The Study Of Personal Information Retrieval

With the development of Internet, the volume of information and the number of information sources are continuously increasing, information retrieval (IR) has become one of the most important jobs of our daily life. Now, using the advanced IT technology, most activities of IR are accomplished through the Search Engine, Information retrieval system, filtering system or Agent. Thus, it is critical to have an efficient tool for retrieving information from various data repositories such that correct information can be collected within reasonable time duration.In order to be efficient, a research tool must be able to filter information and refine the search in accordance with the profile of the user. So the need for information management system or information retrieval system that provides relevant information for specific person is emerging. But, the current and conventional search methods have many problems because of the characteristics of the Internet environments and the disadvantage of the study of personal information retrieval method.This dissertation investigates the theory and method for personal information retrieval from several perspectives. The main research work is as follow.(1) Investigation of the characteristic and the method of personal information retrieval. To begin with, the conception of Individuality and Personality is studied. Then the method and characteristic of personal information retrieval is discussed. Studied the action of personal knowledge in the course of information retrieval. A pattern plate of individual character is presented. Analyze the structure of the plate, and give an example of the plate.(2) Investigation of the evaluation and experiment methods of information retrieval system or algorithm. Combined with the characteristic of personal information retrieval, an experiment, which can judge and examine the performance of system or algorithm, is presented. Based on the personal point, precision, recall and synthesized factor, an evaluation method and an index system to judge theperformance of search engine and other information systems are proposed.(3) Investigation of the theory of personal data mining and personal information pattern recognition. Put forward an algorithm that based on SVD to realize personal information retrieval, and verify the effectiveness of the algorithm through the experiment that is given above. Studied and given the idea that how to develop the algorithm.(4) Investigation of the theory of Artificial Neural Network. Put forward ANN-SVD algorithm to realize personal information recognition. It can make use of the user personal information to construct personal information space, and accomplish the documents' recognizing and matching, and realizing personal information retrieval.(5) Investigation of the theory of feature extraction and genetic algorithm. Two feature extraction algorithms that based on user feature documents sets are proposed. Examine the feature extraction performance of our algorithm.This dissertation investigates the theory and method for personal information retrieval from evaluation method, experiment method, personal information mining algorithm, and so on. The conclusion of this paper could be a foundation of personal information service for the future.