Recognition of tourism documentation fragments from web-page posts

Recognition of information from web pages is an important task for tourism activity support. This article dwells upon procedures for recognition of tourism documentation fragments from web pages of open web resources. These procedures are based on the methods of decomposition and synthesis of the sets of thematic syntactic structures of web page posts. Semantic structures are separate sentences or tagged text fragments. This is feature of the developed approach to the identification of useful tourism information from web pages.