AKIN Natural Language Processing DEMO

Intents (Directives & Inquiries)

This page demonstrates AKIN's ability to detect intent. Intents are things like inquiries (questions) and directives (commands). In this example, the model only tries to detect the intent "GET INFORMATION FLIGHTS". In addition to detecting the intent, AKIN can also detect relevant "Expected Values" that are found within proximity to the intent, such as Departure/Arrival City, Airport, Dates, Times, and Airline specified by the user's input. Edit the text in the input box below and click 'Analyze Text' to see how well AKIN can detect this intent.

Only the following Airlines and Cities/Airports have been added to this demo's model:

Airlines: Alaska, Allegiant, American, Delta, Hawaiian, JetBlue, SouthWest, United, and Virgin
Cities: Seattle, San Francisco, Oakland, Los Angeles, Denver, Dallas, Phoenix, Miami, New York
Airports: SEA (Seattle/Tacoma), SFO San Francisco Intl, OAK Oakland Intl, LAX Los Angeles Intl, DEN Denver Intl, DFW Dallas Fort Worth Intl, PHX Sky Harbor Intl, MIA Miami Intl, JFK John F Kennedy Intl

Only the items listed above have been modeled and will be directly detected. This demo showcases AKIN's ability to detect these items when they are written in a wide variety of ways, including typos, misspellings, grammatical errors, or unexpected composition.

When an intent is detected, its node in the result tree will be colored differently. You can expand the node and see the "Expected Values" that were also detected in proximity and see how the values found were faithfully assigned to these "Expected Values".

Analyze Text

The demo above provides an example of the AKIN NLP API’s ability to sense and understand the conceptual meaning of free unstructured text, and output that understanding into structured standardized representations. Its high sensitivity leads to greater adaptability to variation than other technologies. Additionally, AKIN provides traceability information for downstream consuming systems and users, delivering unparalleled transparency.

Flight Information Examples

The following examples illustrate some ways a person might ask about flight information. They show how AKIN can adapt with agility and tolerance of a wide diversity and variation of human expression. This is "built-in" intelligence.

Example 1

In October I’d like to fly to Seattle… say… on the eighteenth… leaving from Oakland… show me flights on delta.

Example 2 (rambling speech)

I want to go to Miami… I’m in Seattle now… looking for flights… I’d like that to be on delta... and I want to leave on the 23rd of September.

Example 3

I'm thinking of going to Seattle in July probably around the 18th. I'd be returning later in October around the 25th. I'd like to see flights on Alaska.

Example 4

I want to go to Seattle. I'm in Oakland now. I want to see flights leaving on the 5th of next month and be back on the 13th. Let's fly on Alaska and leave in the morning, but I want to get back in the evening.

Example 5

I want to go to Seattle on the 23rd of next month. Show me flights leaving Oakland at 10:30 a.m. and arriving in Seattle at 12:30 p.m. Oh, and I’d like to fly American.

Example 6

What flights are leaving Los Angeles in the morning at 9 and arriving in Seattle at 12 in the afternoon?

Example 7 (very disjointed and out of order)

I want to be back on the 15th of October from Miami. I’ll be flying from Seattle to Miami on the 23rd of June. Show me flights on American... oh and I’d like to leave in the morning and return in the afternoon.

Example 8

Show me flights from Seattle to Miami on Alaska Airlines leaving on July 23rd. I’d like to depart at 10:00 p.m. and arrive in Miami at 6:00 a.m. I’d like to come back on the 15th of August at 8 p.m.

High Level Features

Built-In Artificial Intelligence: The AI model allows you to simply configure/add the concepts you want to detect and AKIN can use that information in combination with its built-in intelligence to detect and make inferences.
Direct Injection of Knowledge: Supports explicit knowledge and rules for interpretation of information or context.
Easy Configuration and Management: Configure models via API and Model Manager User Interface.
Tolerance of Textual Variations: Handles varied expressions, misspellings, and grammatical errors easily.
Transparency: Find out why something was or was not detected.
Built-In Native Concepts Types & Detection: Includes detection of intents, sentiment, descriptors, and actions.
Customer Defined Custom Entity Types: Allows complex entities with properties having multi-level hierarchies.
Advanced Inferred Concept Detection: Detects concepts based on other present ideas.
Command/Intent Detection: Detects concepts in both large paragraphs and short commands.
Advanced Noise Reduction: Optimizes performance with in-memory distributed processing.
Deploy Anywhere: Can be hosted on any .Net compatible platform.
Multi-lingual Support: Designed to work well across diverse language domains, including Asian languages.

Configuration

To configure AKIN, you feed it knowledge in the form of standardized values of concepts and ideas you want detected. Allows easy access and visibility of what it knows and doesn’t know.

Why do I Need Natural Language Processing?

Many businesses have large amounts of information that is unstructured or semi-structured. The goal is for users to be able to write or speak inquiries and directives naturally and have their systems understand and process this information.

Individuals express their thoughts in many unique ways, complicating whether downstream systems can understand and act on it. AKIN provides a reliable solution to this issue by enabling a standardized representation of concepts, enhancing communication between systems.

AKIN Natural Language Processing offers unexcelled accuracy and performance, allowing businesses to extract value from unstructured text and natural language queries.

For more information and licensing inquiries, please contact info@grappledata.com using a valid company/organization email address.