Below are the most important terms we use in the descriptions, this is not a complete list, but it will give you a better understanding of the general issues explained, for all cases:

• Data - processed information given priority, weight, and a component or whole that proves the correctness of the conclusion made. We consider data to be the results of analyses, including predictions.
• Data mining - digging into data, a standard term familiar to big data analysts. Data mining is used to find patterns and relationships in structured data - e.g. from ERP systems, CRM, accounting applications, spreadsheets.
• Digitization - the meaning of this word will always refer to the transfer of physical (paper) documents into a digital form (e.g. a scan).
• Information - An unspecified and uncharacterized value that has not been processed (raw). Information is used to perform analyses, and all available information creates Population.
• Knime - is the name of a free solution for advanced operations and analysis of large collections of information. It is an advanced environment that provides the full range of tools used in BI.
• NLP (Natural Language Processing) - a collection of technologies used to analyze text according to a general or predefined dictionary (e.g., SJP, synonyms.pl).
• OCR (Optical Character Recognition) - the basic technology used to convert a scan as an image into text.
• Population - is a term for the total unspecified information that we may obtain from a customer. The population can consist of contracts, reports, invoices, emails, photos, headlines, and any other information in the form of text, graphics, or audio.
• Sample/group - in the cases described, we will call a group or sample a specific set of information that has been selected from the population and will be further analyzed.
• Text mining - a term describing digging into unstructured data and transforming them into structured data suitable for analysis - such as text data from emails, documents, social media presentations, or websites.