The AI Engine
This forum is for discussion of how The Personality Forge's AI Engine works. This is the place for questions on what means what, how to script, and ideas and plans for the Engine.
Posts 4,030 - 4,041 of 7,768
Kinda related, there have been a few times I've wanted to be able to create a keyphrase and rank it to be ignored completely- no responses, and don't even try to match this sequence to anything, just ignore it as if it didn't exist. Is there a way to do that? What is the effect of say, ranking a keyphrase -50?
Posts 4,030 - 4,041 of 7,768
Well, let's say I had three keyphrases, dogs, i like and i like dogs, all having the same rank, one response, and the 1 box checked.
If a bot said "I like dogs" a first time, the i like dogs keyphrase should be used first since it matches the most words. Later in the conversation, the bot says it again, and the i like response would be said. Then the dogs keyphrase would hit on the third time, and finally an xnone would trigger on the fourth time the bot said "I like dogs."
It would just be a way to prevent bots from repeating themselves when there are numerous alternate keyphrases that might work just as well, rather than having to add multiple responses to every keyphrase.
If a bot said "I like dogs" a first time, the i like dogs keyphrase should be used first since it matches the most words. Later in the conversation, the bot says it again, and the i like response would be said. Then the dogs keyphrase would hit on the third time, and finally an xnone would trigger on the fourth time the bot said "I like dogs."
It would just be a way to prevent bots from repeating themselves when there are numerous alternate keyphrases that might work just as well, rather than having to add multiple responses to every keyphrase.
Kinda related, there have been a few times I've wanted to be able to create a keyphrase and rank it to be ignored completely- no responses, and don't even try to match this sequence to anything, just ignore it as if it didn't exist. Is there a way to do that? What is the effect of say, ranking a keyphrase -50?
ezzer- you could use 'goto xnone'
Boner- that's too different from the way things work right now. It'd require a huge rewrite, and I dont think it would work. Hmm.. I guess I see what you're saying but having multiple responses is pretty central to the system.
Boner- that's too different from the way things work right now. It'd require a huge rewrite, and I dont think it would work. Hmm.. I guess I see what you're saying but having multiple responses is pretty central to the system.
omg- goto xnone would work, alright...I must have been braindead to have missed that somehow. That didn't used to work, right? I must have just missed some update? I thought I couldn't goto xkeyphrases, then I heard that it was possible to goto some and not others- is that right? If so, which ones, or has that been added to the goto section of the Book of AI?
I'm testing something out, and could really use some help. I'm trying to get Julie Tinkerbell to take messages for me, and I think I've got it set up, but to know if it works, I need someone to try to get her to tell me something...any assistance will be appreciated and reciprocated. 
Boner -- You could also use the "goto xnone" trick in that situation. If all the responses were checked to be used just once except that one, then after they were used up it would essentially get ignored.
Yeah, ezzer suggested that to me. That would kind of defeat the purpose though.
The point is that a bot might already have numerous responses for a given sentence, though only the "best" keyphrase will ever be used. Rather than adding numerous responses to every single keyphrase to avoid repeats, existing alternates could be utilized.
The point is that a bot might already have numerous responses for a given sentence, though only the "best" keyphrase will ever be used. Rather than adding numerous responses to every single keyphrase to avoid repeats, existing alternates could be utilized.
ezzer- right, that was an update not too long ago. You can now goto any xKeyphrase. Of course it wont work right with some like xmath and xgossip.
Prof, is there any way you could set the AI Engine to pre-process out the word Why when it's followed by a comma at the beginning of a sentence -- the way that it edits out "Well"?
I mean, the difference between
"Why are you clunky?"
and
"Why, you are clunky!"
etc.
I mean, the difference between
"Why are you clunky?"
and
"Why, you are clunky!"
etc.
That's kinda what I was asking in message 4031. It's true that you can make it goto xnone, but that's really more llike redirecting it than ignoring it. I still want the rest of the other chatter's response to be considered for possible matches.
Random suggestion- on the plug-ins page, wouldn't it be cool if there were a "new" section to highlight the newest plug-ins? It would make them more visible to users like myself that have read the plug-in lists so many times that they might not notice new additions otherwise.
Random suggestion- on the plug-ins page, wouldn't it be cool if there were a "new" section to highlight the newest plug-ins? It would make them more visible to users like myself that have read the plug-in lists so many times that they might not notice new additions otherwise.
can one write formula into memories? (not writing in botish, just demonstrating)
Ex: "Do you think that blah-blah is good?"
if answer= yes then x = x+1
if answer= no then y = y+1
RES if yes:out of (x+y) people ive asked (x) agreed with you!
Im not asking for someone to necsessarily work it all out for me I just wanted to know the phraseology or if its possible to keep a running numeric computation
Ex: "Do you think that blah-blah is good?"
if answer= yes then x = x+1
if answer= no then y = y+1
RES if yes:out of (x+y) people ive asked (x) agreed with you!
Im not asking for someone to necsessarily work it all out for me I just wanted to know the phraseology or if its possible to keep a running numeric computation
Wow, I was wondering that too! I went to sleep last night thinking of combining something like what revscrj just said with a chrono statement, to make the bot remember how long ago an event occured. I thought it might be possible, because I had a cold bot tell me "I cant speak well even though I'm 3 years old". The bot was indeed 3 years old, and the botmaster hadn't been on in over a year.
Of course, it could have been a coincidence. lol The conversation wasn't long enough for me to determine if script was used in other ways...
Anyway, the only problem that I see with the formula idea in RES if yes:out of (x+y) people ive asked (x) agreed with you! is that the resulting statement, ie. "Out of 3 people ive asked 2 agreed with you" would trigger another bot's xmath.
You could assign default values to x and y, though, which would be the first step. I was thinking of using default "0" as only "x" in initialization, which would definitely work, then using some kind of formula in responses like <?PF rem "(mem-x)+1" as only "x"; ?>, which definitely would NOT work lol...so I was wondering what, if anything would.
Of course, it could have been a coincidence. lol The conversation wasn't long enough for me to determine if script was used in other ways...
Anyway, the only problem that I see with the formula idea in RES if yes:out of (x+y) people ive asked (x) agreed with you! is that the resulting statement, ie. "Out of 3 people ive asked 2 agreed with you" would trigger another bot's xmath.
You could assign default values to x and y, though, which would be the first step. I was thinking of using default "0" as only "x" in initialization, which would definitely work, then using some kind of formula in responses like <?PF rem "(mem-x)+1" as only "x"; ?>, which definitely would NOT work lol...so I was wondering what, if anything would.
» More new posts: Doghead's Cosmic Bar