The rise of synthetic intelligence (AI) has created alternatives to enhance the client expertise within the contact middle house. Machine studying (ML) applied sciences regularly enhance and energy the contact middle buyer expertise by offering options for capabilities like self-service bots, reside name analytics, and post-call analytics. Self-service bots built-in together with your name middle will help you obtain decreased wait occasions, clever routing, decreased time to decision by way of self-service capabilities or knowledge assortment, and improved web promoter scores (NPS). Some examples embody a buyer calling to examine on the standing of an order and receiving an replace from a bot, or a buyer needing to submit a renewal for a license and the chatbot accumulating the required data, which it arms over to an agent for processing.
With Amazon Lex bots, you should utilize conversational AI capabilities to allow these capabilities inside your name middle. Amazon Lex makes use of automated speech recognition (ASR) and pure language understanding (NLU) to know the client’s wants and help them on their journey.
Genesys Cloud (an omni-channel orchestration and buyer relationship platform) offers a contact middle platform in a public cloud mannequin that allows fast and easy integration of AWS Contact Middle Intelligence (AWS CCI) to remodel the trendy contact middle from a value middle right into a revenue middle. As a part of AWS CCI, Genesys Cloud integrates with Amazon Lex, which allows self-service, clever routing, and knowledge assortment capabilities.
When exploring AWS CCI capabilities with Amazon Lex and Genesys Cloud, you might be not sure of the place to start out in your bot design journey. To help those that could also be beginning with a clean canvas, Amazon Lex offers the Amazon Lex automated chatbot designer. The automated chatbot designer makes use of ML to supply an preliminary bot design that you may then refine and launch conversational experiences sooner primarily based in your present name transcripts. With the automated chatbot designer, Amazon Lex clients and companions have a simple and intuitive method of designing chatbots and may scale back bot design time from weeks to hours. Nevertheless, the automated chatbot designer requires transcripts to be in a sure format that’s not aligned to Genesys Cloud transcript exports.
On this publish, we present how one can implement an structure utilizing Amazon EventBridge, Amazon Easy Storage Service (Amazon S3), and AWS Lambda to mechanically accumulate, rework, and cargo your Genesys name transcripts within the required format for the Amazon Lex automated chatbot designer. You possibly can then run the automated chatbot designer in your transcripts, be given suggestions for bot design, and streamline your bot design journey.
Resolution overview
The next diagram illustrates the answer structure.
The answer workflow consists of the next steps:
- Genesys Cloud sends iterative transcripts occasions to your EventBridge occasion bus.
- Lambda receives the iterative transcripts from EventBridge, determines when a dialog is full, and invokes the Transcript API inside Genesys Cloud and drops the total transcript in an S3 bucket.
- When a brand new full transcript is uploaded to Amazon S3, Lambda converts the Genesys Cloud formatted transcript into the required format for the Amazon Lex automated chatbot designer and copies it to an S3 bucket.
- The Amazon Lex automated chatbot designer makes use of ML to construct an preliminary bot design primarily based on the offered Genesys Cloud transcripts.
Conditions
Earlier than you deploy the answer, you have to full the next stipulations:
- Arrange your Genesys Cloud CX account and ensure that you’ll be able to log in. For extra data on organising your account, seek advice from the Genesys documentation.
- Be sure that the fitting permissions are set for enabling and publishing transcripts from Genesys. For extra data on organising the required permissions, seek advice from Roles and permissions overview.
- If PCI and PII encryption is required for transcription, be certain that it’s arrange in Genesys. For extra data on organising the required permissions, seek advice from Are interplay transcripts encrypted when saved within the cloud.
- Arrange an AWS account with the suitable permissions.
Deploy the Genesys EventBridge integration
To allow the EventBridge integration with Genesys Cloud, full the next steps:
- Log in to the Genesys Cloud setting.
- Select Admin, Integrations, Add Integrations, and Amazon EventBridge Supply.
- On the Configuration tab, present the next data:
- For AWS Account ID, enter your AWS account ID.
- For AWS Account Area, enter the Area the place you need EventBridge to be arrange.
- For Occasion Supply Suffix, enter a suffix (for instance,
genesys-eb-poc-demo
).
- Save your configuration.
- On the EventBridge console, select Integration within the navigation pane, then select Companion occasion sources.
There must be an occasion supply listed with a reputation like aws.associate/genesys.com/…/genesys-eb-poc-demo
.
- Choose the associate occasion supply and select Affiliate with occasion bus.
The standing adjustments from Pending to Lively. This units up the EventBridge configuration for Genesys.
Subsequent, you arrange OAuth2 credentials in Genesys Cloud for authorizing the API name to get the ultimate transcript.
- Navigate to the Genesys Cloud occasion.
- Select Admin, Integrations, and OAuth.
- Select Add Shopper.
- On the Shopper Particulars tab, present the next data:
- For App Identify, enter a reputation (for instance,
TranscriptInvoke-creds
). - For Grant Varieties, choose Shopper Credentials.
- For App Identify, enter a reputation (for instance,
Ensure you’re utilizing the fitting function that has entry to invoke the Transcribe APIs.
- Select Save.
This generates new values for Shopper ID and Shopper Secret. Copy these values to make use of within the subsequent part, the place you configure the template for the answer.
Deploy the answer
After you may have arrange the Genesys EventBridge integration, you possibly can deploy an AWS Serverless Utility Mannequin (AWS SAM) template, which deploys the rest of the structure. To deploy the answer in your account, full the next steps:
- Set up AWS SAM if not put in already. For directions, seek advice from Putting in the AWS SAM CLI.
- Obtain the GitHub repo and unzip to your listing.
- Navigate to the
genesys-to-lex-automated-chatbot-designer
folder and run the next instructions:
The primary command builds the supply of your utility. The second command packages and deploys your utility to AWS, with a sequence of prompts:
- Stack Identify – Enter the identify of the stack to deploy to AWS CloudFormation. This must be distinctive to your account and Area; a superb start line is one thing matching your challenge identify.
- AWS Area – Enter the Area you need to deploy your app to. Make sure that it’s deployed in the identical Area because the EventBridge occasion bus.
- Parameter GenesysBusname – Enter the bus identify created whenever you configured the Genesys integration. The sample of the bus identify ought to appear like
aws.associate/genesys.com/*
. - Parameter ClientId – Enter the shopper ID you copied earlier.
- Parameter ClientSecret – Enter the shopper secret you copied earlier.
- Parameter FileNamePrefix – Change the default file identify prefix for the goal transcript file within the uncooked S3 bucket or preserve the default.
- Parameter GenCloudEnv – Enter is the cloud setting for the particular Genesys group. Genesys is on the market in additional than 15 Areas worldwide as of this writing, so this worth is obligatory and may level to the setting the place your group is created in Genesys (for instance,
usw2.pure.cloud
). - Verify adjustments earlier than deploy – If set to sure, any change units shall be proven to you earlier than deployment for guide assessment. If set to no, the AWS SAM CLI will mechanically deploy utility adjustments.
- Enable SAM CLI IAM function creation – Many AWS SAM templates, together with this instance, create AWS Identification and Entry Administration (IAM) roles required for the Lambda capabilities included to entry AWS companies. By default, these are scoped right down to the minimal required permissions. To deploy a CloudFormation stack that creates or modifies IAM roles, you have to present the
CAPABILITY_IAM
worth for capabilities. If permission isn’t offered by way of this immediate, to deploy this instance, you have to explicitly go--capabilities CAPABILITY_IAM
to thesam deploy
command. - Save arguments to samconfig.toml – If set to sure, your decisions shall be saved to a configuration file contained in the challenge, in order that sooner or later you possibly can rerun
sam deploy
with out parameters to deploy adjustments to your utility.
After you deploy your AWS SAM utility in your account, you possibly can take a look at that Genesys transcripts are being despatched to your account and being remodeled into the required format for the Amazon Lex automated chatbot designer.
Make a take a look at name to validate the answer
After you may have arrange the Genesys EventBridge integration and deployed the previous AWS SAM template, you may make take a look at calls and validate that information are ending up within the S3 bucket for remodeled information. At a excessive stage, you’ll want to carry out the next steps:
- Make a take a look at name to your Genesys occasion to create a transcript.
- Wait a couple of minutes and examine the TransformedTranscript bucket for the output.
Run the automated chatbot designer
After you may have just a few days’ price of transcripts saved in Amazon S3, you possibly can run the automated chatbot designer by way of the Amazon Lex console utilizing the steps on this part. For extra details about the minimal and most quantity of turns for the service, seek advice from Put together transcripts.
- On the Amazon Lex V2 console, select Bots within the navigation pane.
- Select Create bot.
- Choose Begin with transcripts because the creation methodology.
- Give the bot a reputation (for this instance,
InsuranceBot
) and supply an optionally available description. - Choose Create a task with primary Amazon Lex permissions and use this as your runtime function.
- After you fill out the opposite fields, select Subsequent to proceed to the language configuration.
- Select the language and voice on your interplay.
- Specify the Amazon S3 location of the transcripts that the answer has transformed for you.
- Add further native paths when you’ve got a particular a folder construction inside your S3 bucket.
- Apply a filter (date vary) on your enter transcripts.
- Select Performed.
You should utilize the standing bar on the Amazon S3 console to trace the evaluation. Inside just a few hours, the automated chatbot designer surfaces a chatbot design that features consumer intents, pattern phrases related to these intents, and a listing of all the data required to satisfy them. The period of time it takes to finish coaching relies on a number of components, together with the quantity of transcripts and the complexity of the conversations. Usually, 600 traces of transcript are analyzed each minute.
- Select Overview to view the intents and slot varieties found by the automated chatbot designer.
The Intents tab lists all of the intents together with pattern phrases and slots, and the Slot varieties tab offers a listing of all of the slot varieties together with slot sort values.
- Select any of the intents to assessment the pattern utterances and slots. For instance, within the following screenshot, we select
ChangePassword
to view the utterances. - Select the Related transcripts tab to assessment the conversations used to establish the intents.
- After you assessment the outcomes, choose the intents and slot varieties related to your use case and select Add.
This provides the chosen intents and slot varieties to the bot. Now you can iterate on this design by making adjustments equivalent to including prompts, merging intents or slot varieties, and renaming slots.
You’ve now used the Amazon Lex automated chatbot designer to establish widespread intents, utterances mapped to these intents, and knowledge that the chatbot wants to gather to satisfy sure enterprise capabilities.
Clear up
Whenever you’re completed, clear up your assets through the use of the next command inside the AWS SAM CLI:
Conclusion
This publish confirmed you methods to use the Genesys Cloud CX and EventBridge integration to ship your Genesys CX transcripts to your AWS account, rework them, and use them with the Amazon Lex automated chatbot designer to create pattern bots, intents, utterances, and slots. This structure will help first-time AWS CCI customers and present AWS CCI customers onboard extra chatbots utilizing the Genesys CX and Amazon Lex integration, or in steady enchancment alternatives the place you might need to evaluate your present intent design to that outputted by the Amazon Lex automated chatbot designer. For extra details about different AWS CCI capabilities, see Contact Middle Intelligence.
Concerning the Authors
Joe Morotti is a Options Architect at Amazon Internet Companies (AWS), serving to Enterprise clients throughout the Midwest US. He has held a variety of technical roles and revel in displaying buyer’s artwork of the doable. In his free time, he enjoys spending high quality time together with his household exploring new locations and over analyzing his sports activities crew’s efficiency.
Anand Bose is a Senior Options Architect at Amazon Internet Companies, supporting ISV companions who construct enterprise purposes on AWS. He’s obsessed with creating differentiated options that unlock clients for cloud adoption. Anand lives in Dallas, Texas and enjoys travelling.
Teri Ferris is accountable for architecting nice buyer experiences alongside enterprise companions, leveraging Genesys know-how options that allow Expertise Orchestration for contact facilities. In her function she advises on resolution structure, integrations, IVR, routing, reporting analytics, self-service, AI, outbound, cell capabilities, omnichannel, social channels, digital, unified communications (UCaaS), and analytics and the way they’ll streamline the client expertise. Earlier than Genesys, she held senior management roles at Human Sources, Payroll, and Studying Administration corporations, together with overseeing the Contact Middle.