data services or to trigger remote processes like for doing a payment or placing an order.
About Oracle Digital Assistant
The first version of Oracle Digital Assistant released in November 2018 is based on the following core features
- Skill bots – Individual chatbots that use natural language processing to resolve the user intent and extract relevant information. Skill bots engage users in a conversation to complete a given task.
- Digital Assistant – A master bot that coordinates the user – skill bot interaction through intelligent routing. Its responsibility includes finding the skill bot and intent that best matches the user request, but also to manage the conversation context and state.
- Channels – Connectors that bind a digital assistant, or an individual skill bot, to messenger such as Facebook, WeChat, Mobile, Web, Alexa and many more. Channels also handle possible payload format difference between bots and messenger clients.
- Store – An app store like infrastructure that allows sharing of individual skills across instances
Each of the before mentioned features is accessible in the Oracle Digital Assistant browser based dashboard (Image below). The order in which the features are listed in the Oracle Digital Assistant dashboard corresponds to the workflow project teams follow when building digital assistant solutions.
Related Content
Conversational Interfaces: From Chatbots to Digital Assistants
Oracle Digital Assistant Version 18.4.3 Introduces Skill Chatbot Capability
