You have a question, a project?

Tell us more about it!

*
*
*
*
*
* : mandatory fields
Sinequa finds expertise and experts networks

Find Expertise and Networks of Experts

Most large enterprises are challenged when it comes to rapidly finding the best available experts on a given subject. They cannot rely on self-declared expertise in user profiles of their Enterprise Social Network, too often out of date, incomplete or exaggerated. Finding the true experts requires looking at their work: the footprint they leave in publications, project reports, patent filings, Enterprise Social Media content, emails, HR data and schedules, etc. Of course, this analysis requires Natural Language Processing (NLP) capabilities to "understand" what topics people have written about, rather than simply searching for keywords. Machine Learning (ML) algorithms help find similar user profiles and similar contents, increasing the precision of expert discovery and ranking.

In many large enterprises, this means being able to cope with Big Data. For example, 200 million documents and billions of database records at one of our customers.

User profile

The Sinequa Cognitive Search & Analytics platform can solve this problem: It does not rely on declarations but can sift through tons of text and data, identifying authors and concepts - beyond the actual words used in queries and documents. It will do so in safeguarding contents against unauthorized access. Cognitive Search & Analytics can also verify whether an author is consulted on his fields of expertise via email, and gage the volume of publications and correspondence. It can thus map implicit social networks of experts, and even create links between them.

A research-intensive bio-pharma company, like AstraZeneca or Biogen, has to deal with a vast number of highly technical and scientific data and documents, produced in-house and by others: medical databases, research papers, trial reports of all kinds, patent filings, internal notes, emails and other communications between researchers in different fields.

Complexity
The information to be treated covers a wide range of subjects: medical, pharmaceutical, biological, chemical, biochemical, genetic, etc. It may deal with diseases, genes, drugs, active agents, and mechanisms of action. A lot of the information is textual, but there may be structured information, like molecule structures, formulae, curves, diagrams, etc.

Volume
With external and internal information and data bases, companies may have to deal with about 500 million documents and the number of R&D experts may be in the range of 70,000 people and beyond.

Index of 500,000 documents indicating skills of people

If you need to find a network of experts, e.g. for a drug repositioning project, you will be looking for experts on the drug in question and on its Mechanism of Action (MOA), medical experts, geneticists, biochemists, etc. But where do you even start looking?

Leading bio-pharmaceutical companies turn to Sinequa for a next generation Cognitive Search and Analytics platform with content analytics strong enough to handle Big Data. The Sinequa platform is easy to use and keeps the complexities of interdisciplinary research "under the hood".

Pain points

  • High data volumes
  • Heterogeneity of sources
  • Highly technical content
  • Structured and unstructured data
  • Access security

Solution

  • Find expert networks, expertise and related documents in a few clicks
  • Map expert graphs
  • Index millions of documents and billions of records

Benefits

  • Accelerate research and time-to-market
  • Find specific networks of experts
  • Search, analyze and visualize relevant data, extracted from Big Data
  • Respect information governance and security

Share this