#InterSystems Natural Language Processing (NLP, iKnow)

InterSystems' iKnow technology allows you to identify the concepts in natural language texts and the relations that link them together. As that's still a fairly abstract definition, we produced this video to explain what that means in more detail. But when meeting with customers, what really counts is a compelling demonstration, on data that makes sense to them, so they understand the value in identifying these concepts over classic top-down approaches. That's why it's probably worth spending a few articles on some of the demo apps and tools we've built to work with iKnow.

In the first article in this series, we'll start with the Knowledge Portal, a simple query interface to explore the contents of your domain.

I have a class with text property, which contains html text (usually pieces, so it may be invalid), here's a sample value:

<div moreinfo="none">Word1 Word2</div><br>
<a href = "123" >Word3</a>

When I add iFind index on text, there are at least two problems:

Hi Community!

Enjoy the video of the week about InterSystems iKnow Technology:

A Cure for Clinician Frustration

https://www.youtube.com/embed/johncrm-O0E
[This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]

Anyone can explain iKnow technology? Then Why iknow technology is uses a "bottom up" approach?

If you've worked with iKnow domain definitions, you know they allow you to easily define multiple data locations iKnow needs to fetch its data from when building a domain. If you've worked with DeepSee cube definitions, you'll know how they tie your cube to a source table and allow you to not just build your cube, but also synchronize it, only updating the facts that actually changed since the last time you built or synced the cube. As iKnow also supports loading from non-table data sources like files, globals and RSS feeds, the same tight synchronization link doesn't come out of the box. In this article, we'll explore two approaches for modelling DeepSee-like synchronization from table data locations using callbacks and other features of the iKnow domain definition infrastructure.

This earlier article already announced the new iKnow REST APIs that are included in the 2017.1 release, but since then we've added extensive documentation for those APIs through the OpenAPI Specification (aka Swagger), which you'll find in the current 2017.1 release candidate. Without wanting to repeat much detail on how the APIs are organised, this article will show you how you can consult that elaborate documentation easily with Swagger-UI, an open source utility that reads OpenAPI specs and uses it to generate a very helpful GUI on top of your API.

The iKnow documentation shows an example for adding sources to a domain after an initial loading of sources.

The example uses text files. However, our data is now in Cache SQL tables.

Is it possible to add sources from a Cache SQL table, and is there an example of how this is done?

Thank you.

A group of students at the Chalmers University of Technology (Gothenburg, Sweden) tried different approaches to automatically rating the quality of emergency calls, including iKnow.

Excerpt: "The most impressive results produced by iKnow is its ability to correctly classify 100% of the calls using the Average algorithm. This is quite surprising since iKnow only compares low-level concepts, how words relates to each other."

How to retrive the unstructure data using iknow concept in Cache . Given real time Example of these concepts?

This is the fourth article in a series on iKnow demo applications, showcasing how the concepts and context provided through iKnow's unique bottom-up approach can be used to implement relevant use cases and help users be more productive in their daily tasks. Previous articles discussed the Knowledge Portal, the Set Analysis Demo and the Dictionary Builder Demo, each of which gradually implemented slightly more advanced interactions with what iKnow gleans from unstructured data.

This week, we'll look into one more demo application, the Rules Builder Demo, in which we'll build on previous work but again climb a step on the level ladder, implementing a more high-level use case than in the previous ones. The idea came from an opportunity where we were asked to help the customer in the finance sector make sense of vast volumes of contract data. They wanted to semi-automate the extraction of logical rules from that text (in fluent legalese!), so they could be fed into other systems. While this was an exciting use case to work on (and more on it in this GS2016 presentation), we've also used it in other cases, for example to extract mentions of ejection fraction from Electronic Health Records.

In previous articles on iKnow, we described a number of demo applications (iKnow demo apps parts 1, 2, 3, 4 & 5) that are either part of the regular kit or can be easily installed from GitHub. All of those applications assumed you already had your iKnow domain ready, with your data of interest loaded and ready for exploration. In this article, we'll shed more light on how exactly you can get to that stage: how you define and then build a domain.

Presenter: Danny Wijnschenk
Task: Help people make better decisions by letting application deal with all the data.
Approach: As an example, we’ll extend a demo asset management application for portfolio and trade compliance, using iKnow technology to translate agreements into rules that ensure portfolio compliance prior to trade execution.

In this session, we’ll discuss how easy it is to extend a classic application that deals with straightforward transactions, to also offer insights and actions based on more complex, unstructured data. We’ll present a use case on portfolio compliance from the financial services industry.

Content related to this session, including slides, video and additional learning content can be found here.

Presenter: Dirk Van Hyfte
Task: Leverage unstructured data to improve how clinicians deliver care
Approach: Give real-world examples of organizations that are benefiting from using their unstructured data

This session will feature real-world examples of how healthcare organizations can benefit from exposing unstructured data to clinicians at point-of-care as well as to clinical informatics building predictive models. Presenters are Wesley Williams, PhD, Vice President and Chief Information Officer, Mental Health Center of Denver; Augie Turano PhD. IT Director Veterans Informatics and Computer Infrastructure (VINCI); and Dirk Van Hyfte, MD, PhD, Senior Research Consultant.

Content related to this session, including slides, video and additional learning content can be found here.