I want Pepper robot to understand any human input in the chat.
I know that the correct QiChat syntax is '*' and it requires Internet access. (Robot is connected via Wi-fi)
This is my topic file, where I tell the robot my name, he tells it and assigns qiChat variable to my name.
u:(My name {is} _*)
Nice to see you, $1 $name=$1
This is how I define the chat.
conversationalContents = Arrays.asList(
new NavigationControlConversationalContent(), new GestureControlConversationalContent(), new VolumeControlConversationalContent(),
new DateTimeConversationalContent(), new GreetingsConversationalContent(), new FarewellConversationalContent(),
new RepeatConversationalContent()
);
topic = TopicBuilder.with(qiContext).withResource(R.raw.talks).build(); // build topic
chatbot = QiChatbotBuilder.with(qiContext).withTopic(topic).build(); // build chatbot
chat = ConversationalContentChatBuilder.with(qiContext).withChatbot(chatbot).withConversationalContents(conversationalContents).build(); // build chat
chat.async().run();
And I do have this in the manifest
<uses-permission android:name="android.permission.INTERNET" />
When I tell the robot my name, on the action bar (where robot writes what it understands -> it shows "My name <...>") So it doesn't understand and thus won't answer nor assign $name variable, which it should.
You'll probably want to contact Softbank Customer care and give them your robot serial number, because this feature requires a special licence that they need to activate (if your contract allows that of course!).
Jonas
Related
Our organization wants to develop a "LOST & FOUND System Application" using chatbot integrated in a website.
Whenever the user starts the conversation with the chatbot, the chatbot should ask the details of lost item or item found and it should store the details in database.
How can we do it ?
And can we use our own web-service because organization doesn't want to keep the database in Amazon's Server.
As someone who just implemented this very same situation (with a lot of help from #Sid8491), I can give some insight on how I managed it.
Note, I'm using C# because that's what the company I work for uses.
First, the bot requires input from the user to decide what intent is being called. For this, I implemented a PostText call to the Lex API.
PostTextRequest lexTextRequest = new PostTextRequest()
{
BotName = botName,
BotAlias = botAlias,
UserId = sessionId,
InputText = messageToSend
};
try
{
lexTextResponse = await awsLexClient.PostTextAsync(lexTextRequest);
}
catch (Exception ex)
{
throw new BadRequestException(ex);
}
Please note that this requires you to have created a Cognito Object to authenticate your AmazonLexClient (as shown below):
protected void InitLexService()
{
//Grab region for Lex Bot services
Amazon.RegionEndpoint svcRegionEndpoint = Amazon.RegionEndpoint.USEast1;
//Get credentials from Cognito
awsCredentials = new CognitoAWSCredentials(
poolId, // Identity pool ID
svcRegionEndpoint); // Region
//Instantiate Lex Client with Region
awsLexClient = new AmazonLexClient(awsCredentials, svcRegionEndpoint);
}
After we get the response from the bot, we use a simple switch case to correctly identify the method we need to call for our web application to run. The entire process is handled by our web application, and we use Lex only to identify the user's request and slot values.
//Call Amazon Lex with Text, capture response
var lexResponse = await awsLexSvc.SendTextMsgToLex(userMessage, sessionID);
//Extract intent and slot values from LexResponse
string intent = lexResponse.IntentName;
var slots = lexResponse.Slots;
//Use LexResponse's Intent to call the appropriate method
switch (intent)
{
case: /*Your intent name*/:
/*Call appropriate method*/;
break;
}
After that, it is just a matter of displaying the result to the user. Do let me know if you need more clarification!
UPDATE:
An example implementation of the slots data to write to SQL (again in C#) would look like this:
case "LostItem":
message = "Please fill the following form with the details of the item you lost.";
LostItem();
break;
This would then take you to the LostItem() method which you can use to fill up a form.
public void LostItem()
{
string itemName = string.Empty;
itemName = //Get from user
//repeat with whatever else you need for a complete item object
//Implement a SQL call to a stored procedure that inserts the object into your database.
//You can do a similar call to the database to retrieve an object as well
}
That should point you in the right direction hopefully. Google is your best friend if you need help with SQL stored procedures. Hopefully this helped!
Yes its possible.
You can send the requests to Lex from your website which will extract Intents and Entities.
Once you get these, you can write backend code in any language of your choice and use any DB you want.
In your use case, you might just want to use Lex. PostText will be main function you will be calling.
You will need to create an intent in Lex which will have multiple slots LosingDate, LosingPlace or whatever you want, then it will be able to get all these information from the user and pass it to your web application.
Short summary of what I tried to do and what it's actually doing.
In my project I have two simple nodes: one for listening and publishing, and another for speaking and subscribing. I named them listeningNode and speakingNode, respectively.
The task I wanted to achieve was pretty simple, I would have the user say "remember me" which would be recognized as a keyword and be published to voiceCommandCallback method in the speaking node so my robot could say "Okay, please say your name". Then, back at the listening node, on top of publishing that keyphrase it will also call the method recognize_from_mic_with_dict() which as you can guess will run using a dictionary of names.
This recognize_from_mic_with_dict() method will be listening for a name and will attempt to publish that name to namesCallback() in the listening node and this is where I check if what got published was an actual name or if it was just gibberish, in which case I would kindly ask the user to repeat his/her name and subscribe once again to recognize_from_mic_with_dict() so it could listen once more.
This sounds more complicated that it probably has to be but it's the only way I could think of achieving this "mode switching". The problem is that if it hears gibberish it will say "I'm sorry, I did not quite hear that. Please repeat that!" and I would like to know if there is a way to make the listening node ignore anything that the robot says because it's attempting to recognize names from its own sentence.
you can cast it as a feedback control problem.
given that :
u is the user speech signal
r is the output signal of the robot speaker,
h the feedback path function,
s=h*r the feedback signal; * refers to convolution
y = s + u = h*r + u the input signal of the microphone
the problem is to estimate ĥ and therefore ŝ (r is already known),
so an estimation of the user speech signal is given by û = y - ŝ = y - ĥ * r
I'm new to OTRS (3.2) and also new to PERL but I have been given the task of setting up OTRS so that it will make a call to our remote webservice so a record can be created on our end when a ticket is set as "Closed".
I set up various dynamic fields so the customer service rep can fill in additional data that will be passed into the webservice call along with ticket details.
I couldn't get the webservice call to trigger when the ticket was "Closed" but I did get it to trigger when the "priority" was changed so I'm just using that now to test the webservice.
I'm just using the Test.pm and TestSimple.pm files that were included with OTRS.
When I look at the Debugger for the Webserice, I can see that the calls were being made:
$VAR1 = {
'TicketID' => '6'
};
My webservice currently just has one method "create" which just returns true for testing.
however I get the following from the Test.pm
"Got no TicketNumber (2014-09-02 09:20:42, error)"
and the following from the TestSimple.pm
"Error in SOAP call: 404 Not Found at /TARGET/SHARE/var/otrs/Kernel/GenericInterface/Transport/HTTP/SOAP.pm line 578 (2014-09-02 09:20:43, error)
I've spent countless hours on Google but couldn't find anything on this. All I could find is code for the Test.pm and TestSimple.pm but nothing really helpful to help me create a custom invoker for my needs and configure the webservice in OTRS to get it to work.
Does anyone have any sample invokers that I can look at to see how to set it up?
Basically I need to pass the ticket information along with my custom dynamic fields to my webservice. From there I can create the record on my end and do whatever processing.
I'm not sure how to setup the Invoker to pass the necessary ticket fields and dynamic fields and how to make it call a specific method in my remote webservice.
I guess getting the Test.pm and TestSimple.pm to work is the first step then I can modify those for my needs. I have not used PERL at all so any help is greatly appreciated.
I'm also struggling with similar set of requirements too. I've also never programmed in PERL, but I can tell you at least that the "Got no TicketNumber" in the Test.pm is right from the PrepareRequest method, there you can see this block of code:
# we need a TicketNumber
if ( !IsStringWithData( $Param{Data}->{TicketNumber} ) ) {
return $Self->{DebuggerObject}->Error( Summary => 'Got no TicketNumber' );
}
You should change all references to TicketNumber to TicketID, or remove the validation whatsoever (also there is mapping to ReturnedData variable).
Invoking specific methods on your WS interface is quite simple (but poorly documented). The Invoker name that you specify in the "OTRS as requester" section of web service configuration corresponds to the WS method that will be called. So if you have WS interface with a method called "create" just name the Invoker "create" too.
As far as the gathering of dynamic field goes, can't help you on that one yet, sorry.
Cheers
I'm trying to understand if it's possible to create a web service that can send and answer to WhatsApp messages. I searched on the web and I found the WhatsAPI,
I guess this solution work fine, but with the actual version of WhatsApp it's not possible to get the nickname, the sender, the imei and the password.
To get them I set up a Linux PC in which I installed mitmproxy to sniff the web traffic of a Samsung Galaxy S4. By using mitmproxy I can see the web traffic generated by the phone, so I tried to register to WhatsApp (with an another SIM), but in mitmproxy I can't see the data I need for WhatsAPI.
Does anyone knows if it's possible to get the password by using another way?
If it exist can you suggest me a way? Do you think it's possible to do that or it's better to use Telegram or Wechat (they have public API)?
For Java, you can try WhatsUp
For Python, see YowsUp.
Beware that WhatsApp threatens legal action against many of these library developers and does not officially support using the service this way.
I have also spoken directly with WhatsApp representatives who have said no commercial API use of WhatsApp is acceptable.
Also note that bulk messaging is against the WhatsApp terms of service.
There used to be a PHP implementation at WhatsAPI, and another Java implementation, WhatsApi4J. Both are no longer available due to legal threats.
For .NET you use https://github.com/mgp25/Chat-API-NET
download installer for generate password https://github.com/mgp25/WART from this link
string nickname = "Nickname";
/* Your number in the format CCAANNNNNNNNN
* C - Country Code
* A - Area Code
* N - Phone number */
string sender = "***************"; //phone number
string password = "*****************"; // Obtain it with WART or Yowsup
WhatsApp wa = new WhatsApp(sender, password, nickname, true);
wa.OnConnectSuccess += () =>
{
Console.WriteLine("Connected");
wa.OnLoginSuccess += (phoneNumber, data) =>
{
Console.WriteLine("Connection success!");
wa.SendMessage("**************"/* Number */, "Hello World!");
Console.WriteLine("Message sent!");
};
wa.OnLoginFailed += (data) => {
Console.WriteLine("Login failed: {0}", data);
};
wa.Login();
};
wa.OnConnectFailed += (ex) =>
{
Console.WriteLine("Connect failed: {0}", ex.StackTrace);
};
wa.Connect();
Console.WriteLine("END");
Console.ReadLine();
wart app maybe works good for you.
WART
WhatsApp Registration Tool
Uses token generator created by Jake
Uses WhatsApiNet fork by me
Requires .NET Framework 4 or Mono Framework (mono-complete on Linux)
This tool is used to register new phonenumbers and can also be used to retrieve a new password for already registered numbers.
The registration identity is auto-generated by the program based on the phone number.
The optional (and highly recommended) password field is used as salt when generating the identity. This will generate a unique identity hash which cannot be replicated unless you know the password.
Leaving the password field blank will generate an identity hash of just the phone number, which can be easily replicated and is highly insecure.
If these answers were helpful to you, please consider saying thank you in a more constructive way
I'm writing an application that needs to access to Outlook address book, however, every time I launch it a warning message is shown saying that an application is trying to access to your adress book. I've noticed this behaviour only with the machines where no antivirus is installed. How to get rid of this message?
Here is a part of the code I use to retreive some emails related informations
CApplication l_application;
l_application.CreateDispatch("Outlook.Application");
CNameSpace l_namespace = l_application.GetNamespace(_T("MAPI"));
CMAPIFolder l_mapiFolder = l_namespace.GetDefaultFolder(olFolderInbox);
CItems l_items = l_mapiFolder.GetItems();
m_mailItem = l_items.GetLast();
m_mailItem.Save();
//Get infos (mail's size, from, to, conversation topic...)
CApplication, CNameSpace, CItems are generated automatically, and m_mailItem is a CMailItem object.
See http://www.outlookcode.com/article.aspx?id=52 for a list of your options. Essentially you can either make sure an up-to-date antivirus app is installed or use Redemption (I am its author).