摘要 |
Four phases are executed, which are (A) summing from a target file group (F), (B) sorting in the descending order of appearance frequency, (C) extracting until the rank having an intended appearance ratio, and (D) creating a map. (A1) First, an information generation device reads the target file group (F) and counts appearance frequencies of basic words. (B1) When the counting of basic words is complete in the target file group (F), the information generation device sorts the basic word appearance frequency table (101) in the descending order of appearance frequency. Namely, the basic words are sorted in the order from highest appearance frequency, and ranked from the basic word having the highest appearance frequency. (C1) Next, the information generation device refers to the sorted (B1) basic word appearance frequency table (101), and extracts basic words until the rank having the intended appearance ratio (Pw). (D1) Lastly, the information generation device generates a specific basic word appearance map (M1) regarding a specific basic word group. |