Glossary of Terms

Agent

A physical person that interacts with a caller.

AI

Artificial Intelligence, a wide-ranging branch of computer science concerned with building smart machines capable of performing tasks that typically require human intelligence. AI is an interdisciplinary science with multiple approaches, but advancements in machine learning and deep learning are creating a paradigm shift in virtually every sector of the tech industry. 

AM

Acoustic Model, which is used in automatic speech recognition to represent the relationship between an audio signal and the phonemes or other linguistic units that make up speech. The model is learned from a set of audio recordings and their corresponding transcripts.

ANI

Automatic Number Identification is a feature of a telecommunications network for automatically determining the origination telephone number on toll calls for billing purposes.

In a call center, ANI displays the number of the calling party to the call center agent in real time. Among other things, the call center can use the information to forward calls to different people for different geographic areas.

API

An Application Programming Interface is an interface or communication protocol between a client and a server intended to simplify the building of client-side software.

API Key

An authorization code passed in to an API request via a header or parameter to identify the requester.

App

Short term for Application

Application

Application, can be also referred to as a Dialog Application, is a sequence of combined miniApps® and, optionally, other building blocks for running a conversation according to the logic you define.

Application Type

The type of a miniApp or Flow.

ASR

Automatic Speech Recognition, a technology that allows human beings to use their voices to speak with a computer interface in a way that, in its most sophisticated variations, resembles normal human conversation.

Authentication

Identifying the user of the API. Common techniques for authentication include API Keys and OAuth.

Barge-in

A feature that allows a speaker to interrupt a prompt when activated.

Biokey

A key-value pair attached to a bio user; it can correspond to a physical entity (for example ANI). Can be shared across multiple unique users.

BioScore

A similarity score generated after comparing two voiceprints. It is a float from 0-1 and is commonly visualized in a % form.

BioSearch

Also known as identification or just search. Result of a search by biokey(s) against the users of the database; this will return the user IDs of all the users that share the same biokey(s).

BioResult

A verification label that corresponds to a span of BioScores.

Canvas

The working area where Dialog Applications are created in Orchestrator.

CCaaS

Contact Center as a Service includes call center software with such features as automatic call distribution and interactive voice response. CCaaS helps support and sales representatives communicate with customers across various channels through a single cloud platform.

CDR

Call Detail Records, the records generated by telecommunication systems when a call is made. They contain information such as the time and duration of the call, the phone numbers involved, and the location of the call. CDRs are used by telecommunication companies to track usage and billing, as well as provide data for analysis and research.

CISR

Concept Identification Success Rate, one of the basic KPIs that measures the extent to which the system successfully extracted the correct meaning out of each individual caller utterance.

Conditions

Dialog Control elements that allow users to create scenarios branches in a dialog based on the values of specific fields.

Confidence Threshold

A configurable parameter in OCP Conversational Natural Language®, which defines the confidence level needed to assign intent to an utterance for the Machine Learning part of your model.

Conversational Natural Language®

Omilia’s software designed for creating and deploying NLU models.

Corpus

A collection of conversation, speech or written data.

Critical Error

An error that interrupts the conversation.

deepASR®

Omilia’s software based on the Automated Speech Recognition technology which allows human beings to use their voices to speak with a computer interface in a way that, in its most sophisticated variations, resembles normal human conversation.

Deep Learning

A machine learning technique based on artificial neural networks with representation learning. Deep Learning teaches computers to do what comes naturally to humans: learn by example.

deepNLU®

Omilia’s software based on the Natural Language Understanding technology that works to extract meaning from free, unstructured language.

DELETE

The HTTP method that deletes the specified resource.

Dialog Application

Can be also referred to as Application, is a sequence of combined miniApps® and, optionally, other building blocks for running a conversation according to the logic you define.
Read more on how to create a Dialog Application.

Dialog Control Elements

Features in Orchestrator, such as Conditions, Transfers, Set fields and so on.

DiaManT®

Dialog Management Technologies, a dialog management tool which drives conversational interactions with users from start to finish.

DNIS

Dialled Number Identification Service is a feature of the telephony network that enables us to know which number was dialled by a customer so the appropriate Call Routing strategy can be applied.

DRTviewer®

Dialog Review Tool, Omilia’s software that allows monitoring ongoing or completed sessions between you and DiaManT for all channels (that is, IVR, Chat, Mobile Apps, Facebook Messenger, Viber, and so on). It also provides powerful search capabilities with a large number of available filtering criteria to track down the sessions you need to work with. For more information, refer to DRTviewer User Guide.

DTMF

Dual Tone Multi-Frequency is a technology used with touch tone phones, best known to users as the sound made when pressing a number key. It signals the phone company that you want to make a call and sends a command to the switch. It does this by sending two tones for every number pushed - one high frequency and one low frequency.

miniApps support DTMF and allow to configure the timeout interval after a key has been pressed during DTMF input.

DTMF Termination Key

The key that can be used to declare the completion of the input in DTMF mode.

Endpoint

One end of a communication channel which includes an URL of a server or a service. Each endpoint is the location from which APIs can access the resources they need to carry out their function.

Entity

Represents values collected from the user in a conversation. It is important to understand the difference between intent and an entity. An intent represents the goal the user has in mind when formulating the intent and the entity represents a keyword that you want to be extracted from the user utterance.

Error Handler

The mechanism that decides when and how to end a call depending on the type and number of errors that occurred in a dialog.

Flow

Also referred to as a Flow app, a conversational application that can combine several miniApps in order to implement effective business logic. It is reusable across many applications belonging to the same Group.

GET

An HTTP method used to request data from a specified resource.

Group

A group of users that share miniApps®, Dialog Applications, and Flows.

GUI

Graphical User Interface, a computer program that enables a person to communicate with a computer by clicking on icons or pulling down the menus.

Header

This is the part of an HTTP request or response sent prior to the request or response body.

HTTP

Hyper Text Transfer Protocol, an application protocol that enables a client and a server to communicate. This protocol can be used to transmit messages and digital documents such as HTML. A typical HTTP flow includes a client making a request to a server which then returns a response.

HTTPS

Hyper Text Transfer Protocol Secure is how websites and APIs communicate securely over the internet.

IdP

Identity Provider. For example External IdP setup.

Input Field

Fields from the current dialog context that are passed as input when calling a miniApp or a Flow.

Intent

A goal or purpose that the user expressed in their utterance. An intent represents an action that the user wants to perform while the entity represents a keyword that you want to be extracted from the user utterance.

Interpretation Errors

NoMatch or Rejection events.

Invocations

Invocation refers to the process of initiating a conversation or interaction with a system or an agent. It is the first step in the customer's journey when they dial a customer service number or access a company's self-service system.

IVR

Interactive Voice Response, a technology that allows humans to interact with a computer-operated phone system through the use of voice and DTMF tones input via a keypad.

Javascript

A programming language that conforms to the ECMAScript specification. JavaScript is high-level, often just-in-time compile. It has curly-bracket syntax, dynamic typing, prototype-based object orientation, and first-class functions.

JSON

JavaScript Object Notation, an open standard file format and data interchange format that uses human-readable text to store and transmit data objects consisting of attribute-value pairs and arrays (or other serializable values).

Knowledge base

Also referred to as KB, a self-serve customer service library that includes information about a product, service, or topic that helps customers find answers so they can solve problems on their own.

Link

A fully-qualified HTTP address for a particular resource (for example, http://my.api.com/v1/resources/resource-name). RESTful APIs by definition should provide links from a resource to all related resources and collections which provide subsequent actions using the resource. This allows for an API to be traversed organically and for an application developer to ensure their API Client is not in (as much) jeopardy if a resource’s location changed.

LM

Language Model, a machine learning model designed to represent the language domain. It estimates the probability of different linguistic units: symbols, tokens, token sequences. LM can be used as a basis for a number of different language-based tasks, such as question answering, semantic search, summarization.

LMS

Learning Management System, a software application for the administration, documentation, tracking, reporting, automation, and delivery of educational courses, training programs, materials or learning and development programs.

Locale

A set of parameters that defines the user’s language, region and any special language variant preferences.

Message Body

The part of the HTTP request where additional content can be sent to the server. For example, a file type of JSON or XML. The presence of the body and its size is specified by the request line and HTTP headers.

Method

The messages sent to a server to indicate the kind of actions to take to allow for richer communication between the browser and the server. The most commonly used methods are GET, POST, PUT, DELETE, and more.

miniApp®

Zero-coding, zero-maintenance, instantly deployable and configurable natural language dialog components that handle a single task, such as soliciting a US address or credit card number, or even negotiating an appointment. For more information, refer to How to create your first miniApp.

Mixed Errors

Consecutive error events (NoInput, NoMatch, LowConfRejection, Same State).

ML

Machine Learning, a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

MSISDN

A number uniquely identifying a subscription in the Global System for Mobile communications (GSM) or a Universal Mobile Telecommunications System (UMTC) mobile network.

Monitor

Omilia’s software, part of OCP®, allows the user to drill down into any conversation occurring within an OCP® application. This involves Orchestrator application dialogs, Flows, and miniApp invocations originating from calls or web chats.

Nice reactions

Application reactions that make the dialog sound more conversational.

NLG

Natural Language Generation, the use of artificial intelligence programming to produce written or spoken narratives from a data set. A good example of NLG is automated journalism, where a computer searches the web for real-time news, scapes the data from different sources, and writes a text summary, that can be published very quickly to the web.

NLP

Natural Language Processing, a subfield of linguistics, computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human (natural) languages, in particular, how to program computers to process and analyze natural language.

NLU

Natural Language Understanding, a subtopic of natural-language processing in artificial intelligence that deals with machine reading comprehension and recognizing patterns in a human language.

NLU Model

A collection of utterances, intents, entities, and vocabulary that the system uses to respond to natural language inputs from your users. The model takes the natural language from the input and translates it into actions that can be performed by the system.

OCP®

Omilia Cloud Platform®, a massively scalable, globally reachable, highly reliable platform upon which customers can set up omnichannel automation solutions in a secure and consistent fashion. It brings Omilia Conversational AI experience to any call center as a service platform provider.

OIDC

OpenID Connect is an identity authentication protocol that is an extension of open authorization (OAuth) 2.0 to standardize the process for authenticating and authorizing users when they sign in to access digital services.

OLA

Operating Level Agreements are internal agreements that a service provider defines for internal users to meet SLA. The OLAs would be used to track internal service commitments such as the response time for incidents or problems or availability of servers supporting various applications.

Orchestrator

Omilia’s software which allows users to combine existing miniApps to build and run a complete Dialog Application that can be further connected to a phone number or a chatbot to maintain a conversation. Orchestrator is a part of OCP®.

Output Field

A field elicited by a miniApp or Flow which is returned to the “parent” context as output.

Parameter

An argument sent to the API which helps to define the request and the expected response.

PBX

Private Branch Exchange, a private telephone network used within a company or organization.

PCI

Credit Card Identification, a short number that appears on your credit card apart from the actual credit card number.

PEM

Privacy Enhanced Mail, is the most common format for X. 509 certificates, CSRs, and cryptographic keys. A PEM file is a text file containing for example one or more items in Base64 ASCII encoding, each with plain-text headers and footers

Example

-----BEGIN CERTIFICATE----- 
MIIEnTCCAoWgAwIBAgIJAM1Hx4JJ1OgpMA0GCSqGSIb3DQEBCwUAMH4xCzAJBgNVw5XwmKAC+Vfm8tb7tMiUoU0yvK
 -----END CERTIFICATE-----

PKSC

Public Key Cryptography Standard published by RSA. Specifically PKSC12 defines an archive file format for storing many cryptography objects as a single file. It is commonly used to bundle a private key with its X.509 certificate or to bundle all the members of a chain of trust.

POST

The HTTP method for creating resources with a RESTful API.

PSTN

Public Switched Telephone Network, an agglomeration of an interconnected network of telephone lines owned by both governments as well as commercial organizations. It is also known as Plain Old Telephone Service (POTS). Originally, it was an entirely analog network laid with copper cables and switches. Presently, most part of PSTN networks is digitized and comprises of a wide variety communicating devices.

Prompt

A phrase used by a miniApp to greet a caller, encourage a conversation, discuss, clarify, or extract info from a caller.

PUT

The HTTP method for updating resources with a RESTful API.

Realizer (audio type)

An NLG mechanism that takes a value and generates the proper words in the discussion. For example, it converts 1987-07-03 to July, third, nineteen eighty-seven.

Regex

Regular Expressions, a pattern (or filter) that describes a set of strings that matches the pattern. In other words, a regex accepts a certain set of strings and rejects the rest.

Request (HTTP)

A message sent by the client to initiate an action on the server. An HTTP request consists of three elements: request line, headers, and message body.

Request line (HTTP)

The first line of the request message. In the request line we place the HTTP method to be used, the URI or URL of the request, and the HTTP protocol to be used.

Response (HTTP)

An HTTP response is made by a server to a client. The aim of the response is to provide the client with the resource it requested, or inform the client that the action it requested has been carried out; or else to inform the client that an error occurred in processing its request. An HTTP request consists of three elements: status line, headers and message body

Response Errors

Error or failure, either from a non-successful HTTP status, an error while executing the request, or some other failure which occurred during the parsing of the HTTP response. Error responses have status codes which indicate the error context. The status codes are defined by RFC 9110. If you receive a non-standard response which is not in the list, it is custom to the server's software.

Resource (HTTP)

A data set that an API allows you to work with, and which are accessible via endpoints. They have relationships with other resources as well as a set of allowed operations that you can carry out on them.

REST

Representational State Transfer, an architectural pattern for interacting with resources via HTTP methods.

Rich Content

Refers to additions in chat applications like buttons, a list of options, carousels and other UI elements to improve UX.

SAML

Security Assertion Markup Language is a standard for exchanging authentication and authorization identities between security domains.

Server

Software or hardware that provides a service by responding to requests across a network.

Sessions

Sessions refer to either the number of unique IVR calls or chat sessions (depending on the application), no matter how many invocations were triggered.

Set field

A building block that contains the configurable data from the caller (a field and a value) that can be transferred to other miniApps or building blocks and channel the conversation. The value of the Set Field building block can substitute the value of a previously used miniApp or building block.

SIP

Session Initiation Protocol, a signaling protocol used for initiating, maintaining, and terminating real-time sessions that include voice, video, and messaging applications. SIP is used for signaling and controlling multimedia communication sessions in applications of Internet telephony for voice and video calls, in private IP telephone systems, in instant messaging over Internet Protocol (IP) networks, and mobile phone calling over LTE (VoLTE).

SLA

Service-Level Agreement, a commitment between a service provider and a client. Particular aspects of the service – quality, availability, responsibilities – are agreed between the service provider and the service user.

SLO

Service Level Objectives, an agreement within an SLA about a specific metric like uptime or response time. So, if the SLA is the formal agreement between you and your customer, SLOs are the individual promises you're making to that customer.

SOAP

Simple Object Access Protocol, a message protocol that enables the distributed elements of an application to communicate. SOAP can be carried over a variety of standard protocols, including the HTTP.

Speech Recognition Grammar

Speech Recognition Grammar, a set of word patterns, that tells a speech recognition system what to expect a human to say. For example, a 4-digit grammar will except 4-digit numbers and a collection of sentence patterns that are the typical responses from callers to the prompt.

Speech-to-Text

A speech recognition software that enables the recognition and translation of spoken language into text through computational linguistics. It is also known as speech recognition or computer speech recognition.

SSO

Single Sign-On, an authentication scheme that allows a user to log in with a single ID and password to any of several related, yet independent, software systems.

Status Code

HTTP Status codes are what the server sends as the response back to the client with regards to the status of the request.

Status Line

The first line in the response message. It contains a status code, which is a three-digit number indicating the result of the request.

Transfer

A building block in Orchestrator that allows the deferral of the conversation to a real agent, a chatbot, or any other conversational system.

TTS

Text-to-Speech technology that allows a system to speak out loud a written phrase or sentence.

UAT

User Acceptance Testing, a type of testing performed by the end-user or the client to verify/accept the software system before moving the software application to the production environment. UAT is done in the final phase of testing after the functional, integration, and system testing is done.

UI

User Interface, the space where interactions between humans and machines occur.

URI

Uniform Resource Identifier, identifies a resource and differentiates it from others by using a name, location, or both. It contains components like a scheme, authority, path, and query.

URL

Uniform Resource Locator, identifies the web address or location of a unique resource. It has similar components to a URI, but its authority consists of a domain name and port.

Utterance

An oral or written statement.

UX

User Experience refers to the feeling users experience when using a product, application, system, or service. It is a broad term that can cover anything from how well the user can navigate the product, how easy it is to use, how relevant the content displayed is and so on.

VB

Vocie Biometrics, an OCP Console® feature that uses a person's voice as a uniquely identifying biological characteristic in order to authenticate them.

Voiceprint

A voiceprint is a digital representation of the unique vocal characteristics of an individual. It should not be confused with the audio, as it is a separate entity of a different type. The audio is a wave file, whereas voiceprint could be thought as a text file that represents the voice heard in the audio.

Web Service

A client-server application or application component for communication. There are mainly two types of web services: SOAP web services and RESTful web services.

WER

Word Error Rate, the ratio of errors in a transcript to the total words spoken. A lower WER in speech-to-text means better accuracy in recognizing speech. For example, a 20% WER means the transcript is 80% accurate.