Patents by Inventor Kouta Nakata
Kouta Nakata has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20250037038Abstract: According to one embodiment, the information processing apparatus includes a processor. The processor extracts a plurality of features from a plurality of training data by using a machine learning model. The processor generates a prediction result relating to a task, from the training data and teaching data corresponding to the training data. The processor calculates a similarity between features with respect to the plurality of features. The processor updates a parameter of the machine learning model, based on the prediction result and the similarity, in such a manner that the features become farther from each other.Type: ApplicationFiled: February 27, 2024Publication date: January 30, 2025Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Yuichi KATO, Kentaro TAKAGI, Kouta NAKATA
-
Publication number: 20250029356Abstract: According to one embodiment, an information processing apparatus includes a processor. The processor acquires training data that is used for training of a first feature extractor and a second feature extractor. The processor determines a model size of the second feature extractor. The processor extracts a first feature by inputting the training data to the first feature extractor. The processor extracts a second feature by inputting the first feature to the second feature extractor. The processor trains the first feature extractor in such a manner as to make the first feature closer to the second feature.Type: ApplicationFiled: February 27, 2024Publication date: January 23, 2025Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Yuichi KATO, Kentaro TAKAGI, Kouta NAKATA
-
Publication number: 20240404245Abstract: A similar image set creating apparatus includes processing circuitry. The processing circuitry acquires a plurality of images. The processing circuitry extracts first features from the images by using a first model that executes an image classification task. The processing circuitry extracts second features from the images by using a second model that executes an image classification task. The second model is trained in such a manner that mutually similar images in a latent space are continuously distributed, compared to the first model. The processing circuitry selects, from the images, an image of interest serving as a reference of a similar image set, and an auxiliary image similar to the image of interest, based on the first features and the second features.Type: ApplicationFiled: February 28, 2024Publication date: December 5, 2024Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Kouta NAKATA, Kentaro TAKAGI, Yaling TAO
-
Patent number: 12124503Abstract: According to one embodiment, system includes a determination unit, a first storage, a second storage, a search unit and a display. The determination unit determines a feature quantity of the process-targeted manufacturing data. The first storage stores cause-unidentified manufacturing data. The second storage stores cause-identified manufacturing data. The search unit searches, based on the feature quantity of the process-targeted manufacturing data, the first storage and the second storage for the cause-unidentified manufacturing data and the cause-identified manufacturing data that have a feature quantity similar to that of the process-targeted manufacturing data. The display displays the search result.Type: GrantFiled: February 26, 2021Date of Patent: October 22, 2024Assignee: KABUSHIKI KAISHA TOSHIBAInventors: Takahiro Takimoto, Kouta Nakata, Kazunori Imoto, Ayana Yamamoto, Shun Hirao
-
Patent number: 12124251Abstract: According to one embodiment, a data processing apparatus includes a processor. The processor calculates, from the first measurement data, a first differential value set that is a set of first differential values in a time direction at a time included in the first period of the measurement values of the sensor of interest. The processor calculates, from the second measurement data, a second differential value set that is a set of second differential values in a time direction at a time included in the second period of the measurement values of the sensor of interest. The processor generates a first differential value distribution and a second differential value distribution using the second differential value set.Type: GrantFiled: September 12, 2022Date of Patent: October 22, 2024Assignees: KABUSHIKI KAISHA TOSHIBA, TOSHIBA ENERGY SYSTEMS & SOLUTIONS CORPORATIONInventors: Yasunori Taguchi, Kouta Nakata, Susumu Naito, Yuichi Kato, Shinya Tominaga, Isaku Nagura, Ryota Miyake, Yusuke Terakado, Toshio Aoki
-
Publication number: 20240296467Abstract: A purchase data analysis apparatus includes processing circuitry. The processing circuitry is configured to: acquire, on a customer-by-customer basis, customer information including an action time of a purchase-related action relating to purchase; generate, on a customer-by-customer basis, a customer representation representing an action pattern of a customer, based on the action time; generate, on a store-by-store basis, a store representation representing a representation of a customer coming to a store, based on the customer representation; and cluster stores by using the store representation.Type: ApplicationFiled: October 17, 2023Publication date: September 5, 2024Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Yoshiaki MIZUOKA, Kouta NAKATA
-
Publication number: 20240262653Abstract: According to one embodiment, an abnormal noise detection device includes a first processing circuit. The first processing circuit is configured to collect an operating noise of a moving body by a first microphone installed in the moving body; detect an abnormal noise in the operating noise; input position information of the moving body; and store history information in which a detection result of detecting the abnormal noise and the position information are associated with each other in a first memory. The first processing circuit is configured to determine presence or absence of abnormality of the moving body by integrating the detection result for each piece of the position information on a basis of the history information.Type: ApplicationFiled: August 23, 2023Publication date: August 8, 2024Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Hiroyuki YANAGIHASHI, Takashi SUDO, Kouta NAKATA, Tsukasa IKE
-
Patent number: 12033370Abstract: According to an embodiment, a learning device includes one or more processors. The processors calculate a latent vector of each of a plurality of first target data, by using a parameter of a learning model configured to output a latent vector indicating a feature of a target data. The processors calculate, for each first target data, first probabilities that the first target data belongs to virtual classes on an assumption that the plurality of first target data belong to the virtual classes different from each other. The processors update the parameter such that a first loss of the first probabilities, and a second loss that is lower as, for each of element classes to which a plurality of elements included in each of the plurality of first target data belong, a relation with another element class is lower, become lower.Type: GrantFiled: August 24, 2020Date of Patent: July 9, 2024Assignee: KABUSHIKI KAISHA TOSHIBAInventors: Yaling Tao, Kentaro Takagi, Kouta Nakata
-
Publication number: 20240086428Abstract: According to one embodiment, a data labeling work support apparatus includes a processor including hardware. The processor acquires a first label assigned to data. The processor acquires the data. The processor extracts a feature of the data. The processor groups the data based on a similarity or a distance of the feature. The processor assigns a second label to the grouped data. The processor calculates a degree of matching between the first label and the second label. The processor outputs information regarding a combination of the first label and the second label having a low degree of matching.Type: ApplicationFiled: February 28, 2023Publication date: March 14, 2024Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Kouta NAKATA, Kentaro TAKAGI, Yaling TAO
-
Publication number: 20240085278Abstract: According to one embodiment, an anomaly detection apparatus includes a processing circuit. The processing circuit is configured to: acquire measured values from sensors installed in a system, a first function, a first threshold, and a second function to output a second threshold; generate the predicted values based on the measured value and the first function; detect that a deviation between the measured values and the predicted values exceeds the first threshold; calculate the feature quantities based on the measured values; and determine whether a number of consecutive times is equal to or larger than the second threshold to detect an anomaly or a sign of the anomaly.Type: ApplicationFiled: February 24, 2023Publication date: March 14, 2024Applicants: KABUSHIKI KAISHA TOSHIBA, Toshiba Energy Systems & Solutions CorporationInventors: Yasunori TAGUCHI, Kouta NAKATA, Susumu NAITO, Yuichi KATO, Shinya TOMINAGA, Naoyuki TAKADO, Ryota MIYAKE, Yusuke TERAKADO, Toshio AOKI
-
Publication number: 20240086950Abstract: An information processing apparatus includes one or more hardware processors configured to: acquire a plurality of pieces of purchasing data including any of a plurality of pieces of user identification information, any of a plurality of pieces of product identification information, and performance information including at least one of a price and a number of purchases; perform matrix factorization of a purchase matrix with non-negative values calculated based on the performance information as element values, and calculate user hidden status information indicating a relation between the plurality of pieces of user identification information and hidden statuses related to purchasing, and product hidden status information indicating a relation between the hidden statuses and the plurality of pieces of product identification information; and control output of at least one of the user hidden status information and the product hidden status information.Type: ApplicationFiled: February 28, 2023Publication date: March 14, 2024Applicant: KABUSHIKI KAISHA TOSHIBAInventor: Kouta NAKATA
-
Patent number: 11892829Abstract: According to one embodiment, a monitoring apparatus includes a processing circuit. The processing circuit is configured to generate second data including a prediction value of a second sensor correlated with a first sensor from first data including a measurement value of the first sensor of which a measurement value changes suddenly in a case where the control signal changes, detect an anomaly of the system or an anomaly of at least one sensor, and make it difficult to detect the anomaly in a case where the determination signal indicates that there is a change in the control signal.Type: GrantFiled: February 25, 2022Date of Patent: February 6, 2024Assignees: KABUSHIKI KAISHA TOSHIBA, TOSHIBA ENERGY SYSTEMS & SOULTIONS CORPORATIONInventors: Yasunori Taguchi, Kouta Nakata, Susumu Naito, Yuichi Kato, Eiichi Ookuma, Toshio Aoki, Chikashi Miyamoto
-
Patent number: 11886990Abstract: A classification device includes a generation unit, a learning unit, a classification unit, and an output control unit. The generation unit generates pseudo data having a feature similar to a feature of training data. The learning unit learns, by using the training data and the pseudo data, a classification model that classifies data into one of a pseudo class for classifying the pseudo data and a plurality of classification classes other than the pseudo class and that is constructed by a neural network. The classification unit classifies, by using the classification model, input data as a target for classification into one of the pseudo class and the plurality of classification classes. The output control unit outputs information indicating that the input data classified into the pseudo class is data not belonging to any of the plurality of classification classes.Type: GrantFiled: March 8, 2019Date of Patent: January 30, 2024Assignee: Kabushiki Kaisha ToshibaInventor: Kouta Nakata
-
Patent number: 11868885Abstract: According to an embodiment, a learning device includes a memory and one or more processors coupled to the memory. The one or more processors are configured to: generate a transformation matrix from learning data in which feature quantities and target values are held in a corresponding manner; and learn about parameters of a neural network which includes nodes equal in number to the number of rows of the transformation matrix, a first output layer representing first estimation distribution according to the values of the nodes, and a second output layer representing second estimation distribution decided according to the product of the transformation matrix and the first estimation distribution.Type: GrantFiled: August 21, 2020Date of Patent: January 9, 2024Assignee: KABUSHIKI KAISHA TOSHIBAInventors: Yuichi Kato, Kouta Nakata, Susumu Naito, Yasunori Taguchi, Kentaro Takagi
-
Patent number: 11860716Abstract: According to one embodiment, an information processing apparatus includes a processing circuit. The processing circuit calculates a first input/output error related to normal data and a second input/output error related to pseudo abnormal data different from the normal data, for each of a plurality of autoencoders having different network structures. The processing circuit outputs relational data indicating a relation between the network structure and the first input/output error and the second input/output error.Type: GrantFiled: February 22, 2022Date of Patent: January 2, 2024Assignee: KABUSHIKI KAISHA TOSHIBAInventors: Yuichi Kato, Kentaro Takagi, Kouta Nakata
-
Publication number: 20230367307Abstract: According to one embodiment, an abnormality sign detection system comprising one or more computers configured to perform machine learning of an abnormality-sign detection-model that detects at least one of an abnormality in a target facility to be monitored and a sign of the abnormality, wherein the one or more computers are configured to: acquire a plurality of process amounts generated at the target facility; classify each of the plurality of process amounts into either correlation data for which correlation between the plurality of process amounts is learned or decorrelation data for which correlation between the plurality of process amounts is not learned; generate learning input data depending on classification, the learning input data being data in which each of the plurality of process amounts is associated with the correlation data or the decorrelation data; and perform the machine learning by inputting the learning input data to the abnormality-sign detection-model.Type: ApplicationFiled: May 8, 2023Publication date: November 16, 2023Applicants: KABUSHIKI KAISHA TOSHIBA, TOSHIBA ENERGY SYSTEMS & SOLUTIONS CORPORATIONInventors: Yusuke TERAKADO, Shinya TOMINAGA, Naoyuki TAKADO, Ryota MIYAKE, Toshio AOKI, Chikashi MIYAMOTO, Kouta NAKATA, Susumu NAITO, Yasunori TAGUCHI, Yuichi KATO
-
Patent number: 11768862Abstract: According to one embodiment, an estimation device acquires a data set from history data. The history data includes a plurality of data IDs, path information, first and second qualitative variables. The data IDs respectively indicate a plurality of data flowing through a plurality of nodes. The path information indicates a path of the nodes for each of the data. The first and second qualitative variables are mutually-independent and indicate classifications of each of the data IDs. The data set includes a part of the data IDs having a first variable value assigned as the first qualitative variable. The estimation device estimates an overall relevance indicating a relevancy to the data set for each of the nodes. The estimation device generates a plurality of partial data sets. The estimation device estimates a partial relevance indicating a relevancy to each of the partial data sets for each of the nodes.Type: GrantFiled: September 9, 2019Date of Patent: September 26, 2023Assignee: Kabushiki Kaisha ToshibaInventors: Shun Hirao, Kouta Nakata
-
Patent number: 11740613Abstract: According to an embodiment, a monitoring apparatus configured to generate time-series predicted data based on time-series measured data and a prediction model that generates predicted data including one or more predicted values predicted to be output from one or more sensors; and generate, for a first sensor among the one or more sensors, a displayed image including a measured value graph representing a temporal change in a measured value included in the time-series measured data in a second period after a first period, a predicted value graph representing a temporal change in a predicted value included in time-series predicted data in the second period, past distribution information representing a distribution of a measured value in the first period, and measurement distribution information representing a distribution of the measured value included in the time-series measured data in the second period.Type: GrantFiled: February 25, 2021Date of Patent: August 29, 2023Assignees: Kabushiki Kaisha Toshiba, Toshiba Energy Systems & Solutions CorporationInventors: Yasunori Taguchi, Kouta Nakata, Susumu Naito, Yuichi Kato, Toshio Aoki, Shinya Tominaga, Isaku Nagura, Ryota Miyake, Chikashi Miyamoto
-
Publication number: 20230252361Abstract: According to one embodiment, an information processing apparatus includes a processor. The processor generates a machine learning model by coupling one feature extractor to each of a plurality of predictors, the feature extractor being configured to extract a feature amount of data. The processor trains the machine learning model for a specific task using a result of ensembling a plurality of outputs from the predictors.Type: ApplicationFiled: September 12, 2022Publication date: August 10, 2023Applicant: KABUSHIKI KAISHA TOSHIBAInventors: Yuichi KATO, Kentaro TAKAGI, Kouta NAKATA
-
Publication number: 20230140271Abstract: According to one embodiment, a data processing apparatus includes a processor. The processor calculates, from the first measurement data, a first differential value set that is a set of first differential values in a time direction at a time included in the first period of the measurement values of the sensor of interest. The processor calculates, from the second measurement data, a second differential value set that is a set of second differential values in a time direction at a time included in the second period of the measurement values of the sensor of interest. The processor generates a first differential value distribution and a second differential value distribution using the second differential value set.Type: ApplicationFiled: September 12, 2022Publication date: May 4, 2023Applicants: KABUSHIKI KAISHA TOSHIBA, Toshiba Energy Systems & Solutions CorporationInventors: Yasunori TAGUCHI, Kouta NAKATA, Susumu NAITO, Yuichi KATO, Shinya TOMINAGA, Isaku NAGURA, Ryota MIYAKE, Yusuke TERAKADO, Toshio AOKI