Amazon Lex delivers conversational logs to S3 for each caller utterance.
For this blog, we will focus on the text logs with its associated metadata.
It may deliver more CTR records for the same call, such as new information arriving after initial delivery.Īmazon Lex delivers text and audio logs for the conversation. Amazon Connect delivers contact records at least once. The CTR captures the events associated with a contact call from your contact center. In the above architecture, Amazon Kinesis Streams Amazon Connect CTRs as raw data to an Amazon Simple Storage Service (S3) bucket.
#Aws chatbot logo how to#
In this blog, you will learn how to enable Amazon Lex conversation logs, relate it to the CTR logs, and generate reports using Amazon QuickSight. While CTR captures transactional metrics, such as hold time, wait time, and agent interaction time, and more, Amazon Lex conversation logs capture caller’s utterance, NLP confidence score, sentiment score, intent name, and more. Relating Amazon Lex logs to the Contact Trace Record (CTR) and conversation logs, these organizations can identify chatbot issues, tune the NLP engine, understand customer sentiments, and improve the chatbot performance. Amazon Lex is the natural language understanding (NLP) engine for chatbots used by Amazon Connect. Many organizations want the ability to generate chatbot performance reports for their digital customer experience offering. If you haven’t read “ Analyze Amazon Connect Contact Trace Record with Amazon Athena and Amazon QuickSight–Part 1”, we strongly recommend you do before proceeding further. You can build flows that understand natural language, so callers can say what they want instead of having to listen to long lists of menu options and guess which one is most closely related to what they want to do.Note: This is the fourth blog in the Amazon Connect reporting blog series. Customers can also use Amazon Lex, an artificial intelligence (AI) service that has the same automatic speech recognition (ASR) and natural language understanding (NLU) technology that powers Amazon Alexa. For example, an airline could design a flow to recognize a caller’s phone number, look up their travel schedule in a booking database, and present options such as “rebook” or “cancel” if the caller just missed a flight. You can also design flows to change based on information retrieved by Amazon Connect from AWS services (such as Amazon DynamoDB, Amazon Redshift, or Amazon Aurora) or third-party systems (such as CRM or analytics solutions).
This could include customer information on past purchases, contact history, or customer tendencies. With AWS Lambda, you can create personalized experiences by accessing virtually any backend system and retrieving information to anticipate end-customer needs and deliver answers to questions before they are asked. With Amazon Connect, you also have the flexibility to use other AWS services. Amazon Connect makes it possible to design automated flows that dynamically adapt to the caller experience in real time. With the flow builder’s GUI in Amazon Connect, contact center managers can create dynamic, personal, and automated customer experiences without needing to write a single line of code. The flow includes setting logging behavior, setting text-to-speech language and voice, capturing customer inputs (spoken or by pressing 0–9 on the phone keypad), playing prompts, and transferring a customer to a queue. An Amazon Connect flow defines the customer experience with your contact center from start to finish.
0 kommentar(er)
