Method and device for selecting correlative discussion zone in network community

Abstract

This method includes that: collects all computer logs logging into the discuss section (DS), combines them into a chief log, draws info from the chief log, generates the business set, via frequent item set (FIS) mining algorithm, selects FIS of DS, draws the related DS of each DS from FIS of DS, generates related DS list, then finishes. This invention utilizes the data mining method to find out the related DS of this DS. The related DS presents the behavior of the DS user. This will be convenient for the user's next accessing and will reduce lookup cost. A selection device of related DS in the network community is disclosed as well.

Description

technical field [0001] The invention relates to a method and a device for selecting a discussion area in a network community, in particular to a method and a device for selecting a related discussion area, and belongs to the field of computers. Background technique [0002] With the rapid development of the network, more and more people choose to search for information or find suitable people with similar interests or similar needs to communicate through the Internet. [0003] The traditional community or BBS system is based on manually establishing a content discussion area system and directory index, that is, the system administrator needs to edit a certain number and contents of the directory in the system, and then needs to manually open a forum or discussion area, and establish The association between a forum or discussion board and a table of contents. When browsing and communicating, the user first needs to judge which forum or discussion area under which directory t...

AI Technical Summary

Problems solved by technology

[0007] The defect of the above technical solution is that the discussion board system simply lists the names of other discussion boards that are also logged in by the person who logs into a certain discussion board, which does not reflect the behavior of logging into this discussion board and the behavior of logging into other discussion boards. For example, 99 out of 100 people who logged into discussion board A also logged into discussion board B, but only 1 of the 100 people who logged into discussion board A also logged into discussion board C. The behavior of the discussion area is highly correlated with the behavior of logging into the B discussion area, and the correlation between the behavior of logging into the A discussion area and the behavior of logging into the C discussion area is weak. Listed out, the existence of the C discussion area not only cannot reveal the next behavior of the person who logs into the A discussion area, but may mislead the user's browsing behavior

Images