Automate the customer service experience for flight reservations using Amazon Lex

As an outcome, consumer service is going through an accelerated change as airline companies make every effort to provide a smooth and smooth experience. Customers contact airline company client service for a number of factors, such as making an appointment, querying flight status, tracking baggage, or handling frequent flyer subscription. Airline companies want to deliver a customer-centric experience that gives travelers a choice on how they engage to ensure high client fulfillment.
In this post, we evaluate how you can use the pre-built services in Amazon Lex to automate the airline client service experience for flight bookings and deliver a quicker, more connected, omnichannel experience.
Option summary
Amazon Lex supplies the sophisticated deep knowing functionalities of automatic speech recognition (ASR) for transforming speech to text, and natural language understanding (NLU) to acknowledge the intent of the text. This enables you to construct applications with extremely appealing user experiences and realistic conversational interactions. Amazon Lex for Travel uses pre-built solutions so you can rapidly make it possible for conversational experiences for airline company customers and increase consumer complete satisfaction. The pre-built bots are configured with intents, sample utterances, and slot types for airline company services utilize cases, and are integrated with Amazon Connect contact circulations.
Lets examine a sample conversation of scheduling a flight as we cover the different elements of the pre-built service:

Agent: Youve reached reservations. How can I help you today?
Caller: I desire to schedule a flight
Representative: I see you have a regular flyer account with us. Can you verify the regular leaflet ID?
Caller: Yes, its 12345
Representative: Thank you. And for verification, can I get the last four digits of the charge card on file?
Caller: 1234
Representative: Got it. Let me get some info about your journey. Is this reservation for a one-way trip or a big salami?
Caller: One method
Agent: Got it. Whats the departure city?
Caller: Dallas
Representative: Dallas. Ok. And whats your destination?
Caller: New York
Agent: Got it. What date would you like to take the flight?
Caller: December 1st
Representative: Got it. Whats your preferred time of departure?
Caller: 5 PM
Agent: Ok. I have flight number A123 departing at 5:30 PM at $200. Should I go on and book it?
Caller: Yes
Representative: Can I use the card on file ending in 1234 to make the booking?
Caller: Yes
Representative: Great. I have you on the A123 to New York leaving from Dallas on December 1 at 5:30 PM. Your confirmation code is 123.
Caller: Thank you.

In this sample discussion, the caller desires to schedule a flight. The agent collects information about the journey, such as departure city, destination city, number of travelers, and the preferred departure time. After gathering the details, the representative tries to find available flights, provides finest options, and books the flight.
The AirlinesServicesBot includes intents for common client service activities, such as reserving a flight, checking flight status, getting reservation information, changing a flight appointment, and canceling a flight appointment. It includes the following intents:

BookAFlight– Captures journey and traveler info, and helps in scheduling a flight reservation

GetFlightStatus– Captures flight details and offers the present status of the flight

GetReservationDetails– Captures journey or traveler info and provides appointment details to the caller

ChangeFlightReservation– Captures journey or guest information and helps with changing the flight appointment

CancelFlightReservation– Captures trip or traveler details and aids with canceling the flight booking

GetFlightReservationReceipt– Captures journey or traveler info and supplies the flight appointment receipt

EndConversation– Ends the discussion based upon user input, such as “Thanks, I am done”

When the input does not match any of the set up intents, fallback– Is invoked

def resolve_underspecified_date_to_past( flight_booking_date):.
flight_booking_date = datetime.strptime(.
flight_booking_date, % Y-% m-% d). date().
today = date.today().
if flight_booking_date < 7:. return flight_booking_date. change( year= flight_booking_date. year-1). else:. return flight_booking_date-timedelta( days= 7). number_of_travellers_in_words = dialog.get _ slot(. NumberOfTravellersInWords, intent, choice= interpretedValue) number_of_travellers = dialog.get _ slot(. NumberOfTravellers, intent, choice= interpretedValue) Amazon Lex bots. Lambda functions. DynamoDB table. Amazon Connect contact circulation. IAM functions. For Stack name, enter a name for your stack. This post uses the name airline-bot-solution. DynamoDB table-- airlines_table. Lambda function-- AirlinesBusinessLogic. After a few minutes, your stack should be complete. The core resources are as follows:. An AWS account. Evaluation the IAM resource creation and choose Create stack. Amazon Lex bot-- AirlinesBot. Tidy up. To avoid incurring any charges in the future, delete all the resources created:. After the contact number is associated, the option is prepared to be evaluated. Check the service. If you utilized an Amazon Connect circumstances for release, you can call the Amazon Connect phone number and connect with the bot. You can also test the option straight on the Amazon Lex V2 console utilizing voice or text. Airline services: Key abilities. Lets review a few of the functions used by the pre-built option, such as handling incomplete date information, analyzing expressions as numbers, and contact center flows. Handle insufficient date info. Customers reacting to date-related concerns such as "When did you cancel the reservation?" might leave out the year (for example, "on June 25th") or perhaps the date (" on Monday") in their actions. Due to the fact that the year isnt specified by default, the bot interprets the action as a future date. Similarly, in the second example, the action is interpreted to be a day in the following week. The pre-built service solves such incomplete (or underspecified) dates to a date in the past, based on business logic for the transaction. In addition, an implicit confirmation timely is utilized to let the caller learn about the analyzed date. The following code demonstrates how an incomplete date is interpreted:. Conclusion. Amazon Lex for Travel provides pre-built services that you can use to speed up delivery of smooth connected experiences and allow a fast resolution of client requests. In this post, we examined an option for airline clients to automate tasks such as scheduling a flight, retrieving flight information, and updating a booking. The pre-built solution offers a ready-to-deploy contact center configuration with Amazon Connect. You can quickly extend the solution with extra discussion flows that are specific to your companys requirements. By developing on AWS, leading travel business are able to manage expenses and respond quickly to changing customer requirements. Try the pre-built airline company services solution on Amazon Lex today! Pick Launch Stack to introduce a CloudFormation stack in the Region of your option:. IAM roles-- LexRole, LexImportRole, LambdaRole, and ConnectRole. Associate a phone number with the airline services contact circulation. Amazon Lex to produce bots. Lambda for the business logic functions. DynamoDB to create the tables. IAM with access to produce functions and policies. AWS CloudFormation to run the stack. if departure_date and not number_of_travellers_in_words:. previous_slot_to_elicit = dialog.get _ previous_slot_to_elicit(. intent_request). if previous_slot_to_elicit == NumberOfTravellersInWords:. timely = prompts.get( NumberOfTravellers). return dialog.elicit _ slot(. NumberOfTravellers, active_contexts,. session_attributes, intent,. else:. prompt = prompts.get( NumberOfTravellersInWords). return dialog.elicit _ slot(. NumberOfTravellersInWords, active_contexts,. session_attributes, intent,. , if number_of_travellers or number_of_travellers_in_words. . and not preferred_departure_time:. if not number_of_travellers:. number_of_travellers = number_of_travellers_in_words. timely = prompts.get(. PreferredDepartureTime). return dialog.elicit _ slot(. PreferredDepartureTime, active_contexts,. session_attributes, intent,. Contact center streams. You can deploy the pre-built solution as part of Amazon Connect contact flows. The contact flow uses a Get consumer input block to invoke the Amazon Lex bot. Amazon Connect contact flow-- AirlinesContactFlow. IAM access and secret key credentials. Optionally, an existing Amazon Connect circumstances (if you plan to deploy on Amazon Connect). Release the pre-built option. To deploy this service, finish the following actions:. About the Authors. Jaya Prakash Kommu is a Technology Lead on the Smartbots.ai group. He handles a passionate group of AI engineers constructing next generation conversational AI interfaces. When not architecting bots, JP delights in playing football. Sandeep Srinivasan is a Product Manager on the Amazon Lex team. As a keen observer of human behavior, he is enthusiastic about consumer experience. He spends his waking hours at the intersection of people, innovation, and the future. We utilize an Amazon Lex bot to confirm the caller, carry out deals (for example, cancel a flight booking), or offer the caller with the inquired (for example, inspect flight status). We use Lambda to mimic access to backend systems and run the organization reasoning required for carrying out transactions. For this post, the information we utilize is kept in an Amazon DynamoDB. In the Parameters area, get in names for the Amazon Lex bots, DynamoDB table, and Amazon Connect contact circulation. The following screenshot reveals 2 slots to catch one worth. The following Lambda function code analyzes conversational phrases as numbers:. We consist of an AWS CloudFormation stack for you which contains all these AWS resources, as well as the required AWS Identity and Access Management (IAM) roles. With these resources in location, you can utilize the pre-built option on the Amazon Connect channel. Prerequisites. You should have the following requirements prior to we deploy the solution:. To respond to any user questions, we set up the Amazon Kendra search index so the bot can search for the information and supply a reaction. You can release the conversational experience on an Amazon Connect instance or incorporate it with your website. Access to the following AWS services:. Analyze phrases as numbers. Caller reactions to concerns trying to collect a number (for example, "How numerous individuals traveling?") might contain expressions describing the count (for instance, "my partner and I") instead of a more specific response (" 2"). The pre-built bots are configured to manage such descriptive answers by taking a two-step technique to recording slot values. The setup contains two slots: among a custom-made slot type to comprehend expressions, and an optional slot of the built-in slot type AMAZON.Number to capture a number. In the primary step, the bot attempts to fix using the expressions, which contain synonyms for each number (for instance, "my other half and I" maps to "2"). If the input isnt interpreted with the expressions, the bot attempts once again with an assisted timely (" How numerous tourists? You can state 3 tourists."). The following screenshot shows worths for the NumberofTravellers custom-made slot type. If you supplied an Amazon Connect ARN throughout stack creation, navigate to the Amazon Connect dashboard and, on the Routing menu in the navigation pane, pick Phone numbers. Amazon Lex for Travel provides pre-built solutions so you can quickly allow conversational experiences for airline company consumers and increase client complete satisfaction. The pre-built bots are set up with intents, sample utterances, and slot types for airline services use cases, and are integrated with Amazon Connect contact flows. If you used an Amazon Connect circumstances for implementation, you can call the Amazon Connect phone number and connect with the bot. The contact circulation uses a Get customer input block to conjure up the Amazon Lex bot. Amazon Lex for Travel provides pre-built solutions that you can use to speed up delivery of seamless connected experiences and allow a fast resolution of client requests. The bot meaning consists of a total dialog together with the prompts to manage the discussion. Each bot likewise integrates with an AWS Lambda function which contains code to mimic service reasoning being run. Combination with Amazon Kendra provides the ability to respond to natural language questions during the discussion. Service architecture Lets review the general architecture for the solution (see the following diagram):.

Leave a Reply

Your email address will not be published.