Item Availability Prompt Capping for Non-Deterministic Inventory

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current online concierge systems face challenges in accurately presenting item availability due to varying confidence levels, leading to user experience degradation when low availability items are displayed, which complicates the identification of obtainable items.

Innovation Solution

An online concierge system models user utility based on the number of low availability items shown, determining a cap using a user utility curve to optimize the presentation of low availability items, thereby enhancing the user experience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the system displays a comprehensive listing of all items offered by a warehouse, then the likelihood of a user identifying desired items increases, but the user experience deteriorates due to displaying low availability items that complicate identification of obtainable items

Engineering Contradiction:
Improveitem availability accuracyVSAvoiduser experience
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent segments the item listing into two distinct categories: high availability items and low availability items. This segmentation allows the system to present comprehensive item information while visually distinguishing between items with different availability probabilities, thereby maintaining user experience by making obtainable items easily identifiable.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by displaying different visual indicators or annotations for different subsets of items based on their availability characteristics. High availability items receive one type of presentation while low availability items receive another, allowing the system to maintain overall comprehensiveness while optimizing local presentation quality for each item type.

Inventive Principle:
Principle #3Local quality

2Ease of operation

If the system displays fewer low availability items to improve user experience, then the clarity of obtainable items increases, but the comprehensive listing of available items is reduced

Engineering Contradiction:
Improveuser experienceVSAvoiditem availability information
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent introduces an intermediary mechanism (visual indicators, annotations, or separate sections) that mediates between displaying low availability items and maintaining user experience. This intermediary allows the system to preserve information about low availability items while using visual cues to manage user expectations and maintain ease of operation.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of information

If the system shows non-flattering information about low availability items, then users are informed about potential unavailability, but too much such information diminishes the user experience

Engineering Contradiction:
Improveavailability transparencyVSAvoiduser experience
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent applies partial action by selectively displaying information about low availability items rather than uniformly displaying availability status for all items. The system shows non-flattering information only where necessary (for low availability items) while maintaining a positive presentation for high availability items, thus providing transparency without overwhelming the user.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12579512B2Optimization of item availability prompts in the context of non-deterministic inventory data
Publication Date: 2026.03.17 MAPLEBEAR INC
  • US12579512B2 patent drawing
  • US12579512B2 patent drawing
  • US12579512B2 patent drawing

AI summary

A system receives a request for a set of items at a warehouse from a user device, and determines a set of candidate items responsive to the request. The system applies a trained item availability model to each candidate item to determine a prediction of a likelihood that the candidate item is available for pickup at the warehouse. A subset of candidate items that have a prediction below a threshold is classified as low availability. The computer system also determines a cap of low availability items to present to a user based on a user utility curve. The user utility curve is modeled based on user utility associated with amounts of low availability items presented. The low availability items are filtered to an amount within the determined cap. The filtered low availability items are sent to the user device for presentation in a user interface.