GNOSS Sherlock: an Cognitive Intelligence tool for machines to understand us

GNOSS Sherlock: an Cognitive Intelligence tool for machines to understand us

Processing natural language, automatically generating Knowledge Graphs and querying systems, analysis and recommendations based on entity recognition and linking, and knowledge discovery.

GNOSS Sherlock collaboration accelerates and intensifies capacities for collective anticipation, learning and adaptation. Sherlock helps companies to make better, more confident decisions.

GNOSS Sherlock Components:

Sherlock-NERD-NLU. Natural Language Understanding System

Sherlock Named Entity Recognition and Disambiguation (NERD) is a compilation of APIs that allows for the processing, comprehension, interpretation and analysis of natural language known as Natural Language Understanding (NLU). NLU means recognising, extracting and disambiguating entities, concepts and key words in structured and unstructured texts.

Sherlock-NERD-NLU. Natural Language Understanding System --  NERD-NLU

1. What is NERD-NLU? Named Entity Recognition and Disambiguation (NERD) is a compilation of APIs that enables textual analysis through natural language processing and interpretation (NLU).

NERD-NLU locates, contextualises, classifies and disambiguates the entities designated within a text, offering:

  • An engine in the form of an entity recognition and disambiguation service that understands natural language and is able to analyse texts and extract metadata, such as concepts, entities or key words, based on their content.
  • Learning and training services aimed at building personalised language processing models that achieve results in specific and private knowledge domains.

2. How does it work?

  • NERD identifies, disambiguates and extracts entities in a text based on the recognised context in which they appear, where confidence is expressed by a percentage.
  • The greater and richer the context, the more confident NERD will be (providing higher percentages) when relating the suggested and extracted entities.
  • NERD employs disambiguation enhancement engines, a system of tools that boosts its confidence and success rate.

3. Performance and Scope of Service

  • Speed. The NERD-NLU solution was devised for processing large volumes of information in very competitive time frames:
    • The New Testament - 1,000,000 characters and 10,000 lines - analysed in less than one minute.
    • Able to produce a set of metadata to represent any text with a volume of less than 5,000 words in less than one second.
  • Flexibility:
    • The NERD-NLU solution is capable of identifying and extracting entities from any published text, whether produced by a media outlet, a renowned cultural institution, educational publishing houses or any other organisation.
    • NERD-NLU offers the same performance for private knowledge sources or areas on the basis of initial training that incorporates the necessary contexts for interpretation into the service.  NERD-NLU uses Machine Learning technology to learn from and accompany knowledge evolution in every area.

Sherlock-Connect. Connecting Data System

Connect builds a dynamic Knowledge Graph from a given digital resource in real time, making it possible for machines to incorporate it in semantic computing processes. 

Sherlock-Connect. Connecting Data System -- Connect

What is Sherlock Connect?

The Connect service is designed to generate a dynamic Knowledge Graph from a specified digital resource in real time. This Graph links and relates the entities extracted from the resource.

Connect functions as an API, receiving basic data from the resource and returning information in a suitable format for the visualisation type selected by the user.

Sherlock-Connect offers:

  • Highly-personalisable service. The user can configure the kind of resources and relations to be displayed, making Connect adaptable to any type of project.
  • The option of working with any NLU system, making it simpler for the client to choose the publication and extraction service they prefer for entities, concepts and key words.
  • Continued upgrades to the dynamic graph of a specified entity with the latest data and relations affecting this knowledge domain, all based on an automatic learning system.

Sherlock-Discovery

Discovery makes it easier to unearth and discover hidden knowledge from an organisation dataset by enriching it with related third-party information.

Sherlock-Discovery -- Discovery

What is Sherlock-Discovery?

Discovery is an API for the construction of an advanced Graph that interlinks and consolidates the entities in a repository, enriching them with third-party content.

  • Discovery extends Connect’s capacity, making it possible to enrich the resource-specific dynamic Knowledge Graph with third-party content (from DBpedia-Wikipedia or Geonames for example) or other, more specialised knowledge bases, including ones belonging to the client.
  • Discovery enables the individual creation, reading, updating and deletion of resources.

Sherlock Connect and Discovery Administration

Users can configure the following options on the Connect and Discovery administration panel:

  • Number of levels and nodes in the Graph.
  • Properties used to generate the Graph.
  • Types of entities to be displayed in the Graph.
  • Private client datasheets to be integrated into the Graph (only available with Discovery).

Sherlock-Visualizer, Entity Navigator and Data Analytics

Graph Visualizer and Entity Navigator is the visual counterpart to Connect and Discovery. Providing humans with a rich palette with which to query, navigate and visualise Knowledge Graphs, the Graph Visualizer and Entity Navigator facilitates exploration from different interests and points of view.

See more

Sherlock Data Analytics is a highly specialised graphics-based visualisation service aimed at consolidating and supporting organisational Business Intelligence (BI) processes.

See more

Sherlock-Visualizer, Entity Navigator and Data Analytics -- Data Visualizer and Analytics

Sherlock- Graph Visualizer and Entity Navigator

Sherlock- Data Visualizer

Graph Visualizer and Entity Navigator is the visual counterpart to Connect and Discovery. Providing humans with a rich palette with which to query, navigate and visualise Knowledge Graphs, the Graph Visualizer and Entity Navigator facilitates exploration from different interests and points of view.

This service includes the following views:

  • infoboxes
  • dynamic graphs
  • boxes with contextual information
  • timelines
  • maps

Sherlock- Data Visualizer: Plugin

Graph Visualizer and Entity Navigator can be incorporated into any website using a plugin endowed with a library that encompasses all the necessary functions for painting Graph views into any website. All the user has to do is tell the library the website area where it should display the view, which service they want it to use, and the selected view.

Sherlock- Data Visualizer: Publishing options

Multiplatform

API REST: Available for use by any developer in their projects.

JavaScript Library: Compresses API calls, simplifying use and integration.

Specific platforms

  • WordPress
  • Joomla
  • Drupal
  • Liferay

Sherlock- Data Visualizer: Performance

Capacity

  • Calculate densely-related 1000-node Graphs in fewer than 10 seconds
  • Fast on-screen representation through visualisation rendering in times of less than 1 second for problems like:
    • Dynamic Graphs: 300 full screen entities
    • Map: +500 entities around the globe

Sherlock - Data Analytics

Sherlock- Data Analytics

Sherlock Data Analytics is a highly specialised graphics-based visualisation service that can be integrated using a plugin on any third-party website.

It enables the aggregation and integration of information scattered among different areas in the Knowledge Graph with a strong focus on consolidating and enhancing organisation Business Intelligence (BI) processes.

It can produce any type of personalised report.