An insight engine is a tool that reveals and make available key information hidden in your data.
The detection of those key information is an important step toward a better organisation and a faster access to the information you need.

But why do we need this new kind of tool when search engines are well-known solutions ?

WHY NOT A GOOGLE FOR ENTERPRISE ?

To work, the World Wide Web search engines can rely on millions of user data and behaviours recorded.

They can conbime these user related data with the massive data that is indexed and structured (using for example entity recognition on images and text).

But inside the firewall of a company it is a truly different story.

There are number of situations that are misleading for a search engine :

• User behavior can change along the day as people have multiple role in the company
• The author of a document is hard to find as document template are usually reused with the very initial author,
• The number of internal code and IDs make the understanding difficult,
• The use of generic accounts in lab make impossible the assignment of the data to the operator
• Multiple data migration have caused a lost of the context

Applying general rules of ranking, classification and detection, if the context and history are not understood, will mislead the end user.

On the other hand, apart from the work on image recognition, few echo is made on the work a company like Google has spent to analyse and curate the data they index. But we can for example mention their implication in structuring web data*.
In a company, the format of data can be even more diverse. In particular in life science where data are even more diverse. Data curation and annotation processes are mandatory.

In this context, we can say that indexing the data is just not enouth.

(*) https://developers.google.com/search/docs/guides/intro-structured-data

WHAT IS REALLY THE DIFFERENCE BETWEEN SEARCH ENGINE AND INSIGHT ENGINE ?

• The capacity to understand the meaning of your data instead of just extracting the text, leveraging your existing IT systems,
• The capacity to visually represent how data are spread over their main theme,
• The capacity to combine searches and information from different sources,
• The capacity to find correlation between data,

This last point really make the difference. To be concrete, when a search engine can answer questions like :
“Where are the data mentioning the project PR28?”
Insight Engines, thanks to Naned Entity Recognition and semantics can answer to questions like :
“What are the biomarkers identified in the project PR28?”

You will find at the end of this post few illustrations of how our software, Inquiro, handle these features.

WHY DO YOU NEED AN INSIGHT ENGINE ?

• If you have difficulties to find data generated by your colleagues,
• If you have the impression you already have data that would help you taking better decision but with no idea of where they are,
• If you have the impression to spend a lot of time setting up a data organisation but finally someone always complain that it does not fit their needs,
• If you want to get better understanding of what a set of data is about

When in all these situations, you should be interested by an Insight Engine

FINALLY HOW DOES THE SET UP GOES ?

Well this is exactly what you will learn in our next post so stay tuned !

FIGURE 1 : A ANNOTATED FILE IN INQUIRO

(Clic to enlarge image)

FIGURE 2 : DYNAMIC DATA REORGANISATION BASED ON METADATA:

(Clic to enlarge image)

FIGURE 3 : INFORMATION CORRELATION IN INQUIRO

(Clic to enlarge image)

If you’d like to talk to us about how we can help you make your scientific data more valuable, please follow the contact link on the top bar to arrange a call with one of our data management experts

Erwan David, Co Founder