公开(公告)号：US11568320B2

公开(公告)日：2023-01-31

申请号：US17154928

申请日：2021-01-21

Applicant: SNOWFLAKE INC.

Inventor： Orestis Kostakis ,  Qiming Jiang ,  Boxin Jiang

IPC: G06N20/00 ,  G06F16/24

Abstract: Systems and methods for managing input and output error of a machine learning (ML) model in a database system are presented herein. A set of test queries is executed on a first version of a database system to generate first test data, wherein the first version of the system comprises a ML model to generate an output corresponding to a function of the database system. An error model is trained based on the first test data and second test data generated based on a previous version of the system. The error model determines an error associated with the ML model between the first and previous versions of the system. The first version of the system is deployed with the error model, which corrects an output or an input of the ML model until sufficient data has been produced by the error model to retrain the ML model.

公开(公告)号：US20240346386A1

公开(公告)日：2024-10-17

申请号：US18133477

申请日：2023-04-11

Applicant: Snowflake Inc.

Inventor： Michel Adar ,  Boxin Jiang ,  Anh Quynh Kieu ,  Boyu Wang

IPC: G06N20/20

CPC classification number: G06N20/20

Abstract: Disclosed is a fast and accurate time series forecasting algorithm that eliminates the need for hyperparameter tuning. Time series data may be analyzed using a quadratic function to determine a quadratic trend prediction, which is removed from the time series data to generate first detrended time series data. A moving median of the time series data is determined and the moving median is removed from the time series data to generate second detrended time series data. An amplitude scaling factor is determined based on the second detrended time series data and the first detrended time series data is descaled using the amplitude scaling factor to generate descaled time series data. The descaled time series data is analyzed to determine a seasonal prediction and a time series forecast is generated based on the seasonal prediction, the quadratic trend prediction, and the amplitude scaling factor.

公开(公告)号：US20230401283A1

公开(公告)日：2023-12-14

申请号：US18112944

申请日：2023-02-22

Applicant: Snowflake Inc.

Inventor： Michel Adar ,  Boxin Jiang ,  Qiming Jiang ,  John Reumann ,  Boyu Wang ,  Jiaxun Wu

IPC: G06F17/18

CPC classification number: G06F17/18

Abstract: Using an attributes model of a time series forecasting model, determine a set of features based on time series data, the set of features including periodic components. The time series data may be divided into a set of segments. For each segment of the set of segments, a weight may be assigned using an age of the segment, resulting in a set of weighted segments of time series data. Using a trend detection model of the time series forecasting model, trend data from the set of weighted segments of time series data may be determined. A time series forecast may be generated by combining the set of features and the trend data.

公开(公告)号：US20230136738A1

公开(公告)日：2023-05-04

申请号：US18074830

申请日：2022-12-05

Applicant: SNOWFLAKE INC.

Inventor： Boxin Jiang ,  Qiming Jiang

IPC: G06F16/21 ,  G06N3/08 ,  G06F16/242 ,  G06F16/2458

Abstract: An example method of tuning a machine learning operation can include receiving a data query comprising a reference to an input data set of a database, generating a plurality of unique sets of hyperparameters by varying a hyperparameter value of each set of hyperparameters of the plurality of unique sets of hyperparameters based on the input data set, in response to receiving the data query, training a plurality of machine learning models using the input data set of the data query, each of the plurality of machine learning models configured according to a respective one of a plurality of unique sets of hyperparameters, selecting a first machine learning model of the plurality of machine learning models based on an accuracy of an output of the first machine learning model, and returning the output of the first machine learning model in response to the data query.

公开(公告)号：US20230132117A1

公开(公告)日：2023-04-27

申请号：US18087518

申请日：2022-12-22

Applicant: SNOWFLAKE INC.

Inventor： Orestis Kostakis ,  Qiming Jiang ,  Boxin Jiang

IPC: G06N20/00 ,  G06F16/24

Abstract: Systems and methods for managing input and output error of a machine learning (ML) model in a database system are presented herein. A set of test queries is executed on a first version of a database system to generate first test data, wherein the first version of the system comprises a ML model to generate an output corresponding to a function of the database system. An error model is trained based on the first test data and second test data generated based on a previous version of the system. The error model determines an error associated with the ML model between the first and previous versions of the system. The first version of the system is deployed with the error model, which corrects an output or an input of the ML model until sufficient data has been produced by the error model to retrain the ML model.

公开(公告)号：US11561946B1

公开(公告)日：2023-01-24

申请号：US17514216

申请日：2021-10-29

Applicant: SNOWFLAKE INC.

Inventor： Boxin Jiang ,  Qiming Jiang

IPC: G06F16/20 ,  G06F16/21 ,  G06F16/2458 ,  G06F16/242 ,  G06N3/08

Abstract: Embodiments of the present disclosure describe systems, methods, and computer program products for executing and tuning a machine learning operation within a database. An example method can include receiving a data query referencing an input data set of a database, executing a plurality of machine learning operations to generate, in view of the input data set, a plurality of output data sets each having a respective accuracy value, wherein each of the plurality of machine learning operations is executed by a processing device according to one of a plurality of unique sets of hyperparameters, selecting a first output data set of the plurality of output data sets in view of the accuracy values, and returning the first output data set in response to the data query.

公开(公告)号：US20220230093A1

公开(公告)日：2022-07-21

申请号：US17154928

申请日：2021-01-21

Applicant: SNOWFLAKE INC.

Inventor： Orestis Kostakis ,  Qiming Jiang ,  Boxin Jiang

IPC: G06N20/00 ,  G06F16/24

Abstract: Systems and methods for managing input and output error of a machine learning (ML) model in a database system are presented herein. A set of test queries is executed on a first version of a database system to generate first test data, wherein the first version of the system comprises a ML model to generate an output corresponding to a function of the database system. An error model is trained based on the first test data and second test data generated based on a previous version of the system. The error model determines an error associated with the ML model between the first and previous versions of the system. The first version of the system is deployed with the error model, which corrects an output or an input of the ML model until sufficient data has been produced by the error model to retrain the ML model.