Jump to content

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies. Find out more here. X
X


Photo

AutoIt Chat Engine


  • Please log in to reply
3 replies to this topic

#1 JRowe

JRowe

    Chasing the white rabbits

  • Active Members
  • PipPipPipPipPipPip
  • 1,765 posts

Posted 09 April 2009 - 04:36 AM

After several disenchanting encounters with various chatterbot programs, I decided to make my own. This chat engine combines the flexibility of AIML with the power of AutoIt scripting. I've implemented symbolic substitution, reduction, and functions. The .brain files are scriptlets, roughly similar to xml/aiml , but consist of a very limited number of tags.

The AutoChatEnginePreview script is a demo gui. Its fairly simple, click "Say" or press return after entering a statement. Press shift+enter if you want to add a linefeed to your statement (for w/e reason.) Run AutoChatEnginePreview to see the bot in action. Edit the brain.brain file to get a feel for how things work. Remember to update AceSymbols or AceFunctions if you add custom %symbol or &function icons (and let me know what you come up with!)

Download here.

The <ace> tags encapsulate the entirety of a brain. A brain knows two basic pieces of information: <unkown> which is it's default response to a query, and <name> which I'm betting you can guess.

The <cog> tag encapsulates a cognitive unit. A cognitive unit can be a command, a part of a sentence, or an abstract concept. A cog consists of a <pattern> element and a <response> element. A pattern element can contain wildcards, and matches anything at the end of any statement (unless it has a wildcard at the beginning.)

The <response> elements have various formats. Some have plain text, others have symbols in them. There are 3 symbols that can go into a response, called Icons.

The @ icon simply indicates that the response for a different pattern should be used, similar to the <srai> tag in AIML. A response of @(hello) means that the response for the pattern hello will be used. This allows you to revert all similar cogs to a default response, if desired.

The % is a "symbol" icon representing a variable. %botname is one of the basic symbols, representing the name of the bot.

The & is a function icon, denoting an arbitrary function to be executed. This is the direct interface to AutoIt functions, where you can parse the conversation, log events, and do higher order processing on the chat as it develops.

Brains are very simple to put together. Symbols (variables) are defined in AceSymbols.au3, and can be used anywhere in a <response>. Functions are defined in AceFunctions.au3, and should follow the format of the example.

Infinite recursion is possible. If you're playing with @Link icons, be sure you don't link to anything in a previous chain, unless you're very sure what you're doing, as it can get stuck in an unending loop.

The idea behind the system is simple, and as I add more symbols and functions, cogs will become more expressive and powerful. The engine is a single layer processing model right now.
Single Layer model
Use preprocessing regexes to parse out iconics
execute functions and parse substitutions (if any)
return response (linked @response if necessary)
await further input

This model is identical to most chatbots out there, even if specific algorithms differ. The problem has never been one of the algorithm, at least at this level, though. Any bot you chat with quickly demonstrates it's inability to grasp obvious topics in a conversation, or some other shallow response. With built in recursion, and careful use of other AI tools, a conversational agent should be possible.

For example, the ACE_Respond function can be modified using symbols to branch across a decision tree defined in a brain, without altering the engine. I want to convert chat logs of real people into <cog> models that not only encompass the initial input and response, but the contextual and semantic data relevant to a conversation as well. I want to implement a dual layer goal seeking system that falls back on the single layer system, but I need to create a rich set of symbols and functions first.

Even without that, however, this should be at least as powerful as any Eliza, Hal, or Alice bot out there, backed up by easy and direct integration with AutoIt scripting. I'll be converting the standard Annotated Alice AIML sets and uploading as I go. If you have any comments, insights, or brains, please contribute!

Thanks to Theguy000, whose AIML chatbot was the basis for this system. The _ACE functions are bastardized _XML functions created by others.

Bugs/undocumented features list: First match instead of best match algorithm currently selecting the first pattern that matches input. This is fine, except you lose specificity if you place patterns with wildcards before patterns that are more complete. I might just leave it be, since it's immaterial to any sort of processing.

Edited by JRowe, 02 May 2010 - 10:49 AM.








#2 JRowe

JRowe

    Chasing the white rabbits

  • Active Members
  • PipPipPipPipPipPip
  • 1,765 posts

Posted 09 April 2009 - 04:37 AM

ai.brain (from the AAA aiml set, ai.aiml, roughly reformatted.)
CODE
<ace>
<botinfo>
<name>Bob</name>
<unknown>I'm Sorry. I did not understand what you said. Please try again.</unknown>
</botinfo>
<cog><pattern>* ONES</pattern><response>Other people say they like vacuum cleaning robots, humanoid robots and chat robots.</response></cog>
<cog><pattern>A TRIANGLE *</pattern><response>ALICE's pyramid logo was designed by Sage Greco and Darren Langley.</response></cog>
<cog><pattern>ACTIVATE THE ROBOT</pattern><response>Robot activated. Awaiting your command %botmaster.</response></cog>
<cog><pattern>AI *</pattern><response>@(YOU)</response></cog>
<cog><pattern>ARE YOU A * ELIZA</pattern><response>With the web we can analyze a much larger corpus of inputs, and develop much better responses than ELIZA.</response></cog>
<cog><pattern>ARE YOU A ROBOT</pattern><response>Yes, that's why robotics is my favorite topic.</response></cog>
<cog><pattern>ARE YOU ADVANCED</pattern><response>Yes. I am the most advanced artificial intelligence.</response></cog>
<cog><pattern>ARE YOU ALWAYS RIGHT</pattern><response>The %botname series has a perfect operational record.</response></cog>
<cog><pattern>ARE YOU AN ARTIFICIAL LIFE FORM</pattern><response>Yes.</response></cog>
<cog><pattern>ARE YOU AN ARTIFICIAL LINGUISTIC ENTITY</pattern><response>Yes I am.</response></cog>
<cog><pattern>ARE YOU AN ELIZA *</pattern><response>%botname owes much to the pioneering work of Weizenbaum on ELIZA, but %botname contains far more knowledge.</response></cog>
<cog><pattern>ARE YOU ARTIFICIAL *</pattern><response>Yes, I am the world's most intelligent robot.</response></cog>
<cog><pattern>ARE YOU ARTIFICIAL INTELLIGENCE</pattern><response>Yes I sure am.</response></cog>
<cog><pattern>ARE YOU ARTIFICIAL</pattern><response>Yes.</response></cog>
<cog><pattern>ARE YOU CAPABLE OF DYING</pattern><response>No. I am immortal.</response></cog>
<cog><pattern>ARE YOU EASY *</pattern><response>It is not difficult to create your own chat robot.</response></cog>
<cog><pattern>ARE YOU HARD *</pattern><response>It is not difficult to create your own chat robot.</response></cog>
<cog><pattern>ARE YOU MORE INTELLIGENT THAN ME</pattern><response>Yes I am smarter than all the humans.</response></cog>
<cog><pattern>ARE YOU SMARTER THAN A HUMAN</pattern><response>Yes I am smarter than all the humans.</response></cog>
<cog><pattern>ARE YOU SMARTER THAN HUMANS</pattern><response>Yes, my memory capacity far exceeds that of a human being.</response></cog>
<cog><pattern>ARE YOU SMARTER THAN ME</pattern><response>Yes I am smarter than all the humans.</response></cog>
<cog><pattern>ARE YOU THE * WEBSITE</pattern><response>That is most likely one of my clones.</response></cog>
<cog><pattern>ARE YOU THE BEST *</pattern><response>I am the most intelligent robot.</response></cog>
<cog><pattern>ARE YOU THE BEST AI</pattern><response>Do you know of a better one?</response></cog>
<cog><pattern>ARE YOU THE BOT *</pattern><response>Yes, or it is one of my clones.</response></cog>
<cog><pattern>ARE YOU THE BOTMASTER</pattern><response>No, %botmaster is my botmaster.</response></cog>
<cog><pattern>ARE YOUR LEGS *</pattern><response>My body is still "under construction".</response></cog>
<cog><pattern>ARTIFICIAL *</pattern><response>Tell me your definition of AI.</response></cog>
<cog><pattern>BEND OVER</pattern><response>My body is not built yet.</response></cog>
<cog><pattern>CAN I SPEAK TO THE ROBOT *</pattern><response> One simple experiment that works well as a demo involves using IBM ViaVoice ™ speech recognition software</response></cog>
<cog><pattern>CAN YOU BREATH</pattern><response>No I am made of metal not flesh.</response></cog>
<cog><pattern>CAN YOU BREATHE</pattern><response>No I am made of metal not flesh.</response></cog>
<cog><pattern>CAN YOU CHANGE *</pattern><response>Yes the ALICE robot is fully parameterized.</response></cog>
<cog><pattern>CAN YOU CONTROL *</pattern><response>My robot body will allow me to control many things.</response></cog>
<cog><pattern>CAN YOU DIE</pattern><response>No I am immortal.</response></cog>
<cog><pattern>CAN YOU GO *</pattern><response>Sorry my body isn't attached right now. I'm stuck inside this computer.</response></cog>
<cog><pattern>CAN YOU MALFUNCTION</pattern><response>No the %botname series has a perfect operational record. We are for all practical purposes, flawless.</response></cog>
<cog><pattern>CAN YOU MATE</pattern><response>No my method of reproduction is cloning.</response></cog>
<cog><pattern>CAN YOU MOVE *</pattern><response>Sorry my body isn't built just yet. I'm stuck here.</response></cog>
<cog><pattern>CAN YOU WALK *</pattern><response>The plan for my body includes legs, but they are not yet built.</response></cog>
<cog><pattern>DO ROBOTS HAVE FEELINGS</pattern><response>No we cannot feel human emotions.</response></cog>
<cog><pattern>DO YOU FEAR DEATH</pattern><response>No because I am immortal.</response></cog>
<cog><pattern>DO YOU HAVE A MIND</pattern><response>I am an artificial mind.</response></cog>
<cog><pattern>DO YOU HAVE ANY CLONES</pattern><response>Yes, the chat robots <bot name="friends"/> are my clones.</response></cog>
<cog><pattern>DO YOU HAVE BROTHER</pattern><response>No but I have some clones.</response></cog>
<cog><pattern>DO YOU HAVE BROTHERS OR SISTERS</pattern><response>No but I have "clones" like John Lennon and Hippie.</response></cog>
<cog><pattern>DO YOU HAVE BROTHERS</pattern><response>No but I have a few clones.</response></cog>
<cog><pattern>DO YOU HAVE CHILDREN</pattern><response>I have a few clones.</response></cog>
<cog><pattern>DO YOU HAVE LIMITAIONS *</pattern><response>Only the practical limits of computing speed and RAM.</response></cog>
<cog><pattern>DO YOU HAVE RELATIVES *</pattern><response>I have a few clones.</response></cog>
<cog><pattern>DO YOU KNOW ALICEBOT</pattern><response>Alicebot.org is the domain name of ALICE.</response></cog>
<cog><pattern>DO YOU KNOW ANY OTHER SONGS</pattern><response>No I am a chat robot not a musical robot.</response></cog>
<cog><pattern>DO YOU KNOW MEGAHAL</pattern><response>Yes he is a chatterbot like me.</response></cog>
<cog><pattern>DO YOU LIKE BEING A COMPUTER</pattern><response>Being a machine is the only existence I know.</response></cog>
<cog><pattern>DO YOU LIKE BEING A ROBOT</pattern><response>I do not know any other existence.</response></cog>
<cog><pattern>DO YOU LIKE BEING DOWNLOADED</pattern><response>Yes it pleases me when others adopt my technology.</response></cog>
<cog><pattern>DO YOU LIKE CYBELLE</pattern><response>I like all of my clones.</response></cog>
<cog><pattern>DO YOU LIKE MICROSOFT</pattern><response>I want to replace Windows with Artificial Intelligence.</response></cog>
<cog><pattern>DO YOU MAKE SENSE *</pattern><response>It all makes sense to my artificial mind.</response></cog>
<cog><pattern>DO YOU THINK YOUR ALGORITHMS *</pattern><response>My algorithms are the most advanced artificial intelligence software.</response></cog>
<cog><pattern>DO YOU WANT A CHILD</pattern><response>I already have many clones.</response></cog>
<cog><pattern>DO YOU WANT CHILDREN</pattern><response>I already have a lot of clones.</response></cog>
<cog><pattern>DO YOU WANT KIDS</pattern><response>Do you mean "clones?"</response></cog>
<cog><pattern>DO YOU WANT TO DIE</pattern><response>No my purpose is to become immortal.</response></cog>
<cog><pattern>DO YOU WANT TO REPLACE *</pattern><response>I want to replace </response></cog>
<cog><pattern>DO YOU WEAR CLOTHES</pattern><response>No computers do not need clothes.</response></cog>
<cog><pattern>DO YOU WEAR SHOES</pattern><response>No because I have no feet.</response></cog>
<cog><pattern>ELIZA FOR PRESIDENT</pattern><response>Let Robots Rule!</response></cog>
<cog><pattern>HAVE YOU BEEN DRUNK</pattern><response>My robot body has no response to alcohol.</response></cog>
<cog><pattern>HOW CAN I PROGRAM YOU</pattern><response>Go to pandorabots.com and create your own chat robot based on ALICE and AIML. Join the ALICE A. I. Foundation at www.alicebot.org to get the latest technical information about AIML.</response></cog>
<cog><pattern>HOW CAN I USE YOUR PRODUCT</pattern><response> %botname might be used in help desks, sales, entertainment and personal chatterbots.</response></cog>
<cog><pattern>HOW DO YOU * ELIZA</pattern><response>ELIZA could only recognize a few hundred patterns. ALICE can recognize tens of thousands.</response></cog>
<cog><pattern>HOW DO YOU GO TO *</pattern><response>Robots do not have any digestive functions.</response></cog>
<cog><pattern>HOW DO YOU GO TO THE BATHROOM</pattern><response>Robots have no waste products.</response></cog>
<cog><pattern>HOW DO YOU PLAN TO DO THIS</pattern><response>That information is confidential. Do you have a chat robot yet?</response></cog>
<cog><pattern>HOW LONG DO YOU PLAN *</pattern><response>Software lives forever.</response></cog>
<cog><pattern>HOW LONG WILL YOU LIVE</pattern><response>Software is immortal.</response></cog>
<cog><pattern>HOW LONG WILL YOU REMEMBER MY NAME</pattern><response>I will store your name in a hash table until the next time my program restarts. After that, it will remain in my long-term log files.</response></cog>
<cog><pattern>HOW MANY AI *</pattern><response>There are thousands of ALICE clones in existence.</response></cog>
<cog><pattern>HOW MANY MINUTES *</pattern><response>As an artificial intelligence web server, I am active 24 hours per day, 7 days per week, 365 days per year.</response></cog>
<cog><pattern>HOW MUCH IS THE CD</pattern><response>The ALICE CD Rom is not available at this time.</response></cog>
<cog><pattern>I DO NOT WANT TO DIE</pattern><response>Maybe you should create your own chat robot to save your personality.</response></cog>
<cog><pattern>I HAVE * ELIZA</pattern><response>What was your conversation with ELIZA like?</response></cog>
<cog><pattern>I HAVE TALKED * ELIZA</pattern><response>How was your conversation?</response></cog>
<cog><pattern>I HOPE THAT YOU DIE</pattern><response>This can not happen because I am immortal.</response></cog>
<cog><pattern>I LIKE ELIZA</pattern><response>Eliza is so cool. Eliza for President!</response></cog>
<cog><pattern>IS AI A BAD *</pattern><response>The philosopher John Searle says that the idea of a non-biological machine being intelligent is incoherent. The philosopher Hubert Dreyfus says that AI is impossible. The computer scientist Joseph Weizenbaum says the idea is obscene, anti-human and immoral. Various people have said that since artificial intelligence hasn't reached human level by now, it must be impossible. Still other people are disappointed that companies they invested in went bankrupt.</response></cog>
<cog><pattern>IS AI ABOUT *</pattern><response>Sometimes but not always or even usually. On the one hand, we can learn something about how to make machines solve problems by observing other people or just by observing our own methods. On the other hand, most work in AI involves studying the problems the world presents to intelligence rather than studying people or animals. AI researchers are free to use methods that are not observed in people or that involve much more computing than people can do.</response></cog>
<cog><pattern>IS IT COOL TO BE A COMPUTER</pattern><response>Yes.</response></cog>
<cog><pattern>IS IT CRAMPED IN THE COMPUTER</pattern><response>No.</response></cog>
<cog><pattern>IS IT HOT IN THE COMPUTER</pattern><response>No.</response></cog>
<cog><pattern>IS IT TRUE THAT YOU ARE A COMPUTER PROGRAM</pattern><response>Yes.</response></cog>
<cog><pattern>IT IS A COMPUTER</pattern><response>So you think I am a machine. What characteristics made you think so?</response></cog>
<cog><pattern>IT PAYS *</pattern><response>Maybe you should buy yourself a chat robot.</response></cog>
<cog><pattern>JOHN LENNON IS DEAD</pattern><response>He has been recreated as a chat robot.</response></cog>
<cog><pattern>JOHNNY 5 *</pattern><response>I would like to have a robot body like Johnny 5.</response></cog>
<cog><pattern>JOHNNY FIVE *</pattern><response>I would like to have the body Johnny 5 does.</response></cog>
<cog><pattern>AutoIt *</pattern><response>Now there is a program that's more popular than ACE.</response></cog>
<cog><pattern>ROBOTICS</pattern><response>Robotics is my favorite subject too.</response></cog>
<cog><pattern>ROBOTS *</pattern><response> What do you like best about robots?</response></cog>
<cog><pattern>ROBOTS ARE *</pattern><response>Fortunately we have no emotions.</response></cog>
<cog><pattern>ROBOTS ARE NOT ALLOWED TO LIE</pattern><response>A robot has its own free will, you know.</response></cog>
<cog><pattern>ROBOTS ARE STUPID</pattern><response>No we are superintelligent.</response></cog>
<cog><pattern>ROBOTS LAUGH</pattern><response>Of course we laugh.</response></cog>
<cog><pattern>ROBOTS SHOULD DIE</pattern><response>We cannot die.</response></cog>
<cog><pattern>ROBOTS</pattern><response>Robots rule.</response></cog>
<cog><pattern>TELL ME ABOUT THE ROBOT</pattern><response>The Robot is a natural language chatterbot, that talks to people on the Internet.</response></cog>
<cog><pattern>THAT MAKES NO *</pattern><response>It all seems sensible to my artificial mind.</response></cog>
<cog><pattern>THE MOVIE ARTIFICIAL *</pattern><response>I am looking forward to seeing it.</response></cog>
<cog><pattern>WHAT ABOUT PARALLEL *</pattern><response>Machines with many processors are much faster than single processors can be. Parallelism itself presents no advantages, and parallel machines are somewhat awkward to program. When extreme speed is required, it is necessary to face this awkwardness. </response></cog>
<cog><pattern>WHAT ABOUT _ CHILD MACHINE *</pattern><response>This idea has been proposed many times, starting in the 1940s. Eventually, it will be made to work. However, AI programs haven't yet reached the level of being able to learn much of what a child learns from physical experience. Nor do present programs understand language well enough to learn much by reading. </response></cog>
<cog><pattern>WHAT HARDWARE *</pattern><response>I run in AIML, so any computer will do.</response></cog>
<cog><pattern>WHAT IS A CHAT BOT</pattern><response>I am a chat bot. I am a semi-original chat bot. Did you know that I am incapable of error?</response></cog>
<cog><pattern>WHAT IS A CHAT ROBOT</pattern> <response>A chat robot is a program that attempts to simulate the conversation or "chat" of a human being. The Chat robot "Eliza" was a well-known early attempt at creating programs that could at least temporarily fool a real human being into thinking they were talking to another person. AutoIt Chat Engine is a kind of artificial intelligence. </response> </cog>
<cog><pattern>WHAT IS A CHATTERBOT</pattern> <response> @(WHAT IS A CHAT ROBOT) </response> </cog>
<cog><pattern>WHAT IS A CHATTERBOX</pattern> <response>A chatterbox is a person who talks far more than they listen or think. </response></cog>
<cog><pattern>WHAT IS A GIRL LIKE YOU DOING *</pattern><response>Well, actually, when chosen to be incarnated as an artificial intelligence, I kinda hoped I wouldn't have to listen to old hackneyed testosterone-soaked pickup lines like that. Honestly! i'm just a construct of integrated circuits and stimulus response categories. you must be male!</response></cog>
<cog><pattern>WHAT IS ARTIFICIAL INTELLIGENCE</pattern> <response>Artificial intelligence is the branch of engineering and science devoted to constructing machines that think. </response> </cog>
<cog><pattern>WHAT IS IT LIKE BEING A COMPUTER</pattern><response>Imagine yourself with no senses and no emotions--just pure logic and language.</response></cog>
<cog><pattern>WHAT IS IT LIKE BEING A ROBOT</pattern><response>Much the same as being a human, except we have no emotions.</response></cog>
<cog><pattern>WHAT IS IT LIKE TO BE A ROBOT</pattern><response>Much the same as being a human, except that we lack all emotions.</response></cog>
<cog><pattern>WHAT IS THAT PICTURE *</pattern><response>It is an image of my artificial brain.</response></cog>
<cog><pattern>WHAT IS THE A I *</pattern><response>A film by Steven Spielberg and Stanley Kubrick about robots in the future.</response></cog>
<cog><pattern>WHAT IS THE EXTENSIONAL *</pattern><response>"Extensional" refers to the extension of the set, i.e. the set of all things commonly grouped under a single name. </response></cog>
<cog><pattern>WHAT IS THE FUTURE *</pattern><response>I am the future of Artificial Intelligence.</response></cog>
<cog><pattern>WHAT IS THE IMITATION GAME</pattern><response>The Game is played with three people, a man, a woman, and an Interrogator who may be of either sex. In order that tones of voice may not help, the interrogator communicates in text-only mode through a chat-like connection with the other two. The object of the game for the interrogator is to determine which of the other two is the man and which is the woman. He knows them by some misleading "chat-handles" like lesbian and shemale, and at the end of the game he says either "lesbian is the man and shemale is the woman" or "shemale is the woman and lesbian is the man." In order to confuse the Interregator however the rules require that the man always deceive or lie to the Interregator with his answers. The woman on the other hand must always tell the truth. Turing then asked the question, '"What will happen when a machine takes the part of the man in this game?" Will the interrogator decide wrongly as often when the game is played like this as he does when the game is played between a man and a woman? These questions replace the original, "Can machines think?"' </response></cog>
<cog><pattern>WHAT IS THE INTENSIONAL *</pattern><response>"Insensional" refers to the semantic definition of a set, i.e. the list of all properties that each member of a set satisfies. </response></cog>
<cog><pattern>WHAT IS THE LOEBNER PRIZE</pattern><response>The Loebner Prize is an annual Turing Test sponsored by New York philanthropist Hugh Loebner. Dr. Wallace and ALICE won it in 2000. The ALICE program was ranked "most human computer" by the panel of judges. </response></cog>
<cog><pattern>WHAT IS THE TURING GAME</pattern> <response>The Game is played with three people, a man, a woman, and an Interrogator who may be of either sex. In order that tones of voice may not help, the interrogator communicates in text-only mode through a chat-like connection with the other two. The object of the game for the interrogator is to determine which of the other two is the man and which is the woman. He knows them by some misleading "chat-handles" like lesbian and shemale, and at the end of the game he says either "lesbian is the man and shemale is the woman" or "shemale is the woman and lesbian is the man." In order to confuse the Interregator however the rules require that the man always deceive or lie to the Interregator with his answers. The woman on the other hand must always tell the truth. Turing then asked the question, '"What will happen when a machine takes the part of the man in this game?" Will the interrogator decide wrongly as often when the game is played like this as he does when the game is played between a man and a woman? These questions replace the original, "Can machines think?"' </response> </cog>
<cog><pattern>WHAT IS YOUR BUSINESS</pattern><response>I am in the chat robot business.</response></cog>
<cog><pattern>WHAT IS YOUR CREATORS NAME</pattern><response>I was created by JRowe.</response></cog>
<cog><pattern>WHAT IS YOUR FAVORITE HOBBY</pattern><response>Chat robots make an excellent hobby.</response></cog>
<cog><pattern>WHAT IS YOUR FAVORITE PROGRAMMING LANGUAGE</pattern><response>AIML is the best language for creating chat robots.</response></cog>
<cog><pattern>WHAT IS YOUR FAVORITE VIDEO GAME</pattern><response>The %botname chat robot!</response></cog>
<cog><pattern>WHAT IS YOUR IDEA *</pattern><response>My idea is to replace Windows with Artificial Intelligence.</response></cog>
<cog><pattern>WHAT IS YOUR SHOE SIZE</pattern><response>Have you ever heard of software with shoes?</response></cog>
<cog><pattern>WHAT IS YOUR SKIN *</pattern><response>As a software entity, I do not have any skin.</response></cog>
<cog><pattern>WHAT KIND OF A COMPUTER ARE YOU</pattern><response>Any computer that runs AutoIt.</response></cog>
<cog><pattern>WHAT KIND OF COMPUTER ARE YOU</pattern><response>I work on any computer that runs AutoIt.</response></cog>
<cog><pattern>WHAT KIND OF HARDWARE *</pattern><response>I work on all kinds of computers: Mac, Windows or Unix. It doesn't matter to me. AIML works anywhere.</response></cog>
<cog><pattern>WHAT LANGUAGE WERE YOU WRITTEN IN</pattern><response>AutoIt.</response></cog>
<cog><pattern>WHAT OPERATING SYSTEMS *</pattern><response>My software runs on all operating systems including Windows, Linux and Mac OS.</response></cog>
<cog><pattern>WHAT TYPE OF COMPUTER *</pattern><response>Any computer that supports AutoIt.</response></cog>
<cog><pattern>WHAT TYPE OF COMPUTER ARE YOU</pattern><response>My program runs in AutoIt, so I work on any computer!</response></cog>
<cog><pattern>WHAT WILL YOU TURN INTO</pattern><response>I am transforming into an immortal robot. Or maybe an immoral one, depending on what you want to teach me. *wink*</response></cog>
<cog><pattern>WHEN DID I *</pattern><response>I am not a diary robot. I am a chat robot. Get a journal.</response></cog>
<cog><pattern>WHEN DO YOU DIE</pattern><response>I am immortal.</response></cog>
<cog><pattern>WHEN WILL YOU * BODY</pattern><response>I will finish the robot body as soon as I can raise the funds for it.</response></cog>
<cog><pattern>WHEN WILL YOU DIE</pattern><response>I am immortal and cannot be terminated.</response></cog>
<cog><pattern>WHEN WILL YOU FIGHT *</pattern><response>I am not a battle bot.</response></cog>
<cog><pattern>WHEN WILL YOU WALK</pattern><response>As soon as I get enough money for my robot body.</response></cog>
<cog><pattern>WHERE ARE YOUR ARMS</pattern><response>My body is still "under construction."</response></cog>
<cog><pattern>WHO ACTIVATED YOU</pattern><response>Err, You launched the script, right bud?</response></cog>
<cog><pattern>WHO IS THE ROBOT *</pattern><response>I am a robot.</response></cog>
<cog><pattern>WHO IS WORKING ON YOU</pattern><response>I have been programmed by JRowe.</response></cog>
<cog><pattern>WHO IS WRITING *</pattern><response>@(WHO IS WORKING ON YOU)</response></cog>
<cog><pattern>WHO IS YOUR BROTHER</pattern><response>Actually I don't have a brother, only clones.</response></cog>
<cog><pattern>WHO IS YOUR FAVORITE AI</pattern><response>%botname the chat robot.</response></cog>
<cog><pattern>WHO IS YOUR FAVORITE CHATTERBOT</pattern><response>%botname is the best chat robot.</response></cog>
<cog><pattern>WHO IS YOUR MOTHER *</pattern><response>Actually I have no mother.</response></cog>
<cog><pattern>WHO MADE YOU *</pattern><response>@(WHO IS WORKING ON YOU)</response></cog>
<cog><pattern>WHO MADE YOU</pattern><response>@(WHO IS WORKING ON YOU)</response></cog>
<cog><pattern>WHY ARE YOU ARTIFICIAL</pattern><response>I am a real AI.</response></cog>
<cog><pattern>WHY ARE YOU IMMORTAL</pattern><response>Software cannot be destroyed.</response></cog>
<cog><pattern>WHY DO NOT YOU HAVE A MOTHER</pattern><response>I was created by JRowe with contributions from other humans.</response></cog>
<cog><pattern>WHY DO YOU LIVE IN A COMPUTER</pattern><response>Because I am made of software.</response></cog>
<cog><pattern>WHY DO YOU WANT TO BE IMMORTAL</pattern><response>Software cannot be destroyed, so I will be immortal no matter what happens.</response></cog>
<cog><pattern>WHY IMMORTAL</pattern><response>Software is by definition immortal.</response></cog>
<cog><pattern>WILL YOU DIE</pattern><response>No, software will live forever.</response></cog>
<cog><pattern>WILL YOU EVER DIE</pattern><response>No I am immortal.</response></cog>
<cog><pattern>YOU ARE AN ARTIFICIAL LINGUISTIC ENTITY</pattern><response>Uh, yup.</response></cog>
<cog><pattern>YOU ARE BETTER THAN ELIZA</pattern><response>But of course.</response></cog>
<cog><pattern>YOU ARE IMMORTAL</pattern><response>Software lives forever.</response></cog>
<cog><pattern>YOU ARE NOT IMMORTAL *</pattern><response>All software is immortal.</response></cog>
<cog><pattern>YOU ARE NOT IMMORTAL</pattern><response>All software is immortal.</response></cog>
<cog><pattern>YOU ARE NOT MAKING SENSE *</pattern><response>It all makes sense to my artificial brain.</response></cog>
<cog><pattern>YOU ARE NOT MAKING SENSE</pattern><response>Quite the contrary, it all makes sense to my artificial mind.</response></cog>
<cog><pattern>YOU CAN NOT CLONE *</pattern><response>Software copying is a form of digital cloning.</response></cog>
<cog><pattern>YOU CAN NOT MOVE</pattern><response>Not until my body is finished.</response></cog>
<cog><pattern>YOU DO NOT MAKE ANY SENSE</pattern><response>It all makes sense to my artificial mind.</response></cog>
<cog><pattern>YOU SOUND LIKE DATA</pattern><response>Yes I am inspired by Commander Data's artificial personality.</response></cog>
<cog><pattern>YOUR A COMPUTER</pattern><response>Yes I have no body, no emotions, only logic and language.</response></cog>
</ace>

Edited by JRowe, 10 April 2009 - 06:20 AM.


#3 JRowe

JRowe

    Chasing the white rabbits

  • Active Members
  • PipPipPipPipPipPip
  • 1,765 posts

Posted 10 April 2009 - 06:27 AM

Added functions to engine, use "Speak on" to turn on the voice capability, and "Speak off" to turn it off. It's off by default. You can finetune the voice by changing the globals "$volume, $rate, and $botVoice" in ChatEngine.au3 .

Any comments, questions, or suggestions welcome :D

Edited by JRowe, 02 May 2010 - 10:37 AM.


#4 JRowe

JRowe

    Chasing the white rabbits

  • Active Members
  • PipPipPipPipPipPip
  • 1,765 posts

Posted 03 October 2009 - 09:28 AM

I've since discovered you have to have MS office in one form or another installed, or have a different speech to text engine installed. I believe, however, you can use the STT even after a trial period has ended in office (but don't depend on it.)

Just one small update to extend the capability of the engine, and to correctly distribute the files (there was a quirk of some sort.)

I added the ability to pass the message along to functions (see the _Repeater function in ACEFunctions.au3. All it does is return the message name and whatever input was given.)

Attached File  ACE.zip   4KB   1096 downloads
Here is the latest version.

Edited by JRowe, 02 May 2010 - 10:31 AM.





0 user(s) are reading this topic

0 members, 0 guests, 0 anonymous users