Amazon Lex - V2 Developer Guide

1 Amazon LexV2 Developer GuideAmazon lex v2 Developer GuideAmazon Lex: V2 Developer GuideCopyright Amazon Web Services, Inc. and/or its affiliates. All rights 's trademarks and trade dress may not be used in connection with any product or service that is notAmazon's, in any manner that is likely to cause confusion among customers, or in any manner that disparages ordiscredits Amazon . All other trademarks not owned by Amazon are the property of their respective owners, who mayor may not be affiliated with, connected to, or sponsored by lex v2 Developer GuideTable of ContentsWhat is Amazon lex v2 ? .. 1 Are You a First-time User of Amazon lex v2 ? .. 2 How it works .. 3 Supported languages .. 4 Supported languages and locales .. 4 Languages and locales supported by Amazon lex v2 features .. 5 Getting started .. 7 Step 1: Set Up an Account .. 7 Sign Up for AWS.

2 7 Create an IAM User .. 8 Next step .. 8 Step 2: Getting started (Console) .. 8 Exercise 1: Create a bot from an example .. 9 Exercise 2: Review the conversation flow .. 10 Building 17 Creating a bot .. 17 Adding a language .. 18 Adding intents .. 18 Turning off responses .. 19 Adding slot types .. 19 Testing a bot .. 20 Creating versions .. 23 The Draft version .. 23 Creating a version .. 24 Updating an Amazon lex v2 bot .. 24 Deleting an Amazon lex v2 bot or version .. 24 Built-in intents and slot types .. 24 Built-in intents .. 24 Built-in slot types .. 35 Using a custom grammar slot type .. 43 Adding a grammar slot type .. 44 Grammar 44 Script 51 Industry grammars .. 58 Creating custom slot types .. 140 Creating a custom vocabulary to improve speech recognition .. 141 Custom vocabulary basics.

3 141 Best practices for creating a custom vocabulary .. 141 Creating a custom vocabulary for eliciting intents .. 142 Creating a custom vocabulary file .. 143 Using multiple values in a 143 Using a Lambda function .. 145 Attaching a Lambda function to a bot alias .. 145 Input event format .. 146 Response format .. 150 Lambda router function .. 152 Using the Automated Chatbot Designer (Preview) .. 154 Importing conversation transcripts .. 154 Importing transcripts from Contact Lens for Amazon Connect .. 155 Prepare transcripts .. 155 Upload your transcripts to an S3 bucket .. 156 Analyze your transcripts using Amazon lex v2 console .. 156 Creating intents and slot types .. 157 Input transcript 157iiiAmazon lex v2 Developer GuideOutput transcript 158 Deploying bots .. 160 Integrating with a Java application .. 161 Integrating your bots.

4 165 Messaging platforms .. 165 Integrating with Facebook .. 165 Integrating with 168 Integrating with Twilio SMS .. 171 Contact centers .. 172 Amazon Chime SDK .. 173 Amazon Connect .. 173 Genesys 174 Using 175 Managing conversations .. 175 Managing conversation context .. 176 Setting intent context .. 176 Using default slot 178 Setting session attributes .. 178 Setting request attributes .. 180 Setting the session timeout .. 180 Sharing information between intents .. 181 Setting complex attributes .. 181 Managing 182 Starting a new session .. 183 Switching intents .. 183 Resuming a prior intent .. 184 Validating slot values .. 184 Analyzing 184 Using confidence scores .. 185 Using intent confidence scores .. 186 Using voice transcription confidence scores .. 187 Using runtime hints to improve recognition of slot values.

5 194 Adding slot values in context .. 195 Adding hints to a slot .. 195 Using spelling styles to capture slot values .. 196 Enabling 197 Example code .. 197 Streaming conversations .. 201 Starting a stream to a bot .. 202 Time sequence of events for an audio conversation .. 204 Starting a streaming conversation .. 206 Event stream encoding .. 217 Enabling your bot to be interrupted .. 218 Waiting for the user to provide additional information .. 219 Configuring fulfillment progress updates .. 220 Fulfillment 221 Post-fulfillment response .. 222 Timeouts for user 222 Timeouts for voice input .. 223 Timeouts for text input .. 223 Configuration for DTMF input .. 225 Monitoring with conversation logs .. 225 Configuring conversation logs .. 225 Viewing text logs in Amazon CloudWatch Logs .. 227 Accessing audio logs in Amazon S3.

6 232ivAmazon lex v2 Developer GuideMonitoring conversation log status with CloudWatch metrics .. 232 Obscuring slot 233 Viewing utterance statistics .. 234 Logging with CloudTrail .. 235 Amazon lex v2 information in CloudTrail .. 235 Understanding Amazon lex v2 log file entries .. 236 Monitoring with CloudWatch .. 237 Importing and exporting .. 242 Exporting .. 242 IAM permissions required to export .. 243 Exporting a bot (console) .. 243 Importing .. 244 IAM permissions required to import .. 245 Importing a bot (console) .. 246 Using a password when importing or exporting .. 247 JSON format for importing and exporting .. 247 Manifest file structure .. 248 Bot file structure .. 248 Bot locale file structure .. 248 Intent file structure .. 249 Slot file structure .. 250 Slot type file structure .. 251 Custom vocabulary file structure.

7 252 Tagging resources .. 253 Tagging your resources .. 253 Tag restrictions .. 253 Tagging resources (console) .. 254 Security .. 255 Data protection .. 255 Encryption at rest .. 256 Encryption in transit .. 256 Identity and access management .. 257 Audience .. 257 Authenticating with 257 Managing access using policies .. 259 How Amazon lex v2 works with 261 Identity-based policy examples .. 268 Resource-based policy examples .. 276 AWS managed policies .. 282 Troubleshooting .. 289 Using service-linked roles .. 290 Service-linked role permissions for Amazon lex v2 .. 291 Creating a service-linked role for Amazon lex v2 .. 292 Editing a service-linked role for Amazon lex v2 .. 292 Deleting a service-linked role for Amazon lex v2 .. 292 Supported regions for Amazon lex v2 service-linked roles .. 293 Logging and 293 Compliance validation.

8 293 Resilience .. 294 Infrastructure security .. 294 VPC endpoints (AWS PrivateLink) .. 294 Considerations for Amazon lex v2 VPC endpoints .. 295 Creating an interface VPC endpoint for Amazon lex v2 .. 295 Creating a VPC endpoint policy for Amazon lex v2 .. 295 Migration 297 Amazon lex v2 overview .. 297 Multiple languages in a 297vAmazon lex v2 Developer GuideSimplified information architecture .. 297 Improved builder productivity .. 297 AWS CloudFormation resources .. 299 Amazon lex v2 and AWS CloudFormation templates .. 299 Learn more about AWS CloudFormation .. 299 Guidelines and 300 Regions .. 300 General 301 Build-time 301 Runtime 302 Document history .. 304 API reference .. 308 Actions .. 308 Amazon Lex Model Building V2 .. 310 Amazon Lex Runtime V2 .. 616 Data Types .. 650 Amazon Lex Model Building V2.

9 653 Amazon Lex Runtime V2 .. 781 Common Errors .. 823 Common Parameters .. 825 AWS glossary .. 828viAmazon lex v2 Developer GuideWhat is Amazon lex v2 ? Amazon lex v2 is an AWS service for building conversational interfaces for applications using voice andtext. Amazon lex v2 provides the deep functionality and flexibility of natural language understanding(NLU) and automatic speech recognition (ASR) so you can build highly engaging user experiences withlifelike, conversational interactions, and create new categories of lex v2 enables any Developer to build conversational bots quickly. With Amazon lex v2 , nodeep learning expertise is necessary to create a bot, you specify the basic conversation flow in theAmazon lex v2 console. Amazon lex v2 manages the dialog and dynamically adjusts the responses inthe conversation. Using the console, you can build, test, and publish your text or voice chatbot.

10 You canthen add the conversational interfaces to bots on mobile devices, web applications, and chat platforms(for example, Facebook Messenger). Amazon lex v2 provides integration with AWS Lambda, and you can integrate with many otherservices on the AWS platform, including Amazon Connect, Amazon Comprehend, and Amazon with Lambda provides bots access to pre-built serverless enterprise connectors to link to datain SaaS applications such as lex v2 provides the following benefits: Simplicity Amazon lex v2 guides you through using the console to create your own bot in supply a few example phrases, and Amazon lex v2 builds a complete natural language modelthrough which the bot can interact using voice and text to ask questions, get answers, and completesophisticated tasks. Democratized deep learning technologies Amazon lex v2 provides ASR and NLU technologies tocreate a Speech Language Understanding (SLU) system.