Topic-oriented diversified item recommendation
    3.
    发明授权
    Topic-oriented diversified item recommendation 有权
    主题多元化项目推荐

    公开(公告)号:US08589378B2

    公开(公告)日:2013-11-19

    申请号:US12901917

    申请日:2010-10-11

    IPC分类号: G06F7/00

    CPC分类号: G06F17/30699

    摘要: A content recommendation system and method are provided in which content semantic topic analysis, user interest identification and per interest recommendations are used to deliver relevant and diversified content recommendations to the user. Semantic topic analysis is used to infer underlying topics in content items; for each content item, a topic distribution vector is derived with components that represent relevance of the content item to specific underlying topics. A user's long term and short term user interests are identified using the user's browsing history. Long term user interest(s) can be obtained by a weighted aggregation of topic distribution vectors of content items the user accessed. Short term interest can be represented by the topic distribution vector corresponding to a current content item. Using identified user's interests, relevant content items are selected for recommendations for the user.

    摘要翻译: 提供了一种内容推荐系统和方法,其中使用内容语义主题分析,用户兴趣识别和每个兴趣推荐来向用户传递相关和多样化的内容推荐。 语义主题分析用于推断内容项中的基础主题; 对于每个内容项目,使用表示内容项目与特定基础主题的相关性的组件来导出主题分发向量。 使用用户的浏览记录识别用户的长期和短期用户兴趣。 可以通过用户访问的内容项的主题分布向量的加权聚合来获得长期用户兴趣。 短期利益可以由对应于当前内容项目的主题分布向量表示。 使用识别的用户兴趣,选择相关内容项目以供用户推荐。

    TOPIC-ORIENTED DIVERSIFIED ITEM RECOMMENDATION
    4.
    发明申请
    TOPIC-ORIENTED DIVERSIFIED ITEM RECOMMENDATION 有权
    面向主题的多元化项目建议

    公开(公告)号:US20120089621A1

    公开(公告)日:2012-04-12

    申请号:US12901917

    申请日:2010-10-11

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30699

    摘要: A content recommendation system and method are provided in which content semantic topic analysis, user interest identification and per interest recommendations are used to deliver relevant and diversified content recommendations to the user. Semantic topic analysis is used to infer underlying topics in content items; for each content item, a topic distribution vector is derived with components that represent relevance of the content item to specific underlying topics. A user's long term and short term user interests are identified using the user's browsing history. Long term user interest(s) can be obtained by a weighted aggregation of topic distribution vectors of content items the user accessed. Short term interest can be represented by the topic distribution vector corresponding to a current content item. Using identified user's interests, relevant content items are selected for recommendations for the user.

    摘要翻译: 提供了一种内容推荐系统和方法,其中使用内容语义主题分析,用户兴趣识别和每个兴趣推荐来向用户传递相关和多样化的内容推荐。 语义主题分析用于推断内容项中的基础主题; 对于每个内容项目,使用表示内容项目与特定基础主题的相关性的组件来导出主题分发向量。 使用用户的浏览记录识别用户的长期和短期用户兴趣。 可以通过用户访问的内容项的主题分布向量的加权聚合来获得长期用户兴趣。 短期利益可以由对应于当前内容项目的主题分布向量表示。 使用识别的用户兴趣,选择相关内容项目以供用户推荐。

    Behavior targeting social recommendations
    5.
    发明授权
    Behavior targeting social recommendations 有权
    面向社会建议的行为

    公开(公告)号:US09087106B2

    公开(公告)日:2015-07-21

    申请号:US13381863

    申请日:2010-12-31

    IPC分类号: G06F17/30 G06Q30/02 G06Q50/00

    摘要: A process for generating social recommendations is provided. For each user, a user profile index is accessed to determine reading interests of the user. Further, relevance matching is performed to determine matching users having at least one publishing interest that is relevant to the reading interests of the user. Next, the matching users are ranked. Based on the ranking, one or more top ranked matching user(s) are determined. Additionally, a social recommendation for each of the top ranked matching user(s) is enabled to be made to the user.

    摘要翻译: 提供了一个产生社会建议的过程。 对于每个用户,访问用户简档索引以确定用户的阅读兴趣。 此外,执行相关性匹配以确定具有与用户的阅读兴趣相关的至少一个发布兴趣的匹配用户。 接下来,匹配用户排名。 基于排名,确定一个或多个顶级匹配用户。 此外,能够对用户进行针对每个顶级匹配用户的社交推荐。

    BEHAVIOR TARGETING SOCIAL RECOMMENDATIONS
    6.
    发明申请
    BEHAVIOR TARGETING SOCIAL RECOMMENDATIONS 有权
    行为指导社会建议

    公开(公告)号:US20130304731A1

    公开(公告)日:2013-11-14

    申请号:US13381863

    申请日:2010-12-31

    IPC分类号: G06F17/30

    摘要: A process for generating social recommendations is provided. For each user, a user profile index is accessed to determine reading interests of the user. Further, relevance matching is performed to determine matching users having at least one publishing interest that is relevant to the reading interests of the user. Next, the matching users are ranked. Based on the ranking, one or more top ranked matching user(s) are determined. Additionally, a social recommendation for each of the top ranked matching user(s) is enabled to be made to the user.

    摘要翻译: 提供了一个产生社会建议的过程。 对于每个用户,访问用户简档索引以确定用户的阅读兴趣。 此外,执行相关性匹配以确定具有与用户的阅读兴趣相关的至少一个发布兴趣的匹配用户。 接下来,匹配用户排名。 基于排名,确定一个或多个顶级匹配用户。 此外,能够对用户进行针对每个顶级匹配用户的社交推荐。