Method and apparatus for recommending information using hybrid algorithm

Abstract

A method and apparatus for recommending information is provided. When a client accesses a server and requests information, the server determines whether the client is included in a meaningful set (MS) and generates first preference information of the client based on an access history of the client, or based on additional information directly input by the client. Then, the server selects a number of neighborhood groups including clients having preferences similar to a preference of the client, and generates and transmits first item information on a number of items preferred by the clients of the neighborhood group to the client. The client extracts second item information to be recommended to a user by filtering the first item information with second preference information. Information is filtered respectively by the server and the client by using different algorithms. Accordingly, it is possible to improve the accuracy and speed of recommending information.

Description

technical field [0001] The present invention relates to a method and device for recommending information, and more particularly, to a method and device for recommending information using a hybrid algorithm, which can accurately and quickly recommended information. Background technique [0002] Due to the development of Internet technology, a large amount of information can be searched, so a method is needed to quickly extract information suitable for users from the large amount of information that can be searched through the Internet. As typical algorithms of a method of filtering information suitable for a user, an attribute-aware (AA) algorithm and a collaborative filtering (CF) algorithm are used to search for information. In case a user searches for items such as books, music, movies, etc. over the Internet, the aforementioned algorithm is used to provide search results suitable for the user. [0003] The AA algorithm represents a method of filtering item information b...

AI Technical Summary

Problems solved by technology

[0005] Since the CF algorithm uses the user's past item search results, it is difficult to use this method to accurately recommend information for initial users who do not have data related to past item search results (first-time user problem)

In addition, when the number of items is much larger than the number of users, there is a lack of data to distinguish groups with similar preferences, reducing the filtering accuracy (sparseness problem)

[0006] Therefore, although a hybrid algorithm obtained by combining these two algorithms has been proposed, most methods of filtering information using this hybrid algorithm have the disadvantage that the filtering speed is very slow, and it is difficult to implement the hybrid method

If the AA algorithm is applied to the data using the attribute data to check the user's preference in order to apply the CF algorithm, the amount of data is too large and the filtering speed decreases

Images