Method for collecting data of word segmentation dictionary based on statistical machine learning method

The invention relates to the field of data processing foundations and specifically relates to a method for collecting data of a word segmentation dictionary based on a statistical machine learning method. The method comprises the steps that the machine learning method is applied; a classification idea is used to acquire a domain concept; a domain concept acquisition problem is deemed as a binary classification problem; the concept is acquired and processed; collected information or data is processed; an information database and an index database are established; data contents desired by a user are formed; a response is made to various types of retrieval proposed by the user; and information or relevant pointers required by the user can be provided. In this way, accuracy of information retrieval is increased. 本发明涉及数据处理基础领域，具体来说是种基于统计机器学习方法的分词字典数据采集方法，利用机器学习的方法，采用分类思想获取领域概念，把领域概念获取问题看成是个二值分类问题，进行概念的获取及处理，从而对采集信息或数据进行加工，建立信息数据库和索引数据库，形成用户想要的数据内容，对用户提出的各种检索做出响应，为提供用户所需的信息或相关指针，从而提高了信息检索的准确率和准确率。