公开(公告)号：US20040093282A1

公开(公告)日：2004-05-13

申请号：US10291037

申请日：2002-11-08

Applicant: KONINKLIJKE PHILIPS ELECTRONICS N.V.

Inventor： Anna L. Buczak ,  John Zimmerman ,  Kaushal Kurapati

IPC: G06F017/60

CPC classification number: G06Q30/02 ,  G06Q30/0635

Abstract: A method for providing previous selection information to a user is provided that includes generating a list of possible selections based on a selection request received from the user. A selection history table is accessed to identify previous selections by the user. A determination is made regarding whether a selection in the list of possible selections matches a previous selection. The user is informed when a determination is made that a selection in the list of possible selections matches a previous selection.

Abstract translation: 提供了一种用于向用户提供先前选择信息的方法，其包括基于从用户接收的选择请求生成可能选择的列表。 访问选择历史表以识别用户的先前选择。 确定可能选择的列表中的选择是否与先前的选择相匹配。 当确定可能选择的列表中的选择与先前的选择相匹配时，通知用户。

公开(公告)号：US20040003391A1

公开(公告)日：2004-01-01

申请号：US10183688

申请日：2002-06-27

Applicant: Koninklijke Philips Electronics N.V.

Inventor： Srinivas Gutta ,  Subhash Kumar ,  Kaushal Kurapati

IPC: H04N007/16 ,  H04H009/00

CPC classification number: H04N21/44213 ,  H04N7/16 ,  H04N21/44222 ,  H04N21/4532 ,  H04N21/454 ,  H04N21/4668 ,  H04N21/4826

Abstract: The present invention provides a method, system and program product for locally analyzing (television) viewing behavior. Specifically, under the present invention, a single time interval of viewed programs is chunked into multiple time windows of viewed programs. Then, for each program within each time window, a conditional probability is calculated. The conditional probabilities are then compared to a noise threshold to determine recommended programs for each time window. The recommend programs can be added to a user profile and/or outputted to the viewer.

Abstract translation: 本发明提供一种用于本地分析（电视）观看行为的方法，系统和程序产品。 具体地说，在本发明中，所观看节目的单个时间间隔被划分成所查看的节目的多个时间窗口。 然后，对于每个时间窗内的每个程序，计算条件概率。 然后将条件概率与噪声阈值进行比较，以确定每个时间窗口的推荐程序。 推荐节目可以添加到用户配置文件和/或输出给观众。

公开(公告)号：US20030097186A1

公开(公告)日：2003-05-22

申请号：US10014189

申请日：2001-11-13

Applicant: Koninklijke Philips Electronics N.V

Inventor： Srinivas Gutta ,  Kaushal Kurapati

IPC: G05B015/00

CPC classification number: H04N21/4661 ,  H04N7/163 ,  H04N21/4665 ,  H04N21/4826

Abstract: A method and apparatus are disclosed for recommending items of interest to a user, such as television program recommendations, before a viewing history or purchase history of the user is available. A third party viewing or purchase history is processed to generate stereotype profiles that reflect the typical patterns of items selected by representative viewers. A user can select the most relevant stereotype(s) from the generated stereotype profiles and thereby initialize his or her profile with the items that are closest to his or her own interests. A clustering routine partitions the third party viewing or purchase history (the data set) into clusters using a k-means clustering algorithm, such that points (e.g., television programs) in one cluster are closer to the mean of that cluster than any other cluster. A mean computation routine computes the symbolic mean of a cluster. For a feature-based mean computation, the distance computation between two items is performed on the feature (symbolic attribute) level and the resultant cluster mean is made up of feature values drawn from the examples (programs) in the cluster. The resulting cluster mean may be a nullhypotheticalnull television program, with the individual feature values of this hypothetical program drawn from any one of the examples.

Abstract translation: 公开了一种方法和装置，用于在用户的观看历史或购买历史可用之前推荐用户感兴趣的项目，诸如电视节目推荐。 处理第三方查看或购买历史记录以生成反映由代表性观众选择的项目的典型模式的构图型材。 用户可以从生成的刻板印象简档中选择最相关的原型，从而用最接近他或她自己的兴趣的项目初始化他或她的简档。 聚类例程使用k均值聚类算法将第三方查看或购买历史记录（数据集）划分成簇，使得一个集群中的点（例如，电视节目）比该集群的平均值更接近任何其他集群 。 平均计算例程计算簇的符号平均值。 对于基于特征的平均计算，在特征（符号属性）级别上执行两个项目之间的距离计算，并且所得到的聚类平均值由从集群中的示例（程序）绘制的特征值组成。 所得到的聚类平均值可以是“假设的”电视节目，其中该假设节目的个体特征值来自任何一个示例。

公开(公告)号：US20030014404A1

公开(公告)日：2003-01-16

申请号：US09875594

申请日：2001-06-06

Applicant: Koninklijke Philips Electronics N.V.

Inventor： Srinivas V.R. Gutta ,  J. David Schaffer ,  Kaushal Kurapati

IPC: G06F007/00

CPC classification number: H04N21/466 ,  H04N7/163 ,  H04N21/4662 ,  H04N21/4668

Abstract: A program recommendation system employing a program record module and one of various nearest neighbor modules is disclosed. In response to a reception of a program record, the program record module converts each key field of the program record into a feature value. A single neighbor module selectively generates a recommendation of a program corresponding to the program record based upon a stored program record qualifying as a nearest neighbor of the received program record. A multiple neighbor module selectively generates a recommendation of the program corresponding to the program record based upon N number of stored program records qualifying as N number of nearest neighbors of the received program record. A neighbor cluster selectively generates a recommendation of the program corresponding to the program record based upon the cluster of stored program records qualifying as the nearest neighbor of the received program record.

Abstract translation: 公开了一种采用程序记录模块和各种最近邻模块之一的程序推荐系统。 响应于节目记录的接收，节目记录模块将节目记录的每个关键字段转换为特征值。 单个邻居模块基于被限定为所接收的节目记录的最近邻的所存储的节目记录，选择性地生成与节目记录相对应的节目的推荐。 多邻居模块根据N个被存储的节目记录选择性地生成与节目记录相对应的节目的推荐，该节目记录被限定为接收的节目记录的N个最近邻居。 相邻群集基于被存储的节目记录的集群选择性地生成与节目记录相对应的节目的推荐，所述节目记录的集合被限定为所接收节目记录的最近邻。

公开(公告)号：US20040003401A1

公开(公告)日：2004-01-01

申请号：US10183762

申请日：2002-06-27

Applicant: Koninklijke Philips Electronics N.V.

Inventor： Srinivas Gutta ,  Kaushal Kurapati

IPC: H04N005/445

CPC classification number: H04N21/4667 ,  H04N7/165 ,  H04N21/252 ,  H04N21/25891

Abstract: A method and apparatus are disclosed for recommending items of interest to a user, such as television program recommendations, before a viewing history or purchase history of the user is available. A third party viewing or purchase history is processed to generate stereotype profiles that reflect the typical patterns of items selected by representative viewers. A user can select the most relevant stereotype(s) from the generated stereotype profiles and thereby initialize his or her profile with the items that are closest to his or her own interests. A clustering routine partitions the third party viewing or purchase history (the data set) into clusters using a k-means clustering algorithm, such that points (e.g., television programs) in one cluster are closer to the mean of that cluster than any other cluster. The value of k is incremented in accordance with a measure of cluster compactness.

Abstract translation: 公开了一种方法和装置，用于在用户的观看历史或购买历史可用之前推荐用户感兴趣的项目，诸如电视节目推荐。 处理第三方查看或购买历史记录以生成反映由代表性观众选择的项目的典型模式的构图型材。 用户可以从生成的刻板印象简档中选择最相关的原型，从而用最接近他或她自己的兴趣的项目初始化他或她的简档。 聚类例程使用k均值聚类算法将第三方查看或购买历史记录（数据集）划分成簇，使得一个集群中的点（例如，电视节目）比该集群的平均值更接近任何其他集群 。 k的值根据簇紧凑度的度量而增加。

公开(公告)号：US20030126560A1

公开(公告)日：2003-07-03

申请号：US10034660

申请日：2001-12-28

Applicant: KONINKLIJKE PHILIPS ELECTRONICS N.V.

Inventor： Kaushal Kurapati ,  Srinivas Gutta ,  Miroslav Trajkovic

IPC: G06F007/00

CPC classification number: G06F16/9562

Abstract: A process for adaptive bookmarking of often-visited web sites, comprising the steps of (a) optionally determining the identity of a particular user, (b) determining whether a webpage has been detected, (c) if the webpage in step (b) has been detected, determining whether the webpage has been previously visited by a particular user, (d) performing one of (i) creating an initial record of the webpage visit by the particular user if it has been determined in step (c) that the webpage has not been previously visited by the particular user, and (ii) determining whether the webpage has been previously bookmarked if it has been determined in step (c) that the webpage has been previously visited by the particular user, (e) updating a visitation count if it has been determined in step (c) that the webpage has been previously visited by the particular user, (f) determining whether the visitation count has reached a predetermined threshold; and (g) recommending the bookmarking of the address of the webpage if it determined in step (f) that the predetermined threshold of the visitation count has been reached. The visitation count may be number of plural visits and time spent visiting. The system may either automatically purge bookmarks or do so by recommendation after non-use for predetermined periods of time. A system includes hardware plus a program module to perform the bookmarking functions.

Abstract translation: 一种用于经常访问的网站的自适应书签的过程，包括以下步骤：（a）可选地确定特定用户的身份，（b）确定是否检测到网页，（c）如果步骤（b）中的网页 已经检测到，确定网页是否已经被特定用户先前访问过，（d）执行以下步骤之一：（i）如果在步骤（c）中已经确定了所述网页访问的初始记录，则由特定用户创建 网页以前没有被特定用户访问，并且（ii）如果在步骤（c）中已经确定网页已经被特定用户先前访问过，则确定网页是否已经被预先加入书签;（e）更新网页 如果在步骤（c）中确定网页已经被特定用户先前访问过，则访问次数;（f）确定访问次数是否达到预定阈值; （g）如果在步骤（f）中确定已达到预定的访问次数阈值，则推荐网页的地址的书签。 访问次数可能是多次访问次数和访问次数。 系统可能会自动清除书签，或者在不使用预定时间后通过推荐。 系统包括硬件加上程序模块来执行书签功能。

公开(公告)号：US20030097300A1

公开(公告)日：2003-05-22

申请号：US10014195

申请日：2001-11-13

Applicant: Koninklijke Philips Electronics N.V.

Inventor： Srinivas Gutta ,  Kaushal Kurapati

IPC: G06F017/60

CPC classification number: H04N21/4661 ,  G06Q30/0255 ,  G06Q30/0269 ,  G06Q30/0601 ,  H04N7/163 ,  H04N21/4665 ,  H04N21/4826

Abstract: A method and apparatus are disclosed for recommending items of interest to a user, such as television program recommendations, before a viewing history or purchase history of the user is available. A third party viewing or purchase history is processed to generate stereotype profiles that reflect the typical patterns of items selected by representative viewers. A user can select the most relevant stereotype(s) from the generated stereotype profiles and thereby initialize his or her profile with the items that are closest to his or her own interests. A clustering routine is disclosed to partition the third party viewing or purchase history (the data set) into clusters, such that points (e.g., television programs) in one cluster are closer to the mean of that cluster than any other cluster. A mean computation routine is also disclosed to compute the symbolic mean of a cluster.

Abstract translation: 公开了一种方法和装置，用于在用户的观看历史或购买历史可用之前推荐用户感兴趣的项目，诸如电视节目推荐。 处理第三方查看或购买历史记录以生成反映由代表性观众选择的项目的典型模式的构图型材。 用户可以从生成的刻板印象简档中选择最相关的原型，从而用最接近他或她自己的兴趣的项目初始化他或她的简档。 公开了聚类例程以将第三方观看或购买历史（数据集）划分成群集，使得一个群集中的点（例如，电视节目）比任何其他群集更接近该群集的平均值。 还公开了一种平均计算程序来计算簇的符号平均值。

公开(公告)号：US20020169731A1

公开(公告)日：2002-11-14

申请号：US09794445

申请日：2001-02-27

Applicant: Koninklijke Philips Electronics N.V.

Inventor： Srinivas Gutta ,  Kaushal Kurapati

IPC: G06F015/18

CPC classification number: G06N20/00

Abstract: A method for learning a concept description from an example set containing a plurality of positive and/or negative examples. The method including the steps of: initializing a general set to contain a null concept description; initializing a specific set to contain a concept description of a first positive example from the example set; and making the specific set more general according to each additional positive example from the example set and making the general set more specific according to each additional negative example from the example set until the specific and general sets converge to a single concept description. Preferably, the plurality of positive and negative examples contain description regarding television programming of a viewer and the concept description indicates a type of television programming the viewer likes.

Abstract translation: 一种用于从包含多个正和/或负例子的示例集合中学习概念描述的方法。 该方法包括以下步骤：初始化一般集合以包含空概念描述; 初始化特定集合以包含来自示例集合的第一正例子的概念描述; 并且根据示例集合中的每个附加的正例来使特定集合更一般，并且根据示例集合中的每个附加的负例子使得一般集合更具体，直到特定集合和一般集合收敛到单个概念描述。 优选地，多个正面和反面示例包含关于观看者的电视节目的描述，并且概念描述指示观众喜欢的电视节目的类型。

公开(公告)号：US20030097196A1

公开(公告)日：2003-05-22

申请号：US10014192

申请日：2001-11-13

Applicant: Koninklijke Philips Electronics N.V.

Inventor： Srinivas Gutta ,  Kaushal Kurapati

IPC: G06F019/00

CPC classification number: H04N21/4662 ,  H04N7/163 ,  H04N21/252 ,  H04N21/4532 ,  H04N21/4668 ,  H04N21/4755 ,  H04N21/4826

Abstract: A method and apparatus are disclosed for recommending items of interest to a user, such as television program recommendations, before a viewing history or purchase history of the user is available. A third party viewing or purchase history is processed to generate stereotype profiles that reflect the typical patterns of items selected by representative viewers. A user can select the most relevant stereotype(s) from the generated stereotype profiles and thereby initialize his or her profile with the items that are closest to his or her own interests. A clustering routine partitions the third party viewing or purchase history (the data set) into clusters using a k-means clustering algorithm, such that points (e.g., television programs) in one cluster are closer to the mean of that cluster than any other cluster. A mean computation routine computes the symbolic mean of a cluster. For an item -based mean computation, the distance computation between two items is performed on the item level and the resultant cluster mean is made up of the feature values of the selected mean item. Thus, the one or more items that exhibit the minimum variance are selected as the mean of that cluster.

Abstract translation: 公开了一种方法和装置，用于在用户的观看历史或购买历史可用之前推荐用户感兴趣的项目，诸如电视节目推荐。 处理第三方查看或购买历史记录以生成反映由代表性观众选择的项目的典型模式的构图型材。 用户可以从生成的刻板印象简档中选择最相关的原型，从而用最接近他或她自己的兴趣的项目初始化他或她的简档。 聚类例程使用k均值聚类算法将第三方查看或购买历史记录（数据集）划分成簇，使得一个集群中的点（例如，电视节目）比该集群的平均值更接近任何其他集群 。 平均计算例程计算簇的符号平均值。 对于基于项目的平均计算，在项目级别上执行两个项目之间的距离计算，并且所得到的聚类平均值由所选择的平均项目的特征值组成。 因此，显示最小方差的一个或多个项目被选择为该群集的平均值。

公开(公告)号：US20030061183A1

公开(公告)日：2003-03-27

申请号：US09963245

申请日：2001-09-26

Applicant: Koninklijke Philips Electronics N.V.

Inventor： J. David Schaffer ,  Karen I. Trovato ,  Kaushal Kurapati

IPC: G06F015/18

CPC classification number: H04N21/4662 ,  H04N7/163 ,  H04N21/44218 ,  H04N21/44222 ,  H04N21/4532 ,  H04N21/454 ,  H04N21/4668 ,  H04N21/4755 ,  H04N21/4756

Abstract: A recommendation system and method are disclosed. In the system and method, the personal schedule of the user is used to modify the recommendation functions of media events. The personal schedule may be entered by the user or determined through monitoring over time. An exemplary recommendation function modification is if a media event ends after the user's bedtime, as indicated by the personal schedule. In this example, the recommendation function of that event will be reduced in value because the user will likely go to bed before the event is over.

Abstract translation: 公开了推荐系统和方法。 在系统和方法中，用户的个人日程表用于修改媒体事件的推荐功能。 个人时间表可以由用户输入或通过随时间的监视确定。 示例性的推荐功能修改是如果媒体事件在用户的睡前时间结束，如个人日程表所示。 在这个例子中，该事件的推荐功能将被降低，因为用户在事件结束之前可能会睡觉。