Oracle has announced new features in Oracle Digital Assistant to enable customers to offer AI-powered voice assistant capabilities to their entire organization, without the complexity of language barriers.
According to Oracle, AI-powered conversational interfaces are becoming mainstream staples for consumers and enterprise alike, as automation is a means for increasing scale and efficiency and accelerating efforts to digital. In addition, recent global events and challenges have forced a restructuring of how organizations work, and AI and digital assistants are fundamental to that transformation.
The new capabilities were announced in a blog post by Suhas Uliyar, vice president, AI and digital assistant, Oracle.
The new features to Oracle Digital Assistant include the following:
- New Deep Learning Models: Customers can leverage the power of Oracle Cloud Infrastructure’s native GPU and CPU architecture to improve the ability to distinguish nuances in customer queries, such as:
- Similar vs. unrelated phrases: “Can I get some flatbread?” vs. “Can I get some flowers?”
- Additional context within long sentences:
“I have a large party later this afternoon, and I have several guests coming over. I’d like to order some large pizzas.” - Closely related sentences: “I want to cancel my order” vs. “Why was my order cancelled?”
- Distinguishing names that sound like locations: “When will Devon Arlington come to Stratford-upon-Avon?” or “Find Paris Hilton from the Paris office”
- Distinguishing number vs. currency: “Lunch with 3 for 60 bucks”
- Colloquial terms: “I have a budget for 20M bucks” (colloquial usage)
- Currency formats: “Please add a tip for 2,50 €” (different currency formats)
- Versatile Data Shapes: Customers can use both large as well as small datasets to train their skills without concern that an imbalance would impact the NLU performance.
- Custom Domain Vocabulary: Customers can expand the assistants understanding to their own custom domain vocabulary.
- Data Manufacturing Pipeline: The data manufacturing pipeline provides a cohesive set of tools providing all stakeholders, from technical to line-of-business, the ability to generate, refine, curate, and evaluate conversational data. Combining human sourced intelligence with advanced machine learning delivers better, more nuanced results that only humans can offer.
- Native Multilingual: With Native Multilingual natural language understanding, customers can add training data in different languages, eliminating the need for external translation services to understand users who do not speak English—and customers can provide multilingual outputs directly using resource bundles.
- Key Phrase word clouds and multilingual retrainer: Digital Assistant now features intent and key phrase clouds to help business analysts quickly understand common themes of engagements. The business analyst can quickly drill down into the details of a specific phrase.
With the new updates to Oracle Digital Assistant, Oracle says it is adding the new features customers are looking for to further weave digital assistants into the fabric of the enterprise. As a result, customers are able to offer automation across their entire organization, using a secure AI-powered voice assistant that stores their business’ sensitive data in Oracle’s second generation cloud infrastructure.
For more information, go to www.oracle.com/solutions/chatbots.
To read the blog, go to https://blogs.oracle.com/mobile/oracle-enhances-oracle-digital-assistant-with-multilingual-capabilities-v2.