...
Always Listening Device: A device that is always listening to detect a “wake word.” When detected, the audio is captured after the wake word is sent for additional processing. See Wake word.
Application Programming Interface (API): It connects “bot logic“ to advanced capabilities, including channel, content, abilities, etc.
Artificial Intelligence: The study and design of a system that perceives its environment and is able to perform tasks that normally require human intelligence. These tasks include visual perception, speech recognition, decision-making, and translations between languages.
...
Bixby: Samsung’s voice assistant.
Bot Logic: The conversations and database that we build for the bot’s persona. This can be built using a platform or a framework.
C
Card: Displays information relating to the user’s request, such as displaying what the user asked and Alexa’s response, or a picture, or long numbers or lists, which can be difficult to process and remember when delivered through voice only. Also known as Home card or Detail card.
Cloud-based service: See Service.
Cloud-enabled device: Channel: The medium where users can interact with the bot. (ex. Facebook Messenger)
Chatbot: A computer program designed to simulate conversation with human users, especially over the internet.
Cloud-based service: See Service.
Cloud-enabled device: In the context of smart home devices, a customer device such as a light bulb, switch, thermostat, or another smart home device with the ability to connect to the Internet. The device is normally controlled by the device cloud.
Companion app: See the Alexa app.
Compatibility Testing: Test the skill with different devices and browsers.
Confidence Score: A number (usually a fraction between 0.00 and 1.00 – e.g., 0.87) that is returned by the ASR and that reflects the confidence that the ASR has in the result provided. A 1.00 confidence means that the ASR is as certain as it can be that it has returned the correct result. A result with a confidence score of 0.91 is deemed more likely to be correct by the ASR than one with a score of 0.78.
...
Confirmation: An Alexa response to make sure the user knows she understood correctly. Types of confirmation:
Implicit confirmation (also known as land-marking): a prompt that subtly repeats back what Alexa heard to give the user assurance that they were correctly understood. Example: User: Alexa, ask Astrology Daily for my horoscope. Astrology Daily: Horoscope for what sign?
Explicit confirmation: A prompt that repeats back what Alexa heard and explicitly asks the user to confirm whether she was correct. Example: User: Alexa, ask Astrology Daily for my horoscope. Astrology Daily: You wanted a horoscope from Astrology Daily, right?
Cooperative Principle: The proposition that listeners and speakers must act cooperatively and mutually accept one Content Management System (CMS): This allows the users to create, and manage web content without much technical knowledge.
Conversational AI: The use of messaging apps, speech-based assistants, and chatbots to automate communication and create personalized customer experiences at scale.
Conversation: See Interaction.
Cooperative Principle: The proposition that listeners and speakers must act cooperatively and mutually accept one another to be understood in a particular way to carry out an effective verbal conversation.Conversation: See Interaction.
Cortana: Microsoft’s voice assistant.
...
Custom Skills: A custom skill is a flexible, yet complex skill with a custom interaction model provided by developers. For custom skills, the developer should define three things: Intents: requests the skill can handle such as ordering food delivery. Interaction Model: the words users may say to make intents such as “Order spicy tuna roll.” Invocation Name: The name Alexa uses to identify the skill such as Food Delivery.
Customer Relationship Management (CRM): Using the customer’s data to improve customer relations.
D
Detail card: A card displayed in the Alexa app with information about the skill and how to use it. A user can review detail cards and enable the skills she or he wants.
...
Dialog errors: When something unexpected happened in the conversation between Alexa and the user. Types of dialogue errors:
Low confidence errors: When Alexa has low confidence that she correctly understood what the user said. When this occurs, Alexa cannot proceed in the interaction without asking the question again or ending the interaction.
Timeouts/Silence/No input: When the user does not respond to a question Alexa asked. A re-prompt is usually played to encourage the user to respond.
False accept: When Alexa has mid-to-high confidence that she correctly understood what the user said, but she actually misunderstood.
Directed dialog: Digital Asset Management (DAM): This allows the users to organize media assets such as images, videos, presentations.
Directed dialog: An interaction between the user and the system that is guided by the application: the system asks questions or offers options and the user responds to them.
Directive language: JSON protocol that enables the communication between the Alexa Smart Home Skill API and a smart home skill.
...
Flash Briefing Skills: Compatibility with Alexa’s native Flash Briefing ability. See Flash briefing.
Form Flow: Pre-structured conversations like a “choose your own adventure“.
Framework: A backend that connects the platform to the channel through an API.
G
Google Assistant: The cloud service provided by Google that powers Google’s Far-Field device (Google Home) as well as other Android-based devices (such as smartphones and tablets).
...
Intent: Determines what a user is trying to accomplish. Within the code, this is how you define your function. There are three types:
Full Intent: A spoken request in which the user expresses everything that is required to complete their request, all at once, such as “Alexa ask Elle.com for today’s horoscope for
...
Virgo.”
Partial Intent: A spoken request in which the user expresses just partial information of what is required to complete their request such as “Alexa ask Elle.com for the horoscope.”
No Intent: A spoken request with minimal information such as “Alexa talk to Elle Magazine.”
Interaction: An exchange or of dialog between the user and Alexa. This may be a single request-response or a more extended set of turns.
...
Invoke: A hardware Echo-like device manufactured by Harman Kardon that enables users to engage Cortana in Far-Field conversations.
K
Keyword: simple marker, used to trigger conversation.
L
Lambda blueprint: An option in the AWS Lambda console that provides sample code and a sample configuration for a new Lambda function. Use this to create Lambda functions with just a few clicks.
...
Low confidence errors: See Dialog Errors.
MMax error condition
Machine Learning (ML): A broad set of AI in which computer algorithms are developed and trained to learn inherent patterns in datasets. The resulting algorithms are often used in a predictive fashion (e.g. given some input predict what the output should be), to automate human behavior and decision-making.
Max error condition: When consecutive dialog errors occur. This terminates the interaction and is designed to keep Alexa from making the same mistake repeatedly.
Mixed-initiative Dialog: Interactions where the user may unilaterally issue a request rather than simply provide exactly the information asked for by system prompts. For instance, while making a flight reservation, the system may ask the user, “What day are you planning to flight out?” Instead of answering that question, the user may say, “I’m flying to Denver, Colorado.” A Mixed-initiative system would recognize that the user -has provided not the exact answer to the question asked, but also (additive), or instead (substitutive), volunteered information, that was going to be requested by the system later on. Such a system would accept this information, remember it, and continue the conversation. In contrast, a Directed Dialog system would rigidly insist on the departure date and won’t proceed successfully unless it received that piece of information.
...
Natural Language Processing (NLP): Technology Technology that extracts the “meaning” of a user’s utterance or typed text. A meaning usually consists of an Intent and Name-Value pairs. The utterance, “I want to book a flight from Washington, DC to Boston,” has the Intent “Book-a-Flight” with the Name-Value pairs being, “Departure City”=”Washington, DC” and “Arrival City”=”Boston, MA”.
N-Best: In speech Natural Language Understanding (NLU): is a subset of NLP, which uses syntactic and semantic analysis of text to speech to determine the meaning of the sentence.
N-Best: In speech recognition, given an audio input, an ASR returns a list of results, with each result ascribed a confidence score (usually a fraction between 0 and 1 (e.g., “0.87”) or a percentage). N-Best refers to the “N” results that were returned by the ASR and that were above the “confidence threshold”. For instance, if the user were to say, “Austin,” and the recognizer were to return, “Austin” with a score of 0.92, “Boston” with 0.87, “Houston” with 0.65, “Aspen” with 0.52, and “Oslo” with 0.43, and the threshold were set at 0.70, only the first two, “Austin” and “Boston” would be returned.
Near Field Speech Recognition: In contrast to “Far Field” speech recognition, which processes speech spoken by a human to a device from a distance (usually of 10 feet or more), the Near Field speech recognition technology is used for handing spoken input from hand-held mobile devices (such as Siri on the iPhone) that are used within inches or two feet away at best.
...
Persona: The personality of the system (formal, playful, chatty, aggressive, friendly, etc.) that comes across the way the system engages with the user. The persona is influenced by factors such as the perceived gender of the system, the type of language the system uses, and how the system handles errors.
Phrases. : A list of randomly selected responses that are spoken by the device. For example, “OK. I’ll be glad to help.” “Sure thing! I’ll get right on it.” Similar to slots, which are spoken by the user.
Platform: A graphical interface to construct and manage conversations.
Progressive Prompting: The technique of beginning an exchange by providing the user with minimal instructions and elaborating on those instructions only if encountering response errors (e.g., no-input, no-match, and so on).
Prompt: Words that should be spoken to the user to ask for more information. You include the prompt text in your response to a user’s request. Types of prompts:
Open-ended: A prompt that asks the user a question intended to elicit a wide range of responses such as “What would you like to do?”
Menu-style: A prompt that asks the user a question intended to elicit a response from a small set of possible options (recommended 5 or fewer) such as “Minecraft Helper. You can ask for a recipe, the ingredients of a potion, or game instructions. Now, which would you like?”
Re-prompt: A prompt that asks the user a question after a dialog error has occurred. The general purpose of a re-prompt is to help the user recover from errors. For example:
User: Alexa, open Score Keeper.
Score Keeper: Score Keeper. What’s your update?
User: … (no response)
Score Keeper: You can add points for a player, ask for the current score, or start a new game. To hear a list of everything you can do, say Help. Now, what would you like to do?Landmark: (Also known as implicit confirmation.) A prompt that subtly repeats back what Alexa heard to give the user assurance that they were correctly understood.
Pull: response to a user.
Push: conversation started by the bot, can be structured as either a broadcast or a sequence.
R
Recognition Tuning: The activity of configuring the ASR’s settings to optimize recognition accuracy and processing speed.
Regression Testing: Test to ensure that the old code works when new code is added.
Re-prompt: A question prompt that occurs after a virtual assistant has answered a user question. For example, “Do you have any more questions?“. See also Prompt.
S
Sample utterance: A structured string of words that connects a specific intent to a likely utterance. You provide a set of sample utterances as part of your interaction model for a custom skill. When users say one of these utterances, the Alexa service sends a request to your service that includes the corresponding intent. Note: You only provide sample utterances for custom skills. Utterances for smart home skills are defined by the Smart Home Skill API.
Second Orality: Orality that is dependent on literate culture and the existence of writing, such as a television anchor reading the news or radio. While it exists in sound, it does not have the features of primary orality because it presumes and rests upon literate thought and expression, and may even be people reading written materialexpression, and may even be people reading written material.
Secure File Transfer Protocol (SFTP): A secure location on a server where parties with access can safely pass files back and forth. Used for files with PHI.
Self-Service API (Application Program Interface): A software platform through which developers organize access to data and business processes, and to enable web applications to interact with other applications. Self-service APIs let developers access a large range of features so they can evolve and customize their projects.
Service: A cloud-based service you create to support a skill. This service takes requests from Alexa and returns responses. For a custom skill, the service accepts requests with intents and returns responses with the text to speak back to the user. For a smart home skill, the service takes device directives, communicates with the device cloud to control devices such as lights and thermostats, and sends device events back to Alexa. You can deploy the service for a custom skill either as an AWS Lambda function or a web service. Smart home skills can only be hosted using Lambda.
...
Slot type: Determines how the user input is handled and passed on to your skill. You can assign slot types from the detail page for intent or the slot detail page for the slotis handled and passed on to your skill. You can assign slot types from the detail page for intent or the slot detail page for the slot.
Small Talk: A base set of questions that someone may ask specifically to the virtual assistant such as “What is your name?“, “Who created you?“, and so on.
Smart Home skill: A skill intended to control smart home devices such as lights and thermostats. When using the Smart Home Skill API, the API defines the requests the skill can handle (device directives) and the words the users say to make those requests. A complete smart home skill includes the code hosted as an AWS Lambda function and a configuration that provides the information the Alexa service needs to route requests to the Lambda function. The code for the skill must be able to control the device (such as a light) using the cloud.
...
Tapered Prompting: the technique of eliding a prompt or a piece of a prompt in the context of a multi-step interaction or a multi-part system response. Instead of the system asking repetitively, “What is your level of satisfaction with our service?” “What is your level of satisfaction with our pricing?” “What is your level of satisfaction with our cleanliness,” the system would ask: “What is your level of satisfaction with our service?” “How about our pricing?” “And Cleanliness?” The technique is used to provide a more natural and less robotic-sounding user experience.
Taxonomy: Library of all intents and entities for a particular application of conversational AI, structured for a medical context.
Tell: A keyword a user can say to tell Alexa to invoke a particular custom skill. See also Ask.
...
Wake Word: Spoken keywords that activate an always-listening device. Amazon offers a choice of Alexa, Amazon, Echo, or Computer for as word to activate a device. A device is always listening for a wake word.
Webchat: An unbranded channel that we can customize for websites, portals, etc.
Web service: In the context of the Alexa Skills Kit, an Internet-accessible service that can accept requests from the Alexa service and return responses. You can use a web service as the a cloud-based service for a custom skill.
Widget: The device that “holds“ webchat on the website.
| Attachments | ||||||
|---|---|---|---|---|---|---|
|
...