Intelligent placename recognition technology based on statistical model

Abstract

The invention relates to a placename recognition technology, and provides an intelligent placename recognition technology based on a statistical model. The intelligent placename recognition technology based on the statistical model comprises the steps that firstly, a basic word segmentation sequence is obtained and placenames are labeled in a statistical probability model and dictionary mode, then, some placenames are determined at first through independent placename recognition, then, superior and subordinate placename recognition, placename statistical model context recognition, placename ambiguity elimination in person names and other information are adopted for screening placename quality for the passible placenames, and finally statistical analysis is carried out on the placenames recognized in the full text so as to further filter out mistaken placenames. According to the intelligent placename recognition technology, various flexible modes for placename description by means of Chinese are fully utilized, the higher accuracy of practical levels is provided for placename recognition, and forceful help is provided for text division according to geographic attributions and mechanism recognition.

Description

technical field [0001] The invention relates to the technical field of place name recognition, in particular to an intelligent place name recognition technology based on a statistical model. Background technique [0002] The current place name recognition technology is mainly the way of place name keyword matching. However, due to various reasons such as the flexible description of Chinese place names, the names that are originally place names cannot be recognized in place name recognition, or non-place names are misidentified. The limitation of toponymy technology has brought great difficulties to the division of article regions. [0003] There are usually three ways for the human brain to recognize place names: matching known place names, guessing unknown place names based on internal composition, and only guessing unknown place names based on context. In previous studies, these three means are often integrated into statistical and rule systems in different combinations....

AI Technical Summary

Problems solved by technology

According to the action mechanism of human brain recognition, it is applied to the place name recognition technology. At present, there are mainly the following existing technologies: 1. The automatic recognition of Shen Dayang's Chinese place names adopts a statistical model, uses attribute matrix and frequency level to screen, and achieves a relatively high level of recognition. High recall rate, but low precision rate; 2. Liu Kaiying's automatic word segmentation and labeling of Chinese texts adopts a corpus-based method, and uses geographical names dictionary to statistically analyze the information of place names and the use of program information in real texts for place names. Recognition has achieved a certain effect on place name recognition, but there are still the following deficiencies: the detection of flexible description methods for place names is not comprehensive; the interfering information in place name texts cannot be accurately distinguished (such as place names in person names); 3. Tan Hong Ye Research on Method of Automatic Recognition of Chinese Place Named Based on Transformation, on the basis of technology 2, this prior art proposes an exchange-based place name recognition method, which obtains the rules of the place name context and screens the rules. The method effectively improves the accuracy of the system, but there are still the following shortcomings: the quality of recognition depends on the known context rules; the process of adding new context rules is more complicated

Images