公开(公告)号：US11720590B2

公开(公告)日：2023-08-08

申请号：US17091941

申请日：2020-11-06

Applicant: ADOBE INC.

Inventor： Ryan Rossi ,  Vasanthi Holtcamp ,  Tak Yeon Lee ,  Sungchul Kim ,  Sana Lee ,  Nathan Ross ,  John Anderson ,  Fan Du ,  Eunyee Koh ,  Xin Qian

IPC: G06F16/9535 ,  G06F16/26 ,  G06F3/0482 ,  G06F11/34 ,  G06F11/30 ,  G06F16/9038

CPC classification number: G06F16/26 ,  G06F3/0482 ,  G06F11/302 ,  G06F11/3438 ,  G06F16/9038

Abstract: Systems and methods for personalized visualization recommendation are described. Embodiments of the described systems and methods are configured to identify a first matrix representing user interactions with a plurality of data attributes corresponding to a plurality of datasets, a second matrix representing user interactions with a plurality of visualizations, and a third matrix representing a plurality of meta-features for each of the data attributes; compute low-dimensional embeddings representing user characteristics, the data attributes, visualization configurations, and the meta-features using joint factorization of the first matrix, the second matrix and the third matrix; generate a model for predicting visualization preference weights based on the low-dimensional embeddings; predict the visualization preference weights for a user corresponding to a plurality of candidate visualizations of dataset using the model; and generate a personalized visualization of the dataset for the user based on the predicted visualization preference weights.

公开(公告)号：US11288541B1

公开(公告)日：2022-03-29

申请号：US17015495

申请日：2020-09-09

Applicant: Adobe Inc.

Inventor： Ryan Rossi ,  Vasanthi Holtcamp ,  Tak Yeon Lee ,  Sana Lee ,  Nathan Ross ,  John Anderson ,  Fan Du ,  Eunyee Koh

IPC: G06K9/62 ,  G06F17/18 ,  G06F3/0482

Abstract: This disclosure involves generating, from a user data set, a ranked list of recommended secondary variables in a user interface field similar to primary variable selected in another user interface field. A system receives a data set having variables and corresponding sets of values. The data visualization system determines a feature vector for each variable based on statistics of a corresponding values set. The system generates a variable similarity graph having nodes representing variables and links representing degrees of similarity between feature vectors of variables. The system receives a selection of a first variable via a first field of the user interface, detects a selection of a second field, and identifies a relationship between the first field and the second field. The system generates a contextual menu of recommended secondary variables for use with the selected first variable based on similarity value of the links in the variable similarity graph.

公开(公告)号：US20230306033A1

公开(公告)日：2023-09-28

申请号：US17693811

申请日：2022-03-14

Applicant: ADOBE INC.

Inventor： Arpit Ajay Narechania ,  Fan Du ,  Atanu R. Sinha ,  Ryan A. Rossi ,  Jane Elizabeth Hoffswell ,  Shunan Guo ,  Eunyee Koh ,  John Anderson ,  Sonali Surange ,  Saurabh Mahapatra ,  Vasanthi Holtcamp

IPC: G06F16/2457 ,  G06F16/25 ,  G06F16/215

CPC classification number: G06F16/24575 ,  G06F16/215 ,  G06F16/254

Abstract: Embodiments provide systems, methods, and computer storage media for management, assessment, navigation, and/or discovery of data based on data quality, consumption, and/or utility metrics. Data may be assessed using attribute-level and/or record-level metrics that quantify data: “quality” - the condition of data (e.g., presence of incorrect or incomplete values), its “consumption” - the tracked usage of data in downstream applications (e.g., utilization of attributes in dashboard widgets or customer segmentation rules), and/or its “utility” - a quantifiable impact resulting from the consumption of data (e.g., revenue or number of visits resulting from marketing campaigns that use particular datasets, storage costs of data). This data assessment may be performed at different stages of a data intake, preparation, and/or modeling lifecycle. For example, current and historical data metrics may be periodically aggregated, persisted, and/or monitored to facilitate discovery and removal of less effective data from a data lake.

公开(公告)号：US20230289839A1

公开(公告)日：2023-09-14

申请号：US17693799

申请日：2022-03-14

Applicant: ADOBE INC.

Inventor： Arpit Ajay Narechania ,  Fan Du ,  Atanu R. Sinha ,  Ryan A. Rossi ,  Jane Elizabeth Hoffswell ,  Shunan Guo ,  Eunyee Koh ,  John Anderson ,  Sonali Surange ,  Saurabh Mahapatra ,  Vasanthi Holtcamp

IPC: G06Q30/02

CPC classification number: G06Q30/0204

Abstract: Embodiments provide systems, methods, and computer storage media for management, assessment, navigation, and/or discovery of data based on data quality, consumption, and/or utility metrics. Data may be assessed using attribute-level and/or record-level metrics that quantify data: “quality”—the condition of data (e.g., presence of incorrect or incomplete values), its “consumption”—the tracked usage of data in downstream applications (e.g., utilization of attributes in dashboard widgets or customer segmentation rules), and/or its “utility”—a quantifiable impact resulting from the consumption of data (e.g., revenue or number of visits resulting from marketing campaigns that use particular datasets, storage costs of data). This data assessment may be performed at different stages of a data intake, preparation, and/or modeling lifecycle. For example, a data selection interface may filter based on consumption and/or quality metrics to facilitate discovery of more effective data for machine learning model training, data visualization, or marketing campaigns.

公开(公告)号：US20220147540A1

公开(公告)日：2022-05-12

申请号：US17091941

申请日：2020-11-06

Applicant: ADOBE INC.

Inventor： RYAN Rossi ,  Vasanthi Holtcamp ,  Tak Yeon Lee ,  Sungchul Kim ,  Sana Lee ,  Nathan Ross ,  John Anderson ,  Fan Du ,  Eunyee Koh ,  Xin Qian

IPC: G06F16/26 ,  G06F11/30 ,  G06F11/34 ,  G06F3/0482

Abstract: Systems and methods for personalized visualization recommendation are described. Embodiments of the described systems and methods are configured to identify a first matrix representing user interactions with a plurality of data attributes corresponding to a plurality of datasets, a second matrix representing user interactions with a plurality of visualizations, and a third matrix representing a plurality of meta-features for each of the data attributes; compute low-dimensional embeddings representing user characteristics, the data attributes, visualization configurations, and the meta-features using joint factorization of the first matrix, the second matrix and the third matrix; generate a model for predicting visualization preference weights based on the low-dimensional embeddings; predict the visualization preference weights for a user corresponding to a plurality of candidate visualizations of dataset using the model; and generate a personalized visualization of the dataset for the user based on the predicted visualization preference weights.

公开(公告)号：US20230289696A1

公开(公告)日：2023-09-14

申请号：US17693778

申请日：2022-03-14

Applicant: ADOBE INC.

Inventor： Arpit Ajay Narechania ,  Fan Du ,  Atanu R. Sinha ,  Ryan A. Rossi ,  Jane Elizabeth Hoffswell ,  Shunan Guo ,  Eunyee Koh ,  John Anderson ,  Sonali Surange ,  Saurabh Mahapatra ,  Vasanthi Holtcamp

IPC: G06Q10/06

CPC classification number: G06Q10/06393 ,  G06F3/0482

Abstract: Embodiments provide systems, methods, and computer storage media for management, assessment, navigation, and/or discovery of data based on data quality, consumption, and/or utility metrics. Data may be assessed using attribute-level and/or record-level metrics that quantify data: “quality”—the condition of data (e.g., presence of incorrect or incomplete values), its “consumption”—the tracked usage of data in downstream applications (e.g., utilization of attributes in dashboard widgets or customer segmentation rules), and/or its “utility”—a quantifiable impact resulting from the consumption of data (e.g., revenue or number of visits resulting from marketing campaigns that use particular datasets, storage costs of data). This data assessment may be performed at different stages of a data intake, preparation, and/or modeling lifecycle. For example, an interactive tree view may visually represent a nested attribute schema and attribute quality or consumption metrics to facilitate discovery of bad data before ingesting into a data lake.

公开(公告)号：US20220076048A1

公开(公告)日：2022-03-10

申请号：US17015495

申请日：2020-09-09

Applicant: Adobe Inc.

Inventor： Ryan Rossi ,  Vasanthi Holtcamp ,  Tak Yeon Lee ,  Sana Lee ,  Nathan Ross ,  John Anderson ,  Fan Du ,  Eunyee Koh

IPC: G06K9/62 ,  G06F3/0482 ,  G06F17/18

Abstract: This disclosure involves generating, from a user data set, a ranked list of recommended secondary variables in a user interface field similar to primary variable selected in another user interface field. A system receives a data set having variables and corresponding sets of values. The data visualization system determines a feature vector for each variable based on statistics of a corresponding values set. The system generates a variable similarity graph having nodes representing variables and links representing degrees of similarity between feature vectors of variables. The system receives a selection of a first variable via a first field of the user interface, detects a selection of a second field, and identifies a relationship between the first field and the second field. The system generates a contextual menu of recommended secondary variables for use with the selected first variable based on similarity value of the links in the variable similarity graph.