公开(公告)号：US20240119118A1

公开(公告)日：2024-04-11

申请号：US18353243

申请日：2023-07-17

申请人： Fujitsu Limited

发明人： Yuma ICHIKAWA

IPC分类号： G06F17/18

CPC分类号： G06F17/18

摘要： A non-transitory computer-readable recording medium stores a program for causing a computer to execute a sampling process including: converting first data in a latent space into second data in a data space by using a machine learning model that has the latent space transformable into an isometric space with same probability distribution as the data space according to a predetermined transformation rule; determining whether or not to accept the second data as a transition state in a Markov chain Monte Carlo method from an accepted first sample in the data space with an acceptance probability based on the transformation rule; and outputting the second data as a second sample of the transition state from the first sample when the second data is determined to be accepted.

公开(公告)号：US20240118250A1

公开(公告)日：2024-04-11

申请号：US18543667

申请日：2023-12-18

申请人： Regeneron Pharmaceuticals, Inc.

发明人： Eric Shierly ,  Kevin Brennan ,  Nathan Mao

IPC分类号： G01N30/74 ,  G01N1/34 ,  G01N21/33 ,  G01N30/04 ,  G01N30/88 ,  G01N33/48 ,  G06F17/18

CPC分类号： G01N30/74 ,  G01N1/34 ,  G01N21/33 ,  G01N30/04 ,  G01N30/88 ,  G01N33/48 ,  G06F17/18 ,  G01N2030/027

摘要： Disclosed are methods for monitoring column chromatography performance. The methods can include acquiring one or more chromatogram ultraviolet (UV) traces generated by a chromatography system during sample purification and/or separation; and analyzing the one or more acquired chromatogram UV traces with an orthogonal partial least squares (OPLS) model, thereby allowing detection of column deterioration prior to column failure and quantitative analysis of UV signal in the one or more chromatogram UV traces.

公开(公告)号：US20240115211A1

公开(公告)日：2024-04-11

申请号：US18389700

申请日：2023-12-19

申请人： Dexcom, Inc.

发明人： Esteban CABRERA, JR. ,  Lauren Danielle ARMENTA ,  Scott M. BELLIVEAU ,  Jennifer BLACKWELL ,  Leif N. BOWMAN ,  Rian DRAEGER ,  Arturo GARCIA ,  Timothy Joseph GOLDSMITH ,  John Michael GRAY ,  Andrea Jean JACKSON ,  Apurv Ullas KAMATH ,  Katherine Yerre KOEHLER ,  Paul KRAMER ,  Aditya Sagar MANDAPAKA ,  Michael Robert MENSINGER ,  Sumitaka MIKAMI ,  Gary A. MORRIS ,  Hemant Mahendra NIRMAL ,  Paul NOBLE-CAMPBELL ,  Philip Thomas PUPA ,  Eli REIHMAN ,  Peter C. SIMPSON ,  Brian Christopher SMITH ,  Atiim Joseph WILEY

IPC分类号： A61B5/00 ,  A61B5/145 ,  G06F1/16 ,  G06F3/0484 ,  G06F3/04847 ,  G06F3/0488 ,  G06F17/18 ,  G16H15/00 ,  G16H40/63 ,  G16H40/67 ,  G16H50/20 ,  G16H50/30 ,  G16H70/40

CPC分类号： A61B5/7275 ,  A61B5/0022 ,  A61B5/14532 ,  A61B5/743 ,  A61B5/746 ,  G06F1/163 ,  G06F3/0484 ,  G06F3/04847 ,  G06F3/0488 ,  G06F17/18 ,  G16H15/00 ,  G16H40/63 ,  G16H40/67 ,  G16H50/20 ,  G16H50/30 ,  G16H70/40 ,  G06F16/00

摘要： Disclosed are systems and methods for generating graphical displays of analyte data and/or health information. In some implementations, the graphical displays are generating based on a self-referential dataset that are modifiable based on identified portions of the data. The modified graphical displays can indicate features in the analyte data of a host.

公开(公告)号：US11948180B2

公开(公告)日：2024-04-02

申请号：US17393598

申请日：2021-08-04

申请人： UIF (University Industry Foundation), Yonsei University

发明人： Il Im ,  Seok Yoon Suh

IPC分类号： G06Q30/00 ,  G06F17/11 ,  G06F17/16 ,  G06F17/18 ,  G06Q30/0601

CPC分类号： G06Q30/0631 ,  G06F17/11 ,  G06F17/16 ,  G06F17/18 ,  G06Q30/0641

摘要： Disclosed herein are a system and method for recommending repeat-purchase products using modified self-similarity. The system is operated by a computer in an environment in which user equipment (UE), a database, and a web server are connected over a network. The system includes: a user information reception unit configured to receive user information from the database when the UE connects with the web server; a modified self-similarity calculation unit configured to calculate a modified self-similarity (MSS) using the user information received by the user information reception unit; a similarity calculation unit configured to calculate the sums of similarities between products by substituting the modified self-similarity, calculated by the modified self-similarity calculation unit, into an inter-product similarity calculation matrix; and a product recommendation unit configured to align the sums of similarities between products calculated by the similarity calculation unit and to transmit product information fulfilling preset criteria to the UE.

公开(公告)号：US11947624B2

公开(公告)日：2024-04-02

申请号：US17794257

申请日：2020-11-23

申请人： BEIJING TENHE ELECTRONIC TECHNOLOGY CO. , LTD.

发明人： Hongshan Chang ,  Guang He

IPC分类号： G06F17/18 ,  G01R35/04

CPC分类号： G06F17/18 ,  G01R35/04

摘要： A method and system for analyzing the error of a measurement domain based on a single load jump and a computer-readable storage medium are provided. According to the method and the system, high-density measurement is performed on the load of a master meter and sub-meters in a measurement domain for a long time to obtain massive load data. After that, based on a single load jump, a load measurement difference of the master meter before and after the jump, and a load measurement difference of a jumping sub-meter before and after the jump are obtained. The error deviation degree of the jumping sub-meter relative to the master meter is uniquely defined. After statistical data of error deviation degrees of all the sub-meters relative to the master meter is obtained, error analysis is performed on the whole measurement domain based on the statistical data.

公开(公告)号：US11947623B2

公开(公告)日：2024-04-02

申请号：US17186261

申请日：2021-02-26

申请人： KABUSHIKI KAISHA TOSHIBA

发明人： Kaneharu Nishino ,  Ryusei Shingaki ,  Ken Ueno

IPC分类号： G06F17/18 ,  G06F3/14 ,  G06N20/00

CPC分类号： G06F17/18 ,  G06F3/14 ,  G06N20/00

摘要： An information processing device according to an embodiment estimates a probability distribution of a maximum value or a minimum value of time-series target sensor data in a designated estimation period after a base time. The information processing device includes one or more hardware processors that: calculate a reference feature amount representing a feature of related sensor data at a reference time before the base time based on a preset feature amount calculation model; estimate a reference distribution parameter in a reference period based on a preset parameter estimation model; update the feature amount calculation model and the parameter estimation model; calculate an estimation feature amount representing the feature of related sensor data at the base time based on the updated feature amount calculation model; and estimate an estimation distribution parameter based on the updated parameter estimation model.

公开(公告)号：US11946470B2

公开(公告)日：2024-04-02

申请号：US16467472

申请日：2018-03-13

申请人： EBARA CORPORATION

发明人： Keiji Maishigi ,  Tetsuro Sugiura ,  Katsuaki Usui ,  Masahiro Hatakeyama ,  Chikako Honma ,  Toru Osuga ,  Koichi Iwasaki ,  Jie Yuan Lin

IPC分类号： F04C28/28 ,  F04D27/00 ,  G06F9/54 ,  G06F17/18

CPC分类号： F04C28/28 ,  F04D27/001 ,  G06F9/542 ,  G06F17/18

摘要： An information processing apparatus detecting presence or absence of abnormality of a vacuum pump derived from a product produced within a target vacuum pump, including:



a determination unit configured to determine a normal variation range or a normal time variation behavior of a target state quantity which is a state quantity varying depending on a load of gas flowing into the vacuum pump, based on at least one of past target state quantities of the target vacuum pump or another vacuum pump; and
a comparison unit configured to compare a current target state quantity of the target vacuum pump with the normal variation range or the normal time variation behavior and output the comparison result.

公开(公告)号：US11940894B2

公开(公告)日：2024-03-26

申请号：US17888104

申请日：2022-08-15

申请人： Express Scripts Strategic Development, Inc.

发明人： Michael D. Trapani ,  Jeevan Kumar Goud Bandharapu

IPC分类号： G06F11/34 ,  G06F11/30 ,  G06F17/18 ,  G06N20/00 ,  H04L41/14 ,  H04L43/045 ,  H04L43/08

CPC分类号： G06F11/3409 ,  G06F11/3055 ,  G06F11/3457 ,  G06F17/18 ,  G06N20/00 ,  H04L41/145 ,  H04L43/045 ,  H04L43/08

摘要： A computer system includes processor hardware configured to execute instructions from memory hardware. The instructions include training first and second machine learning models with the measured historical performance metrics to generate a component health status output and a component health score output, respectively, and generating a plurality of elements for display in a multi-level application monitoring interface. The measured historical performance metrics include at least one of a component response time, a component volume, a component memory utilization, and a component processor utilization. The instructions include obtaining measured performance metrics of an application infrastructure component, processing the measured performance metrics with the first machine learning model to produce the component health status output for the component, processing the measured performance metrics with the second machine learning model to produce the component health score output for the first component, and generating an output to transform a display visible to an operator.

公开(公告)号：US11939859B2

公开(公告)日：2024-03-26

申请号：US16753073

申请日：2018-10-02

申请人： Schlumberger Technology Corporation

发明人： Geir Kroslid ,  Johan Lindal Haug

IPC分类号： E21B47/09 ,  E21B41/00 ,  E21B47/12 ,  G05B15/02 ,  G06F17/18

CPC分类号： E21B47/09 ,  E21B41/00 ,  E21B47/12 ,  G05B15/02 ,  G06F17/18

摘要： Systems and methods for utilizing performance based condition monitoring to determine health condition of wellsite equipment. A method may include operating a piece of equipment at an oil and gas wellsite by performing a plurality actions by a component of the piece of equipment, and generating a plurality of sensor measurements, wherein each sensor measurement is indicative of a corresponding action. The method may further include receiving the plurality of sensor measurements by a processing system, calculating a condition indicator for each component based on a corresponding sensor measurement, recording each condition indicator over a period of time, and determining condition of the piece of equipment based on at least one of the condition indicators recorded over time.

公开(公告)号：US20240098138A1

公开(公告)日：2024-03-21

申请号：US18240799

申请日：2023-08-31

申请人： Google LLC

发明人： Ananda Theertha Suresh ,  Sanjiv Kumar ,  Hugh Brendan McMahan ,  Xinnan Yu

IPC分类号： H04L67/10 ,  G06F17/12 ,  G06F17/16 ,  G06F17/18 ,  G06N7/01 ,  G06N20/00 ,  H03M7/30 ,  H03M7/40

CPC分类号： H04L67/10 ,  G06F17/12 ,  G06F17/16 ,  G06F17/18 ,  G06N7/01 ,  G06N20/00 ,  H03M7/3059 ,  H03M7/3082 ,  H03M7/40 ,  H04L67/01

摘要： The present disclosure provides systems and methods for communication efficient distributed mean estimation. In particular, aspects of the present disclosure can be implemented by a system in which a number of vectors reside on a number of different clients, and a centralized server device seeks to estimate the mean of such vectors. According to one aspect of the present disclosure, a client computing device can rotate a vector by a random rotation matrix and then subsequently perform probabilistic quantization on the rotated vector. According to another aspect of the present disclosure, subsequent to quantization but prior to transmission, the client computing can encode the quantized vector according to a variable length coding scheme (e.g., by computing variable length codes).