If you are detecting an emotion in your app the easiest way to notify the bot of the emotion is to send a message to the bot and have a response for this.
i.e.
emotion: happy

Sorry, but I do found an emotion detection API already and now for testing. What I am looking for was that whenever the user utters a happy or sad conversation, the avatar will detect the tone he is using like happy or sad without displaying the percentage just the voice

How to embed a 3rd party Tone API to my app? 

This is not a line of code, but a involved development project.
We can develop this for you through our development services, contact [email protected]

I do have through text, but what I am trying to do is through speech/tone. Is there a line of code to do this? 

 

Thanks

There are 2 ways to detect emotion, either from the user's speech/tone or from the text of the user's input (only based on the words, not tone).

For speech, Bot Libre Analytics support creating your own audio classification deep learning network.

 

Will it be possible for the avatar to detect the emotion of the user when asking a question like for example if he is happy or sad based on the voice input by the user. Because I am doing an application that can detect human emotion.

 

Thank you in advance

The avatars speech and talking animation play simultaneously.

If you are seeing an issue, what web browser and OS are you using?

The microsoft speech does look pretty good. I think that will probably do for this project. 

Looking at the demos, it seems like the speech and videos play sequentially rather than simultaneously. Is that a problem or something that can be gotten around somehow?

thanks

Bot Libre supports several speech providers including:

• Bot Libre (Mary TTS)
• HTML 5 (Google speech in Chrome, Apple is Safari, etc.)
• ResponsiveVoice

I'm working on using bot libre for a chatbot. But the voices are all very mechanical. Amazon polly has some much more natural sounding voices. Is there a way I can link that as the voice engine instead?

thanks

Randy

You would need to use our web API to connect a bot to your server.

See,

Hi all,

I have a little server openfire for friends and family. I would like to connect a bot to my openfire server is it possible? And how to do that ?

Other idea, our chat client are pidgin, spark or gajim. An adress like "[email protected]" to add to the list of connected to operate as a service and discussion is it possible ?

We would like the bot give some informations style Weather, rss news, etc... And may be coffee :) 

ok is there any way to upload a script direct to the bots workspace?

Cliff

 

This web API changes the precedence of a script (move up/down), it does not upload a new script.

It takes a <script-source> parameter, which should have the bot's id (instance), and the scripts id (id) set,

<script-source application="..." user="..." token="..." instance="1234" id="4567"/>

In Self the learn() function takes a response category object that has a pattern and template.

For example: learn( { pattern : "hello", template : "How are you today?" } ); or, var response = new Object();
response.pattern = "hi";
response.template = "bye";
learn( response );

the web api endpoints section suggest that there is a script upload facility ie  /rest/api/up-bot-script

but what parameters does it take, is it post or get?

 

in self what is the syntax for the "learn" operator please? 

You can access any global object using #<var-name>.

For example,

#self.name = "Jim";

how do I access the self object in a self script?

If you have a sample conversation that consistently reproduces the issue please email [email protected]

She used to utter what the user must utter. What I did was to repeat the chat again and again

There were times that it didn't work. My worry was that when I present this to my adviser and panelist for approval. What i did was to enter corrections whenever I encounter this issue

I tested your bot and it seemed ok.
Does the issue still occur?

As I trained my bot using my Android phone, I noticed that the responses did not match with my chat logs. She always says my default response. But in context there is a response. When I repeat the entire process of training the bot, it works but sometimes did not. There is no topic nor required clicked on the chat logs. What is the problem here?
Thanks in advance

I want to add my IBM bluemix to my next bot how do I do this

j'adore être super

You can integrate a third party system using a Self script and the system's web API.

Here is an example script for IBM Watson,

Hi,

I am spending some time exploring Botlibre and I want to use it as a dialogue management system in our application.

We would be using a third party library for Natural Language understanding which will helps us in intent classification and entity extraction.

We want to use the extracted intend to tell Botlibre what should be the response based on intend and what are the entities participating in this intends.

From your bot's Training & Chat Logs page you can enter questions and responses. The question is indexed and use by Bot Libre's NLP to match similar user questions to the response.

For an intent, or for having many question refer to the same response you can use intent labels. Just label the primary question/response and use the label for other question that you want to use the same response.

Thanks for the reply.

I went through the process of NLP in Botlibre but still not able to understand two things

1. How is intend classification done in Botlibre NLP

2. How is entitiy extraction done in Botlibre NLP.

When you correct a bot, it will then use your correction the next time you ask the same question, or a similar question.

Using correction is a very easy way to train a bot, but not the best way. It is best to training your bot from its Training & Chat Logs page in its Admin Console.

Hi,

I just created a bot that provides information on motivation speakers,videos and categories.

It was a bot with no knowledge. As I started interacting with bot I corrected its response. I wan to understand whether Botlibre bots 

1. converstational (they can remember the context during a conversation)

2. possess NLU so that it can respond as a human does.

You can email [email protected]

Thank you very much for your help.Can I get your contact information?

The conversation id in TextEntry is the #gid of the conversation object. (global unique id)

conversation.get(#gid)

thank you, I want to know the relationship between this ID and the conversationId in TextEntry.

In a Self script the conversation is available in the "conversation" variable.

To access the conversation object's id you can use,

How to get the conversation id in the script

thank you

Thank you very much for your answer.

But my leader said that this is not very good, so we intend to take other plans.

You can set the topic for a response in a Response List file, or in AIML, and import it into your bot.
Just set the topic for each response in the topic.

Thank you for replying to me.

sorry, My English is poor.

“multi-session”：

In the same topic, multiple questions, multiple answers. But must be within the same topic.

 

The open source version I use is not an enterprise version.

Not sure what you mean by "multi-session" training?

The best way to train your bot is using a "response list" file, or the bot's Training & Chat Logs page,

How to conduct multi-session training？

One question and one answer has been completed.
How to train multiple questions and answers similar to a topic from source？

What do you mean by "writing first"?

A bot has a "greeting" if set the bot will start the conversation with the greeting. If you delete its greeting, then it wait wait for the user to ask a question.

Hello! I want to ask a question - How do I prevent a bot from writing first?

Thank!

Is it possible to create more functionality with our bots using javascript? I'd like to be able to make my bots do things like open web pages and initiate timers in between sequenced responses

We release the "Swingdroid" project into open source today.
Swingdroid lets you port a Java Android app to Windows/Mac desktop as a Java swing application.

The test GUI has a menu item to load a file.

You can also write a Java class to load a script into the bot.