Identification process for locating and sorting document in different languages - processing information by comparing sequences of characters with those of a reference document

摘要

The documentation identification system provides a means of identifying, locating and sorting the contents informations that can be in the form of language or symbols. A first stage of the process involves the execution of an algorithm that identifies the specific language of the document. For this a character sequence is obtained and is compared with other character sequences from a reference document. The reference can be structured for a number of different languages. Each of the obtained character sequences are assigned weighting values. The repeated comparison generates results that are accumulated to signal identification. ADVANTAGE - Identification without code words or context information.