公开(公告)号：US11176145B2

公开(公告)日：2021-11-16

申请号：US15295318

申请日：2016-10-17

Applicant: eBay Inc.

Inventor： Ashish Gupta ,  Ranjan Sinha

IPC: G06F16/2457 ,  G06F16/248 ,  G06F16/31

Abstract: In various example embodiments, a system and method for constructing and scoring word vectors between natural language words and generating output to a user in the form of personalized recommendations are presented.

公开(公告)号：US09699049B2

公开(公告)日：2017-07-04

申请号：US14586381

申请日：2014-12-30

Applicant: eBay Inc.

Inventor： Chaitali Gupta ,  Mayank Bansal ,  Tzu-Cheng Chuang ,  Ranjan Sinha ,  Sami Ben-Romdhane

IPC: H04L12/26 ,  H04L12/24 ,  G06N99/00

CPC classification number: H04L43/08 ,  G06N99/005 ,  H04L41/0896 ,  H04L41/142 ,  H04L41/147 ,  H04L41/16

Abstract: In an example embodiment, clusters of nodes in a network are monitored. Then the monitored data may be stored in an open time-series database. Data from the open time-series database is collected and labeled it as training data. Then a model is built through machine learning using the training data. Additional data is retrieved from the open time-series database. The additional data is left as unlabeled. Anomalies in the unlabeled data are computed using the model, producing prediction outcomes and metrics. Finally, the prediction outcomes and the network.

公开(公告)号：US20220035826A1

公开(公告)日：2022-02-03

申请号：US17501855

申请日：2021-10-14

Applicant: eBay Inc.

Inventor： Ashish Gupta ,  Ranjan Sinha

IPC: G06F16/2457 ,  G06F16/248 ,  G06F16/31

Abstract: In various example embodiments, a system and method for constructing and scoring word vectors between natural language words and generating output to a user in the form of personalized recommendations are presented.

公开(公告)号：US20170109357A1

公开(公告)日：2017-04-20

申请号：US15295318

申请日：2016-10-17

Applicant: eBay Inc.

Inventor： Ashish Gupta ,  Ranjan Sinha

IPC: G06F17/30

CPC classification number: G06F16/24578 ,  G06F16/24575 ,  G06F16/248 ,  G06F16/313

Abstract: In various example embodiments, a system and method for constructing and scoring word vectors between natural language words and generating output to a user in the form of personalized recommendations are presented.

公开(公告)号：US20150286645A1

公开(公告)日：2015-10-08

申请号：US14680018

申请日：2015-04-06

Applicant: eBay Inc.

Inventor： Ranjan Sinha ,  Charles Bracher ,  Matthias Spycher

IPC: G06F17/30

CPC classification number: G06F17/30867 ,  G06F17/30699

Abstract: A personalization system includes a user events module configured to receive a plurality of user events, each user event of the plurality of user events including one or more of a transactional event and a behavioral event associated with the online user, and a personalization cluster including a plurality of personalization servers, each personalization server of the plurality of personalization servers configured to receive a personalization request from a requesting system, the personalization request including a plurality of intermediate results identified by the requesting system, each intermediate result representing a possible outcome that may be presented by the requesting system to the online user, compute a score for each intermediate result of the plurality of immediate results based at least in part on the plurality of user events, thereby generating a plurality of scores, and return the plurality of scores to the requesting system.

Abstract translation: 个性化系统包括被配置为接收多个用户事件的用户事件模块，所述多个用户事件的每个用户事件包括与在线用户相关联的事务事件和行为事件中的一个或多个，以及包括 多个个性化服务器，多个个性化服务器的每个个性化服务器被配置为从请求系统接收个性化请求，个性化请求包括由请求系统标识的多个中间结果，每个中间结果表示可能的结果 由所述请求系统向所述在线用户呈现，至少部分地基于所述多个用户事件来计算所述多个即时结果的每个中间结果的分数，从而生成多个分数，并将所述多个分数返回到 请求系统。