Structured Preference Generation from Unstructured Text

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current online concierge systems face inefficiencies in order fulfillment due to the time-consuming process of entering unstructured text instructions for item preferences, which leads to increased fulfillment time and potential discrepancies when users and shoppers have different language fluencies.

Innovation Solution

The online concierge system retrieves and analyzes previously received orders to extract specific words from user instructions, maps them to standardized terminology, and generates structured suggestions for users, allowing for quicker and clearer specification of item attributes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If users enter unstructured text instructions for item preferences, then users can specify detailed preferences for items, but the time required for users to create orders increases

Engineering Contradiction:

Improvepreference specification accuracyVSAvoidorder creation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system extracts keywords from previously received unstructured text instructions and stores them as structured suggestions in advance. When a user needs to specify preferences, they can select from pre-generated structured suggestions rather than composing new unstructured text, significantly reducing order creation time while maintaining preference specification accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system analyzes historical unstructured text instructions and creates standardized keyword templates that can be reused. Instead of requiring users to re-enter similar preferences repeatedly, the system copies and adapts proven instruction patterns from previous orders, converting them into structured selectable options.

Inventive Principle:

Principle #26Copying

2Reliability

If users enter unstructured text instructions for item preferences, then users can specify detailed preferences for items, but the time required for shoppers to interpret instructions increases

Engineering Contradiction:

Improvepreference specification accuracyVSAvoidorder fulfillment speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system transforms unstructured text parameters into structured keyword parameters through extraction and standardization. By converting free-text preferences into standardized structured formats with defined vocabularies and formats, the system enables shoppers to quickly interpret and execute instructions without needing to analyze or clarify unstructured text.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system replaces the manual interpretation process with automated keyword extraction and standardization algorithms. Instead of relying on shoppers to manually parse and understand varied unstructured text descriptions, the system automatically converts these into consistent structured instructions that are immediately actionable.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If unstructured text instructions are used for item preferences, then users can express preferences in their own words, but translation discrepancies and errors occur when users and shoppers have different language fluencies

Engineering Contradiction:

Improvelanguage flexibilityVSAvoidinstruction accuracy

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system introduces structured keywords as an intermediary layer between user input and shopper execution. Users can provide preferences in various language formats, the system extracts and standardizes them into controlled vocabulary keywords, and shoppers receive clear standardized instructions. This intermediary structured format eliminates translation ambiguity while preserving language flexibility.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system converts language-specific unstructured text parameters into language-neutral structured keywords. By transforming free-text preferences into standardized parameters with defined meanings and formats, the system eliminates translation discrepancies while maintaining the ability to accept diverse language inputs during the extraction phase.

Inventive Principle:

Principle #35Parameter changes

4Reliability

If unstructured text instructions are used for item preferences, then users can provide detailed specifications, but the complexity of the system increases

Engineering Contradiction:

Improvepreference specification capabilityVSAvoidsystem processing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system extracts only the essential keywords from unstructured text instructions rather than processing the entire text. By identifying and isolating critical preference parameters through keyword extraction, the system reduces processing complexity while retaining the detailed specification capability. Only relevant keywords are stored and transmitted, filtering out redundant information.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20230186360A1Generating structured preferences for item selection for display in an interface from unstructured text previously provided to shoppers by users

Publication Date: 2023.06.15 MAPLEBEAR INC

AI summary

An online concierge system allows users to add items to an order and provide instructions to a shopper specifying attributes for selecting an item in the order from a warehouse. To simplify entry of the instructions, the online concierge system converts previously received instructions comprising unstructured text into structured suggestions by extracting words from the previously received instructions. The suggestions are associated with items or generic item descriptions. When a user includes an item in an order, the online concierge system displays one or more suggestions associated with the item as selectable options in an interface to simplify specification of instructions for the item.