The model is an end-to-end question-answering system and improves the assistant’s ability to understand the question, instead of asking the user to rephrase it.

(Subscribe to our Today’s Cache newsletter for a quick rundown of the 5 best tech stories. Click here to subscribe for free.)

Voice assistants use the Natural Language Processing (NLP) algorithm, an artificial intelligence (AI) model to train computers to understand spoken and written human language. The model is best suited for users accustomed to technology because they know how to put questions to the machine.

But older adults, especially those with limited experience using the latest gadgets, often find it difficult to ask conventional questions in a way the machine can understand.

To help senior users, a researcher at the University of California at San Diego has developed a voice assistant that will focus on understanding and responding to medical queries from elderly users, the institute said in a statement.

The model is an end-to-end question-answering system and improves the assistant’s ability to understand the question, instead of asking the user to rephrase it.

Read also | A feature that allows Google Assistant to pronounce names accurately

When asked, the system breaks down key components and matches the abbreviated medical question with a frequently asked question from a database of 17,000 medical queries from the National Institute of Health. Finally, it will select the relevant parts of the response to share with the user, the researcher noted.

The researcher will train AI and NLP systems to summarize the questions comprehensively. The model can be integrated with existing voice assistants like Alexa and Siri. The researcher also aims to make the system available to older and underserved communities around the world in native languages.