公开(公告)号：US20230153455A1

公开(公告)日：2023-05-18

申请号：US18155293

申请日：2023-01-17

Applicant: SNOWFLAKE INC.

Inventor： Boxin Jiang ,  Qiming Jiang

IPC: G06F21/62 ,  G06F16/2455

CPC classification number: G06F21/6227 ,  G06F16/24564

Abstract: Embodiments of the present disclosure describe systems, methods, and computer program products for redacting sensitive data within a database. An example method can include receiving a data query referencing unredacted data of a database, wherein the data query that is received comprises a value identifying a type of sensitive data to be redacted from the unredacted data, responsive to the data query, executing, by a processing device, a redaction operation to identify sensitive data that matches the type within the unredacted data of the database, and returning a redacted data set in which the sensitive data that matches the type is replaced or removed to the data query.

公开(公告)号：US11609970B1

公开(公告)日：2023-03-21

申请号：US17877588

申请日：2022-07-29

Applicant: Snowflake Inc.

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

IPC: G06F17/18

Abstract: A processing device may analyze a set of time series data using a time series forecasting model comprising an attributes model and a trend detection model. The attributes model may comprise a modified gradient boosting decision tree (GBDT) based algorithm. Analyzing the set of time series data comprises determining a set of features of the set of time series data, the set of features including periodic components as well as arbitrary components. A trend of the set of time series data may be determined using the trend detection model and the set of features and the trend may be combined to generate a time series forecast.

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：US11620289B1

公开(公告)日：2023-04-04

申请号：US17930277

申请日：2022-09-07

Applicant: Snowflake Inc.

Inventor： Qiming Jiang ,  Orestis Kostakis ,  John Reumann

IPC: G06F16/00 ,  G06F16/2453 ,  G06F16/27

Abstract: Embodiments of the present disclosure may provide a database optimization system that can generate computational values through a database compiler and assignment data for execution of a query by a plurality of nodes of a database system. The computational values and assignment data can be generated by one or more machine learning schemes. The machine learning schemes can be trained on previous computational values and previous assignment data.

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.

公开(公告)号：US11216481B2

公开(公告)日：2022-01-04

申请号：US17345484

申请日：2021-06-11

Applicant: Snowflake Inc.

Inventor： Istvan Cseri ,  Qiming Jiang

IPC: G06F16/25 ,  G06N20/00 ,  G06F9/46

Abstract: The subject technology determines a number of execution nodes to execute a task. The subject technology determines that no virtual warehouse from a pool of virtual warehouses includes at least the number of execution nodes. The subject technology generates a new virtual warehouse including at least the number of execution nodes. The subject technology determines whether a previous execution of a prior task was completed in less than a threshold time period of a time interval, the time interval corresponding to a particular period of time for executing at least one task. The subject technology increments a score corresponding to a size of a particular virtual warehouse. The subject technology selects the new virtual warehouse from the pool of virtual warehouses based at least in part on the incremented score and the number of execution nodes included in the selected new virtual warehouse.

公开(公告)号：US11138038B1

公开(公告)日：2021-10-05

申请号：US17173717

申请日：2021-02-11

Applicant: Snowflake Inc.

Inventor： Qiming Jiang ,  Orestis Kostakis ,  Abdul Munir ,  Prayag Chandran Nirmala ,  Jeffrey Rosen

IPC: G06F9/46 ,  G06F9/50 ,  G06N5/04 ,  G06F16/2455 ,  G06N20/00

Abstract: The subject technology determines usage history metadata. The subject technology predicts a size value indicating an amount of computing resources to request for executing a set of queries based at least in part on the usage history metadata. The subject technology determines, during a prefetch window of time within a first period of time, a current size of a freepool of computing resources. The subject technology, in response to the current size of the freepool of computing resources being smaller than the predicted size value, sends a request for additional computing resources to include in the freepool of computing resources. The subject technology receives an indication that the request for additional computing resources was granted. The subject technology performs an operation to include the additional computing resources in the freepool of computing resources.