Artificial intelligence with real impact
HIGHER EDUCATION'S FINEST
Why Ocelot’s AI approach is superior
Better answers.
Immediate "Day 1" value.
Staff maximizes impact.
QUALITY IN. QUALITY OUT.
The power of big data
A key driver of AI quality is the breadth of inputs from which the AI feeds on to create responses to student interactions. Ocelot takes a big data approach so students get the best answers.
This centralized architecture means the AI is learning from data across Ocelot’s entire network. Clients benefit from the collective strength of the network that includes millions of student interactions and hundreds of thousands of questions instead of only having a single-school environment to fuel the engagement experience with our platform.
Ocelot also curates comprehensive content libraries to supplement other key inputs (web crawling, internal FAQs, data from integrated platforms) ensuring students get the best answers that a individual school cannot provide on its own.
BEST-IN-CLASS EXPERTISE
Human supervised learning
Ocelot’s AI Conversation Design team takes a unique approach to make the platform smarter. This team consists of data scientists, content creators, and conversation design experts. Additionally, Ocelot has a Compliance and Content Review committee that, with a combined 70 years of higher education experience, ensures that general content stays up-to-date with the latest regulations and trends. In simple terms – Ocelot does the heavy lifting when it comes to managing the technology and building the AI algorithms, so clients can focus on facilitating more impactful interactions with their students.
Intent Classification
Constant refining of precision/recall and multiple analytic models
The chatbot’s ability to understand a user’s intent is based on how well the AI algorithms are trained. The team measures precision/recall, transfers learnings from millions of interactions and manages multiple analytical models. The team also often collaborates with clients to build examples and make sure we are capturing the different ways users are communicating with the chatbots.
Entity Development
Continuous development and creation of new domain-specific entities
Entities are keywords or terms relevant to the intent. The team manages entity development which includes responsibly expanding the vocabulary of the Chatbot.
Knowledge Base
Dedicated team to expand libraries
The team continually improves the knowledge base by creating new content which naturally expands the topics our Chatbots can converse about without any additional training from our clients. For example, we regularly add or modify content due to regulatory updates, industry trends and we look at client submissions to grow our General Library. Our team regularly mines conversations across our entire network, identifies potential gaps and develops a roadmap for new content development. Finally, Ocelot’s development team is regularly creating conversational design features that allow for more complex and sophisticated dialog building.
Dialog Flow
Optimization of dialog logic, conversation abandonment and classification-to-prediction workflow
The Ocelot team oversees how user dialogs are flowing. They are looking to make sure the chatbot has sound dialog logic, and understands what causes users to abandon a conversation with a chatbot.
IMPROVING OUR AI RESPONSIBLY
Always getting smarter
We use natural language processing (the process of organizing language into structured data), natural language understanding (teaching machines reading comprehension), and deep learning and neural networks (understanding relationships in data) to inform our AI.
This approach, combined with continuous optimization of our knowledge base, regular analysis of intent, entity and dialog data, plus client input ensures a best-in-class experience with our AI.
CUSTOMER SUCCESS STORIES
Dive into more success stories
Colorado State University Global
How Bakersfield College Leverages AI-Powered Solutions To Fuel Student Engagement, Re-Enrollment, & Financial Aid Strategy
How Empire State University Unifies A Decentralized Campus With AI Technology
Over 15.6 million questions answered in the last 12 months alone.
to increase enrollment, retention, and student success.