Item recommendation system

• US 20080294625A1
• Filed: 02/11/2008
• Published: 11/27/2008
• Est. Priority Date: 05/23/2007
• Status: Abandoned Application

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Takeuchi, Masaru
• Application Number:
  US12/068,702
• Publication Number:
  US 20080294625A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04N 21/4332 by placing content in organized collections, e.g. local EPG data repository interfaces, Database management systems or updating for information retrieval G06F16/23; details of retrieval of video data and associated meta data in video database G06F16/739
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies

Abstract

To recommend an item which is highly unexpected to a user because its similarity to user preferences is low and which is useful to the user. A rule that modifies a set of keywords for recommending an item is randomly applied, and a keyword which a user does not prefer is added and a keyword which a user prefers is removed, and then this recommendation result is mixed with a recommendation result of a set of keywords before the above modification, and the mixed result is presented to a user and at the same time the application probability of a rule is learned on the basis of the user'"'"'s evaluation to a recommended item.

Claims

1. An item recommendation system, comprising:

a client including;

a keyword extracting unit that extracts keywords related to an accessed or selected item;

a recording unit that stores information about a user, and keywords with high frequency of appearance among the extracted keywords; and

an input and output unit,

the client sending a plurality of keywords stored in the recording unit; and

a server including;

a content database that associates an item with keywords indicative of a content of the item, and stores information about the association;

a modification rule database that stores a plurality of rules for changing a part of keywords in a keyword group;

a retrieval keyword preparing unit that randomly applies one of the rules stored in the modification rule database to a plurality of keywords received from the client, so as to prepare a retrieving keyword group;

a retrieval unit that retrieves information from the content database by using the retrieving keyword group; and

a sending unit that sends, to the client, information about an item, the information being retrieved by the retrieval unit by using the retrieving keyword group prepared by the retrieval keyword preparing unit.

2. The item recommendation system according to claim 1, wherein the rules include a rule for adding a set of predetermined keywords to the plurality of keywords received from the client.

3. The item recommendation system according to claim 1, wherein the rules include a rule for removing a part of keywords from the plurality of keywords received from the client.

4. The item recommendation system according to claim 1, wherein each rule includes a condition about a user, and can be applied when the condition is satisfied by the information about the user, the information being received from the client.

5. The item recommendation system according to claim 1, wherein each rule includes a condition about a keyword, and can be applied when the plurality of keywords received from the client include a keyword specified by the condition.

6. The item recommendation system according to claim 1, wherein each rule is given a weight indicative of to what degree the rule can be applied to a keyword.

7. The item recommendation system according to claim 1, wherein the server has a function to change the weight on the basis of at least one of item selection and item evaluation by the client.

8. The item recommendation system according to claim 1, wherein

information about an item, which information is retrieved by the retrieval unit using a retrieving keyword group prepared by the retrieval keyword preparing unit, is mixed with information about an item, which information is retrieved by the retrieval unit using, as a retrieving keyword group, the plurality of keywords received from the client, and

information on the result of the mixture is sent to the client from the sending unit.

9. The item recommendation system according to claim 1, wherein

information about an item, which information is retrieved by the retrieval unit using a retrieving keyword group prepared by the retrieval keyword preparing unit;

information about an item, which information is retrieved by the retrieval unit using, as a retrieving keyword group, the plurality of keywords received from the client; and

information about an item, which information is retrieved by the retrieval unit using, as a retrieving keyword group, keywords obtained by adding a predetermined keyword to the plurality of keywords received from the client, are mixed together, and

information on the result of the mixture is sent from the sending unit to the client.