公开(公告)号：US20210356920A1

公开(公告)日：2021-11-18

申请号：US17286268

申请日：2019-10-11

Applicant: SONY CORPORATION

Inventor： SHINGO TAKAMATSU ,  MASANORI MIYAHARA ,  KOGA TAMAMURA ,  TOMOKO TAKAHASHI ,  MOTOKI HIGASHIDE

IPC: G05B13/04 ,  G06N20/00 ,  G05B13/02 ,  G06Q30/02 ,  G05B17/02

Abstract: This technology relates to an information processing apparatus, an information processing method, and a program for permitting relatively easy comparison and examination of learning histories. An information processing apparatus includes a control section configured to perform control to display multiple prediction models as models trained by machine learning, and respective pieces of model information regarding the prediction models. This technology can be applied, for example, to information processing apparatuses that perform learning and prediction by machine learning.

公开(公告)号：US20170097985A1

公开(公告)日：2017-04-06

申请号：US15311673

申请日：2015-03-10

Applicant: SONY CORPORATION

Inventor： MASANORI MIYAHARA

IPC: G06F17/30

CPC classification number: G06F16/288 ,  G06F16/24578 ,  G06F16/248 ,  G06F16/9537 ,  G06Q10/04 ,  G06Q10/067 ,  G06Q30/02 ,  G06Q30/0201 ,  G06Q30/0251

Abstract: [Object] To provide information more useful to users by applying an estimation model for a relation between items more widely. [Solution] There is provided an information processing apparatus including: a status information acquisition unit configured to acquire information representing a first situation of a user and information representing a second situation of the user; a status feature quantity extraction unit configured to extract a first status feature quantity corresponding to the first situation and a second status feature quantity corresponding o the second situation; a result information acquisition unit configured to acquire information indicating a first result generated in the first situation; a result feature quantity extraction unit configured to extract a result feature quantity corresponding to the first result; a relation feature quantity generation unit configured to generate a relation feature quantity indicating a relation between the first situation and the first result on the basis of the first status feature quantity and the result feature quantity; a result estimation unit configured to estimate a second result generated in the second situation on the basis of the relation feature quantity and the second status feature quantity; and an information generation unit configured to generate information reflecting the second result.

公开(公告)号：US20190045751A1

公开(公告)日：2019-02-14

申请号：US16076483

申请日：2016-11-29

Applicant: SONY CORPORATION

Inventor： MASANORI MIYAHARA ,  TAKASHI OGATA ,  MASATAKA SHINODA ,  NOBUHIRO KIHARA

IPC: A01K29/00 ,  G06K9/78 ,  G06Q50/02 ,  B64C39/02

CPC classification number: A01K29/005 ,  B64C39/024 ,  B64C2201/123 ,  B64C2201/127 ,  B64C2201/145 ,  G06K9/78 ,  G06Q10/06311 ,  G06Q50/02

Abstract: [Object] To further improve the efficiency of livestock management. [Solution] Provided is an information processing device including: a display control unit that controls display of condition information indicating conditions of livestock; an acquisition unit that acquires task information indicating a task related to the livestock, which is input on a basis of the condition information; and an output unit that outputs command information for providing a command for the task indicated by the task information.

公开(公告)号：US20210117828A1

公开(公告)日：2021-04-22

申请号：US17253005

申请日：2019-06-13

Applicant: SONY CORPORATION

Inventor： SHINGO TAKAMATSU ,  KENTO NAKADA ,  YUJI HORIGUCHI ,  HIROSHI IIDA ,  MASANORI MIYAHARA

IPC: G06N5/04 ,  G06N20/00 ,  G06F16/22 ,  G06F16/28

Abstract: The present disclosure relates to an information processing apparatus, an information processing method, and a program that allow improvement of a learning data set to be facilitated. A prediction analysis section calculates an evaluation value for an evaluation data set used to evaluate a prediction model, for a predetermined number of data samples in a learning data set used for training of the prediction model, and on the basis of the evaluation value for all the data samples in the learning data set and gradients of the data samples, an advice generation section generates presentation information for presenting advice related to at least one of the data samples in the learning data set or feature amounts of the data samples. A technique according to the present disclosure can be applied to prediction of a contract price of a previously used condominium, for example.

公开(公告)号：US20150269232A1

公开(公告)日：2015-09-24

申请号：US14658474

申请日：2015-03-16

Applicant: SONY CORPORATION

Inventor： TOMOHIRO TSUNODA ,  KAZUKI YOSHIYAMA ,  RYO NAKAHASHI ,  MASANORI MIYAHARA

IPC: G06F17/30

CPC classification number: G06F16/248

Abstract: There is provided an information processing apparatus including an obtaining unit configured to obtain one or more other information elements corresponding to one information element based on a degree of association between the one information element and the other information elements, an extraction unit configured to extract a description of a type of association between the one information element and the obtained other information elements, and a presentation control unit configured to perform control in a manner that the one information element, the other information elements, the type of association, and the description of the type of association are presented.

Abstract translation: 提供了一种信息处理设备，包括：获取单元，被配置为基于一个信息元素和其他信息元素之间的关联度来获得与一个信息元素相对应的一个或多个其他信息元素;提取单元，被配置为提取描述 所述一个信息元素与所获得的其他信息元素之间的关联类型，以及呈现控制单元，被配置为以所述一个信息元素，其他信息元素，关联类型以及所述其他信息元素的描述的方式来执行控制 呈现关联类型。

公开(公告)号：US20150052140A1

公开(公告)日：2015-02-19

申请号：US14450403

申请日：2014-08-04

Applicant: SONY CORPORATION

Inventor： MASANORI MIYAHARA ,  KAZUNORI ARAKI ,  KATSUYOSHI KANEMOTO ,  RYO NAKAHASHI ,  KAZUKI YOSHIYAMA ,  TOMOHIRO TAKAGI

IPC: G06F17/30

CPC classification number: G06F16/3338 ,  G06F16/355

Abstract: Disclosed is an information processing apparatus including an expression extraction unit, a feature extraction unit, a clustering unit, a related expression extraction unit, and an output unit. The expression extraction unit extracts a plurality of expressions from a plurality of documents. The feature extraction unit extracts feature amounts of the extracted respective expressions while distinguishing the expressions having the same notation. The clustering unit clusters the extracted respective expressions together while distinguishing the expressions having the same notation and calculates assignment degree vectors having assignment degrees of the respective expressions to two or more respective clusters as components. The related expression extraction unit extracts related expressions having the assignment degree vectors similar to those of a provided input expression while distinguishing the expressions having the same notation. The output unit outputs the related expressions and identification information for identifying the related expressions.

Abstract translation: 公开了一种包括表达提取单元，特征提取单元，聚类单元，相关表达式提取单元和输出单元的信息处理设备。 表达式提取单元从多个文档中提取多个表达式。 特征提取单元在区分具有相同符号的表达式的同时提取提取的各个表达式的特征量。 将所提取的各个表达式聚集在一起，同时区分具有相同符号的表达式，并将具有各表达式的分配度的分配度向量计算为两个或更多个相应的簇作为分量。 相关表达式提取单元提取具有与所提供的输入表达式相同的分配度向量的相关表达式，同时区分具有相同符号的表达式。 输出单元输出用于识别相关表达的相关表达和识别信息。