Emotion-based AI prompting involves the use of AI systems to detect, analyze and respond to prompts based on specific human emotions. These systems leverage NLP, large language models (LLMs), sentiment analysis to provide response based on an individual’s emotional state. This emotion-based AI prompting can play a vital role in improving the quality of life for individuals with dementia and Alzheimer's, fostering a supportive and adaptive care environment.
Aryan Bharti and Yug D Oswal in their blog proposed a solution for supporting people with dementia and Alzheimer's – Rekindle application. The goal of the application is to create a life journal where people share their daily experiences and the chatbot provides guidance or encouragement based on their emotions. This application helps them to revisit and reconnect with their memories.
How does the application work?
- Users can input a message to the chatbot.
- Emotion classifier will detect the emotion of the user’s message or story (this message will be stored in the backend).
- The retriever retrieves relevant information and sends it to the LLM.
- The LLM generates a response based on the user’s message, the emotion, and the retrieved information.
Learn more about the project on Medium and GitHub.
They have developed this project using TensorFlow* Optimizations from Intel, Intel® Extension for Scikit-Learn*, Modin* and Intel® Tiber™ AI Cloud.
Learn more about Intel’s AI Tools and Technologies Used
- TensorFlow Optimizations from Intel - Intel collaborates with Google* to upstream most optimizations into the stock distribution of TensorFlow with the newest optimizations and features being released earlier as Intel® Extension for TensorFlow*. These optimizations can be enabled with a few lines of code and will accelerate TensorFlow-based training and inference performance on Intel CPU and GPU hardware.
- Intel Extension for Scikit-Learn - Dynamically patches scikit-learn estimators while improving performance for machine learning algorithms.
- Modin - Modin is a drop-in replacement for the extensively used Python library, Pandas. Intel up streams all optimizations to open source Modin from 2024.2 AI Tools release.
- Intel Tiber AI Cloud - Accelerates AI workloads using Intel optimized software on the latest Intel hardware.
What’s Next?
We encourage you to check out and incorporate Intel’s other AI/ML Framework optimizations and tools into your AI workflow and learn about the unified, open, standards-based oneAPI programming model that forms the foundation of Intel’s AI Software Portfolio to help you prepare, build, deploy, and scale your AI solutions.
About the Authors
Aryan Bharti is pursuing his bachelors in computer science at Vellore Institute of Technology. He is passionate about backend development, cloud, designing and building complex systems.
Yug D Oswal is pursuing his bachelors in computer science at Vellore Institute of Technology. He is passionate about AI/ML, data science, web, and app development. Recently, he finished his internship as a ML Engineer with the Ministry of Defence, India.
Product Marketing Engineer bringing cutting edge AI/ML solutions and tools from Intel to developers.