公开(公告)号：US20140379329A1

公开(公告)日：2014-12-25

申请号：US14311079

申请日：2014-06-20

Applicant: Alibaba Group Holding Limited

Inventor： Xinghua Dong ,  Kewen Wu ,  Peng Huang ,  Feng Lin

IPC: G06F17/27

CPC classification number: G06F17/2775 ,  G06F17/275 ,  G06F17/2795 ,  G06F17/2827

Abstract: The present disclosure is related to a method and an apparatus of mining synonymous phrases. The method comprises: obtaining, according to a parallel text corpus, a first phrase-alignment relationship from phrases of a current language to phrases of an intermediate language, and a second phrase-alignment relationship from the phrases of the intermediate language to the phrases of the current language; obtaining, for a target phrase of current language, a first set of aligned phrases of the intermediate language that are aligned with the target phrase of the current language based on the first phrase-alignment relationship; obtaining a second set of aligned phrases of the current language that are aligned with selected phrase(s) in the first set of aligned phrases based on the second phrase-alignment relationship; and obtaining synonymous phrases for the target phrase from the second set of aligned phrases.

Abstract translation: 本公开涉及挖掘同义短语的方法和装置。 该方法包括：根据平行文本语料库获得从当前语言的短语到中间语言的短语的第一短语对齐关系，以及从中间语言的短语到短语的第二短语对齐关系 当前语言; 针对当前语言的目标短语获得基于第一短语对齐关系与当前语言的目标短语对准的中间语言的第一组对齐短语; 基于第二短语对齐关系，获得与第一组对齐短语中的所选短语对准的当前语言的第二组对齐短语; 并从第二组对齐的短语中获取目标短语的同义词。

公开(公告)号：US10025807B2

公开(公告)日：2018-07-17

申请号：US14022634

申请日：2013-09-10

Applicant: Alibaba Group Holding Limited

Inventor： Linfeng Zhang ,  Peng Huang ,  Xipu Wang ,  Wenbin Zheng

IPC: G06F17/30 ,  G06Q30/02

Abstract: Acquiring dynamic data is disclosed including extracting a search term from a search request string that is received, looking up the search term in a threshold value dictionary to acquire a dynamic threshold score corresponding to the search term, using the search term as a query condition and the dynamic threshold score corresponding to the search term as a filter condition to acquire, in an index data table, one or more corresponding pieces of index information, acquiring data information corresponding to the search term based on the index information in the index data table, and sending the data information to be displayed in a page of a website. The dynamic threshold score varies based on a characteristic factor.

公开(公告)号：US20160085871A1

公开(公告)日：2016-03-24

申请号：US14958817

申请日：2015-12-03

Applicant: Alibaba Group Holding Limited

Inventor： Feng Lin ,  Zhanhui Kang ,  Peng Huang

IPC: G06F17/30 ,  H04L29/06

CPC classification number: G06F17/30867 ,  G06F17/30345 ,  G06F17/30528 ,  G06F17/30598 ,  G06F17/3064 ,  G06F17/30643 ,  G06F17/30864 ,  H04L67/42

Abstract: Searching information includes: receiving current query data from a client; extracting generic attribute features of the current query data, wherein the generic attribute features are used for calculating a plurality of confidence degrees of the current query data that correspond to a plurality of categories, each of the confidence degrees indicating a degree of confidence that the current query data belongs to a respective one of the plurality of categories; determining the plurality of confidence degrees of the current query data based at least in part on the generic attribute features; selecting a category based at least in part on the plurality of confidence degrees, the selected category being one of the plurality of categories and having a confidence degree higher than a confidence degree of another category; searching in the selected category for a search result that corresponds to the current query data; and returning the search result.

Abstract translation: 搜索信息包括：从客户端接收当前查询数据; 提取当前查询数据的通用属性特征，其中通用属性特征用于计算对应于多个类别的当前查询数据的多个置信度，每个置信度表示当前信任度的置信度 查询数据属于多个类别中的相应一个; 至少部分地基于通用属性特征来确定当前查询数据的多个置信度; 至少部分地基于所述多个置信度来选择类别，所选择的类别是所述多个类别之一并且具有高于另一类别的置信度的置信度; 在所选类别中搜索与当前查询数据相对应的搜索结果; 并返回搜索结果。

公开(公告)号：US20150039604A1

公开(公告)日：2015-02-05

申请号：US14486666

申请日：2014-09-15

Applicant: Alibaba Group Holding Limited

Inventor： Huaxing Jin ,  Wei Zheng ,  Peng Huang ,  Xu Yang ,  Feng Lin ,  Jiong Feng ,  Qin Zhang

IPC: G06F17/30

CPC classification number: G06F17/3053 ,  G06F17/30964

Abstract: Ordering search results may include obtaining an exposed log file from a log system, computing a Bayesian posterior probability for relevancy between the log file and a search request, computing an expected value of the relevancy between the log file and the search request based on the Bayesian posterior probability, storing the search request and an identifier of the log file as a key and the expected value of the relevancy between the log file and the search request as a value into a search data structure, in response to receiving a search request submitted by a user, finding expected values of relevancy between the submitted search request and log files that are relevant to the submitted search request from the search data structure, and ordering the found log files in a descending order of the expected values.

Abstract translation: 订购搜索结果可以包括从日志系统获取暴露的日志文件，计算日志文件和搜索请求之间的相关性的贝叶斯后验概率，基于贝叶斯计算日志文件和搜索请求之间的相关性的期望值 后验概率，响应于接收到由所述搜索请求提交的搜索请求，将所述搜索请求和所述日志文件的标识符作为密钥存储，并将所述日志文件和所述搜索请求之间的相关性的期望值作为值存储到搜索数据结构中 一个用户，从搜索数据结构中找到所提交的搜索请求和与提交的搜索请求相关的日志文件之间的相关性的预期值，并按照预期值的降序对找到的日志文件进行排序。

公开(公告)号：US20140074851A1

公开(公告)日：2014-03-13

申请号：US14022634

申请日：2013-09-10

Applicant: Alibaba Group Holding Limited

Inventor： Linfeng Zhang ,  Peng Huang ,  Xipu Wang ,  Wenbin Zheng

IPC: G06F17/30

CPC classification number: G06F17/30339 ,  G06Q30/0201

Abstract: Embodiments of the present application relate to a dynamic data acquisition method, a dynamic data acquisition system, and a computer program product for dynamically acquiring data. A dynamic data acquisition method is provided. The method includes extracting a search term from a search request string that is received, looking up the search term in a threshold value dictionary to acquire a dynamic threshold score corresponding to the search term, using the search term as a query condition and the dynamic threshold score corresponding to the search term as a filter condition to acquire, in an index data table, one or more corresponding pieces of index information, acquiring data information corresponding to the search term based on the index information in the index data table, and sending the data information to be displayed in a page of a website. The dynamic threshold score varies based on a characteristic factor.

Abstract translation: 本申请的实施例涉及动态数据获取方法，动态数据采集系统和用于动态获取数据的计算机程序产品。 提供动态数据采集方法。 该方法包括从接收到的搜索请求字符串中提取搜索项，在阈值字典中查找搜索项以获取与搜索项对应的动态阈值分数，使用搜索项作为查询条件，并且动态阈值 对应于搜索项的分数作为过滤条件，以在索引数据表中获取索引信息的一个或多个相应索引，基于索引数据表中的索引信息获取与搜索项对应的数据信息，并且发送 要显示在网页的数据信息。 动态阈值分数根据特征因素而变化。

公开(公告)号：US09230025B2

公开(公告)日：2016-01-05

申请号：US14019427

申请日：2013-09-05

Applicant: Alibaba Group Holding Limited

Inventor： Feng Lin ,  Zhanhui Kang ,  Peng Huang

IPC: G06F17/30

CPC classification number: G06F17/30867 ,  G06F17/30345 ,  G06F17/30528 ,  G06F17/30598 ,  G06F17/3064 ,  G06F17/30643 ,  G06F17/30864 ,  H04L67/42

Abstract: Searching information includes: receiving current query data from a client; extracting generic attribute features of the current query data, wherein the generic attribute features are used for calculating a plurality of confidence degrees of the current query data that correspond to a plurality of categories, each of the confidence degrees indicating a degree of confidence that the current query data belongs to a respective one of the plurality of categories; determining the plurality of confidence degrees of the current query data based at least in part on the generic attribute features; selecting a category based at least in part on the plurality of confidence degrees, the selected category being one of the plurality of categories and having a confidence degree higher than a confidence degree of another category; searching in the selected category for a search result that corresponds to the current query data; and returning the search result.

Abstract translation: 搜索信息包括：从客户端接收当前查询数据; 提取当前查询数据的通用属性特征，其中通用属性特征用于计算对应于多个类别的当前查询数据的多个置信度，每个置信度表示当前信任度的置信度 查询数据属于多个类别中的相应一个; 至少部分地基于通用属性特征来确定当前查询数据的多个置信度; 至少部分地基于所述多个置信度来选择类别，所选择的类别是所述多个类别之一并且具有高于另一类别的置信度的置信度; 在所选类别中搜索与当前查询数据相对应的搜索结果; 并返回搜索结果。

公开(公告)号：US20150302476A1

公开(公告)日：2015-10-22

申请号：US14692586

申请日：2015-04-21

Applicant: Alibaba Group Holding Limited

Inventor： Kaiming Huang ,  Kewen Wu ,  Peng Huang ,  Bo Li ,  Feng Lin

IPC: G06Q30/02

CPC classification number: G06Q30/0256

Abstract: Candidate promotion keywords are selected. Features of the candidate promotion keywords are extracted. The features include at least one of a search engine feature, an effect feature of non-directed traffic, and a text feature. The features of the candidate promotion keywords are used as input data of a pre-established keyword screening model, and superior promotion keywords are obtained according to a prediction result of the keyword screening model.

Abstract translation: 选择候选推广关键字。 提取候选促销关键词的特征。 功能包括搜索引擎特征，非定向流量的效果特征和文本特征中的至少一个。 候选促销关键字的特征被用作预先建立的关键词筛选模型的输入数据，并且根据关键词筛选模型的预测结果获得优良的促销关键词。

公开(公告)号：US20140040229A1

公开(公告)日：2014-02-06

申请号：US14019427

申请日：2013-09-05

Applicant: Alibaba Group Holding Limited

Inventor： Feng Lin ,  Zhanhui Kang ,  Peng Huang

IPC: G06F17/30

CPC classification number: G06F17/30867 ,  G06F17/30345 ,  G06F17/30528 ,  G06F17/30598 ,  G06F17/3064 ,  G06F17/30643 ,  G06F17/30864 ,  H04L67/42

Abstract: Searching information includes: receiving current query data from a client; extracting generic attribute features of the current query data, wherein the generic attribute features are used for calculating a plurality of confidence degrees of the current query data that correspond to a plurality of categories, each of the confidence degrees indicating a degree of confidence that the current query data belongs to a respective one of the plurality of categories; determining the plurality of confidence degrees of the current query data based at least in part on the generic attribute features; selecting a category based at least in part on the plurality of confidence degrees, the selected category being one of the plurality of categories and having a confidence degree higher than a confidence degree of another category; searching in the selected category for a search result that corresponds to the current query data; and returning the search result.

Abstract translation: 搜索信息包括：从客户端接收当前查询数据; 提取当前查询数据的通用属性特征，其中通用属性特征用于计算对应于多个类别的当前查询数据的多个置信度，每个置信度表示当前信任度的置信度 查询数据属于多个类别中的相应一个; 至少部分地基于通用属性特征来确定当前查询数据的多个置信度; 至少部分地基于所述多个置信度来选择类别，所选择的类别是所述多个类别之一并且具有高于另一类别的置信度的置信度; 在所选类别中搜索与当前查询数据相对应的搜索结果; 并返回搜索结果。

公开(公告)号：US20150332315A1

公开(公告)日：2015-11-19

申请号：US14712749

申请日：2015-05-14

Applicant: Alibaba Group Holding Limited

Inventor： Jinjie Gu ,  Lihui Huang ,  Peng Huang ,  Wei Zheng ,  Feng Lin

IPC: G06Q30/02

CPC classification number: G06Q30/0246

Abstract: Methods and systems for establishing a click-through rate estimation model. A computing device may extract basic characteristics corresponding to a current language channel associated with a server provider. The computing device may combine the basic characteristics to obtain a combination characteristic. The computing device may further obtain an effective high-order characteristic based on the basic characteristics and the combination characteristic and calculate a weight of the effective high-order characteristic. The computing device may generate the CTR estimation model by applying a CTR equation to the weight corresponding to effective high-order characteristic. The implementations may not be limited by human factors, therefore achieving high efficiency in establishing CTR estimation models and high accuracy of the CTR estimation model.

Abstract translation: 建立点击率估算模型的方法和系统。 计算设备可以提取与与服务器提供商相关联的当前语言信道相对应的基本特征。 计算设备可以组合基本特征以获得组合特征。 计算装置还可以基于基本特征和组合特征获得有效的高阶特征，并计算有效高阶特征的权重。 计算设备可以通过将CTR等式应用于对应于有效高阶特征的权重来生成CTR估计模型。 这些实现可能不受人为因素的限制，因此在建立CTR估计模型和CTR估计模型的高精度方面实现高效率。

公开(公告)号：US10055741B2

公开(公告)日：2018-08-21

申请号：US14851464

申请日：2015-09-11

Applicant: Alibaba Group Holding Limited

Inventor： Tao Wang ,  Peng Huang ,  Feng Lin

IPC: G06F17/30 ,  G06Q30/00

CPC classification number: G06Q30/00 ,  G06F16/90324 ,  G06Q30/0242 ,  G06Q30/0251

Abstract: A method and an apparatus of matching an object to be displayed are disclosed. The method includes obtaining a plurality of search keywords and released product information and grouping each of the plurality of search keywords with the released product information to form a plurality of search keyword and released product information pairs, with each search keyword and released product information pair comprising a respective search keyword and the released product information; determining and matching a plurality of features for the plurality of search keyword and released product information pairs according to a constructed first decision tree; and determining respective correlation classes of the plurality of search keyword and released product information pairs based at least in part on a result of determining and matching of the plurality of features. The disclosed method and apparatus are able to accurately and conveniently determine a matching degree between a search keyword and released product information.