The First True Concept Search Engine
Knowledge workers need to identify content in the context of what they are seeking. The fundamental problem with most enterprise search solutions, and all statistical search solutions, is that they are based on an index of single words. Yet most queries are expressed in short patterns of words and not single words in isolation which are highly ambiguous.
conceptSearch can isolate the key meaning that is normally expressed as proper nouns, nouns phrases and verb phrases. The technology can accept queries in natural language with the user typing words, phrases or whole sentences. The system then analyzes the natural language query to extract the keywords and phrases to identify the main concepts and retrieve content that is highly relevant.
Consider the following examples:
|
Isolated Words
|
Concepts
|
|
New
|
New York City
|
|
Dealing
|
Insider dealing
|
|
Company
|
Company securities
|
|
The isolated words have no real meaning since they are ambiguous out of context whilst, in contrast, the two and three word phrases have clear meaning. With conceptSearch the stemmed versions will also be valid e.g. Deal, Deals, Dealing, Dealings.
conceptSearch automatically identifies the most significant patterns in any text and uses these compound terms to rank results based on an understanding of meaning rather than simply based on finding the required words. This is significantly more adaptive and flexible than exact phrase or proximity searching. Queries can be expressed in natural language, with no need for complex query syntax associated with traditional Boolean techniques.
conceptSearch is the first true concept search engine in that it combines Bayesian Inference with Shannon's Information Theory to correctly weight not only single words but also compound terms (i.e. multi-word phrases). Since most concepts are expressed in short phrases, rather than in single words used in isolation, our unique technology is being used to build ground-breaking applications.
Collateral: conceptSearchAutomatic Metadata GenerationWatch this
webcast to find out more about our unique technology.