|
|
Taxonomic content is the key to next generation
Content Intelligence solutions. Building a taxonomy for most organizations
can take 2-3 hours per concept, resulting in taxonomies too small
and restricted to cover the entire business effectively. Previous
attempts at automation failed to provide taxonomies with the embedded
knowledge that experts provide.
Intellisophic has developed
a disruptive technology for creating deep, authoritative reference
content on any subject area. Unlike other methods for taxonomy
development which are limited by the expense of corporate librarians
and subject matter experts, Intellisophic content is machine developed,
leveraging knowledge from the world's most respected reference
works. Through this patented process, we have created the largest
library of taxonomic content, covering several million topics
defined by hundreds of millions of terms.
Our taxonomy library is
constantly growing with the addition of new titles and
publishing partners. Currently contributing to our library are
esteemed reference publishers like John Wiley & Sons, Thomson Gale, Oxford University Press, Pharmaceutical Press, Woodhead Publishing, WorldBook Encyclopedia,
Encyclopedia Britannica, C. Hurst and Company, Aspen Publishers
and American Society of Microbiology.
The taxonomies are delivered
in a variety of commonly used formats such as XTM (XML
Topic Map) format, OWL (Web Ontology Language) and RDF (Resource
Description Framework). Intellisophic can also customize this
format for specific applications such as Inxight, Mark Logic,
Convera, Verity, among others. These taxonomies provide a table
of contents for navigating the concept tree as well as concept
signatures that are essential for identifying all concept instances
in a text document. In other words, the taxonomies are rich with
content, organized for effective usage and easily integrate into
existing applications.
Intellisophic provides
taxonomic content and technology that enables the systematic use
of unstructured information. Detailed taxonomies are necessary
to derive understanding from unstructured data sources. Without
taxonomies, companies are left dealing with unstructured data
as a collection of words. By using detailed taxonomies, businesses
can map taxonomies into structured entities knows as concepts.
The heart of Intellisophic’s
technology is the identification of concepts inside unstructured
data. A concept is any abstract thought or idea. A concept
is defined by a collection of words and phrases that distinguish
one concept from another within a specific taxonomy.
For example,
a concept like ‘balance sheet’ in a business
taxonomy might look like: liabilities, balance sheet, owners,
realizable, balance, sheets, consolidated, total current, amount
of cash, balance sheets, payable, assets, current, current liabilities,
historical cost, current assets, owners equity, consolidated balance
sheet, valuation, sheet
These terms, when taken
together, define the distinguishing characteristics for this concept.
A collection of concepts that define a specific area of
knowledge is referred to as a concept taxonomy. Typically, this
is represented as a hierarchy of concepts.
A number of taxonomies
grouped together in the same business area, define a subject area.
Intellisophic technology uses concept taxonomies to identify the
existence of concepts in unstructured data, whether or not the
word ‘balance sheet’ is contained in the data. Once
identified, these concept attributes are stored in a relational
database where they can be queried for search and understanding,
trend analysis, data mining or enrichment with other structured
data.
Intellisophic taxonomies
can be used by themselves or in combination with company specific
taxonomies. Intellisophic’s team of experts will
evaluate the customer and pick the right combination of taxonomies
to meet the business needs. Taxonomy details can be found by following
the sector of interest below:
|
