Back to results
US 2024/0403929 A1Published application
Dynamic service quality adjustments based on causal estimates of service quality sensitivity
AssigneeMaplebear, Inc.(dba Instacart)
InventorsTilman Drerup, Zhida Gui, Michael Kurish
Life of this patent
Estimating the term…
Abstract
An online system, such as a concierge service, provides services to users using a set of limited resources. To allocate the limited resources of the system among the users, the system uses a model to predict each user's sensitivity to different levels of service. An allocation module then allocates the limited resources among a set of users based in part on the estimated sensitivities and the supply of available resources.
Claims20
A method, performed at a computer system comprising a processor and a computer-readable medium, comprising:
- obtaining a machine learning model trained to map characteristics of customers to estimated sensitivities to service quality using historical data associated with an online concierge system, wherein the online concierge system receives orders from customers via a customer application, assigns the orders to available pickers to procure items from a warehouse, and facilitates deliveries of the orders to the customers;
- applying the machine learning model to estimate respective service quality sensitivities for a population of users;
- obtaining supply data indicative of a supply of service resources available to fulfill orders from the population of users;
- applying an allocation model to allocate the supply of service resources to the orders from the population of users based at least in part on the respective service quality sensitivities for the population of users;
- and
- communicating the orders from the population of users to the allocated service resources to facilitate fulfillment of the orders according to the allocation.
3 more elements
A non-transitory computer-readable storage medium storing instructions executable by one or more processors for performing steps comprising:
- obtaining a machine learning model trained to map characteristics of customers to estimated sensitivities to service quality using historical data associated with an online concierge system, wherein the online concierge system receives orders from customers via a customer application, assigns the orders to available pickers to procure items from a warehouse, and facilitates deliveries of the orders to the customers;
- applying the machine learning model to estimate respective service quality sensitivities for a population of users;
- obtaining supply data indicative of a supply of service resources available to fulfill orders from the population of users;
- applying an allocation model to allocate the supply of service resources to the orders from the population of users based at least in part on the respective service quality sensitivities for the population of users;
- and
- communicating the orders from the population of users to the allocated service resources to facilitate fulfillment of the orders according to the allocation.
3 more elements
A computer system comprising:
- one or more processors;
- and
- a non-transitory computer-readable storage medium storing instructions executable by the one or more processors for performing steps including:
- obtaining a machine learning model trained to map characteristics of customers to estimated sensitivities to service quality using historical data associated with an online concierge system, wherein the online concierge system receives orders from customers via a customer application, assigns the orders to available pickers to procure items from a warehouse, and facilitates deliveries of the orders to the customers;
- applying the machine learning model to estimate respective service quality sensitivities for a population of users;
- obtaining supply data indicative of a supply of service resources available to fulfill orders from the population of users;
- applying an allocation model to allocate the supply of service resources to the orders from the population of users based at least in part on the respective service quality sensitivities for the population of users;
- and
- communicating the orders from the population of users to the allocated service resources to facilitate fulfillment of the orders according to the allocation.
6 more elements
Dependencies are inferred from the claim text.