公开(公告)号：US10592958B2

公开(公告)日：2020-03-17

申请号：US15394378

申请日：2016-12-29

Applicant: SONY CORPORATION

Inventor： Hiroyuki Koike ,  Tomoharu Ohsumi

IPC: G06F16/20 ,  G06Q30/06 ,  G06F16/33 ,  G06F16/338 ,  G06F16/2457 ,  G06Q30/02

Abstract: An information processing method is disclosed which includes the steps of: (a) calculating levels of similarity between a standard form vector as a comparison basis vector and each of a plurality of item characteristic vectors of the standard form which are characteristic of a plurality of items, the standard form vector being made up of N components individually representative of N attributes of each of the plurality of items, N being an integer of at least 1, step (a) further determining as the items to be recommended to a user a plurality of items corresponding to the item characteristic vectors of which the level of similarity satisfies a first condition; (b) determining one of the N attributes of the plurality of recommended items determined in step (a) as a common recommendation reason common to the plurality of recommended items when the determined attribute satisfies a second condition; and (c) controlling presentation to the user of either the plurality of recommended items determined in step (a) or information about the recommended items, together with the common recommendation reason determined in step (b).

公开(公告)号：US09552413B2

公开(公告)日：2017-01-24

申请号：US14617531

申请日：2015-02-09

Applicant: Sony Corporation

Inventor： Noriyuki Yamamoto ,  Mitsuhiro Miyazaki ,  Mari Saito ,  Hiroyuki Koike

IPC: G06F7/00 ,  G06F17/30 ,  H04N21/235 ,  H04N21/262 ,  H04N21/432 ,  H04N21/435 ,  H04N21/442 ,  H04N21/466 ,  H04N21/84 ,  H04L29/06

CPC classification number: G06F17/30663 ,  H04L65/60 ,  H04N21/235 ,  H04N21/2353 ,  H04N21/26283 ,  H04N21/4325 ,  H04N21/435 ,  H04N21/44213 ,  H04N21/4661 ,  H04N21/4668 ,  H04N21/84

Abstract: A program vector can represent attributes of a program to be generated. EPG data can be received, and metadata necessary for generation of a program vector PP can be extracted from the EPG data. A morphological analysis can be carried out on contents and title included in the metadata to disassemble the contents and the title into words. Items included in the metadata can be subjected to a vector creation process to generate the program vector PP. An effect vector can be extracted on the basis of a genre of a program associated with the metadata. The extracted effect vector can be associated with the generated program vector PP and the processing can be ended. This can be applied to a distribution server for distributing contents.

Abstract translation: 程序向量可以表示要生成的程序的属性。 可以接收EPG数据，并且可以从EPG数据中提取用于生成节目向量PP所需的元数据。 可以对元数据中包含的内容和标题进行形态分析，将内容和标题分解成单词。 包含在元数据中的项目可以进行向量创建过程以生成程序向量PP。 可以基于与元数据相关联的节目的类型来提取效果向量。 提取的效果矢量可以与生成的节目矢量PP相关联，并且处理可以结束。 这可以应用于分发服务器来分发内容。

公开(公告)号：US09495438B2

公开(公告)日：2016-11-15

申请号：US13974787

申请日：2013-08-23

Applicant: Sony Corporation

Inventor： Mari Saito ,  Noriyuki Yamamoto ,  Mitsuhiro Miyazaki ,  Hiroyuki Koike

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/30595 ,  G06F17/30867 ,  Y10S707/99943

Abstract: Disclosed herein are an information processing apparatus and method, a program, and a recording medium, in which a content is recommended to each user on the basis of even the metadata that is assigned with no classification. A metadata analysis block resolves metadata acquired by a metadata acquisition block into components. A dictionary data generation block generates dictionary data in which genre is correlated with keyword and each component. An associated-information database generation block references the dictionary data to assign genre to the metadata which are assigned with no genre, thereby generating an associated-information database of content. An associated-information search block references the dictionary data to identify a genre from a keyword of interest data to search for associated information, thereby recommending content to the user. The present invention is applicable to personal computers or HDD recorders.

Abstract translation: 这里公开了一种信息处理装置和方法，程序和记录介质，其中，基于甚至不分配分配的元数据向每个用户推荐内容。 元数据分析块将由元数据获取块获取的元数据解析为组件。 字典数据生成块生成类型与关键字和每个组件相关联的字典数据。 相关联的信息数据库生成块引用字典数据以将类型分配给没有类型的元数据，从而生成内容的关联信息数据库。 相关联的信息搜索块引用字典数据以从感兴趣的关键字数据识别类型以搜索相关联的信息，从而向用户推荐内容。 本发明可应用于个人计算机或HDD记录器。

公开(公告)号：US09558243B2

公开(公告)日：2017-01-31

申请号：US14456591

申请日：2014-08-11

Applicant: Sony Corporation

Inventor： Hiroyuki Koike ,  Tomoharu Ohsumi

IPC: G06F17/30 ,  G06Q30/02

CPC classification number: G06Q30/0631 ,  G06F17/3053 ,  G06F17/30675 ,  G06F17/30696 ,  G06Q30/02

Abstract: An information processing method is disclosed which includes the steps of: (a) calculating levels of similarity between a standard form vector as a comparison basis vector and each of a plurality of item characteristic vectors of the standard form which are characteristic of a plurality of items, the standard form vector being made up of N components individually representative of N attributes of each of the plurality of items, N being an integer of at least 1, step (a) further determining as the items to be recommended to a user a plurality of items corresponding to the item characteristic vectors of which the level of similarity satisfies a first condition; (b) determining one of the N attributes of the plurality of recommended items determined in step (a) as a common recommendation reason common to the plurality of recommended items when the determined attribute satisfies a second condition; and (c) controlling presentation to the user of either the plurality of recommended items determined in step (a) or information about the recommended items, together with the common recommendation reason determined in step (b).

Abstract translation: 公开了一种信息处理方法，其包括以下步骤：（a）计算作为比较基础向量的标准形式向量与作为多个项目的特征的标准形式的多个项目特征向量之间的相似度的级别 ，所述标准形式向量由分别表示所述多个项目中的每一个的N个属性的N个分量组成，N是至少为1的整数，步骤（a）进一步确定作为要向用户推荐的项目 对应于相似度满足第一条件的项目特征向量的项目; （b）当所确定的属性满足第二条件时，将在步骤（a）中确定的多个推荐项目的N个属性中的一个确定为多个推荐项目的共同推荐原理; 以及（c）控制对步骤（a）中确定的多个推荐项目或关于推荐项目的信息给用户的呈现以及步骤（b）中确定的共同推荐原因。

公开(公告)号：US20130346410A1

公开(公告)日：2013-12-26

申请号：US13974787

申请日：2013-08-23

Applicant: Sony Corporation

Inventor： Mari SAITO ,  Noriyuki Yamamoto ,  Mitsuhiro Miyazaki ,  Hiroyuki Koike

IPC: G06F17/30

CPC classification number: G06F17/30595 ,  G06F17/30867 ,  Y10S707/99943

Abstract: Disclosed herein are an information processing apparatus and method, a program, and a recording medium, in which a content is recommended to each user on the basis of even the metadata that is assigned with no classification. A metadata analysis block resolves metadata acquired by a metadata acquisition block into components. A dictionary data generation block generates dictionary data in which genre is correlated with keyword and each component. An associated-information database generation block references the dictionary data to assign genre to the metadata which are assigned with no genre, thereby generating an associated-information database of content. An associated-information search block references the dictionary data to identify a genre from a keyword of interest data to search for associated information, thereby recommending content to the user. The present invention is applicable to personal computers or HDD recorders.

Abstract translation: 这里公开了一种信息处理装置和方法，程序和记录介质，其中，基于甚至不分配分配的元数据向每个用户推荐内容。 元数据分析块将由元数据获取块获取的元数据解析为组件。 字典数据生成块生成类型与关键字和每个组件相关联的字典数据。 相关联的信息数据库生成块引用字典数据以将类型分配给没有类型的元数据，从而生成内容的关联信息数据库。 相关联的信息搜索块引用字典数据以从感兴趣的关键字数据识别类型以搜索相关联的信息，从而向用户推荐内容。 本发明可应用于个人计算机或HDD记录器。