Development of A Natural Language Based Transportation Network Blockage System

• Main Authors: Yi-Fang Yu, 游怡芳
• Other Authors: Chin-Hong Sun
• Format: Others
• Language: zh-TW
• Published: 2001
• Online Access: http://ndltd.ncl.edu.tw/handle/50277738944253347911

碩士 === 國立臺灣大學 === 地理環境資源學研究所 === 89 === Numerous of natural disasters had attacked Taiwan and caused severe damage and losses in the past and it is not surprising that the natural will strike again. However a more effective response can significantly reduce the damage and losses. One key point for effective response is the blockage information of the transportation network. Currently the officials had combined GIS system with their blockage information system by using digital maps, either in grid format or vector format, as background for display. Two different ways are used to generate the blockage records. One way is to identify the blocked location from digital map by an operator and then key in manually. The other way is to identify the point on digital map automatically by key in the coordinate of the blocked location. Both have their disadvantages. The first one is lack of accuracy and waste too much time while the second one is that it is not easy to get the coordinate value from current reporting system. It is used to every one to report a block situation by verbal descriptions such as cross section of two roads or mileage of certain route. Starting with classifying different type of reporting description and analyzing the construction of the description, this research is aimed to study the possibility in combining a natural-language concept and GIS system to establish a system that can parse the verbal description and identify the reported location automatically. The prototype of the system has been established. By key in a description with geographical meanings, the system can identify the location on the digital map automatically and save it as a point record. A case study of Wen-San district of Taipei city has been done and demoded in this thesis.