公开(公告)号：US20230055760A1

公开(公告)日：2023-02-23

申请号：US17405011

申请日：2021-08-17

Applicant: Maplebear Inc.(dba Instacart)

Inventor： Saurav Manchanda ,  Krishnakumar Subramanian ,  Haixun Wang ,  Min Xie

IPC: G06K9/62 ,  G06N3/08

Abstract: An online concierge system trains a classification model as a domain adversarial neural network from training data labeled with source classes from a source domain that do not overlap with target classes from a target domain output by the classification model. The online concierge system maps one or more source classes to a target class. The classification model extracts features from an image, classifies whether an image is from the source domain or the target domain, and predicts a target class for an image from the extracted features. The classification model includes a gradient reversal layer between feature extraction layers and the domain classifier that is used during training, so the feature extraction layers extract domain invariant features from an image.

公开(公告)号：US20250095046A1

公开(公告)日：2025-03-20

申请号：US18888607

申请日：2024-09-18

Applicant: Maplebear Inc.

Inventor： Shih-Ting Lin ,  Saurav Manchanda ,  Prithvishankar Srinivasan ,  Shishir Kumar Prasad ,  Min Xie ,  Benwen Sun ,  Axel Mange ,  Wenjie Tang ,  Sanchit Gupta

IPC: G06Q30/0601 ,  G06Q10/0833 ,  G06Q30/0201

Abstract: An online system obtains a target food from an order for a user and alcohol preferences from an order purchase history. The online system generates a prompt for a machine learning model to request alcohol candidates based on the target food category. The prompt includes the alcohol preferences, and requests for each alcohol candidate, a pairing score indicating how well the target food category pairs with the alcohol candidate and a user preference score indicating how well the alcohol candidate aligns with the alcohol preferences. The online system receives as output the candidate alcohol items. Each alcohol candidate has the pairing score, the user preference score, and a textual reason for scores. The online system matches at least one alcohol item from a catalog with each alcohol candidate. A subset of alcohol items is presented to the user as a carousel.

公开(公告)号：US20250069298A1

公开(公告)日：2025-02-27

申请号：US18236346

申请日：2023-08-21

Applicant: Maplebear Inc.

Inventor： Prithvishankar Srinivasan ,  Shih-Ting Lin ,  Min Xie ,  Shishir Kumar Prasad ,  Yuanzheng Zhu ,  Katie Ann Forbes

IPC: G06T11/60 ,  G06F16/55 ,  G06F16/583 ,  G06Q30/0601 ,  G06T11/20

Abstract: An online concierge system trains a fine-tuned generative image model for distinct categories of items based on a generative image model that takes a textual query as input and outputs and an associated image. Training of the fine-tuned generative image model is additionally based on a small set of representative images associated with the various categories, as well as textual tokens associated with the categories. Once trained, the fine-tuned generative image model can be used to generate realistic representative images for items in a database of the online concierge system that are lacking associated images. The fine-tuned model permits the generation of different variants of an item, such as different quantities or amounts, different packaging or packing density, and the like.

公开(公告)号：US12210591B2

公开(公告)日：2025-01-28

申请号：US17407158

申请日：2021-08-19

Applicant: Maplebear Inc.

Inventor： Shih-Ting Lin ,  Jonathan Newman ,  Min Xie ,  Haixun Wang

IPC: G06K9/62 ,  G06F18/21 ,  G06F18/214 ,  G06F18/22 ,  G06F18/23 ,  G06Q30/06 ,  G06Q30/0601

Abstract: An online concierge system receives unstructured data describing items offered for purchase by various warehouses. To generate attributes for products from the unstructured data, the online concierge system extracts candidate values for attributes from the unstructured data through natural language processing. One or more users associate a subset candidate values with corresponding attributes, and the online concierge system clusters the remaining candidate values with the candidate values of the subset associated with attributes. One or more users provide input on the accuracy of the generated clusters. The candidate values are applied as labels to items by the online concierge system, which uses the labeled items as training data for an attribute extraction model to predict values for one or more attributes from unstructured data about an item.

公开(公告)号：US20240176852A1

公开(公告)日：2024-05-30

申请号：US18436611

申请日：2024-02-08

Applicant: Maplebear Inc.

Inventor： Saurav Manchanda ,  Krishnakumar Subramanian ,  Haixun Wang ,  Min Xie

IPC: G06F18/2411 ,  G06F18/214 ,  G06F18/22 ,  G06N3/084

CPC classification number: G06F18/2411 ,  G06F18/214 ,  G06F18/22 ,  G06N3/084

Abstract: An online concierge system trains a classification model as a domain adversarial neural network from training data labeled with source classes from a source domain that do not overlap with target classes from a target domain output by the classification model. The online concierge system maps one or more source classes to a target class. The classification model extracts features from an image, classifies whether an image is from the source domain or the target domain, and predicts a target class for an image from the extracted features. The classification model includes a gradient reversal layer between feature extraction layers and the domain classifier that is used during training, so the feature extraction layers extract domain invariant features from an image.

公开(公告)号：US11947632B2

公开(公告)日：2024-04-02

申请号：US17405011

申请日：2021-08-17

Applicant: Maplebear Inc.

Inventor： Saurav Manchanda ,  Krishnakumar Subramanian ,  Haixun Wang ,  Min Xie

IPC: G06F18/2411 ,  G06F18/214 ,  G06F18/22 ,  G06N3/084

CPC classification number: G06F18/2411 ,  G06F18/214 ,  G06F18/22 ,  G06N3/084

Abstract: An online concierge system trains a classification model as a domain adversarial neural network from training data labeled with source classes from a source domain that do not overlap with target classes from a target domain output by the classification model. The online concierge system maps one or more source classes to a target class. The classification model extracts features from an image, classifies whether an image is from the source domain or the target domain, and predicts a target class for an image from the extracted features. The classification model includes a gradient reversal layer between feature extraction layers and the domain classifier that is used during training, so the feature extraction layers extract domain invariant features from an image.

公开(公告)号：US20240029132A1

公开(公告)日：2024-01-25

申请号：US17868572

申请日：2022-07-19

Applicant: Maplebear Inc. (dba Instacart)

Inventor： Shih-Ting Lin ,  Amirali Darvishzadeh ,  Min Xie ,  Haixun Wang

IPC: G06Q30/06 ,  G06F40/20

CPC classification number: G06Q30/0627 ,  G06F40/20 ,  G06N20/00

Abstract: To improve attribute prediction for items, item categories are associated with a schema that is augmented with additional attributes and/or attribute labels. Items may be organized into categories and similar categories may be related to one another, for example in a taxonomy or other organizational structure. An attribute extraction model may be trained for each category based on an initial attribute schema for the respective category and the items of that category. The extraction model trained for one category may be used to identify additional attributes and/or attribute labels for the same or another, related category.

公开(公告)号：US20230146336A1

公开(公告)日：2023-05-11

申请号：US17524491

申请日：2021-11-11

Applicant: Maplebear Inc. (dba Instacart)

Inventor： Haixun Wang ,  Taesik Na ,  Tejaswi Tenneti ,  Saurav Manchanda ,  Min Xie ,  Chuan Lei

IPC: G06Q30/06 ,  G06N20/00

CPC classification number: G06Q30/0603 ,  G06N20/00

Abstract: To simplify retrieval of items from a database that at least partially satisfy a received query, an online concierge system trains a model that outputs scores for items from the database without initially retrieving items for evaluation by the model. The online concierge system pre-trains the model using natural language inputs corresponding to items from the database, with a natural language input including masked words that the model is trained to predict. Subsequently, the model is refined using multi-task training where a task is trained to predict scores for items from the received query. The online concierge system selects items for display in response to the received query based on the predicted scores.