Content Enhancement & Knowledge Services

Technical Data Extraction

Description of services

Technical data extraction is the process of extracting properties, attributes, metadata and conceptual entities from unstructured technical documents such as patents and non-patent technical literature.

Specific scope offerings

Few examples of data that can be extracted from typical chemical and life science related documents are:

  • Systematic Chemical Names (IUPAC Nomenclature) with different spellings; Commas, Periods, Hyphens, Parentheses, Apostrophes, Plusses, Minuses and Greek Symbols
  • Common or Generic Names
  • Trade Names
  • Company Codes
  • Abbreviations
  • Fragmented Descriptors
  • Molecular Formula
  • Genetic Information

Scope Methodology

Scope uses the services of highly qualified and experienced professionals in chemical and life science domains for technical data extraction and these professionals are assisted by automated tools that help in automated pre-processing, data capture, data validation workflow optimization, data validation and quality control.

Client Benefits

With this niche service, Scope helps clients to create exclusive and path-breaking information products in various fields such as Chemistry, Life Sciences, Pharmaceutical Science and Medicine. The technical properties extracted from unstructured content can be used to create structured databases, annotate and semantically enrich content with more information on the properties and attributes of substances and compounds of chemical and biological entities.