A computer receives a search query from a user for finding a resource. The computer extracts one or more words from the search query using morphological analysis. The computer assigns at least one first category to at least one first word of the one or more words using a dictionary. In response to identifying an unknown word not in the dictionary within the one or more words, the computer searches for the unknown word on a net. If the unknown word is found on the net, the computer obtains a description on a page on the net on which the unknown word is found, extracts one or more second words from the description using morphological analysis, assigns, using the dictionary, at least one second category to the one or more second words extracted from the description, finds, among the one or more second words, a particular word to which a predetermined category was assigned, extracts a correlation word from among the one or more second words having a high correlation with the found particular word, and finds, among the first words, a search word assigned the at least one first category that is the same as the predetermined category, finds, from a repository, resource data or worksite data using the correlation word and the search word, and lists the found resource data.