Patents by Inventor Takuya MINAMI
Takuya MINAMI 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: 20250046403Abstract: A design support device supports design of a first compound and design of a second compound containing the first compound, and the design support device includes a first design condition proposing unit configured to propose a candidate for design condition information for the first compound that satisfies required property information for the first compound that is input; and a first property predicting unit configured to perform property prediction of the second compound based on design condition information for the second compound that is input.Type: ApplicationFiled: December 13, 2022Publication date: February 6, 2025Inventors: Shogo NISHINO, Naoto AONUMA, Koji MIYAKOSHI, Kohsuke KAKUDA, Takuya MINAMI, Shimpei TAKEMOTO
-
Patent number: 12206689Abstract: An anomaly detection device is provided with a learning unit that generates a detection model using a communication log during normal operation of a communication apparatus as learning data and an anomaly detection unit that detects anomaly of the communication apparatus using the generated detection model. The anomaly detection device is further provided with a data acquisition unit that acquires a communication log (second communication log) generated during a predetermined period later than a first communication log and a determination unit that instructs relearning using the second communication log when there is difference information between the learning data (first communication log) of the current detection model and the second communication log and when the number of pieces of additional information (information on the additional flow) or the number of pieces of deletion information (information on the delete flow) included in the difference information satisfies predetermined evaluation criteria.Type: GrantFiled: June 24, 2019Date of Patent: January 21, 2025Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Masami Izumi, Tomoyasu Sato, Takeshi Nakatsuru, Takuya Minami, Naoto Fujiki
-
Patent number: 12190032Abstract: A material design device derives the optimal solution for a design condition satisfying a desired material property. A design condition setting unit for setting a specified range of a design condition of a material to be designed. A comprehensive prediction point generation unit generates a plurality of comprehensive prediction points within the specified range set by the design condition setting unit. A design condition-material property table stores data sets in which each point of the comprehensive prediction points is associated with a material property value calculated by inputting the comprehensive prediction points generated by the comprehensive prediction point generation unit, to a learned model. A required property setting unit sets a specified range of a required property of the material. A design condition extraction unit extracts, from the design condition-material property table, a data set satisfying the required property set by the required property setting unit.Type: GrantFiled: October 30, 2019Date of Patent: January 7, 2025Assignee: Showa Denko K.K.Inventors: Katsuki Okuno, Takuya Minami, Shimpei Takemoto, Eriko Takeda, Yoshishige Okuno, Masamichi Kitano
-
Publication number: 20250005451Abstract: A composition search method for a material includes constructing a prediction model by learning training data in which information related to a composition of a material is set as an explanatory variable and a value of a physical property of the material is set as an objective variable; calculating a predicted value of the physical property by inputting, into the prediction model, prediction data for newly searching for a composition; calculating an influence degree of each explanatory variable on prediction by using the training data and the prediction model; calculating a weighted distance of the prediction data with respect to the training data by using the influence degree; and displaying a relationship between the predicted value and the weighted distance, and outputting corresponding prediction data as a search candidate.Type: ApplicationFiled: September 28, 2022Publication date: January 2, 2025Inventors: Haein LEE, Takuya MINAMI, Yoshishige OKUNO
-
Publication number: 20240428895Abstract: A compound safety prediction device includes an input unit for inputting the structural formula of at least one molecule, a safety prediction unit for predicting a safety evaluation of the molecule and computing a confidence score level of the prediction, a similar molecule data searching unit for acquiring the safety evaluation data of a similar molecule similar to the molecule, and an output unit for outputting the result of prediction of the safety evaluation of the molecule, the confidence score level of the prediction, and the safety evaluation data of the similar molecule.Type: ApplicationFiled: August 31, 2022Publication date: December 26, 2024Inventors: Takuya MINAMI, Naoki HASHIZUME
-
Publication number: 20240378355Abstract: A property prediction device includes a processor; and a memory storing program instructions that cause the processor to: create a prediction model by using a training dataset of a composite material including raw materials in first and second categories to perform machine learning of a correspondence relationship between a property of the composite material, which is an objective variable, versus a mixing amount of the raw material in the first category and a weighted feature of the raw material in the second category, which are explanatory variables; and input, as explanatory variables, a mixing amount of a raw material in the first category and a weighted feature of a raw material in the second category, created based on prediction data of a composite material whose property is to be predicted, into the prediction model so as to predict the property of the composite material corresponding to the prediction data.Type: ApplicationFiled: August 25, 2022Publication date: November 14, 2024Inventors: Kohsuke KAKUDA, Takuya MINAMI, Naoto AONUMA, Shimpei TAKEMOTO, Hiroko TAKASHI, Yoshishige OKUNO
-
Patent number: 12113816Abstract: An acquisition unit acquires a communication feature for normal communication of communication equipment. If a data count or a data acquisition period for the acquired communication feature exceeds a predetermined value, an amplification unit amplifies the data count for the communication feature by a plurality of predetermined schemes in accordance with data counts for respective groups, each group sharing a same 5-tuple. A creation unit creates, for each of the predetermined schemes, reference value information for normal communication of the communication equipment through learning using the amplified communication feature. A determination unit determines accuracy of abnormality detection for each of the predetermined schemes using an anomaly score representing a deviation of test data representing a communication feature for abnormal communication from the reference value information.Type: GrantFiled: July 23, 2019Date of Patent: October 8, 2024Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Naoto Fujiki, Takuya Minami, Masanori Shinohara
-
Patent number: 12099935Abstract: Technical knowledge which is difficult for the expert to express in words or numerical form is predicted and reproduced. A technical knowledge prediction apparatus according to one embodiment of the present invention includes a problem setting unit configured to automatically create and set a problem which includes a control factor of a manufacturing step, and a variable of the control factor, an answer acquiring unit configured to acquire an answer with respect to the problem and indicating a decision of the manufacturing step, a query acquiring unit configured to acquire a query, and a prediction output unit configured to predict and output an answer corresponding to the query acquired by the query acquiring unit, based on a corresponding relationship between the problem and the answer.Type: GrantFiled: November 22, 2019Date of Patent: September 24, 2024Assignee: RESONAC CORPORATIONInventors: Katsuki Okuno, Yoshishige Okuno, Shimpei Takemoto, Takuya Minami, Masamichi Kitano
-
Patent number: 12093292Abstract: To improve accuracy in a document search for a document that includes a typographical error. A document retrieval device according to one embodiment of the present invention includes a misidentification table storing a correctly identified character string and a misidentified character string. The document retrieval device includes a document searcher. The document searcher obtains a search character string, and retrieves the search character string from both a document and a character string that is obtained by changing the misidentified character string included in the document to the correctly identified character string.Type: GrantFiled: September 7, 2021Date of Patent: September 17, 2024Assignee: Resonac CorporationInventors: Yu Kawahara, Takuya Minami, Yu Okano, Hiroko Takashi, Yoshishige Okuno
-
Patent number: 12086189Abstract: A document search device includes a processor, and a memory storing program instructions that cause the processor to search for an input keyword in a document database in which document information including text data extracted by using a character recognition process from document image data generated by imaging a paper document is stored, select a similar keyword in accordance with a degree of similarity to the input keyword from a group of wildcard strings generated from the input keyword and search for the similar keyword in the document database, the degree of similarity being determined by comparing each character of the input keyword with a corresponding character of a wildcard string in the group of wildcard strings, and output a search result obtained by searching for the input keyword in the document database and a search result obtained by searching for the similar keyword in the document database.Type: GrantFiled: June 22, 2023Date of Patent: September 10, 2024Assignee: RESONAC CORPORATIONInventors: Yoshishige Okuno, Takuya Minami, Eriko Takeda, Hajime Hotta
-
Publication number: 20240290439Abstract: A physical property prediction device for predicting a physical property of a compound including: a generation unit configured to generate a first stage trained model, by using, as training data, first stage synthesis information and synthesis result information; a generation unit configured to generate second stage through last stage trained models, by using, as training data, n-th stage (n?2) synthesis information, n-th stage synthesis result information, and n?1-th stage synthesis result information; a reception unit configured to receive a synthesis information setting for the compound for which the physical property is predicted; a prediction unit configured to predict a physical property value of a product synthesized by the first stage chemical reaction of the compound; a prediction unit configured to repeat, from a second stage chemical reaction to a last stage chemical reaction of the compound, a process of predicting a physical property value of a product synthesized by the n-th stage chemical reactType: ApplicationFiled: June 22, 2022Publication date: August 29, 2024Inventors: Naoto AONUMA, Shimpei TAKEMOTO, Takuya MINAMI, Kohsuke KAKUDA, Yoshishige OKUNO, Hiroko TAKASHI
-
Publication number: 20240256667Abstract: An estimation device includes processing circuitry configured to estimate normal data having maximum similarity between abnormal data determined to be abnormal and each of a plurality of pieces of normal data determined to be normal, and compare the abnormal data with normal data estimated to have the maximum similarity and extract a portion of the abnormal data having no portion corresponding to the normal data as a portion causing abnormality.Type: ApplicationFiled: May 17, 2021Publication date: August 1, 2024Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Tomohiro NAGAI, Takuya MINAMI
-
Publication number: 20240232659Abstract: Prediction accuracy is increased in a prediction device using a trained model. A prediction device includes: a first trained model and a second trained model configured to respectively output first output data and second output data in response to input of input data of a prediction target; and an output portion configured to obtain the first output data and the second output data and calculate a weighted average value or take a weighted majority, thereby outputting prediction data. The first trained model is configured such that prediction accuracy for the input data of an interpolation region becomes higher than in the second trained model. The second trained model is configured such that prediction accuracy for the input data of an extrapolation region becomes higher than in the first trained model.Type: ApplicationFiled: April 14, 2022Publication date: July 11, 2024Inventors: Kohsuke KAKUDA, Takahiro FUJIMORI, Haein LEE, Shimpei TAKEMOTO, Takuya MINAMI, Yoshishige OKUNO
-
Patent number: 11985151Abstract: A generation device includes a memory, and processing circuitry coupled to the memory and configured to sense anomaly of a network based on information having a plurality of items related to communication in the network, identify a cause of anomaly corresponding to each piece of the information when anomaly is sensed, and generate, based on values of the items in the information and the cause of anomaly identified, a cause-of-anomaly pattern for each predetermined set of pieces of the information.Type: GrantFiled: July 2, 2019Date of Patent: May 14, 2024Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Takeshi Nakatsuru, Tomoyasu Sato, Takuya Minami, Naoto Fujiki, Masami Izumi
-
Patent number: 11960839Abstract: A cause-effect sentence analysis device including: a cause-effect sentence extraction unit configured to extract a cause-effect sentence including a cause expression and an effect expression from a text; an acquisition unit configured to acquire information indicating a reference expression for analyzing the degree of similarity; a similarity degree analysis unit, for a cause-effect sentence extracted by the cause-effect sentence extraction unit, configured to calculate a cause similarity degree, namely, the degree of similarity between the reference expression and the cause expression included in the cause-effect sentence, and an effect similarity degree, namely, the degree of similarity between the reference expression and the effect expression; and a desired cause-effect sentence extraction unit for extracting a cause-effect sentence in which one of the cause expression and the effect expression included in the cause-effect sentence is similar to the reference expression and the other is not similar to theType: GrantFiled: October 30, 2018Date of Patent: April 16, 2024Assignees: Resonac Corporation, School Juridical Person Seikei GakuenInventors: Takuya Minami, Yoshishige Okuno, Chinatsu Tanabe, Yusuke Yamazaki, Hiroyuki Sakai, Hiroki Sakaji
-
Patent number: 11915799Abstract: A polymer physical property prediction device includes a processor, and a memory storing program instructions that cause the processor to read a structural unit from a storage unit and use the structural unit to calculate numbers each indicating how many substructures are in a polymer, the polymer being formed of repetition of the structural unit, calculate a number indicating how many atoms are in the structural unit, calculate number densities of the substructures from the numbers of substructures and the number of atoms in the structural unit, construct a regression model that predicts a physical property value by using an experimental value of a physical property of the polymer and the number densities of the substructures, input a polymer structure of which the physical property value is to be predicted, and predict the physical property value corresponding to the input polymer structure by using the regression model.Type: GrantFiled: September 1, 2020Date of Patent: February 27, 2024Assignee: RESONAC CORPORATIONInventors: Takuya Minami, Yoshishige Okuno
-
Publication number: 20230366936Abstract: A lithium ion battery lifetime prediction method executes, by a computer, acquiring training data including cycle measurement data and lifetime data of a battery, learning a lifetime prediction model using the training data with respect to one or more cycle numbers at which a prediction is made, to acquire a set of learned lifetime prediction models corresponding to the cycle numbers at which the prediction is made, respectively, successively acquiring cycle measurement data for prediction of a battery that is a prediction target, up to the cycle numbers at which the prediction is made, respectively, and inputting the cycle measurement data for prediction acquired up to the cycle numbers at which the prediction is made, to the learned lifetime prediction models of the corresponding cycle numbers at which the prediction is made, and acquiring a probability distribution of a lifetime at the cycle numbers at which the prediction is made, respectively, as an output.Type: ApplicationFiled: October 12, 2021Publication date: November 16, 2023Inventors: Yuji KURAUCHI, Takuya MINAMI, Yuji ITO, Daisuke KOHNO, Hirofumi INOUE, Yoshishige OKUNO
-
Publication number: 20230359653Abstract: To improve accuracy in a document search for a document that includes a typographical error. A document retrieval device according to one embodiment of the present invention includes a misidentification table storing a correctly identified character string and a misidentified character string. The document retrieval device includes a document searcher. The document searcher obtains a search character string, and retrieves the search character string from both a document and a character string that is obtained by changing the misidentified character string included in the document to the correctly identified character string.Type: ApplicationFiled: September 7, 2021Publication date: November 9, 2023Inventors: Yu KAWAHARA, Takuya MINAMI, Yu OKANO, Hiroko TAKASHI, Yoshishige OKUNO
-
Publication number: 20230362182Abstract: An anomaly detection device is provided with a learning unit that generates a detection model using a communication log during normal operation of a communication apparatus as learning data and an anomaly detection unit that detects anomaly of the communication apparatus using the generated detection model. The anomaly detection device is further provided with a data acquisition unit that acquires a communication log (second communication log) generated during a predetermined period later than a first communication log and a determination unit that instructs relearning using the second communication log when there is difference information between the learning data (first communication log) of the current detection model and the second communication log and when the number of pieces of additional information (information on the additional flow) or the number of pieces of deletion information (information on the delete flow) included in the difference information satisfies predetermined evaluation criteria.Type: ApplicationFiled: July 14, 2023Publication date: November 9, 2023Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Masami IZUMI, Tomoyasu SATO, Takeshi NAKATSURU, Takuya MINAMI, Naoto FUJIKI
-
Patent number: 11805142Abstract: A communication system including an operational network including a host and a learning and detection server, and a staging network including a host of the same type as the host, a test execution server, and a learning and detection server. The test execution server performs a communication test by transmitting test communication in a normal state to the host and receiving communication performed by the host. The learning and detection server learns the communication of the host, generates an initial model for detecting an anomalous communication of the host, and transmits the initial model to the learning and detection server. The learning and detection server learns the communication of the host and generates a model for detecting an anomalous communication of the host, while monitoring the communication of the host using the initial model received from the learning and detection server.Type: GrantFiled: June 26, 2019Date of Patent: October 31, 2023Assignee: NIPPON TELEGRAPH AND TELEPHONE CORPORATIONInventors: Takuya Minami, Tomoyasu Sato, Naoto Fujiki, Takeshi Nakatsuru, Masami Izumi