System of Generative Chatbot in Real Multi-Person Response Situation and Method Thereof

A system of generative chatbot in a real multi-person response situation, comprising:

• an artificial intelligence device, configured to receive a context message and a timing logic corresponding to the context message through an application programming interface, input the context message and the timing logic to a large language model to generate at least one response message, and transmit the at least one response message through the application programming interface;
• a portable device, comprising:
• at least one sensor, configured to continuously sense speech signals;
• a speaker, configured to output a feedback speech;
• a storage device, configured to store feature vectors and text messages corresponding to the speech signals, wherein each of the text messages comprises a timing label and a classification label;
• and
• a speech processor, electrically connected to the sensor, the speaker, and the storage device, and configured to:
• convert the sensed speech signals into the feature vectors based on Mel-frequency cepstral coefficients, and classify the speech signals;
• perform a speech-to-text (STT) process to convert the speech signals into the text messages;
• embed the timing label and the classification label into the text messages corresponding to the speech signals based on a timing relationship and a classification result, and store the text messages to the storage device as the context message;
• and
• when an on-demand chat message is received, perform a text-to-speech process to convert the on-demand chat message into the feedback speech, and output the feedback speech through the speaker;
• and
• a server-end host, connected to the artificial intelligence device and the portable device, and comprising:
• a non-transitory computer-readable storage medium configured to store computer readable instructions;
• and
• a hardware processor, electrically connected to the non-transitory computer-readable storage medium, and configured to execute the computer readable instructions to make the server-end host execute:
• continuously loading the context message from the storage device of the portable device, and determining a timing logic of a multi-person conversation based on the embedded timing label and the classification label, wherein the timing logic comprises the number of people, a timing and a topic of conversation;
• transmitting the context message and the timing logic to the artificial intelligence device, receiving the response message from the artificial intelligence device, and storing the response message into a response list;
• and
• automatically selecting at least one of the response messages in the response list as the on-demand chat message, and transmitting the on-demand chat message to the portable device.