Researchers at RPI are developing a cognitive logic-enabled AI that can operate on multiple screens and in multiple environments for the K-12 sector. Declining public school math and science test scores have concerned American politicians and educators since the 1980s. This educational failure coincides with the large number of employees unable to fill the growing number of technology and engineering-related jobs. Unfortunately, the COVID-19 pandemic has further complicated the K-12 STEM education crisis. Public schools have transferred most of their coursework online, thereby placing a heavy onus on parents to monitor student participation and engagement. For minority and low-income families, monitoring children on their screens while working outside the home is nearly impossible. Public school systems have therefore outsourced their requirements to interactive, virtual classroom providers who offer machine learning-based educational services - tutoring, grading, and proctoring. Student information system (SIS) have built out early-alert tools for student success centers. Faculty and staff use SIS products to refer at risk students for further counseling and resources. While they all enable scheduling and reminders, none of these software tools offer built-in or integrated tutoring or student support services. To address the SIS market, researchers at RPI are developing a cognitive logic-enabled AI that can operate on multiple screens and in multiple environments for the K-12 sector. Teleportative Intelligent Personalized Persistent Agents for Education (TIPPAE) - an artificial intelligence that seeks to tutor experiences on multiple devices, in multiple formats and in multiple experiences is a part of a continuous educational experience. TIPPAE can be a chatbot that can communicate via text message while a user is in transit and then continue the conversation on a toy once the user arrives at home. The chatbot can assist the user with addition or subtraction problems on a smartphone with completion of the tutoring conversation on a web browser/PC. The chatbot can personalize its tutoring and content to the precise needs of its user based on natural language processing.

Submission Date
Reference Number
R21-042
Department
Inventor(s)
Contact
Natasha Sanford