Generic Item Generation for Out-of-Stock Inventory in Online Concierge Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current online systems and mobile applications often fail to provide customers with options for out-of-stock items, as they do not allow customers to indicate a desire to include items like toilet paper in their orders if all types, brands, and sizes are unavailable.

Innovation Solution

An online concierge system uses a prediction model to determine item availability and generates a generic item for low-availability product categories, allowing customers to select a generic item as an option in their order, with a presented maximum price based on a selected price range.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the online system presents only specific items from the catalog, then the system maintains inventory accuracy and stock control, but customers cannot order out-of-stock items and lose shopping flexibility

Engineering Contradiction:
Improvecustomer ordering flexibilityVSAvoidinventory accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent introduces a generic item as an intermediary representation that mediates between the customer's desire to order specific out-of-stock items and the system's need to maintain inventory accuracy. The generic item serves as a placeholder that allows customers to express their intent without committing to a specific unavailable product, thus resolving the contradiction between ordering flexibility and inventory reliability

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates a copy or representation of the out-of-stock item in the form of a generic item. This generic item replicates the essential characteristics and category information of the unavailable specific items, allowing customers to interact with a virtual representation rather than the actual physical inventory, thereby maintaining inventory accuracy while enabling flexible ordering

Inventive Principle:
Principle #26Copying

2Ease of operation

If the online system allows customers to order any item regardless of availability, then customer satisfaction improves, but the system cannot fulfill orders and loses reliability

Engineering Contradiction:
Improvecustomer convenienceVSAvoidorder fulfillment reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary actions by generating generic items in advance for categories where specific items may be out of stock. This preliminary preparation allows the system to offer ordering options before the customer actually places their order, ensuring that customers can express their intent without compromising future order fulfillment reliability

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The generic item system enables a form of self-service where the system automatically manages inventory availability by presenting generic alternatives when specific items are unavailable. This automated mechanism allows customers to conveniently order without manual intervention while the system independently ensures fulfillment reliability through its inventory management logic

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20230394551A1Determining generic items for orders on an online concierge system
Publication Date: 2023.12.07 MAPLEBEAR INC
  • US20230394551A1 patent drawing
  • US20230394551A1 patent drawing
  • US20230394551A1 patent drawing

AI summary

An online system provides options for selection by a user. The online system receives a query entered on a client device. The online system queries an item database to retrieve a set of items related to the query and assigns each item to a product category in a predefined taxonomy that maps items to product categories. The online system inputs each item into a prediction model trained to predict a probability that an item is available at a warehouse location. The online system determines that a first product category has low availability based on predicted probabilities for items in the first product category. Responsive to determining that a first product category has low availability, the online system generates a generic item for the first product category and sends a list of items including the generic item to the client device for display responsive to the query.