What is conceptSearch?
conceptSearch is a unique, language independent technology and is the first content retrieval solution to integrate relevance ranking based on the Bayesian Inference Probabilistic Model and concept identification based on Shannon’s Information Theory. Unlike other enterprise search engines that require significant customization with marginal results, conceptSearch is delivered with an out-of-the-box application that demonstrates a simple search interface and indexing facilities for internal content, web sites, file systems, and XML documents. Application developers experience a minimal learning curve and the organization can look forward to a rapid return on investment.Because of the innovative technology, conceptSearch delivers both high precision and high recall. This is particularly important for organizations who need sophisticated search and retrieval solutions. By weighting compound terms (multi-word) phrases, instead of the typical single words, or words in proximity, the retrieval experience is significantly more accurate and relevant. Much more powerful than single word, multiple words, or Boolean searches, the ability for the search engine to identify concepts enables the organization to improve the search experience for a variety of users.conceptSearch is incorporated into Concept Searching’s Smart Content Framework™ for information governance, which was developed as a toolset that provides the enterprise framework to mitigate risk, automate processes, manage information, protect privacy, and address compliance issues. The framework is being used to enable intelligent metadata solutions to improve search, records management, enterprise metadata management, text analytics, migration, and data security.
Benefits and Insights
Why use conceptSearch?
Key differentiators & advantages of conceptSearch
- Compound terms are extracted when content is indexed from internal or external content sources, enabling the delivery of greater precision of relevant content at the top of the search results- Relevance ranking display extracts from the documents based on the query and are returned to the user
- Search refinement delivers to the end user highly correlated concepts that may be used to refine the search
- Taxonomy browse capabilities are also standard
- Documents can be classified into one or more taxonomy nodes, enhancing the precision of documents returned
- In addition to static summaries, Dynamic Summarization, a modified weighting system, can be applied that will identify real-time short extracts that are most relevant to the user’s query
- Related Topics will return results based on the conceptual meaning of the search terms used. Using the ability to generate compound terms in a search, for example, ‘triple’ is a single word term but ‘triple heart bypass’ is a compound term that provides a more granular meaning
- Based on previous queries, or on extracts retrieved, end users can use the text to perform additional searches to retrieve more granular results
- The product is based on an open architecture with all API’s based on XML and Web Services. Transparent access to system internals including the statistical profile of terms is standard- Easily customized for your requirements