| 摘要 |
Provided is an information recommendation system capable of recommending an unexpected item which a user is interested in but cannot assume easily. A server gives one or more times of initial recommendations of recommending information by a means of a user profile and a behavior history, and narrows down second recommended items to recommend next by using not only information relating to items having responses but also information relating to items having no response together. In narrowing down, the items are arranged by means of an item arrangement program by using the results of the initial recommendations, and it is identified depending on similarity by means of a boundary calculation program where the boundary between user's interest and no interest is positioned in all the items. Then, it is identified where items not recommended yet are positioned in user's interest/no interest the areas, and items in the vicinity of the boundary between the interest and no interest are determined as the second recommended items which are not uninterested and maximize unexpectedness. |
