公开(公告)号：US20230304979A1

公开(公告)日：2023-09-28

申请号：US18023422

申请日：2020-09-02

申请人： NEC Corporation

发明人： Hiromi Shimizu ,  Shinnosuke Nishimoto ,  Junko Watanabe ,  Riki Eto ,  Noriyuki Tonouchi ,  So Yamada

IPC分类号： G06Q30/0208 ,  G01N33/00

CPC分类号： G01N33/0027 ,  G06Q30/0208

摘要： An information processing device is configured to include an acquisition unit, a determination unit, an instruction unit, an instruction unit, and output unit. The acquisition unit is configured to acquire measurement target and measurement environment information, and measurement environment information that a measurer can measure with an odor sensor. The determination unit is configured to determine a measurement target that the measurer should be instructed to measure, based on the measurement target and measurement environment information and the measurement environment information that can be measured, the instruction is configured to instruct the measurer to measure the determined measurement target. The output unit configured to output a reward to the measurer after the acquisition means acquires odor data of the determined measurement target.

公开(公告)号：US09324026B2

公开(公告)日：2016-04-26

申请号：US14032295

申请日：2013-09-20

申请人： NEC Corporation

发明人： Yosuke Motohashi ,  Satoshi Morinaga ,  Ryohei Fujimaki ,  Riki Eto

IPC分类号： G06N5/02 ,  G06N99/00

CPC分类号： G06N5/02 ,  G06N7/005 ,  G06N99/005

摘要： A hierarchical latent structure setting unit 81 sets a hierarchical latent structure that is a structure in which latent variables are represented by a tree structure and components representing probability models are located at nodes of a lowest level of the tree structure. A variational probability computation unit 82 computes a variational probability of a path latent variable that is a latent variable included in a path linking a root node to a target node in the hierarchical latent structure. A component optimization unit 83 optimizes each of the components for the computed variational probability. A gating function optimization unit 84 optimizes a gating function model that is a model for determining a branch direction according to the multivariate data in a node of the hierarchical latent structure, based on the variational probability of the latent variable in the node.

摘要翻译： 分层潜在结构设置单元81设置作为其中潜变量由树结构表示的结构的分层潜在结构，并且表示概率模型的分量位于树结构的最底层的节点处。 变分概率计算单元82计算作为潜在变量的路径潜变量的变分概率，所述潜变量包括在将根节点链接到分层潜在结构中的目标节点的路径中。 分量优化单元83针对所计算的变分概率优化每个分量。 门控功能优化单元84基于节点中的潜在变量的变分概率来优化门控功能模型，门控功能模型是根据层级潜在结构的节点中的多变量数据确定分支方向的模型。

公开(公告)号：US12066417B2

公开(公告)日：2024-08-20

申请号：US17251337

申请日：2018-06-29

申请人： NEC CORPORATION

发明人： Riki Eto

IPC分类号： G06N20/00 ,  G01N33/00 ,  G05B13/02 ,  G05B13/04

CPC分类号： G01N33/0034 ,  G05B13/0265 ,  G05B13/048 ,  G06N20/00

摘要： A learning model generation support apparatus 10 is an apparatus for supporting generation of a learning model to be utilized in odor detection using an odor sensor that reacts to a plurality of types of odors. The learning model generation support apparatus 10 includes a data acquisition unit 11 that acquires sensor data output by the odor sensor under specific measurement conditions and condition data specifying the measurement conditions, and inputs, as training data, the acquired sensor data and condition data to a machine learning engine 31 that generates the learning model, and a condition setting unit 12 that acquires a predictive accuracy output by the machine learning engine in response to input of the training data, and sets new measurement conditions for when the odor sensor newly outputs sensor data as training data, based on the acquired predictive accuracy.

公开(公告)号：US20230316132A1

公开(公告)日：2023-10-05

申请号：US18023532

申请日：2020-08-31

申请人： NEC Corporation

发明人： Riki Eto

IPC分类号： G06N20/00

CPC分类号： G06N20/00

摘要： An input means 81 accepts input of an extended objective function, in which each term indicative of a score of each classification result in an objective function of classification analysis is multiplied by a bias parameter as a parameter indicative of a degree of bias of the score of each classification result concerned. An optimization means 82 optimizes a logistic regression weight in the extended objective function. An estimation means 83 estimates the bias parameter by inverse reinforcement learning using the extended objective function of logistic regression to which the optimized weight is set.

公开(公告)号：US20230169706A1

公开(公告)日：2023-06-01

申请号：US17920430

申请日：2020-04-28

申请人： NEC Corporation

发明人： Dai KUBOTA ,  Riki Eto

IPC分类号： G06T11/20 ,  B61L27/16

CPC分类号： G06T11/206 ,  B61L27/16

摘要： The output means 81 outputs a diagram to a display device. The input means 82 accepts designation of a change point and a change condition for the displayed diagram. The constraint generation means 83 generates a constraint for an objective function used for optimization of the diagram based on the designation. The change proposal generation means 84 generates a change proposal for the diagram by optimizing the objective function based on the generated constraint. Then, the input means 82 accepts, for each change point, the designation of a hard constraint indicating a condition that must be satisfied, or a soft constraint indicating a condition that increases a penalty according to degree of unsatisfactory, as the designation of the change condition, the constraint generation means 83 generates the constraint according to the hard constraint or soft constraint, and the output means 81 outputs the change proposal of the diagram.

公开(公告)号：US12044667B2

公开(公告)日：2024-07-23

申请号：US17262955

申请日：2018-07-31

申请人： NEC Corporation

发明人： Ryota Suzuki ,  Riki Eto

IPC分类号： G01N33/00 ,  G01N1/24

CPC分类号： G01N33/0067 ,  G01N1/24 ,  G01N33/0009 ,  G01N33/0011 ,  G01N33/0016 ,  G01N33/0027 ,  G01N33/0031

摘要： An information processing apparatus (2000) acquires time-series data (14) output by a sensor (10) and computes a plurality of feature constants θi and a contribution value ξi representing contribution with respect to the time-series data (14) for each feature constant θi. Thereafter, the information processing apparatus (2000) outputs information in which a set Θ of the feature constants θi and a set Ξ of the contribution values ξi are associated with each other as a feature value of a target gas. As the feature constant θ, a velocity constant β or a time constant τ that is a reciprocal of the velocity constant can be adopted.

公开(公告)号：US11789001B2

公开(公告)日：2023-10-17

申请号：US17280439

申请日：2018-09-28

申请人： NEC Corporation

发明人： Riki Eto

IPC分类号： G01N33/00

CPC分类号： G01N33/0062 ,  G01N33/0036 ,  G01N2033/0068

摘要： An information processing apparatus (20) includes a sensor output data acquisition unit (210), a prediction equation generation unit (220), and an operation setting unit (230). The sensor output data acquisition unit (210) acquires sensor output data for each sampling length of an odor sensor with respect to a target gas. The prediction equation generation unit (220) generates, by using the sensor output data for each sampling length, a prediction equation for making a prediction for an odor component of the target gas. The operation setting unit (230) determines, by using the prediction equation, a sampling length for operating the odor sensor.

公开(公告)号：US20230186099A1

公开(公告)日：2023-06-15

申请号：US17922485

申请日：2020-05-11

申请人： NEC Corporation

发明人： Dai Kubota ,  Riki Eto

IPC分类号： G06N3/092

CPC分类号： G06N3/092

摘要： The target output means 91 outputs a plurality of second targets, which are optimization results for a first target using one or more objective functions generated in advance by inverse reinforcement learning based on decision making history data indicating an actual change to a target. The selection acceptance means 92 accepts a selection instruction from a user for a plurality of the output second targets. The data output means 93 outputs the actual change from the first target to the accepted second target as the decision making history data. The learning means 94 learns the objective function using the decision making history data.

公开(公告)号：US20230166783A1

公开(公告)日：2023-06-01

申请号：US17920885

申请日：2020-04-28

申请人： NEC Corporation

发明人： Dai Kubota ,  Riki Eto

IPC分类号： B61L27/60 ,  B61L27/12

CPC分类号： B61L27/60 ,  B61L27/12

摘要： The congestion degree calculation means 81 calculates a congestion degree at a vehicle and a stop. The diagram output means 82 outputs a modified diagram in which a current diagram is modified by optimizing an objective function learned using business history data including an actual change of a diagram. The risk calculation means 83 calculates a current risk which is a risk occurring at the present time, and a modification risk which is a risk caused by modifying the diagram, based on the congestion degree. The risk output means 84 outputs the calculated current risk and the modification risk.

公开(公告)号：US20230061026A1

公开(公告)日：2023-03-02

申请号：US17800305

申请日：2020-03-13

申请人： NEC Corporation

发明人： Hiromi Shimizu ,  Shinnosuke Nishimoto ,  Junko Watanabe ,  Riki Eto ,  Noriyuki Tonouchi ,  So Yamada

IPC分类号： G06N20/00 ,  G06V10/774 ,  G06F40/279 ,  G10L15/06 ,  G10L15/26

摘要： A training data generation device includes a label candidate generation unit, a reception unit, and a training data generation uni. The acquisition unit is configured to acquire smell data and information pertaining to the smell data. The label candidate generation unit which generates label candidates on the basis of the information pertaining to the smell data; an output unit which outputs the generated label candidates. The reception unit is configured to receive selection of a label from the output label candidates. The training data generation unit which generates training data from the selected label and the smell data.