Method and server for dementia test based on voice question and answer using artificial intelligence call

A dementia test server based on an artificial intelligence telephone call performing a dementia test based on question and answer using the artificial intelligence telephone call, the server including:

• a communication unit communicating with a user terminal to provide an artificial intelligence telephone call, transmitting a question and test result to the user terminal, and receiving an answer from the user terminal;
• a dementia test progress unit providing guidance to the user terminal, conducting a first test, which is an initial familiarization test, in order to increase a test subject's understanding of a test progress method, conducting a second test, a main test, used to determine a presence of dementia or a dementia symptom level of the test subject, wherein the first test is conducted by providing a first question for requesting an answer to a first topic to the user terminal for a first time period and acquiring a first answer from the user terminal, and the second test is conducted by providing a second question for requesting an answer to a second topic, different from the first topic, to the user terminal for a second time period, longer than the first time period, and acquiring a second answer from the user terminal;
• and
• an analysis unit analyzing content of the first test by calculating an understanding value, which is a value numerically quantifying a degree of the test subject's understanding of the test progress method based on the first answer, and when the understanding value is lower than a preset value, determining that the test subject does not understand the test progress method, and guiding the test progress method without conducting the second test or scheduling a test thereafter, and analyzing content of the second test by converting the second answer into text data, extracting at least one word corresponding to the second topic from the text data, calculating a language fluency value based on at least one word corresponding to the extracted second topic, comparing and analyzing the language fluency value with a preset reference value, and when the language fluency value is lower than the preset reference value, determining that the test subject is a subject for a follow-up test.