Internet and computer information retrieval and mining with intelligent conceptual filtering, visualization and automation

Abstract

The invention discloses a novel method, software and a system about information intelligent retrieval, mining, filtering, graphic display and retrieval automation. The invention can carry out artificial intelligence information query, information monitoring and carry out searching, filtering, graph displaying and tracing according to the concept, so as to assist the user to carry out intelligent, high- quality searching and mining to especially large amount of information data in the internet or in a local computer. The method of the invention can extract important concepts and creative concepts contained on web pages and documents, ordering the concepts and displaying relations between the concepts by graphs. The product formed by the invention can be applied to such fields as the enterprise management and planning, the consumption market, the market research, the scientific research, the technology development, the middle-high education, the military affairs, the nation security and the diplomacy.

Description

technical field [0001] The present invention relates to the technical field of information retrieval, and more specifically, relates to a method for information retrieval, mining, filtering, illustration and retrieval automation on a local computer and multiple computers on the network and the software for realizing the method and system. The priority date of the present invention is the preliminary application (application number 60 / 624,249) submitted to the United States Patent Office on November 1, 2004, and also the patent application (application number 200410073518.4) submitted to the State Intellectual Property Office of China on December 28, 2004 ) section continues. Background technique [0002] The limitations of current web search methods are listed below: [0003] 1. The prior art web search methods often return a large number of results, for example, a searched item may have hundreds or thousands or even millions of results. In pr...

AI Technical Summary

Problems solved by technology

Compared with the present invention, previous clustering techniques not only have deficiencies in extracting correct and important words and concepts, but also have duplicate files in multiple attributes, making it inconvenient for users to select multiple attributes to filter search results

[0004] 2. Previous search engines forced users to use keywords / words or strings to search for information

[0005] 3. Using the previous search method, users often have to sit in front of the computer and spend hours looking for the information they need

[0006] 4. For users, the previous search technology has no effective solution to monitor the site and search results

[0007] 5. In some previous search technologies, the user had to search the Internet and the personal computer separately to find relevant information in these two places

In some previous implementations, local file searches did not work when the computer was not connected to the Internet

[0008] 6. The search engine receives and usually records the search keywords / word strings used by the user, which will reveal the user's intention or creative idea sent to the search engine

Images