公开(公告)号：US20250037323A1

公开(公告)日：2025-01-30

申请号：US18785665

申请日：2024-07-26

Applicant: Maplebear Inc.

Inventor： Prithvishankar Srinivasan ,  Shih-Ting Lin ,  Yuanzheng Zhu ,  Min Xie ,  Shishir Kumar Prasad ,  Shrikar Archak ,  Karuna Ahuja

IPC: G06T11/00 ,  G06T5/70 ,  G06V10/764

Abstract: An online system performs a task in conjunction with the model serving system or the interface system. The system generates a first prompt for input to a machine-learned language model, which specifies contextual information and a first request to generate a theme. The system provides the first prompt to a model serving system for execution by the machine-learned language model, receives a first response, and generates a second prompt. The second prompt specifies the theme and a second request to generate a third prompt for input to an image generation model that includes a third request to generate one or more images of one or more items associated with the theme. The system receives the third prompt by executing the model on the second prompt, provides the third prompt to the image generation model, and receives one or more images for presentation.

公开(公告)号：US20250028768A1

公开(公告)日：2025-01-23

申请号：US18776104

申请日：2024-07-17

Applicant: Maplebear Inc.

Inventor： Riddhima Sejpal ,  Prithvishankar Srinivasan ,  Luis Manrique

IPC: G06F16/9535 ,  G06F9/451 ,  G06F16/9538 ,  G06Q30/0282 ,  G06Q30/0601

Abstract: An online system performs an inference task in conjunction with the model serving system or the interface system to generate customized recipes for users. The online system identifies a plurality of popular recipes based on historical user search data. The online system uses the collection of popular recipes to generate customized recipes for users based on user data and retailer data. The online system presents a customized recipe to the user, which may include items required to fulfill the recipe, a list of retailers at which the items are available for purchase, and instructions to combine the items. The online system collects user ratings and feedback on customized recipes to calculate a quality score. The online system may use the quality score to rank the customized recipes.

公开(公告)号：US20250086395A1

公开(公告)日：2025-03-13

申请号：US18244098

申请日：2023-09-08

Applicant: Maplebear Inc.

Inventor： Prithvishankar Srinivasan ,  Saurav Manchanda ,  Shih-Ting Lin ,  Shishir Kumar Prasad ,  Riddhima Sejpal ,  Luis Manrique ,  Min Xie

IPC: G06F40/30

Abstract: Embodiments relate to utilizing a language model to automatically generate a novel recipe with refined content, which can be offered to a user of an online system. The online system generates a first prompt for input into a large language model (LLM), the first prompt including a plurality of task requests for generating initial content of a recipe. The online system requests the LLM to generate, based on the first prompt input into the LLM, the initial content of the recipe. The online system generates a second prompt for input into the LLM, the second prompt including the initial content of the recipe and contextual information about the recipe. The online system requests the LLM to generate, based on the second prompt input into the LLM, refined content of the recipe. The online system stores the recipe with the refined content in a database of the online system.

公开(公告)号：US20250005279A1

公开(公告)日：2025-01-02

申请号：US18215505

申请日：2023-06-28

Applicant: Maplebear Inc. (dba Instacart)

Inventor： Shih-Ting Lin ,  Prithvishankar Srinivasan ,  Saurav Manchanda ,  Shishir Kumar Prasad ,  Min Xie

IPC: G06F40/247 ,  G06F16/21 ,  G06F16/215 ,  G06F16/28

Abstract: A computer system uses clustering and a large language model (LLM) to normalize attribute tuples for items stored in a database of an online system. The online system collects attribute tuples, each attribute tuple comprising an attribute type and an attribute value for an item. The online system initially clusters the attribute tuples into a first plurality of clusters. The online system generates prompts for input into the LLM, each prompt including a subset of attribute tuples grouped into a respective cluster of the first plurality. Based on the prompts, the LLM generates a second plurality of clusters, each cluster including one or more attribute tuples that have a common attribute type and a common attribute value. The online system maps each attribute tuple to a respective normalized attribute tuple associated with each cluster. The online system rewrites each attribute tuple in the database to a corresponding normalized attribute tuple.

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：US20250124498A1

公开(公告)日：2025-04-17

申请号：US18917136

申请日：2024-10-16

Applicant: Maplebear Inc.

Inventor： Prithvishankar Srinivasan ,  Shishir Kumar Prasad ,  Min Xie ,  Shrikar Archak ,  Shih-Ting Lin ,  Haixun Wang

IPC: G06Q30/08 ,  G06Q30/0601

Abstract: An online system presents a sponsored content page to a user in conjunction with a model serving system. The online system accesses a content page for a food item and identifies one or more sponsorship opportunities at the content page. The online system identifies one or more candidate sponsors for each sponsorship opportunity. The online system selects a bidding sponsor for the sponsorship opportunity from the one or more candidate sponsors and a candidate item associated with the bidding sponsor as a sponsored item. The online system provides a content page, a description of the sponsored item, and a request to generate a sponsored content page for the sponsorship opportunity to a model serving system. The online system receives a sponsored content page generated by a machine-learning language model at the model serving system and presents the sponsored content page to a user.

公开(公告)号：US20250086651A1

公开(公告)日：2025-03-13

申请号：US18827318

申请日：2024-09-06

Applicant: Maplebear Inc.

Inventor： Prithvishankar Srinivasan ,  Ayesha Saleem ,  Steven Gross ,  Ankit Joshi

IPC: G06Q30/016 ,  G06F16/31 ,  G06Q30/0601

Abstract: An online system provides a support application including a chatbot application. One or more tools may each be configured to access external data. The interface system hosts an agent powered by an underlying large language model. The online system receives a user query via the chatbot application. For at least one or more iterations, the online system performs steps to provide a prompt to the LLM that specifies at least the user query, contextual information, a list of available tools, or a request to output an action. The system parses the response from the LLM to extract a selected action and action inputs for the selected action. The system triggers execution of a respective tool that corresponds to the selected action with the action inputs. The system generates a response to the user query and transmits the response to the client device.

公开(公告)号：US20250078056A1

公开(公告)日：2025-03-06

申请号：US18240719

申请日：2023-08-31

Applicant: Maplebear Inc.

Inventor： Aoshi Li ,  Prithvishankar Srinivasan ,  Shang Li ,  Mengyu Zhang ,  Daniel Haugh ,  Cheryl D’Souza ,  Syed Wasi Hasan Rizvi ,  William Halbach ,  Ziwei Shi ,  Annie Zhang ,  Giovanny Castro ,  Sonali Parthasarathy ,  Shishir Kumar Prasad

IPC: G06Q20/14 ,  G06Q10/087 ,  G06Q30/0601

Abstract: An online concierge system compensates pickers who fulfill orders including one or more items based in part on weights of the items included in an order. Because the online concierge system does not physically possess the items that are obtained, the online concierge system cannot directly weigh the items and weights specified for items in a catalog from a retailer may be inaccurate. To more accurately determine weights of items, the online concierge system trains a weight prediction model to estimate an item's weight from attributes of the item and uses the output of the weight prediction model to determine compensation to a picker. The weight prediction model may output a predicted weight of an item or a classification of the item as heavy or light. Where discrepancies are found between a predicted weight and the catalog weight of an item, additional information about the item is obtained.