公开(公告)号：US10354309B2

公开(公告)日：2019-07-16

申请号：US15049677

申请日：2016-02-22

Applicant: eBay Inc.

Inventor： Rami El-Charif ,  Sanjay Pundlkrao Ghatare ,  Steven Chen ,  Olivier G. Dumon ,  Muhammad Faisal Rehman ,  Guanglei Song

IPC: G06F17/30 ,  G06Q30/06 ,  G06F16/248 ,  G06F16/951 ,  G06F16/33 ,  G06F16/9535 ,  G06F16/2457

Abstract: Methods and systems for simulating a search, for the purpose of evaluating one or more scoring functions used in ordering item listings for presentation in a search results page are described. Consistent with some embodiments, a simulation platform includes a real-time simulation module that receives search result sets for search queries that result in the conclusion of a transaction. The result set is then processed by the simulation platform with one or more test scoring functions, such that the resulting position of the item listing that has resulted in the transaction can be compared with the actual position at which the item listing was displayed in the actual search results. For each test scoring function, an average rank shift metric is determined, and displayed, thereby providing a metric with which to base decisions about which scoring functions to use in the production system.

公开(公告)号：US20170091275A1

公开(公告)日：2017-03-30

申请号：US15375144

申请日：2016-12-11

Applicant: eBay Inc.

Inventor： Qian Zhong ,  Guanglei Song ,  Zhaohui Chen

IPC: G06F17/30

CPC classification number: G06F16/24544 ,  G06F16/2246 ,  G06F16/2282 ,  G06F16/2456 ,  G06F16/24575 ,  G06F16/24578 ,  G06F16/285 ,  G06Q30/02

Abstract: In various example embodiments, systems and methods for providing category aspect information by mining historical data is provided. In example embodiments, a table comprising joined data is accessed. The table includes historical data that comprises user behavior data based on actions performed with past queries by users, data describing publication, and a determined category for each publication. Demand scores based on the joined data are determined. The determined demand scores are used to determine most relevant aspect name and aspect value pairs for a category. Publications having at least one of the most relevant aspect name and aspect value pairs are displayed visually distinguished from less relevant publications that exclude the most relevant aspect name and aspect value pairs.

公开(公告)号：US20140164387A1

公开(公告)日：2014-06-12

申请号：US14180649

申请日：2014-02-14

Applicant: eBay Inc.

Inventor： Yan Chen ,  Joseph Anthony Beynon ,  Baruch Perlov ,  Sanjay Pundlkrao Ghatare ,  Alvaro Bolivar ,  Nishith Parikh ,  Karin Mauge' ,  Guanglei Song

IPC: G06F17/30

CPC classification number: G06F16/285 ,  G06F16/36

Abstract: Systems and methods for generating data dictionaries are disclosed. In one example, a system comprises a candidate list generator module to generate a list of keywords from search query information, a validation module to validate candidate token pairs based on a divergence value wherein candidate token pairs having divergence values exceeding a divergence threshold are valid token pairs, and a data dictionary module to receive the validated token pairs as entries in a vocabulary, and provide the validated token pairs in response to a search query containing a keyword corresponding to at least one entry in the vocabulary.

Abstract translation: 公开了生成数据字典的系统和方法。 在一个示例中，系统包括候选列表生成器模块，用于从搜索查询信息生成关键字列表，基于发散值来验证候选令牌对的验证模块，其中具有超出发散阈值的发散值的候选令牌对是有效的令牌 以及数据字典模块，用于接收经验证的令牌对作为词汇表中的条目，并且响应于包含与词汇表中的至少一个条目相对应的关键字的搜索查询来提供经验证的令牌对。

公开(公告)号：US09519702B2

公开(公告)日：2016-12-13

申请号：US15071309

申请日：2016-03-16

Applicant: eBay Inc.

Inventor： Qian Zhong ,  Guanglei Song ,  Zhaohui Chen

IPC: G06F17/30 ,  G06Q30/02

CPC classification number: G06F17/30466 ,  G06F17/30327 ,  G06F17/30339 ,  G06F17/30498 ,  G06F17/30528 ,  G06F17/3053 ,  G06F17/30598 ,  G06Q30/02

Abstract: Systems and methods for providing category aspect information by mining historical data is provided. A table comprising joined data is accessed. The table includes historical data that comprises user behavior data based on actions performed with past queries by users listing data that includes aspect data for each listing and a determined category for each listing. Demand scores based on the joined data are determined. The determined demand scores are used to determine at least one relevant aspect name for a category. A message is transmitted for display on a device of the user that indicates the at least one most relevant aspect name for the category and suggests the user provide an aspect value that corresponds to the at least one most relevant aspect name to be included in a new listing.

Abstract translation: 提供了通过挖掘历史数据提供类别方面信息的系统和方法。 访问包含连接数据的表。 该表包括历史数据，其包括基于用户列出包括每个列表的方面数据的数据的过去查询执行的操作的用户行为数据以及每个列表的确定类别。 确定基于加入数据的需求分数。 确定的需求分数用于确定类别的至少一个相关方面名称。 发送消息以在用户的​​设备上显示以指示该类别的至少一个最相关的方面名称，并且建议用户提供对应于要包括在新的至少一个最相关方面名称中的方面值 清单。

公开(公告)号：US20160171587A1

公开(公告)日：2016-06-16

申请号：US15049677

申请日：2016-02-22

Applicant: eBay Inc.

Inventor： Rami El-Charif ,  Sanjay Pundlkrao Ghatare ,  Steven Chen ,  Olivier G. Dumon ,  Muhammad Faisal Rehman ,  Guanglei Song

IPC: G06Q30/06 ,  G06F17/30

CPC classification number: G06Q30/0629 ,  G06F16/24578 ,  G06F16/248 ,  G06F16/3331 ,  G06F16/951 ,  G06F16/9535

Abstract: Methods and systems for simulating a search, for the purpose of evaluating one or more scoring functions used in ordering item listings for presentation in a search results page are described. Consistent with some embodiments, a simulation platform includes a real-time simulation module that receives search result sets for search queries that result in the conclusion of a transaction. The result set is then processed by the simulation platform with one or more test scoring functions, such that the resulting position of the item listing that has resulted in the transaction can be compared with the actual position at which the item listing was displayed in the actual search results. For each test scoring function, an average rank shift metric is determined, and displayed, thereby providing a metric with which to base decisions about which scoring functions to use in the production system.

Abstract translation: 描述了用于模拟搜索的方法和系统，用于评估在排序项目列表中用于在搜索结果页面中呈现的一个或多个评分函数。 与一些实施例一致，仿真平台包括实时模拟模块，其接收导致交易结束的搜索查询的搜索结果集。 然后，结果集由仿真平台处理，具有一个或多个测试评分功能，使得导致事务的项目列表的结果位置可以与在实际中显示项目列表的实际位置进行比较 搜索结果。 对于每个测试评分函数，确定并显示平均排位移度量，从而提供用于基于关于在生产系统中使用的评分功能的决定的度量。

公开(公告)号：US20140032593A1

公开(公告)日：2014-01-30

申请号：US13730583

申请日：2012-12-28

Applicant: EBAY INC.

Inventor： Davide Libenzi ,  Richard D. Henderson ,  Anand Lakshminath ,  Guanglei Song ,  Prasad Sriram ,  Nicholas Whyte

IPC: G06F17/30

CPC classification number: G06F16/316 ,  G06F16/2228 ,  G06F16/245 ,  G06F16/24578 ,  G06F16/319 ,  G06F16/337 ,  G06F16/93

Abstract: Systems and methods to process a query with a unified storage interface are described. The system receives a query from a client machine and generates a query expression tree based on the query expression. The system generates a cursor expression tree based on the query expression tree. The system executes a plurality of software components in the cursor expression tree to retrieve data from a first storage device. The plurality of software components comprise a first software component that is utilized to retrieve data irrespective of a plurality of storage devices and a second software component that is utilized to retrieve data from a first storage device. Finally, the system communicates search results to the client machine, the search results include at least a portion of the data.

Abstract translation: 描述使用统一存储接口处理查询的系统和方法。 系统从客户机接收查询，并根据查询表达式生成查询表达式树。 系统基于查询表达式树生成游标表达式树。 系统在光标表达树中执行多个软件组件以从第一存储设备检索数据。 多个软件组件包括用于检索数据的第一软件组件，而不管多个存储设备以及用于从第一存储设备检索数据的第二软件组件。 最后，系统将搜索结果传达给客户机，搜索结果至少包括一部分数据。

公开(公告)号：US10459919B2

公开(公告)日：2019-10-29

申请号：US15375144

申请日：2016-12-11

Applicant: eBay Inc.

Inventor： Qian Zhong ,  Guanglei Song ,  Zhaohui Chen

IPC: G06F16/30 ,  G06F16/2453 ,  G06F16/28 ,  G06F16/22 ,  G06F16/2455 ,  G06F16/2457 ,  G06Q30/02

Abstract: In various example embodiments, systems and methods for providing category aspect information by mining historical data is provided. In example embodiments, a table comprising joined data is accessed. The table includes historical data that comprises user behavior data based on actions performed with past queries by users, data describing publication, and a determined category for each publication. Demand scores based on the joined data are determined. The determined demand scores are used to determine most relevant aspect name and aspect value pairs for a category. Publications having at least one of the most relevant aspect name and aspect value pairs are displayed visually distinguished from less relevant publications that exclude the most relevant aspect name and aspect value pairs.

公开(公告)号：US20160196329A1

公开(公告)日：2016-07-07

申请号：US15071309

申请日：2016-03-16

Applicant: eBay Inc.

Inventor： Qian Zhong ,  Guanglei Song ,  Zhaohui Chen

IPC: G06F17/30

CPC classification number: G06F17/30466 ,  G06F17/30327 ,  G06F17/30339 ,  G06F17/30498 ,  G06F17/30528 ,  G06F17/3053 ,  G06F17/30598 ,  G06Q30/02

Abstract: In various example embodiments, systems and methods for providing category aspect information by mining historical data is provided. In example embodiments, a table comprising joined data is accessed. The table includes historical data that comprises user behavior data based on actions performed with past queries by users, listing data that includes aspect data for each listing, and a determined category for each listing. Demand scores based on the joined data are determined. The determined demand scores are used to determine at least one relevant aspect name for a category. A message is transmitted for display on a device of the user that indicates the at least one most relevant aspect name for the category and suggests the user provide an aspect value that corresponds to the at least one most relevant aspect name to be included in a new listing.

Abstract translation: 在各种示例性实施例中，提供了通过挖掘历史数据来提供类别方面信息的系统和方法。 在示例实施例中，访问包括连接数据的表。 该表包括历史数据，其包括基于用户过去查询执行的操作的用户行为数据，列出包括每个列表的方面数据的数据，以及每个列表的确定类别。 确定基于加入数据的需求分数。 确定的需求分数用于确定类别的至少一个相关方面名称。 发送消息以在用户的​​设备上显示以指示该类别的至少一个最相关的方面名称，并且建议用户提供对应于要包括在新的至少一个最相关方面名称中的方面值 清单。