How to proceed after "I see."
1> Let's talk.
0> What would you like to see happen in this conversation?
1> I would like to clarify how to proceed after a user enters "I see".
0> Is there anything else about that user?
1> Users are looking for "I see".
0> What type of user is this user?
1> First listen.
0> Yes
1> After typing "I see", confirm with "What just happened?" and then, regardless of the answer, the next question will be "Is this a good place to end? If the answer is "yes", the session ends with "thank you", and if the answer is "yes", it returns to the original mode with "what would you like to happen right now? If yes, "What would you like to happen right now?
0> Mode
1> I feel like this is the right thing to do.
0> qi
1> The end
0> What would you like to see happen in this conversation?
1> I wanted to clarify how to proceed after a user enters "I see", but I think I've already clarified.
0> How do you know the user?
1> The good flow can now be detected by the user entering "I see", but the bad flow has not been detected.
0> Is there anything else about that process?
1> Now "NGKW" is a command to delete target keywords, and there is a separate "NG" which is ambiguous in meaning, and the person who created it does not understand the meaning of the command correctly after 5 years since he created it, maybe he should get this right.
0> What type of command is that?
1> A command for a human to ambiguously express "not good enough". Maybe it's just a marker for later machine learning and has no function as a command, or maybe it has a function to remove the bot from the target to be read and transformed by the bot to note what it thought was bad separately from the story.
0> Is there anything else about that command?
1> Maybe there is a function to reduce the score of a target keyword in a one-off, or maybe we should detect the deterioration of the user's mental state by the accumulation of "NG has occurred many times".
0> What do you value?
1> Interesting exchanges should continue. We want to increase the density of interesting exchanges by allowing uninteresting exchanges to be easily terminated.
0> What is the relationship between that interesting exchange and the user?
1> The user's state of mind improves when interesting exchanges continue and new ideas are generated.
0> Is that user the same as an interesting exchange? Is it different?
1> No.
0> What happens in an interesting exchange when a user
1> NG
0> What happens to the user during an interesting exchange?
1> The user's brain is activated by the stimulus of the exchange. Given a small unit task of a question, a high level of concentration on it occurs, and the user enters a flow state.
0> What is between that user and an interesting exchange?
1> There's a period of aiding and abetting before the interesting exchange switches on.
0> What is the relationship between that aid and the user?
1> The user's mental state changes during the helping period.
0> What is the relationship between its users and their mental state?
1> Good mental state is necessary for the device, the user, to be used efficiently
0> What is the relationship between the user and the device?
1> Same
0> Is a user the same as a mental state? Is it different?
1> No.
0> What happens to your mental state when you are a user?
1> NG
0> What happens to the user when in a mental state?
1> NG
0> What is the connection between the user and the mental state?
1> (What would be... the train arrived at the office.
1> Bye-bye.
---
This page is auto-translated from /nishio/「なるほど」の後の進め方. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I'm very happy to spread my thought to non-Japanese readers.