Building custom skills with Amazon Alexa
Download as pptx, pdf1 like154 views
This document discusses building custom skills with Amazon Alexa, highlighting the advancements in intelligent voice assistants powered by natural language processing and machine learning. It outlines the process for creating an Alexa skill, including the setup of intents, slots, and utterances, as well as integration with AWS services. Key components such as user audio streaming, intent schemas, and request types are also covered.
![Intents & Slots
• Intent is a action that my skill can perform
• You define interactions for your voice app
through intent schemas.
• Each intent consists of two fields. The intent field
gives the name of the intent. The slots field lists
the slots associated with that intent.
• Slots can also included types such as LITERAL,
NUMBER, DATE, etc.
• Intent schemas are uploaded to your skill in the
Amazon Developer Portal
{
"intents": [
{
"intent": “RequestForLeave",
"slots": [
{
"name": “ProjectName",
"type": “ProjectNames"
}
]
}
]
}](https://image.slidesharecdn.com/buildingcustomskillswithalexa-171023181806/85/Building-custom-skills-with-Amazon-Alexa-6-320.jpg)
Building custom skills with Amazon Alexa
- 1. Building Custom Skills With Alexa Brian Perera
- 2. Intelligent “Voice” Assistant (I.A.) • Web in 1995, Apps in 2005, and now we are entering an era of Intelligent Assistants powered by advancements in natural language processing, machine learning, and sophisticated voice recognition. • An intelligent assistant (or simply, IA) is a software agent that can perform tasks or services for an individual. • Speech Interpretation and Recognition Interface (SIRI) • Google Assistant • Cortana • Watson • Alexa
- 3. Amazon Alexa Audio Stream Is Sent Up To Alexa Alexa Sends Customer Intent To Your Service Respond to Intent Through Text & Visual You Pass Back a Textual or Audio Response You Pass Back a Graphical Response “Alexa, Ask Thisara if I can take a leave tomorrow?” Knowledge Base AWS Lambda Or REST
- 4. Alexa Skills Kit Amazon Alexa Service Amazon’s Developer Portal Developer’s Application Service Application, intents, sample data, developer service URL endpoint Configured through portal User audio is streamed to the service User intents and arguments are sent to the developer service Text response and/or GUI card data is returned User audio is streamed to the service GUI cards are rendered in the Amazon Alexa app
- 5. Alexa Skills Kit Hosting Your Skills • AWS Lambda • HTTPS endpoint with a trusted certificate What you need to get things started • AWS Cloud Account (If your planning on hosting your skill set in AWS Lambda) • Amazon Developer Account
- 6. Intents & Slots • Intent is a action that my skill can perform • You define interactions for your voice app through intent schemas. • Each intent consists of two fields. The intent field gives the name of the intent. The slots field lists the slots associated with that intent. • Slots can also included types such as LITERAL, NUMBER, DATE, etc. • Intent schemas are uploaded to your skill in the Amazon Developer Portal { "intents": [ { "intent": “RequestForLeave", "slots": [ { "name": “ProjectName", "type": “ProjectNames" } ] } ] }
- 7. Utterances • The mappings between intents and the typical utterances that invoke those intents are provided in a tab-separated text document of sample utterances. Each possible phrase is assigned to one of the defined intents. • “What is…” • “Are there…” • “Tell me…” • “Give me…” • “Give…” • “Find…” • “Find me…” • ------------------------- • Can I take a leave • Can I stay at home • Can you give me leave • Wanted to find out if I can take a leave
- 8. Request Types • LaunchRequest Maps to onLaunch() and occurs when the users launch the app without specifying what they want. • IntentRequest Maps to onIntent() and occurs when the user specifies an intent • SessionEndedRequest Maps to OnSessionEnded() and occurs when the user ends the session
- 9. Sample Skill Service in NodeJS