中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.022 seconds)

    INCREMENTAL COST PREDICTION FOR USER TREATMENT SELECTION
    1.
    发明公开
    INCREMENTAL COST PREDICTION FOR USER TREATMENT SELECTION 审中-公开

    公开(公告)号：US20230325856A1

    公开(公告)日：2023-10-12

    申请号：US18186141

    申请日：2023-03-17

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Trace Levinson ,  Nicholas Sturm

    IPC: G06Q30/0202

    CPC classification number: G06Q30/0202

    Abstract: An online system computes an incremental cost prediction for each of a set of user-treatment pairs to select a set of treatments to apply to users to satisfy a predicted interaction gap. The online system generates a set of candidate user-treatment pairs that each include user data for a user of the online system and treatment data for a treatment of a set of treatments. The online system computes an incremental interaction prediction and a treatment cost prediction for each of the candidate user-treatment pairs by applying an incremental interaction model to the user data and the treatment data in each user-treatment pair. The online system computes incremental cost predictions for each of the user-treatment pairs based on the computed incremental interaction predictions and treatment cost predictions and selects which users to apply treatments to and which treatments to apply to those users based on the incremental cost predictions.

    SELECTING METHODS TO ALLOCATE SHOPPERS FOR ORDER FULFILLMENT IN GEOGRAPHIC REGIONS BY AN ONLINE CONCIERGE SYSTEM BASED ON MACHINE-LEARNED EFFICIENCIES FOR DIFFERENT ALLOCATION METHODS
    2.
    发明公开
    SELECTING METHODS TO ALLOCATE SHOPPERS FOR ORDER FULFILLMENT IN GEOGRAPHIC REGIONS BY AN ONLINE CONCIERGE SYSTEM BASED ON MACHINE-LEARNED EFFICIENCIES FOR DIFFERENT ALLOCATION METHODS 审中-公开

    公开(公告)号：US20230196442A1

    公开(公告)日：2023-06-22

    申请号：US17556936

    申请日：2021-12-20

    Applicant: Maplebear Inc. (dba Instacart)

    Inventor： Trace Levinson ,  Aman Jain ,  Ji Chen ,  Andrew Kephart

    IPC: G06Q30/06

    CPC classification number: G06Q30/0635

    Abstract: An online concierge system allocates shoppers to different geographic regions at different times to fulfill orders received from users. The online concierge system uses different methods for adjusting allocation of shoppers to geographic regions, such as obtaining new shoppers or providing incentives to additional shoppers, based on estimated numbers of orders identifying different geographic regions. To account for costs to the online concierge system for allocating shoppers to geographic regions, the online concierge system trains multiple machine learned models to predict different efficiency metrics for methods for adjusting shopper allocation. Discrete samples are obtained from each efficiency metric, and samples that do not satisfy one or more constraints removed. From the remaining samples, a combination of samples for different methods for adjusting shopper allocation is selected to optimize a value to the online concierge system based on one or more criteria.

    Conditional Loss Function for Training a Multitask Machine Learning Model
    3.
    发明申请
    Conditional Loss Function for Training a Multitask Machine Learning Model 有权

    公开(公告)号：US20250045619A1

    公开(公告)日：2025-02-06

    申请号：US18228569

    申请日：2023-07-31

    Applicant: Maplebear Inc.

    Inventor： Jin Zhang ,  Trace Levinson

    IPC: G06N20/00

    Abstract: A computing system uses a conditional loss function to train a multitask model. A conditional loss function is a loss function whose output is conditional on which branch's output the conditional loss function is scoring. Specifically, when the conditional loss function is applied to an output score generated by a branch whose corresponding task is not relevant to the training example for the output score, the conditional loss function generates a loss score that, when used in backpropagation, does not significantly change the parameters of the multitask model. The computing system uses conditional loss functions to generate a loss score for each output score generated by applying a multitask model to features of a set of training examples. If the task indicators indicate that the branch task is not relevant to the training example, the conditional loss function outputs a loss score of zero.

    Automation engine using a hyperparameter learning model to optimize sub-systems of an online system
    4.
    发明授权
    Automation engine using a hyperparameter learning model to optimize sub-systems of an online system 有权

    公开(公告)号：US12271939B2

    公开(公告)日：2025-04-08

    申请号：US17855788

    申请日：2022-06-30

    Applicant: Maplebear Inc.

    Inventor： Sonali Deepak Chhabria ,  Xiangyu Wang ,  Aman Jain ,  Ganesh Krishnan ,  Trace Levinson ,  Jian Wang

    IPC: G06Q30/0601 ,  G01C21/34 ,  G06Q10/0631 ,  G06Q10/0637 ,  G06Q10/087

    Abstract: An online concierge system includes a marketplace automation engine for setting various control parameters affecting marketplace operation. The marketplace automation engine applies a hyperparameter learning model to the marketplace state data to predict a set of hyperparameters affecting a set of respective parameterized control decision models. The hyperparameter learning model is trained on historical marketplace state data and a configured outcome objective for the online concierge system. The marketplace automation engine independently applies the set of parameterized control decision models to the marketplace state data using the hyperparameters to generate a respective set of control parameters affecting marketplace operation of the online concierge system. The marketplace automation engine applies the respective set of control parameters to operation of the online concierge system.

Patent Agency Ranking