An information collection, processing and retrieval system

Abstract

The invention relates to an information collecting, processing and retrieving system. The information collecting, processing and retrieving system comprises an information collecting module, an information processing module, a retrieving module, an information base and a knowledge base, wherein the knowledge base comprises an interest model base, a professional field knowledge base, an authoritative website list and a threshold value base, the information collecting module comprises a searcher and an interest customizing module, and the interest customizing module is used for customizing an interest customization and document relevance model for a user. According to the information collecting, processing and retrieving system, downloaded information is filtered and sorted through calculation of the relevance between user definition and interests, and then collection, processing and management of public informative information on the Internet can be well achieved.

Description

technical field [0001] The invention relates to an information collection, processing and retrieval system, which includes an information collection module, an information processing module, a retrieval module and an information library. Background technique [0002] With the development of the times and technology, the Internet has become an important channel for public information collection among newspapers, books, maps, audio-visual materials and many other sources of public information. The computer network has spread all over the world, and the Internet has been widely used in various fields such as politics, economy, and military. [0003] However, the Internet is a massive source of information, and it is an open and distributed information space. Its inherent three characteristics have obviously hindered people from making full use of information resources on the Internet: 1. Information available on the Internet It is unorganized, has multiple structures, and is d...

AI Technical Summary

Problems solved by technology

The information retrieval methods currently provided, such as search engines, cannot fundamentally solve this problem

The reasons are as follows: 1. There is a considerable distance between the user's expression of interest and the computer's understanding and recognition of the user's interest; 2. During the retrieval process, a large amount of irrelevant information will be provided to the user, resulting in The phenomenon of "information overload"; 3. Almost all search engines cannot index all the information on the Internet, and only a part of it is covered, so the recall rate of intelligence cannot be guaranteed; 4. Search engines are in the process of searching for information , cannot crack and index restricted sites

Therefore, the information on these sites will be missed; 5. Search engines cannot guarantee the timeliness and authority of information when retrieving information, which is also a very serious and even fatal weakness for intelligence collection

Images