Content information analyzing method and apparatus

Abstract

This invention is to automatically extract noteworthy information from a large amount of information. First, a disclosure unit of an individual opinion such as a statement in a personal web page or a bulletin board is extracted from collected contents information, and information (URL and / or statement number) to specify the disclosure unit of the individual opinion is registered. Next, an object (company name and / or industry type) of the individual opinion is specified. Then, the disclosed contents of the individual opinion are analyzed, so that an evaluation as to the object (good evaluation / bad evaluation) is specified. Besides, the reliability is determined based on referenced degree ranking and based on whether information to indicate the basis of the opinion and / or the identity of the speaker is included. Thus, the evaluation as to the object as characteristics of the individual opinion can be presented to requesters. Besides, for example, only a bad evaluation can be extracted from evaluations as to the object of the individual opinion. Furthermore, the opinion, which has a high influence degree and is noteworthy, can also be found based on the referenced degree ranking and / or the reliability.

Description

technical field [0001] The present invention relates to a technique for automatically extracting specific information from a large amount of information. Background technique [0002] It has previously been possible to automatically extract slander against a business from information published on the Internet through document retrieval tools. However, a method of extracting a web page after specifying a keyword, or specifying a URL (Uniform Resource Locator: Universal Resource Locator) to be searched in advance is employed. That is, it cannot be judged whether the collected information is good information or bad information. Furthermore, information about the influence of the collected information cannot be obtained. Therefore it is inappropriate to find "the spread of rumors" for stock price manipulation. [0003] In addition, US Patent No. 6,438,632 discloses an electronic bulletin board system having a function of automatically checking content of desired information t...

AI Technical Summary

Problems solved by technology

[0004] In this way, although the specified information can be extracted from the huge amount of information in the prior art, the information that needs attention cannot be automatically extracted, and the interpretation and analysis of the extracted information must be performed manually.

Without further operation here, the user cannot obtain the characteristics of the extracted information and the source code of the information, etc.

Images