公开(公告)号：US06760714B1

公开(公告)日：2004-07-06

申请号：US09675867

申请日：2000-09-29

申请人： William R. Caid ,  Robert Hecht-Neilsen

发明人： William R. Caid ,  Robert Hecht-Neilsen

IPC分类号： G06F1518

CPC分类号： G06F17/30265 ,  G06F17/30256 ,  G06F17/3061 ,  G06K9/4623

摘要： Image features are generated by performing wavelet transformations at sample points on images stored in electronic form. Multiple wavelet transformations at a point are combined to form an image feature vector. A prototypical set of feature vectors, or atoms, is derived from the set of feature vectors to form an “atomic vocabulary.” The prototypical feature vectors are derived using a vector quantization method (e.g., using neural network self-organization techniques) in which a vector quantization network is also generated. The atomic vocabulary is used to define new images. Meaning is established between atoms in the atomic vocabulary. High-dimensional context vectors are assigned to each atom. The context vectors are then trained as a function of the proximity and co-occurrence of each atom to other atoms in the image. After training, the context vectors associated with the atoms that comprise an image are combined to form a summary vector for the image. Images are retrieved using a number of query methods (e.g., images, image portions, vocabulary atoms, index terms). The user's query is converted into a query context vector. A dot product is calculated between the query vector and the summary vectors to locate images having the closest meaning. The invention is also applicable to video or temporally related images, and can also be used in conjunction with other context vector data domains such as text or audio, thereby linking images to such data domains.

摘要翻译： 通过在以电子形式存储的图像上的采样点执行小波变换来生成图像特征。 将点处的多个小波变换组合以形成图像特征向量。 特征向量或原子的原型集是从特征向量集合中导出的，以形成“原子词汇”。 使用其中也生成矢量量化网络的矢量量化方法（例如，使用神经网络自组织技术）导出原型特征向量。 原子词汇用于定义新图像。 在原子词汇中的原子之间建立意义。 高维上下文向量分配给每个原子。 然后将上下文矢量作为每个原子与图像中其他原子的邻近和共现的函数进行训练。 在训练之后，与构成图像的原子相关联的上下文向量被组合以形成图像的汇总向量。 使用许多查询方法（例如，图像，图像部分，词汇原子，索引项）来检索图像。 用户的查询被转换为查询上下文向量。 在查询向量和汇总向量之间计算点积，以定位具有最接近意义的图像。 本发明也适用于视频或时间相关的图像，并且还可以与诸如文本或音频的其他上下文矢量数据域一起使用，从而将图像链接到这样的数据域。

公开(公告)号：US07072872B2

公开(公告)日：2006-07-04

申请号：US10868538

申请日：2004-06-14

申请人： William R. Caid ,  Robert Hecht-Neilsen

发明人： William R. Caid ,  Robert Hecht-Neilsen

IPC分类号： G06F15/18

CPC分类号： G06F17/30265 ,  G06F17/30256 ,  G06F17/3061 ,  G06K9/4623

摘要： Image features are generated by performing wavelet transformations at sample points on images stored in electronic form. Multiple wavelet transformations at a point are combined to form an image feature vector. A prototypical set of feature vectors, or atoms, is derived from the set of feature vectors to form an “atomic vocabulary.” The prototypical feature vectors are derived using a vector quantization method, e.g., using neural network self-organization techniques, in which a vector quantization network is also generated. The atomic vocabulary is used to define new images. Meaning is established between atoms in the atomic vocabulary. High-dimensional context vectors are assigned to each atom. The context vectors are then trained as a function of the proximity and co-occurrence of each atom to other atoms in the image. After training, the context vectors associated with the atoms that comprise an image are combined to form a summary vector for the image. Images are retrieved using a number of query methods, e.g., images, image portions, vocabulary atoms, index terms. The user's query is converted into a query context vector. A dot product is calculated between the query vector and the summary vectors to locate images having the closest meaning. The invention is also applicable to video or temporally related images, and can also be used in conjunction with other context vector data domains such as text or audio, thereby linking images to such data domains.

摘要翻译： 通过在以电子形式存储的图像上的采样点处执行小波变换来生成图像特征。 将点处的多个小波变换组合以形成图像特征向量。 特征向量或原子的原型集是从特征向量集合中导出的，以形成“原子词汇”。 使用矢量量化方法导出原型特征向量，例如使用其中也产生矢量量化网络的神经网络自组织技术。 原子词汇用于定义新图像。 在原子词汇中的原子之间建立意义。 高维上下文向量分配给每个原子。 然后将上下文矢量作为每个原子与图像中其他原子的邻近和共现的函数进行训练。 在训练之后，与构成图像的原子相关联的上下文向量被组合以形成图像的汇总向量。 使用许多查询方法（例如，图像，图像部分，词汇原子，索引项）来检索图像。 用户的查询被转换为查询上下文向量。 在查询向量和汇总向量之间计算点积，以定位具有最接近意义的图像。 本发明也适用于视频或时间相关的图像，并且还可以与诸如文本或音频的其他上下文矢量数据域一起使用，从而将图像链接到这样的数据域。

公开(公告)号：US06173275B2

公开(公告)日：2001-01-09

申请号：US08931927

申请日：1997-09-17

申请人： William R. Caid ,  Robert Hecht-Neilsen

发明人： William R. Caid ,  Robert Hecht-Neilsen

IPC分类号： G06F1518

CPC分类号： G06F17/30265 ,  G06F17/30256 ,  Y10S706/934

摘要： Image features are generated by performing wavelet transformations at sample points on images stored in electronic form. Multiple wavelet transformations at a point are combined to form an image feature vector. A prototypical set of feature vectors, or atoms, is derived from the set of feature vectors to form an “atomic vocabulary.” The prototypical feature vectors are derived using a vector quantization method (e.g., using neural network self-organization techniques) in which a vector quantization network is also generated. The atomic vocabulary is used to define new images. Meaning is established between atoms in the atomic vocabulary. High-dimensional context vectors are assigned to each atom. The context vectors are then trained as a function of the proximity and co-occurrence of each atom to other atoms in the image. After training, the context vectors associated with the atoms that comprise an image are combined to form a summary vector for the image. Images are retrieved using a number of query methods (e.g., images, image portions, vocabulary atoms, index terms). The user's query is converted into a query context vector. A dot product is calculated between the query vector and the summary vectors to locate images having the closest meaning. The invention is also applicable to video or temporally related images, and can also be used in conjunction with other context vector data domains such as text or audio, thereby linking images to such data domains.

摘要翻译： 通过在以电子形式存储的图像上的采样点执行小波变换来生成图像特征。 将点处的多个小波变换组合以形成图像特征向量。 特征向量或原子的原型集是从特征向量集合中导出的，以形成“原子词汇”。 使用其中也生成矢量量化网络的矢量量化方法（例如，使用神经网络自组织技术）导出原型特征向量。 原子词汇用于定义新图像。 在原子词汇中的原子之间建立意义。 高维上下文向量分配给每个原子。 然后将上下文矢量作为每个原子与图像中其他原子的邻近和共现的函数进行训练。 在训练之后，与构成图像的原子相关联的上下文向量被组合以形成图像的汇总向量。 使用许多查询方法（例如，图像，图像部分，词汇原子，索引项）来检索图像。 用户的查询被转换为查询上下文向量。 在查询向量和汇总向量之间计算点积，以定位具有最接近意义的图像。 本发明也适用于视频或时间相关的图像，并且还可以与诸如文本或音频的其他上下文矢量数据域一起使用，从而将图像链接到这样的数据域。

公开(公告)号：US6134532A

公开(公告)日：2000-10-17

申请号：US971091

申请日：1997-11-14

申请人： Michael A. Lazarus ,  William R. Caid ,  Richard S. Pugh ,  Bradley D. Kindig ,  Gerald S. Russell ,  Kenneth B. Brown ,  Ted E. Dunning ,  Joel L. Carleton

发明人： Michael A. Lazarus ,  William R. Caid ,  Richard S. Pugh ,  Bradley D. Kindig ,  Gerald S. Russell ,  Kenneth B. Brown ,  Ted E. Dunning ,  Joel L. Carleton

IPC分类号： G06F15/00 ,  G06F17/30 ,  G06Q30/02 ,  G06F17/60

CPC分类号： G06Q30/02 ,  G06F17/30867 ,  G06Q30/0224 ,  G06Q30/0256 ,  G06Q30/0264 ,  G06Q30/0269

摘要： A system and method for selecting and presenting personally targeted entities such as advertising, coupons, products and information content, based on tracking observed behavior on a user-by-user basis and utilizing an adaptive vector space representation for both information and behavior. The system matches users to entities in a manner that improves with increased operation and observation of user behavior. User behavior and entities (ads, coupons, products) and information (text) are all represented as content vectors in a unified vector space. The system is based on an information representation called content vectors that utilizes a constrained self organization learning technique to learn the relationships between symbols (typically words in unstructured text). Users and entities are each represented as content vectors.

摘要翻译： 一种用于基于逐个用户的跟踪观察行为来选择和呈现诸如广告，优惠券，产品和信息内容的个人目标实体的系统和方法，并且利用信息和行为的自适应向量空间表示。 该系统以增加操作和观察用户行为的方式将用户与实体相匹配。 用户行为和实体（广告，优惠券，产品）和信息（文本）都表示为统一向量空间中的内容向量。 该系统基于称为内容向量的信息表示，其利用受约束的自组织学习技术来学习符号之间的关系（通常是非结构化文本中的单词）。 用户和实体各自表示为内容向量。

公开(公告)号：US06839682B1

公开(公告)日：2005-01-04

申请号：US09679022

申请日：2000-10-03

申请人： Matthias Blume ,  Michael A. Lazarus ,  Larry S. Peranich ,  Frederique Vernhes ,  William R. Caid ,  Ted E. Dunning ,  Gerald R. Russell ,  Kevin L. Sitze

发明人： Matthias Blume ,  Michael A. Lazarus ,  Larry S. Peranich ,  Frederique Vernhes ,  William R. Caid ,  Ted E. Dunning ,  Gerald R. Russell ,  Kevin L. Sitze

IPC分类号： G06Q30/02 ,  G06F17/60

CPC分类号： G06Q30/02 ,  G06Q30/0202 ,  G06Q30/0207 ,  G06Q30/0241 ,  G06Q30/0255 ,  G06Q30/0269 ,  G06Q30/0601

摘要： Predictive modeling of consumer financial behavior, including determination of likely responses to particular marketing efforts, is provided by application of consumer transaction data to predictive models associated with merchant segments. The merchant segments are derived from the consumer transaction data based on co-occurrences of merchants in sequences of transactions. Merchant vectors represent specific merchants, and are aligned in a vector space as a function of the degree to which the merchants co-occur more or less frequently than expected. Consumer vectors are developed within the vector space, to represent interests of particular consumers by virtue of relative vector positions of consumer and merchant vectors. Various techniques, including clustering, supervised segmentation, and nearest-neighbor analysis, are applied separately or in combination to generate improved predictions of consumer behavior.

摘要翻译： 通过将消费者交易数据应用于与商家细分相关的预测模型，提供消费者财务行为的预测建模，包括对特定营销努力的可能响应的确定。 商业细分是根据交易序列中商家的共同出现从消费者交易数据中得出的。 商家向量表示特定商家，并且在向量空间中对齐，作为商家与预期频繁相同程度的函数。 消费者向量在向量空间内发展，通过消费者和商户向量的相对向量位置来代表特定消费者的兴趣。 各种技术，包括聚类，监督分割和最近邻分析，分别或组合应用，以产生消费者行为的改进预测。

公开(公告)号：US06430539B1

公开(公告)日：2002-08-06

申请号：US09306237

申请日：1999-05-06

申请人： Michael A. Lazarus ,  A. U. Mattias Blume ,  Kenneth B. Brown ,  William R. Caid ,  Ted E. Dunning ,  Larry S. Peranich ,  Gerald R. Russell ,  Kevin L. Sitze

发明人： Michael A. Lazarus ,  A. U. Mattias Blume ,  Kenneth B. Brown ,  William R. Caid ,  Ted E. Dunning ,  Larry S. Peranich ,  Gerald R. Russell ,  Kevin L. Sitze

IPC分类号： G06F1760

CPC分类号： G06Q30/02 ,  G06Q30/0202 ,  G06Q30/0207 ,  G06Q30/0241 ,  G06Q30/0255 ,  G06Q30/0269 ,  G06Q30/0601

摘要： Predictive modeling of consumer financial behavior is provided by application of consumer transaction data to predictive models associated with merchant segments. Merchant segments are derived from consumer transaction data based on co-occurrences of merchants in sequences of transactions. Merchant vectors representing specific merchants are clustered to form merchant segments in a vector space as a function of the degree to which merchants co-occur more or less frequently than expected. Each merchant segment is trained using consumer transaction data in selected past time periods to predict spending in subsequent time periods for a consumer based on previous spending by the consumer. Consumer profiles describe summary statistics of consumer spending in and across merchant segments. Analysis of consumers associated with a segment identifies selected consumers according to predicted spending in the segment or other criteria, and the targeting of promotional offers specific to the segment and its merchants.

摘要翻译： 消费者财务行为的预测建模是通过将消费者交易数据应用于与商家细分相关联的预测模型来提供的。 商家细分来自消费者交易数据，这是根据交易顺序中商家的共同出现。 代表特定商户的商家向量被聚集以在向量空间中形成商家分段，作为商家与预期频繁地共同出现的程度的函数。 在选定的过去时间段内，使用消费者交易数据对每个商业细分进行培训，以根据消费者以前的消费来预测消费者的后续时间段的消费。 消费者个人资料描述了商业细分市场内外的消费支出总结统计。 根据分段或其他标准中的预测支出以及针对细分受众群及其商家的促销优惠的定位，对与细分相关联的消费者的分析识别所选择的消费者。

公开(公告)号：US5619709A

公开(公告)日：1997-04-08

申请号：US561167

申请日：1995-11-21

申请人： William R. Caid ,  Pu Oing

发明人： William R. Caid ,  Pu Oing

IPC分类号： G06F17/16 ,  G06F17/30

CPC分类号： G06F17/3069 ,  G06F17/30265 ,  G06F17/30696 ,  Y10S707/99932 ,  Y10S707/99935

摘要： A system and method for generating context vectors for use in storage and retrieval of documents and other information items. Context vectors represent conceptual relationships among information items by quantitative means. A neural network operates on a training corpus of records to develop relationship-based context vectors based on word proximity and co-importance using a technique of "windowed co-occurrence". Relationships among context vectors are deterministic, so that a context vector set has one logical solution, although it may have a plurality of physical solutions. No human knowledge, thesaurus, synonym list, knowledge base, or conceptual hierarchy, is required. Summary vectors of records may be clustered to reduce searching time, by forming a tree of clustered nodes. Once the context vectors are determined, records may be retrieved using a query interface that allows a user to specify content terms, Boolean terms, and/or document feedback. The present invention further facilitates visualization of textual information by translating context vectors into visual and graphical representations. Thus, a user can explore visual representations of meaning, and can apply human visual pattern recognition skills to document searches.

摘要翻译： 一种用于生成用于文件和其他信息项的存储和检索的上下文矢量的系统和方法。 上下文向量通过定量方式表示信息项之间的概念关系。 神经网络使用训练语料库来记录，以使用“窗口共现”技术基于词近似和共同重要性来开发基于关系的上下文向量。 上下文向量之间的关系是确定性的，因此上下文向量集具有一个逻辑解，尽管其可以具有多个物理解。 不需要人类知识，词库，同义词列表，知识库或概念层次结构。 可以通过形成聚类节点树来聚合记录的汇总向量以减少搜索时间。 一旦确定了上下文向量，就可以使用允许用户指定内容项，布尔项和/或文档反馈的查询界面来检索记录。 本发明通过将上下文矢量转换为视觉和图形表示来进一步促进文本信息的可视化。 因此，用户可以探索意义的视觉表示，并且可以应用人类视觉模式识别技能来记录搜索。

公开(公告)号：USRE42663E1

公开(公告)日：2011-08-30

申请号：US12729218

申请日：2010-03-22

申请人： Michael Lazarus ,  Larry S. Peranich ,  Frederique Vernhes ,  A. U. Matthias Blume ,  William R. Caid ,  Ted E. Dunning ,  Gerald R. Russell ,  Kevin Sitze

发明人： Michael Lazarus ,  Larry S. Peranich ,  Frederique Vernhes ,  A. U. Matthias Blume ,  William R. Caid ,  Ted E. Dunning ,  Gerald R. Russell ,  Kevin Sitze

IPC分类号： G06Q10/00

CPC分类号： G06Q30/02 ,  G06Q30/0202 ,  G06Q30/0207 ,  G06Q30/0241 ,  G06Q30/0255 ,  G06Q30/0269 ,  G06Q30/0601

摘要： Predictive modeling of consumer financial behavior, including determination of likely responses to particular marketing efforts, is provided by application of consumer transaction data to predictive models associated with merchant segments, which are derived from the consumer transaction data based on co-occurrences of merchants in sequences of transactions. Merchant vectors represent specific merchants, and are aligned in a vector space as a function of the degree to which the merchants co-occur. Supervised segmentation is applied to merchant vectors to form merchant segments. Merchant segment predictive models provide predictions of spending in each merchant segment for any particular consumer, based on previous spending by the consumer. Consumer profiles describe summary statistics of each consumer's spending in the merchant segments, and across merchant segments. Consumer profiles include consumer vectors derived as summary vectors of selected merchants patronized by the consumer. Predictions of consumer behavior are made by applying nearest-neighbor analysis to consumer vectors.

摘要翻译： 消费者财务行为的预测建模，包括对特定营销努力的可能响应的确定，通过将消费者交易数据应用于与商家分段相关联的预测模型来提供，所述预测模型是根据基于商家的序列顺序的消费者交易数据得出的消费者交易数据 的交易。 商家向量代表特定商家，并且在向量空间中对齐，作为商家共同发生的程度的函数。 监督分割被应用于商家向量以形成商家分段。 商业细分预测模型根据消费者以前的支出，为每个特定消费者的每个商业细分市场提供支出预测。 消费者个人资料描述了每个消费者在商家细分中以及跨商家细分的消费的总体统计。 消费者概况包括作为由消费者光顾的所选商家的汇总向量导出的消费者向量。 消费者行为的预测是通过对消费者向量应用最近邻分析来做出的。

公开(公告)号：USRE42577E1

公开(公告)日：2011-07-26

申请号：US12729215

申请日：2010-03-22

申请人： Matthias Blume ,  Michael A. Lazarus ,  Larry S. Peranich ,  Frederique Vernhes ,  William R. Caid ,  Ted E. Dunning ,  Gerald S. Russell ,  Kevin L. Sitze

发明人： Matthias Blume ,  Michael A. Lazarus ,  Larry S. Peranich ,  Frederique Vernhes ,  William R. Caid ,  Ted E. Dunning ,  Gerald S. Russell ,  Kevin L. Sitze

IPC分类号： G06Q10/00

CPC分类号： G06Q30/02 ,  G06Q30/0202 ,  G06Q30/0207 ,  G06Q30/0241 ,  G06Q30/0255 ,  G06Q30/0269 ,  G06Q30/0601

摘要： Predictive modeling of consumer financial behavior, including determination of likely responses to particular marketing efforts, is provided by application of consumer transaction data to predictive models associated with merchant segments. The merchant segments are derived from the consumer transaction data based on co-occurrences of merchants in sequences of transactions. Merchant vectors represent specific merchants, and are aligned in a vector space as a function of the degree to which the merchants co-occur more or less frequently than expected. Supervised segmentation is applied to merchant vectors to form the merchant segments. Merchant segment predictive models provide predictions of spending in each merchant segment for any particular consumer, based on previous spending by the consumer. Consumer profiles describe summary statistics of each consumer's spending in the merchant segments, and across merchant segments. The consumer profiles include consumer vectors derived as summary vectors of selected merchants patronized by the consumer. Predictions of consumer behavior are made by applying nearest-neighbor analysis to consumer vectors, thus facilitating the targeting of promotional offers to consumers most likely to respond positively.

摘要翻译： 通过将消费者交易数据应用于与商家细分相关的预测模型，提供消费者财务行为的预测建模，包括对特定营销努力的可能响应的确定。 商业细分是根据交易序列中商家的共同出现从消费者交易数据中得出的。 商家向量表示特定商家，并且在向量空间中对齐，作为商家与预期频繁相同程度的函数。 监督分割被应用于商家向量以形成商家分段。 商业细分预测模型根据消费者以前的支出，为每个特定消费者的每个商业细分市场提供支出预测。 消费者个人资料描述了每个消费者在商家细分中以及跨商家细分的消费的总体统计。 消费者资料包括作为由消费者光顾的所选商家的汇总向量导出的消费者向量。 消费者行为的预测是通过对消费者向量应用最近邻分析来做出的，从而有助于向最有可能积极响应的消费者定位促销优惠。

公开(公告)号：US07165037B2

公开(公告)日：2007-01-16

申请号：US11012812

申请日：2004-12-14

申请人： Michael A. Lazarus ,  Larry S. Peranich ,  Frederique Vernhes ,  A. U. Mattias Blume ,  Kenneth B. Brown ,  William R. Caid ,  Ted E. Dunning ,  Gerald R. Russell ,  Kevin L. Sitze

发明人： Michael A. Lazarus ,  Larry S. Peranich ,  Frederique Vernhes ,  A. U. Mattias Blume ,  Kenneth B. Brown ,  William R. Caid ,  Ted E. Dunning ,  Gerald R. Russell ,  Kevin L. Sitze

IPC分类号： G06Q10/00

CPC分类号： G06Q30/02 ,  G06Q30/0202 ,  G06Q30/0207 ,  G06Q30/0241 ,  G06Q30/0255 ,  G06Q30/0269 ,  G06Q30/0601

摘要： Predictive modeling of consumer financial behavior, including determination of likely responses to particular marketing efforts, is provided by application of consumer transaction data to predictive models associated with merchant segments, which are derived from the consumer transaction data based on co-occurrences of merchants in sequences of transactions. Merchant vectors represent specific merchants, and are aligned in a vector space as a function of the degree to which the merchants co-occur. Supervised segmentation is applied to merchant vectors to form merchant segments. Merchant segment predictive models provide predictions of spending in each merchant segment for any particular consumer, based on previous spending by the consumer. Consumer profiles describe summary statistics of each consumer's spending in the merchant segments, and across merchant segments. Consumer profiles include consumer vectors derived as summary vectors of selected merchants patronized by the consumer. Predictions of consumer behavior are made by applying nearest-neighbor analysis to consumer vectors.

摘要翻译： 消费者财务行为的预测建模，包括对特定营销努力的可能响应的确定，通过将消费者交易数据应用于与商家分段相关联的预测模型来提供，所述预测模型是根据基于商家的序列顺序的消费者交易数据得出的消费者交易数据 的交易。 商家向量代表特定商家，并且在向量空间中对齐，作为商家共同发生的程度的函数。 监督分割被应用于商家向量以形成商家分段。 商业细分预测模型根据消费者以前的支出，为每个特定消费者的每个商业细分市场提供支出预测。 消费者个人资料描述了每个消费者在商家细分中以及跨商家细分的消费的总体统计。 消费者概况包括作为由消费者光顾的所选商家的汇总向量导出的消费者向量。 消费者行为的预测是通过对消费者向量应用最近邻分析来做出的。