公开(公告)号：US11531907B2

公开(公告)日：2022-12-20

申请号：US17854264

申请日：2022-06-30

Applicant: SAS Institute Inc.

Inventor： Afshin Oroojlooyjadid ,  Mohammadreza Nazari ,  Davood Hajinezhad ,  Amirhassan Fallah Dizche ,  Jorge Manuel Gomes da Silva ,  Jonathan Lee Walker ,  Hardi Desai ,  Robert Blanchard ,  Varunraj Valsaraj ,  Ruiwen Zhang ,  Weichen Wang ,  Ye Liu ,  Hamoon Azizsoltani ,  Prathaban Mookiah

IPC: G06N5/02

Abstract: A computing device trains a machine state predictive model. A generative adversarial network with an autoencoder is trained using a first plurality of observation vectors. Each observation vector of the first plurality of observation vectors includes state variable values for state variables and an action variable value for an action variable. The state variables define a machine state, wherein the action variable defines a next action taken in response to the machine state. The first plurality of observation vectors successively defines sequential machine states to manufacture a product. A second plurality of observation vectors is generated using the trained generative adversarial network with the autoencoder. A machine state machine learning model is trained to predict a subsequent machine state using the first plurality of observation vectors and the generated second plurality of observation vectors. A description of the machine state machine learning model is output.

公开(公告)号：US20220374732A1

公开(公告)日：2022-11-24

申请号：US17854264

申请日：2022-06-30

Applicant: SAS Institute Inc.

Inventor： Afshin Oroojlooyjadid ,  Mohammadreza Nazari ,  Davood Hajinezhad ,  Amirhassan Fallah Dizche ,  Jorge Manuel Gomes da Silva ,  Jonathan Lee Walker ,  Hardi Desai ,  Robert Blanchard ,  Varunraj Valsaraj ,  Ruiwen Zhang ,  Weichen Wang ,  Ye Liu ,  Hamoon Azizsoltani ,  Prathaban Mookiah

IPC: G06N5/02

Abstract: A computing device trains a machine state predictive model. A generative adversarial network with an autoencoder is trained using a first plurality of observation vectors. Each observation vector of the first plurality of observation vectors includes state variable values for state variables and an action variable value for an action variable. The state variables define a machine state, wherein the action variable defines a next action taken in response to the machine state. The first plurality of observation vectors successively defines sequential machine states to manufacture a product. A second plurality of observation vectors is generated using the trained generative adversarial network with the autoencoder. A machine state machine learning model is trained to predict a subsequent machine state using the first plurality of observation vectors and the generated second plurality of observation vectors. A description of the machine state machine learning model is output.

公开(公告)号：US11176692B2

公开(公告)日：2021-11-16

申请号：US17060504

申请日：2020-10-01

Applicant: SAS Institute Inc.

Inventor： Hamza Mustafa Ghadyali ,  Kedar Shriram Prabhudesai ,  Jonathan Lee Walker ,  Xunlei Wu ,  Xingqi Du ,  Bahar Biller ,  Mohammadreza Nazari ,  Afshin Oroojlooyjadid ,  Alexander Richard Phelps ,  Davood Hajinezhad ,  Varunraj Valsaraj ,  Jorge Manuel Gomes da Silva ,  Jinxin Yi

IPC: G06T7/292 ,  G06T7/00 ,  G06T7/246 ,  G06K9/00 ,  G06K9/32 ,  G06T11/60 ,  G06F11/20 ,  G05B13/04

Abstract: A computing system responsive to obtaining original image data, detects a set of data point(s), in the original image data, that indicates an object. The system determines, based on the set of data point(s), a set of pixels associated with the object in the original image data. The system generates an alternative visual identifier for the object that provides a unique identifier for the set of pixels absent in the original image data. The system generates, autonomously from intervention by any user of the computing system, pixel information to conceal feature(s) of the object. The system obtains modified image data comprising the alternative visual identifier. The modified image data further comprises the feature(s) of the object in the original image data visually concealed in the modified image data according to the pixel information. The system outputs an image representation of a trajectory of the object through the modified image data.

公开(公告)号：US20210312277A1

公开(公告)日：2021-10-07

申请号：US17088403

申请日：2020-11-03

Applicant: SAS Institute Inc.

Inventor： Kedar Shriram Prabhudesai ,  Varunraj Valsaraj ,  Jinxin Yi ,  Daniel Keongson Woo ,  Roger Lee Baldridge, JR.

IPC: G06N3/08

Abstract: Requests for computing resources and other resources can be predicted and managed. For example, a system can determine a baseline prediction indicating a number of requests for an object over a future time-period. The system can then execute a first model to generate a first set of values based on seasonality in the baseline prediction, a second model to generate a second set of values based on short-term trends in the baseline prediction, and a third model to generate a third set of values based on the baseline prediction. The system can select a most accurate model from among the three models and generate an output prediction by applying the set of values output by the most accurate model to the baseline prediction. Based on the output prediction, the system can cause an adjustment to be made to a provisioning process for the object.

公开(公告)号：US11055639B1

公开(公告)日：2021-07-06

申请号：US17064280

申请日：2020-10-06

Applicant: SAS Institute Inc.

Inventor： Pelin Cay ,  Nabaruna Karmakar ,  Natalia Summerville ,  Varunraj Valsaraj ,  Antony Nicholas Cooper ,  Steven Joseph Gardner ,  Joshua David Griffin

IPC: G06N20/00 ,  G06N3/08 ,  G06Q10/04 ,  G06F9/54 ,  G06N3/02 ,  G06N20/20 ,  G06N20/10 ,  G06N3/04 ,  G06F9/50

Abstract: Manufacturing processes can be optimized using machine learning models. For example, a system can execute an optimization model to identify a recommended set of values for configurable settings of a manufacturing process associated with an object. The optimization model can determine the recommended set of values by implementing an iterative process using an objective function. Each iteration of the iterative process can include selecting a current set of candidate values for the configurable settings from within a current region of a search space defined by the optimization model; providing the current set of candidate values as input to a trained machine learning model that can predict a value for a target characteristic of the object or the manufacturing process based on the current set of candidate values; and identifying a next region of the search space to use in a next iteration of the iterative process based on the value.

公开(公告)号：US20210082129A1

公开(公告)日：2021-03-18

申请号：US17060957

申请日：2020-10-01

Applicant: SAS Institute Inc.

Inventor： Mohammadreza Nazari ,  Afshin Oroojlooyjadid ,  Alexander Richard Phelps ,  Davood Hajinezhad ,  Bahar Biller ,  Jonathan Lee Walker ,  Hamza Mustafa Ghadyali ,  Kedar Shriram Prabhudesai ,  Xunlei Wu ,  Xingqi Du ,  Jorge Manuel Gomes da Silva ,  Varunraj Valsaraj ,  Jinxin Yi

IPC: G06T7/292 ,  G06T7/00 ,  G06T7/246 ,  G06F11/20 ,  G06T11/60

Abstract: A computing system receives historical data. The historical data comprises physical actions taken in an experiment in a physical environment. The experiment comprises user-defined stages. The historical data comprises a recorded outcome, according to user-defined performance indicator(s) related to the user-defined stages, for each physical action taken in the experiment. The system generates, by a discrete event simulator, a computing representation of a simulated environment of the physical environment. The simulated environment comprises processing stages. The system obtains simulation data. The simulation data comprises simulated actions taken by the discrete event simulator. The simulation data comprises a predicted outcome, according to user-defined performance indicator(s) related to the processing stages, for each simulated action taken by the discrete event simulator. The system validates accuracy of the discrete event simulator at predicting the recorded outcome in the experiment. The system trains a computing agent according to a sequential decision-making algorithm.

公开(公告)号：US20210019528A1

公开(公告)日：2021-01-21

申请号：US17060260

申请日：2020-10-01

Applicant: SAS Institute Inc.

Inventor： Hamza Mustafa Ghadyali ,  Kedar Shriram Prabhudesai ,  Mohammadreza Nazari ,  Bahar Biller ,  Afshin Oroojlooyjadid ,  Alexander Richard Phelps ,  Jonathan Lee Walker ,  Xunlei Wu ,  Xingqi Du ,  Davood Hajinezhad ,  Varunraj Valsaraj ,  Jorge Manuel Gomes da Silva ,  Jinxin Yi

IPC: G06K9/00 ,  G05B13/04 ,  G06K9/32

Abstract: A computing system obtains image data representing images. Each of the images is captured at different time points of a physical environment. The physical environment comprises a first object and a second object. The computing system executes a control system to augment the physical environment. The control system detects a group forming in the images. The control system tracks an aspect of a movement, of a given object, in the group. The control system simulates the physical environment and the movement, of the given object, in the group in a simulated environment. The control system evaluates simulated actions in the simulated environment for a predefined objective for the physical environment. The predefined objective is related to an interaction between objects in the group. The control system generates based on evaluated simulated actions and autonomously from involvement by any user of the control system, an indication to augment the physical environment.

公开(公告)号：US10255085B1

公开(公告)日：2019-04-09

申请号：US16182930

申请日：2018-11-07

Applicant: SAS Institute Inc.

Inventor： Varunraj Valsaraj ,  Bahadir Aral ,  Jinxin Yi ,  Roger Lee Baldridge, Jr. ,  Rebecca Gallagher

IPC: G06F9/451 ,  G06N20/00 ,  G06F16/904

Abstract: One exemplary system can receive a selection of a dataset via a graphical user interface (GUI). The dataset can represent a time-series projection. The system can feed the dataset into a first machine-learning model to obtain an output indicating whether the time-series projection has a data value that should be overridden with an override value. If the first machine-learning model indicates that the time-series projection has the data value that should be overridden, the system can feed the data value as input to a second machine-learning model to obtain an output indicating whether the override value should be greater than or less than the data value. The system can then render a visual directionality cue within the GUI based on the output from the second machine-learning model. The visual directionality cue can provide guidance for overriding the data value.

公开(公告)号：US09705751B1

公开(公告)日：2017-07-11

申请号：US15335070

申请日：2016-10-26

Applicant: SAS Institute Inc.

Inventor： Jinxin Yi ,  Necip Baris Kacar ,  Varunraj Valsaraj

IPC: G06F15/177 ,  H04L12/24

CPC classification number: H04L41/147 ,  G06F11/00 ,  H04L41/0823 ,  H04L41/145

Abstract: A computing device quantifies an expected benefit from a calibrated coefficient of variation (CV) and/or a calibrated service level (SL). The target optimization model determines a number and a time a new requisition is placed for an item at each node of the plurality of nodes. A validation time value is updated using an incremental time value and the process is repeated until the validation time value is greater than or equal to a stop time.