Unique Similar Search

SoftInform Search Technology – a document search technology developed by SearchInform Technologies, that searches documents based on their content similarity to the query document. It lets you conduct a quick and precise search of similar content documents in any volumes of data. This technology was developed based on a mathematical model of analyzing the structure of the document and picking similar words, phrases and text extracts. In result, the application displays documents with the maximum similarity to the query text and shows the percentage of relevancy to the query. As opposed to the standard phrase search, with similar search you won’t need to think through the query key words since the search is conducted with the whole document acting as a query. The technology works with various information sources, which may exist in formats like txt, doc, rtf, pdf, htm, html, in databases of the majority of widely spread systems like Access, MS SQL, Oracle, as well as any DBMS, supporting SQL. Stemming, thesaurus and “important words” features, helping you specify the search, are also included in the application.

The similar search technology lets you significantly decrease the time wasted on data processing the duplicate data when first inserting it into archive, save the time spent on search and going through the same documents over and over again, as well as categorize your documents by theme. In addition to that, this technology from SearchInform Technologies Inc. is not at all as sensitive to the capacities of your computer as other existing tools and processes data with an exceptionally high speed even on your average office computers.

This technology is not anymore underway. It has been tested and is successfully used in, for instance, a project offering legal advice by phone, where the speed of information search is extremely critical. This technology will definitely be useful in any information base, as well as analytical services and support services of a large enterprise. SoftInform Search Technology’s flexibility and efficiency let it solve a large specter of problems arising when working with the information. This as well as fuzziness of information content (when inputting documents into the database it quickly recognizes whether it’s a new document or a duplicate of an already existing one), analysis of similarity with the previously inserted into the database documents, and the quick search of thematically similar documents saves the time spent on selecting the proper keywords and looking through the irrelevant documents.