公开(公告)号：US20250005629A1

公开(公告)日：2025-01-02

申请号：US18498967

申请日：2023-10-31

Applicant: Maplebear Inc.

Inventor： Li Tan ,  Haixun Wang ,  Jian Li

IPC: G06Q30/0251 ,  G06N20/00 ,  G06Q50/12

Abstract: A computer system finetunes a machine-learned language model to generate a personalized response to a user request. The system may generate a user representation for each of a plurality of users by applying a transformer model to a sequence of tokens representing a sequence of activities of the user. The system may train an evaluation model coupled to receive a user representation and a response to a user request and generate an estimated evaluation score indicating a level of personalization of the response to the user. The system may finetune a first machine-learned language model to generate a second machine-learned language model. The finetuned machine-learned language model is configured to provide personalized responses for customer services at an online concierge system.

公开(公告)号：US20240289632A1

公开(公告)日：2024-08-29

申请号：US18588622

申请日：2024-02-27

Applicant: Maplebear Inc.

Inventor： Li Tan ,  Haixun Wang ,  Jian Li

IPC: G06N3/092 ,  H04L51/02

CPC classification number: G06N3/092 ,  H04L51/02

Abstract: An online system trains a specific-purpose LLM. The online system obtains training examples and divides training examples across batches. The online system generates a specific response by applying parameters of the specific-purpose LLM to a batch of training examples. The online system generates a general response by applying parameters of a general-purpose LLM to the batch of training examples. The online system computes a human readability score representing the difference between the specific response and the general response. The online system computes an objective compliance score by applying an evaluation model to the specific response, the evaluation model trained to score the first response based on a specific objective. The online system updates the parameters of the specific-purpose LLM based on the human readability score and the objective compliance score.

公开(公告)号：US20240241897A1

公开(公告)日：2024-07-18

申请号：US18415551

申请日：2024-01-17

Applicant: Maplebear Inc.

Inventor： Haixun Wang ,  Taesik Na ,  Li Tan ,  Jian Li ,  Xiao Xiao

IPC: G06F16/33 ,  G06F16/338 ,  G06N20/00

CPC classification number: G06F16/3344 ,  G06F16/338 ,  G06N20/00

Abstract: A system may generate a prompt based in part on a search query from a customer client device. The prompt instructs a machine learned model to provide item predictions. And the model was trained by: converting structured data describing items of an online catalog to annotated text data (unstructured data), generating training examples based in part on the annotated text data, and training the model using the training examples. The system may receive item predictions generated by the prompt being applied to the machine learned model, the item predictions may have corresponding item identifiers. The item predictions are processed to identify a recommended item from the item predictions. The processing includes determining item information for the recommended item using an item identifier associated with the recommended item. The item information is provided to the customer client device.

公开(公告)号：US12287819B2

公开(公告)日：2025-04-29

申请号：US18415551

申请日：2024-01-17

Applicant: Maplebear Inc.

Inventor： Haixun Wang ,  Taesik Na ,  Li Tan ,  Jian Li ,  Xiao Xiao

IPC: G06F16/33 ,  G06F16/334 ,  G06F16/338 ,  G06N20/00

Abstract: A system may generate a prompt based in part on a search query from a customer client device. The prompt instructs a machine learned model to provide item predictions. And the model was trained by: converting structured data describing items of an online catalog to annotated text data (unstructured data), generating training examples based in part on the annotated text data, and training the model using the training examples. The system may receive item predictions generated by the prompt being applied to the machine learned model, the item predictions may have corresponding item identifiers. The item predictions are processed to identify a recommended item from the item predictions. The processing includes determining item information for the recommended item using an item identifier associated with the recommended item. The item information is provided to the customer client device.