公开(公告)号：US20230274310A1

公开(公告)日：2023-08-31

申请号：US17680932

申请日：2022-02-25

Applicant: ADOBE INC.

Inventor： Gaurav Sinha ,  Vibhor Porwal ,  Isha Chaudhary ,  Simarpreet Singh Saluja ,  Rashul Chutani ,  Shaurya Goel

IPC: G06Q30/02 ,  G06K9/62

CPC classification number: G06Q30/0246 ,  G06K9/6232 ,  G06K9/6256

Abstract: An analytics system jointly predicts values for multiple unobserved individual-level features using aggregate data for those features. Given a dataset, a transformation is applied to individual-level information for the dataset to generate transformed data in a higher dimensional space. Bag-wise mean embeddings are generated using the transformed data. The bag-wise mean embeddings and aggregate data for unobserved individual-level features for the dataset are used to train a model to jointly predict values for the unobserved individual-features for data instances. In particular, a given data instance can be transformed to a representation in a higher dimensional space. Given this representation, the trained model predicts values for the unobserved individual-level features for the data instance, and the data instance can be augmented with the predicted values.