-
公开(公告)号：US11809375B2
公开(公告)日：2023-11-07
申请号：US17368338
申请日：2021-07-06
CPC分类号： G06F16/164 , G06N5/04 , G06N20/00
摘要： Methods and systems for multi-dimensional data labeling. A structured data set having a plurality of rows is obtained, the structured data set comprising a set of data attributes, each data attribute having a data value for each of the plurality of rows of the structured data set. The structured data set is decomposed into a plurality of dimensions, each dimension defining a proper subset of the data attributes based on coherence criterion. A dimension label is obtained for each dimension of at least a portion of the plurality of rows of the structured data set and the dimension labels for a given one of the rows of the structured data set are consolidated into at least one row label for the given one of the rows.
-
公开(公告)号：US20210174196A1
公开(公告)日：2021-06-10
申请号：US16708792
申请日：2019-12-10
摘要： Methods, systems and computer program products for improving ground truth quality for modeling are provided. Aspects include receiving a plurality of data inputs, wherein each of the plurality of data inputs has an associated label. Aspects also include training a model based on the plurality of data inputs. Aspects also include generating a plurality of vector representations corresponding to the plurality of data inputs based on the model. Aspects also include clustering the plurality of vector representations into one or more clusters. Aspects also include identifying at least one anomalous data input based on the one or more clusters. The at least one anomalous data input can be a data input of the plurality of data inputs that is mislabeled, contributes to an ambiguous class structure or is an outlier. Aspects also include outputting a notification that provides an indication of the at least one anomalous data input.
-
公开(公告)号：US09218321B2
公开(公告)日：2015-12-22
申请号：US13752483
申请日：2013-01-29
发明人： Rachel K. E. Bellamy , Michael Desmond , Jacquelyn A. Martino , Paul M. Matchen , Harold L. Ossher , John T. Richards , Calvin B. Swart
CPC分类号： G06F17/21 , G06F17/20 , G06F17/30277 , G06F17/30722
摘要： Mechanisms are provided for generating a shape tag cloud display. A user input is received that specifies an arbitrarily hand-drawn shape tag. A set of shape tag equivalence classes is updated based on the received user input to assign the arbitrarily hand-drawn shape tag to a shape tag equivalence class having similar previously entered arbitrarily hand-drawn shape tags. Rankings of the shape tags relative to one another are generated. The shape tag cloud display is generated based on the rankings. A representation of each shape tag within the shape tag cloud display has display characteristics based on the rankings. The shape tag cloud display is then output.
摘要翻译： 提供了用于生成形状标签云显示的机制。 接收到指定任意手绘形状标签的用户输入。 基于所接收的用户输入更新一组形状标签等价类，以将任意的手绘形状标签分配给具有类似的先前输入的任意手绘形状标签的形状标签等价类。 生成形状标签相对于彼此的排列。 根据排名生成形状标签云显示。 形状标签云显示中每个形状标签的表示具有基于排名的显示特征。 然后输出形状标签云显示。
-
4.发明申请公开(公告)号：US20150046217A1
公开(公告)日：2015-02-12
申请号：US13960909
申请日：2013-08-07
CPC分类号： G06Q30/0202 , G06Q50/01
摘要： A method for identifying influence on user interest for products and ability of users and products to be influenced is disclosed. A processor identifies a degree of influence a number of influencers has over user interest for each of a number of products based on a history of user interest of a number of users for the number of products, wherein each influencer in the number of influencers as one of a user in the number of users and a product in the number of products. The processor also identifies a degree of ability of one or more of the number of users and the number of products to be influenced based on the degree of influence of each of the number of influencers and a number of relationships between the one or more of the number of users and the number of products and the number of influencers.
摘要翻译： 公开了一种识别对用户对产品的兴趣影响的方法，以及影响用户和产品的能力。 处理器基于用户对于多个产品数量的用户兴趣的历史来确定多个影响者对于多个产品中的每一个的用户兴趣的影响程度，其中影响者的数量的每个影响者作为一个 一个用户的用户数量和一个产品数量的产品。 处理器还根据每个影响者数量的影响程度以及一个或多个用户的数量之间的关系程度来识别一个或多个用户的数量和受影响的产品数量的程度。 用户数量和产品数量以及影响力的数量。
-
公开(公告)号：US11941493B2
公开(公告)日：2024-03-26
申请号：US16287224
申请日：2019-02-27
摘要： A method optimizes a training of a machine learning system. A conflict detection system discovers a conflict between a first training data and a second training data for a machine learning system, where the first training data and the second training data are ground truths that describe a same type of entity, and where the first training data and the second training data have different labels. In response to discovering the conflict between the first training data and the second training data for the machine learning system, an oracle adjusts the different labels of the first training data and the second training data. The machine learning system is then trained using the first training data and the second training data with the adjusted labels.
-
公开(公告)号：US20170004428A1
公开(公告)日：2017-01-05
申请号：US14939200
申请日：2015-11-12
发明人： Michael Desmond , Matous Havlena , Stacy F. Hobson , Minkyong Kim , Sophia Krasikov , Ying Li , Robin Lougee , Valentina Salapura
IPC分类号： G06Q10/06
摘要： A method for generating event profiles comprises receiving source data in a processor, extracting an attire property from the source data, extracting an event attribute from the source data, associating the attire property with the event attribute, generating an event profile that includes the associated attire property and the event attribute, and saving the event profile in a memory.
摘要翻译： 一种用于生成事件简档的方法，包括在处理器中接收源数据，从源数据提取服装属性，从源数据提取事件属性，将服装属性与事件属性相关联，生成包括相关服装的事件简档 属性和事件属性，并将事件配置文件保存在内存中。
-
公开(公告)号：US20160148242A1
公开(公告)日：2016-05-26
申请号：US14552528
申请日：2014-11-25
发明人： Michael Desmond , Sophia Krasikov , Juan Fernando Mancilla Caceres , Harini Srinivasan , Emmanuel Yashchin
IPC分类号： G06Q30/02
CPC分类号： G06Q30/0226
摘要： A set of current and historical electronic activity data are received from a customer. The activity data corresponds to the customer's interaction with an electronic product entry within a store. One or more electronic activities can be associated with one or more predetermined seller objectives. The seller's objectives are based on maximizing financial profit and minimizing cost of reward distribution. A reward score value is assigned to a customer based on an association between one or more of the customer's electronic activities and one or more of the predetermined seller objectives. A reward is selected based on the reward score wherein the rewards are also associated with one or more of the predetermined seller objectives, also based on the reward score value. The selected reward associated with the calculated reward score is communicated to the customer.
摘要翻译： 从客户接收一组当前和历史的电子活动数据。 活动数据对应于客户与商店内的电子产品入口的交互。 一个或多个电子活动可以与一个或多个预定卖方目标相关联。 卖方的目标是以最大限度地提高财务利润为目标，并尽量减少奖励分配成本。 基于一个或多个客户的电子活动与一个或多个预定卖方目标之间的关联，向客户分配奖励积分值。 基于奖励分数来选择奖励，其中奖励也与预定卖家目标中的一个或多个相关联，也基于奖励得分值。 与计算的奖励分数相关联的所选奖励被传达给客户。
-
公开(公告)号：US09244889B2
公开(公告)日：2016-01-26
申请号：US13752550
申请日：2013-01-29
发明人： Rachel K. E. Bellamy , Michael Desmond , Jacquelyn A. Martino , Paul M. Matchen , Harold L. Ossher , John T. Richards , Calvin B. Swart
CPC分类号： G06F17/21 , G06F17/20 , G06F17/30277 , G06F17/30722
摘要： Mechanisms are provided for generating a shape tag cloud display. A user input is received that specifies an arbitrarily hand-drawn shape tag. A set of shape tag equivalence classes is updated based on the received user input to assign the arbitrarily hand-drawn shape tag to a shape tag equivalence class having similar previously entered arbitrarily hand-drawn shape tags. Rankings of the shape tags relative to one another are generated. The shape tag cloud display is generated based on the rankings. A representation of each shape tag within the shape tag cloud display has display characteristics based on the rankings. The shape tag cloud display is then output.
-
公开(公告)号：US11379718B2
公开(公告)日：2022-07-05
申请号：US16708792
申请日：2019-12-10
摘要： Methods, systems and computer program products for improving ground truth quality for modeling are provided. Aspects include receiving a plurality of data inputs, wherein each of the plurality of data inputs has an associated label. Aspects also include training a model based on the plurality of data inputs. Aspects also include generating a plurality of vector representations corresponding to the plurality of data inputs based on the model. Aspects also include clustering the plurality of vector representations into one or more clusters. Aspects also include identifying at least one anomalous data input based on the one or more clusters. The at least one anomalous data input can be a data input of the plurality of data inputs that is mislabeled, contributes to an ambiguous class structure or is an outlier. Aspects also include outputting a notification that provides an indication of the at least one anomalous data input.
-
10.发明申请公开(公告)号：US20210166079A1
公开(公告)日：2021-06-03
申请号：US16701128
申请日：2019-12-02
发明人： Matthew Arnold , Evelyn Duesterwald , Darrell Reimer , Michael Desmond , Harold Leon Ossher , Robert Yates
摘要： The generating of actionable recommendations for tuning model metrics of an Artificial Intelligence (AI) system includes partitioning a key performance indicator (KPI) range associated with a target system into a plurality of buckets. Log data including at least one KPI of the target system and one or more AI model metrics is partitioned and distributed across the plurality of buckets. For each bucket, an aggregate value of the one or more AI model metrics across the log data is computed and weighted according to the volume of log data in that bucket. A correlation factor between the aggregate value and a representative KPI value for each bucket is determined. A model tuning recommendation to increase ranking of the AI model metrics according to the determined correlation factor is provided to an output device and/or to the AI system for updating the one or more AI model.
-
-
-
-
-
-
-
-
-
搜索结果
23 条记录 (耗时 0.022 秒)
