AKIN Natural Language Processing DEMO

Intents (Directives & Inquiries)

(Extremely tolerant of variation)

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" as shown in this example screenshot:

Please input text below and test AKIN. A starting example of input text has been provided for you in the input box below. You can edit or replace it. The results are sorted by high relevance items first and then by word position.

First please confirm that you are not a robot to start.
The first call to the service may take a moment to bring the service up. After that, all subsequent queries to the service should be fast, unless there is a long pause in between queries.

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. It's 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. The traceability info shown in this demo is only a small sample of the full set of information that AKIN provides to consuming systems.

The following examples illustrate some ways a person might ask about flight information. They show how AKIN can adapt with agility and tolerant of a wide diversity and variation of human expression. This is "built-in" intielligence. Notice how AKIN is able to adapt to rambling and disjointed speech that is more like real-world scenarios. Most of us don't talk like robots. Our software and robots should be able to adapt to us instead of us having to become robots.

Also notice that AKIN is able to very intelligently extrapolate values like numbers, ordinals, and  dates without any training necessary. It can also even infer dates from surrounding context and assign them to the appropriate expected value types. To see how it does this, just copy and paste the example below into the input text box above and click the "Analyze Text" button, or create some of your own.

While certainly not perfect, AKIN takes accuracy and agility to a whole new level and sets the bar very high. In that vein, we challenge you to take the examples below and put them into any of your favorite personal assistants and see how well THEY can handle this input.

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… im in seattle now… looking for flights… id 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. Id be returning later in october around the 25th. Id 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. Lets 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 pm. Oh, and id 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 id 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. Id like to depart at 10:00 pm and arrive in miami at 6:00 a.m. id like to come back on the 15th of august at 8 p.m.



High Level Features:
  • Built-In Artificial Intelligence
    • There is no need to do the tedious and expensive work of testing and selecting machine learning algorithms and approaches that end up being brittle and blind to unexpected variations, tagging thousands of records, or train the AI. The concepts you want to detect are directly injected, and AKIN uses that information along with its built-in intelligence to detect those concepts.
  • Easy to configure and manage Domain Knowledge Models
    • Directly via API and Model Manager User Interface
  • Extremely tolerant of textual variations
    • Varied expressions, mispellings, and grammatical errors
  • Highly Transparent Model
    • Easy to find out why something was or was not detected, and make necessary adjustments or improvements
  • Built-In Native Concepts Types & Detection
    • Intents, Sentiment, Descriptors, Actions
    • Numbers, ordinals, dates/times, timespans, units of measure & account, assignment & equality operators
  • Customer defined custom entity types
    • Complex Entities with properties having multi-level hierarchies and multiple relationships
    • Graph + Hierarchical Relationships
  • Advanced Inferred Concept Detection
    • Some concepts are not explicitly stated but inferred based on the presence of other concepts and ideas
  • Command/Intent detection and user interaction
    • Detects concepts in large paragraphs or documents of text, as well as shorter user commands or intents equally well
  • Advanced Noise Reduction
  • Highly Optimized Performance
    • In-memory distributed processing
    • Sub-second response times
  • Deploy Anywhere
    • API dll can be hosted on any .Net compatible platform in the cloud or on premises
  • Multi-lingual support
    • Although currently only certified for English, AKIN has been designed to work extremely well across cultural 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 and fed to your downstream consuming systems. This is done either through easy to use API functions/methods, or via the Model Manager UI. Additionally, you give it synonymous and related terms for the concepts you define. AKIN uses this knowledge to make smart determinations about the text you want it to analyze. You don't have to spend hours tagging up thousands of records to "train" it in a haphazard, disorganized way. You directly feed it knowledge in an orderly fashion, and you can always see what it knows and what it doesn't know. Then, AKIN uses its sophisticated probabilistic AI to detect concepts and ideas within the text even when there are a lot of variations in the way something is written, such as spelling and grammatical errors.

Why do I Need Natural Language Processing?

For many types of businesses a large amount of information is still collected, bound up, and stored in unstructured or semi-structured text. Every year, businesses spend enormous amounts of money attempting to successfully manage and extract value from this data, that frequently require manual efforts enhanced by discovery technology that often feels rudimentary and inadequate.

Additionally, businesses and application developers are looking to create more natural interactions with their information systems for consumers, customers, and their employees. They want the ability for users to be able to write or speak inquiries and directives naturally, and have their information systems understand and be able to process this information. This is no easy task.

The problem is that everyone communicates differently. Individuals express their thoughts, ideas, and concepts in so many different, non-standard, unique, and individualistic ways. Exacerbating the problem, people also make mistakes, or speak different native languages leading to unexpected grammatical structures when they write or speak (speech to text). For example, in a medical domain people may have symptoms or issues they express in different unique ways. Several people might describe the issue of having difficulty breathing in a number of ways:

  • “I have a hard time breathing”
  • “Sometimes it’s painful when I inhale”
  • “I find myself gasping for air”
  • “There are times when I can’t catch my breath”
  • “It hurts to breathe”
  • Etc.

Downstream consuming software systems need to be able to understand those concepts and do things like alert key stakeholders or gather significant data for analysis and research. However, those downstream systems need a standardized representation of these concepts, in this case the symptom we describe above, something like “Difficulty Breathing” or “Labored Respiration”. Having a single representation of this symptom makes it extremely easy for other systems to use this information in a structured way.

AKIN Natural Language Processing provides unparalleled accuracy and performance allowing your business to effectively extract the value from your unstructured text and natural language queries. There is no need to rely solely on centralized Cloud-Only-Based solutions like Google, Alexa, or Cortana that tie you down to an ecosystem and take your data out of your hands. With AKIN you can host anywhere on-premises, and use any speech to text technology with it, like Dragon Naturally Speaking, and those already freely available on mobile devices.

AKIN has been designed to be super intelligent and high performance, and yet still be very lightweight and efficient. It can even be hosted directly on mobile devices or very lightweight client Virtual Machines.

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