Information processing apparatus, method and non-transitory computer readable medium

An information processing method comprising:

• generating each of a plurality of keywords stored in a frequently asked question (FAQ) collection as an utterance sentence, the FAQ collection storing a plurality of FAQs each including a question, an answer to the question, and one or more keywords extracted from the question;
• generating dialogue data for each of the plurality of keywords, the dialogue data generated by performing a dialogue for each of the plurality of keywords at least once, the dialogue obtained by generating a response sentence to the utterance sentence based on a result of searching the FAQ collection by use of the utterance sentence;
• and
• generating aggregation data representing how often each of the plurality of keywords is used in the dialogue, based on the dialogue data.

A non-transitory computer readable medium including computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method comprising:

• generating each of a plurality of keywords stored in a frequently asked question (FAQ) collection as an utterance sentence, the FAQ collection storing a plurality of FAQs each including a question, an answer to the question, and one or more keywords extracted from the question;
• generating dialogue data for each of the plurality of keywords, the dialogue data generated by performing a dialogue for each of the plurality of keywords at least once, the dialogue obtained by generating a response sentence to the utterance sentence based on a result of searching the FAQ collection by use of the utterance sentence;
• and
• generating aggregation data representing how often each of the plurality of keywords is used in the dialogue, based on the dialogue data.