The NLP process of extracting information from documents is done through the following processes:

Unstructured text:
From text documents in different formats processes are performed to divide the whole document into different syntactic units.

Entity Extraction:
The main factors in the sentences are detected

POS Tagging:
Identifying the parts into which each sentence is divided

Syntactic analysis:
We obtain the relations and dependencies of each of the actors involved in the sentences.

Semantic Role Labeling:
Used for the detection of the role arguments of a sentence for a given context automatically.

Machine Learning algorithms are used to understand the data and what it tells in the context of the whole Knowledge Base.

Topic Modeling:
It learns to capture the statistical distribution of attributes among the users and items, and generates a number of topics or dimensions.

Matrix Factorization:
This technique is used in recommendations engines, to compute predictions of how much a user would find an item or another user useful

everis knowler provides several components for extracting data, transform it, generate new knowledge with different techniques of artificial intelligence, and store it in an RDF format. everis knowler defines different workflows depending on its origin and type:

Data to Knowledge Flow:
This flow is applied to data in Relational Databases, Information Systems and other stores where the information is structured. This technique allows to turn the information structured into a relational database model based on triplets.

Text to Knowledge Flow:
It’s the extraction process to apply on documents and other unstructured elements such as e-mails, actions of users, etc., processing and loading in the ontology.

The extraction of unstructured data is done via a connector to Office 365, or any other data source that allows access to all content stored on the platform such as e-mails, documents stored in OneDrive or SharePoint, communities, MS Teams, etc.

everis knowler offers personalize content to each user, using different techniques:

Recognizing salient attributes of the profiles of users, documents or any entity.
Recommendation algorithms that model user likes and preferences, to offer them their most relevant items.
Text to Knowledge Collaborative algorithms, to identify similar users to a given user, in order to offer them more suitable results.

everis knowler adapts to the needs and characteristics of each client. Allows to adjust the platform to the changing environment of the organization, taking the most suitable and efficient technology.

everis knowler integrates natively with Microsoft Suite through the collaboration agreement between everis and Microsoft to develop a Smart Knowledge Management solution on Office 365 and Azure. This solution combines Artificial Intelligence technologies with ontologies to extract both structured and unstructured data contained in any document Word, Excel, PowerPoint, pdf, mail or agenda, as well as in any database of the company. everis knowler contemplates searches using natural language and establishes relationships between different documents and indexes them to offer the useful information.

everis knowler has a base platform across all SharePoint environments to connect to data. everis knowler is an integrated solution whose standard option is Public dedicated cloud / SaaS and can also be installed on-premise. everis knowler integrates natively amplifying the capabilities and functionalities of Sharepoint. In hybrid installations everis knowler synchronizes the ontologies to ensure a revolutionary reading and understanding across all environments. Due to Microsoft has the most complete cloud solution of the market, the PaaS/Iaas integration guarantees an accomplished and fully scalable functionality thanks to the powerful of Azure.