公开(公告)号：US10402449B2

公开(公告)日：2019-09-03

申请号：US15105840

申请日：2014-03-18

申请人： Rakuten, Inc.

发明人： Keiji Shinzato

IPC分类号： G06F16/58 ,  G06F16/54 ,  G06F16/248 ,  G06F16/951

摘要： An information processing system according to one embodiment includes an extraction unit and a generation unit. The extraction unit extracts a word specified by a user and contained in a request transmitted from a user terminal and an image displayed as a choice on the user terminal in response to the request. The generation unit generates combination data by associating image data corresponding to the image and obtained from an image storage unit with a name based on the word.

公开(公告)号：US09311607B2

公开(公告)日：2016-04-12

申请号：US13984382

申请日：2013-01-30

申请人： Rakuten, Inc.

发明人： Keiji Shinzato

IPC分类号： G06F15/00 ,  G06F15/18 ,  G06N99/00 ,  G06F17/30

CPC分类号： G06N99/005 ,  G06F17/30268

摘要： A base word to be a base, a compound word in which the base word becomes a modifiee, classification items to classify the compound word, and feature information about a feature that provides a clue to classify the compound word are acquired (S10, S11, S12, S13), the compound word containing the base word is distributed into the acquired classification item using a classification model generated in advance and the acquired feature information (S14, S15), base word related information containing a plurality of elements related to the base word is acquired based on the base word (S16), each of at least a portion of the elements contained in the acquired base word related information is classified into one of the classification items in accordance with a result of the classification (S17), and the classified base word related information (Web pages 40, 50, 51) is output (S18).

摘要翻译： 获取作为基数的基本词，基本词变为复数的复合词，对复合词进行分类的分类项，以及关于提供分类复合词的线索的特征的特征信息（S10，S11， S12，S13），使用预先生成的分类模型将包含基本词的复合词分配到所获取的分类项目中，并且获取到的特征信息（S14，S15），包含与基础相关的多个元素的基本词相关信息 基于所述基本字（S16）获取字，根据所述分类的结果，将所获取的基字相关信息中包含的至少一部分元素中的每一个分类为一个分类项（S17），并且 输出分类的基本词相关信息（网页40,50,51）（S18）。

公开(公告)号：US10108639B2

公开(公告)日：2018-10-23

申请号：US15022931

申请日：2014-02-14

申请人： Rakuten, Inc.

发明人： Soh Masuko ,  Keiji Shinzato

IPC分类号： G06F17/30 ,  G06K9/62

摘要： Based on information being associated with one image among a plurality of images and concerning an object of the one image and information being associated with another image among the plurality of images and concerning an object of the other image, a characteristic information specification unit specifies characteristic information of the object of the one image as compared with the object of the other image. A characteristic information obtaining unit obtains the characteristic information specified by the characteristic information specification unit. A display control unit displays a screen image including a plurality of images on a display unit. Further, the display control unit displays the characteristic information so as to be associated with the one image.

公开(公告)号：US20150006533A1

公开(公告)日：2015-01-01

申请号：US14374692

申请日：2013-03-06

申请人： Rakuten, Inc.

发明人： Keiji Shinzato

IPC分类号： G06F17/30

CPC分类号： G06F17/30684 ,  G06F17/247 ,  G06F17/271 ,  G06F17/2795 ,  G06F17/30705

摘要： A counting device (100) provided with a subtree generating part (123) for generating first subtree comprising a first sentence and a second subtree comprising a second sentence. The counting device (100) is provided with: a categorizing part (125) for categorizing the first subtree in the same group as the second subtree when it is determined that a first expression represented by the first subtree and a second expression represented by a second subtree represent a matching content; and an output part (127) for outputting the number of subtrees categorized in the group, or an expression represented by a plurality of syntax trees or one of the subtrees categorized in the aforementioned group.

摘要翻译： 具有子树生成部（123）的计数装置（100），用于生成包括第一句子的第一子树和包括第二句子的第二子树。 计数装置（100）具有：分类部（125），其在确定由第一子树表示的第一表达式和由第二子表达式表示的第二表达式时，将与第二子树相同的组中的第一子树进行分类 子树表示匹配的内容; 以及用于输出分组在该组中的子树数量的输出部分（127），或由多个语法树表示的表达式或分类在上述组中的一个子树。

公开(公告)号：US09645979B2

公开(公告)日：2017-05-09

申请号：US14420424

申请日：2013-09-30

申请人： RAKUTEN INC

发明人： Keiji Shinzato

IPC分类号： G06F17/21 ,  G06F17/27

CPC分类号： G06F17/218 ,  G06F17/21 ,  G06F17/2735 ,  G06F17/274 ,  G06F17/2785

摘要： A corpus generation device according to an embodiment includes a web page acquisition unit, a reference word acquisition unit, an attachment unit and an output unit. The web page acquisition unit acquires a web page including description sentence data regarding a presentation target. The reference word acquisition unit acquires a reference word that is an attribute value regarding the presentation target from the web page. The attachment unit extracts a broader word belonging to a layer above the reference word acquired by the reference word acquisition unit from a storage unit that stores hierarchical relationship information indicating a hierarchical relationship between attribute values, and attaches an attribute tag corresponding to the reference word to the broader word included in the description sentence data. The output unit outputs, as corpus data, the description sentence data to which the attribute tag is attached by the attachment unit.

公开(公告)号：US10007935B2

公开(公告)日：2018-06-26

申请号：US14766072

申请日：2014-02-28

申请人： Rakuten, Inc.

发明人： Keiji Shinzato

IPC分类号： G06F17/30 ,  G06Q30/02

CPC分类号： G06Q30/0282 ,  G06F16/313 ,  G06F16/3344 ,  G06F16/355

摘要： The information processing system according to one embodiment includes a specifying unit and an extraction unit. The specifying unit specifies a content word co-occurring with onomatopoeia in one review among a plurality of posted reviews stored in a storage unit. The extraction unit extracts a posted sentence containing the content word from the plurality of posted reviews. In general, posted sentences or posted reviews containing onomatopoeia are likely to include users' actual experiences. By extracting the posted sentences that contain the content word which is likely to co-occur with onomatopoeia, it is possible to effectively extract the posted sentences on which users' actual experiences are written.

公开(公告)号：US09740770B2

公开(公告)日：2017-08-22

申请号：US14374692

申请日：2013-03-06

申请人： Rakuten, Inc.

发明人： Keiji Shinzato

IPC分类号： G06F17/30 ,  G06F17/24 ,  G06F17/27

CPC分类号： G06F17/30684 ,  G06F17/247 ,  G06F17/271 ,  G06F17/2795 ,  G06F17/30705

摘要： A counting device (100) provided with a subtree generating part (123) for generating first subtree comprising a first sentence and a second subtree comprising a second sentence. The counting device (100) is provided with: a categorizing part (125) for categorizing the first subtree in the same group as the second subtree when it is determined that a first expression represented by the first subtree and a second expression represented by a second subtree represent a matching content; and an output part (127) for outputting the number of subtrees categorized in the group, or an expression represented by a plurality of syntax trees or one of the subtrees categorized in the aforementioned group.

公开(公告)号：US20150019382A1

公开(公告)日：2015-01-15

申请号：US14371132

申请日：2013-03-07

申请人： Rakuten, Inc.

发明人： Keiji Shinzato

IPC分类号： G06Q30/06

CPC分类号： G06Q30/0627 ,  G06F16/951 ,  G06F17/2795

摘要： A corpus creation device includes an acquisition unit that acquires item page data containing description data related to an item and an attribute list where an attribute name and an attribute value related to the item are associated, an adding unit that, when an attribute value in an attribute list contained in item page data is contained in description data in the item page data, adds an attribute tag identifying an attribute name with which the attribute value is associated in the attribute list to the attribute value contained in the description data, and an output unit that outputs description data in which an attribute tag is added as corpus data.

摘要翻译： 语料库创建装置包括：获取单元，其获取包含与项目相关的描述数据的项目页面数据和与所述项目相关联的属性名称和属性值相关联的属性列表;添加单元， 项目页数据中包含的属性列表包含在项目页数据中的描述数据中，将识别属性列中的属性值所属的属性名称的属性标签与包含在描述数据中的属性值相加， 输出添加了属性标签的描述数据作为语料库数据的单元。