I am trying to create a demo call centre using AWS connect.
Part of my contact flow makes use of the "Get Customer Input", as I want to use an Amazon lex bot. I have created to divert to a specific working queue. For example, if the user says "sales" they should be directed to the sales queue.
I have tested the Lex bot within the Lex console and it works as intended.
However when testing the Lex integration within AWS connect it will always follow the "error" path on the block after a user says something on the phone.
Here is the CloudWatch log showing the Error result of the module.
{
"Results": "Error",
"ContactFlowName": "Inbound Flow",
"ContactFlowModuleType": "GetUserInput",
"Timestamp": "2022-02-12T18:06:10.940Z"
}
Here is the contact flow:
Here is the settings for the "Get Customer Input Block":
Here is a test of the Lex bot in the Lex dashboard:
Any help would be greatly appreciated.
Turns out the solution was if you're using LexV2 make sure you set the proper Language Attribute as well. Easiest way is using the set Voice block in your Contact Flow, on the very bottom of the block you can enable "set language attribute".
Related
I am just new to Amazon Connect and Lex and have just starting creating simple projects. I already have created an entire contact flow which uses Lex and Lambda for routing. Problem is in the "Get Customer Input" stage, it seems to always go to the error output and I could not figure out why. I tried to check if there's any way I can find logs for each stages in the contact flow but could not find any.
Can anyone help me solve this issue? I need to see logs to find out the cause of the error.
EDIT: I got the contact flow logs from cloudwatch. See below. I can't find any significant error from it.
{
"Results": "Error",
"ContactId": "<contact-id>",
"ContactFlowId": "<the contact flow id>",
"ContactFlowModuleType": "GetUserInput",
"Timestamp": "2019-07-08T08:27:01.185Z"
}
You might be getting error because you are getting error from your Lex and that is why the flow is going in error.
You can check the logs for connect and Lex in Amazon service - Amazon CloudWatch.
You can also provide details from logs/screenshot what exactly error you are getting, so that I can help.
This might be due to language settings mismatch.
If you're using LexV2 make sure you set the proper Language Attribute as well. Easiest way is using the set Voice block in your Contact Flow, on the very bottom of the block you can enable "set language attribute".
Original answer: https://repost.aws/questions/QUn9bLLnclQxmD_DMBgfB9_Q/amazon-connect-error-using-lex-as-customer-input
I was wondering if anybody has ever experimented with this issue I'm having and could give me any input on the subject.
As it stands right now I'm trying to see if there is a way to grab a users input through the AWS Connect. I understand that there is already a "Get User Input" block in the GUI that is available for me to use, unfortunately it does not offer the fine grain control I am looking for with requests and responses from Lex.
Right now I am able to Post Content to Lex and get responses just fine, as well as output speech using Amazon Polly via my Lambda. This works great for things that do not require a user to have to give feedback for a question.
For example if a client asks
"What time is my appointment?"
and we give back
"Your appointment is for X at X time, would you like an email with
this confirmation?"
I want to be able to capture what the user says back within that same lambda.
So the interaction would go like so:
User asks a question.
Lambda POST's it to Lex and gets a response
Amazon Polly says the response - i.e: 'Would you like an email to confirm?'
Lambda then picks up if the user says yes or no - POST's info to Lex
Gets response and outputs voice through Polly.
If anybody has any information on this please let me know, thank you!
Why do you make so much complications to implement IVR system using Amazon Connect. I have done the complete IVR automated system to one of my biggest US banking client. Use the below procedure to achieve what you desire.
Build a complete interactive lex bot(So that you can avoid amazon poly & using lex post content api). It is advised to build each bot has only one intent in it.
In connect using "Get User Input" node map the lex bot which you have created earlier with the question to be asked "What time is my appointment?". Once this question has been played the complete control goes to lex and then you fulfilled your intent from lex side, you can come back to connect as like that.
Refer AWS contact center for the clear idea.
I'm using the Amazon Lex service. My input is always a text message, but sometimes I'd like a spoken response in addition to the text. I configured an output voice in the Lex settings.
I've tried adding a header amz-lex:accept-content-types=SSML to the request, but it returns with Invalid Bot Configuration: No usable messages given the current slot and sessionAttribute set. (Service: AmazonLexRuntime; Status Code: 400; Error Code: BadRequestException;. The same request works just fine when I ask for PlainText. And even if I ask for SSML,PlainText it'll respond with plain text only.
Do I need to configure something else inside Lex to allow it to do voice responses?
Lex cannot actually output voice by itself.
Lex will always output a JSON response and that response needs to be processed by the channel the user is accessing Lex with. So that channel is what outputs either text or voice based on how it processes the response message delivered from Lex.
Amazon Lex can handle speech-to-text.
Amazon Polly can do the reverse: text-to-speech.
If you go to the above Lex page, they have a few examples of using Lex for conversation logic and then Polly for text-to-speech and outputting voice to the user.
You can utilize SSML(Speech Synthesis Markup Language) for this, even to test voice in Lex Test Bot Console, using message content-type.
Using SSML tags, you can customize and control aspects of speech, such as pronunciation, volume, and speech rate.
SSML comes with a variety of directives with which you can customize pronunciation and create based on your requirement . Eg - say-as directive
`"message": {
"contentType": "SSML",
"content": "<speak> Hi " + data["User ID"].split('.')[0]+", Your Reference Number <say-as interpret-as="characters">" + "ABC"+event.currentIntent.slots.RefNo+ "</say-as> is ," + data["Status"] +"</speak>"
}`
Introduced in 2018 - https://aws.amazon.com/about-aws/whats-new/2018/02/announcing-responses-capability-in-amazon-lex-and-ssml-support-in-text-response/
As part of some testing that I was doing, I replied STOP to an SMS message that was sent via Amazon's Pinpoint service. I received the acknowledgement that I had been removed from further notifications.
I want to opt back in to receiving those messages, but I can't figure out how to do that. I looked at the Pinpoint documentation and I did not see a way to do it. I looked in the Amazon Pinpoint Console and I did not see a way to remove a number from the blacklist. I have tried the standard terms that other SMS providers use such as UNSTOP, UNBLOCK, and START, but none of those work either. Does anyone have any suggestions. I do not want to contact Amazon support about this unless I have to.
As described here: https://docs.aws.amazon.com/cli/latest/reference/sns/opt-in-phone-number.html
aws sns opt-in-phone-number --phone-number ###-###-####
You can also use AWS Console -> Amazon SNS -> Mobile -> Text Messaging(SMS) section to see a list of opt-out phone numbers that was done through Pinpoint and choose to opt-in these numbers...
AWS Pinpoint has not come up with the APIs to check if the number is opted out or not. You can use the AWS SNS APIs for checking this as well for marking a mobile number as active again.
I've been trying to figure this out as well and I think I have a solution from a set of documentation I found about setting up Pinpoint. Below is python pseudocode; from my understanding we just have to update the "OptOut" status for the endpoint (i.e. the phone number that originally opted out).
# Python pseudo code with comments
import boto 3
import datetime
pinpoint = boto3.Session(**login_kwargs).client("pinpoint")
opt_in_response = pinpoint.update_endpoint(
ApplicationId="<App ID from your project>",
EndpointId="<Endpoint you are updating>", # Same as your phone number?
EndpointRequest={
"Address": "<Phone you are updating>",
"ChannelType": 'SMS',
"OptOut": "NONE", # Change from "ALL" (which is opt-out) to "NONE", opt-in
"EffectiveDate": datetime.datetime.utcnow().isoformat(),
"Attributes": {
"OptInTimestamp": [datetime.datetime.utcnow().isoformat()]
}
}
)
I attempted to follow this documentation https://docs.aws.amazon.com/pinpoint/latest/developerguide/pinpoint-dg.pdf (the relevant stuff starts on page 92), which happens to not be in Python.
I wasn't successful but I'm pretty sure this is how you should be able to opt back in (if anyone who knows node.js can verify this solution that'd be awesome).
I have been doing a bit of experimentation with Amazon Lex but I can't get voice to work in the console at all.
I'm using the Flower bot demo with the associated Python Lambda function connected and working with text on Chrome browser running on a Mac (10.13.1).
I am able to log any text entered into the test bot on the console from the Lambda function along with the rest of the event.
By going to the monitoring tab of the bot in the console I can see utterances from previous days (seems to be a one day delay on utterances appearing wether missed or detected, no idea why…).
I made a bunch of attempts to use voice yesterday that appear in the utterance table as a single blank entry with a count of 13 now that it is the next day. I'm not sure if this means that audio isn't getting to Lex or if Lex can't understand me.
I'm a native English speaker with a generic American accent (very few people can identify where I'm from more specifically than the U.S.) and Siri has no trouble understanding me.
My suspicion is that something is either blocking or garbling the audio before it gets to Lex but I don't know how to find what Lex is hearing to check that.
Are there troubleshooting tools I haven't found yet? Is there a way to get a live feed of what is being fed to a bot under test? (All I see for the test bot is the inspect response section, nothing for inspecting the request.)
Regarding the one day delay in appearance of utterances, according to AWS documentation:
Utterance statistics are generated once a day, generally in the
evening. You can see the utterance that was not recognized, how many
times it was heard, and the last date and time that the utterance was
heard. It can take up to 24 hours for missed utterances to appear in
the console.
In addition to #sid8491's answer, you can get the message that Lex parsed from your speech in the response it returns. This is in the field data.inputTranscript when using the Node SDK.
CoffeeScript example:
AWS = require 'aws-sdk'
lexruntime = new AWS.LexRuntime
accessKeyId: awsLexAccessKey
secretAccessKey: awsLexSecretAccessKey
region: awsLexRegion
endpoint: "https://runtime.lex.us-east-1.amazonaws.com"
params =
botAlias: awsLexAlias
botName: awsLexBot
contentType: 'audio/x-l16; sample-rate=16000; channels=1'
inputStream: speechData
accept: 'audio/mpeg'
lexruntime.postContent params, (err, data) ->
if err?
log.error err
else
log.debug "Lex heard: #{data.inputTranscript}"
Go to Monitoring tab of your Bot in Amazon Lex console, click "Utterances", there you can find a list of "Missed" and "Detected" utterance. From the missed utterances table, you can add them to any intent.