Group Order Chat Interface Using LLM Ingredient-to-Item Mapping

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing online systems lack a user interface that supports multiple users collaborating to discuss and automatically place a group order across various modalities, such as texts, images, and audio, for delivery.

Innovation Solution

A chat interface with a chatbot agent supported by language models that integrates multi-modal inputs from multiple users to generate a list of ingredients and items for a group order, facilitating automatic order placement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a traditional user interface is used for placing online orders, then the system is simple to operate for single users, but it cannot support multiple users collaborating to discuss and build a group order

Engineering Contradiction:

Improvemulti-user collaboration capabilityVSAvoiduser interface complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The chat interface is designed to serve multiple functions: it enables multi-user communication, captures diverse input modalities (text, image, audio), and automatically processes group order placement. This single interface replaces the need for separate collaboration tools and order placement systems, achieving multi-functionality that resolves the contradiction between versatility and complexity

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The chatbot agent acts as an intermediary between multiple users and the online system. It receives inputs from multiple users through the chat interface, processes their collaborative discussion, and automatically places the group order. This intermediary simplifies the interaction by managing the complexity of multi-user collaboration behind the scenes while presenting a unified interface to users

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If multiple users discuss a group order through various modalities (texts, images, audio), then the system captures comprehensive user inputs, but it becomes challenging to automatically process and convert these diverse inputs into a structured order

Engineering Contradiction:

Improvecompleteness of user inputsVSAvoidprocessing complexity of multi-modal inputs

Core Design Contradiction:

Loss of informationVSDifficulty of detecting and measuring

Solution Approach 1:

The system replaces manual processing of multi-modal inputs with automated language models. Instead of requiring manual extraction and structuring of information from text, images, and audio, the language model automatically processes these diverse inputs and converts them into structured order data, reducing processing complexity while maintaining information completeness

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms different input modalities (text, image, audio) into a unified parameter space that the language model can process. By converting diverse input types into comparable representations, the system maintains the completeness of user inputs while simplifying the processing difficulty through parameter standardization

Inventive Principle:

Principle #35Parameter changes

3Productivity

If the system automatically places group orders based on user discussions, then the productivity of order placement is improved, but the reliability of accurate order interpretation may be compromised

Engineering Contradiction:

Improveorder placement efficiencyVSAvoidorder interpretation accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system incorporates feedback mechanisms where the chatbot agent processes user discussions and presents the generated order back to users for confirmation. This feedback loop allows users to verify the automatic interpretation of their discussion and correct any misunderstandings, thereby maintaining high reliability while preserving the productivity benefits of automated order placement

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20250363545A1Chat interface with chatbot agent supported by language models for placing group orders

Publication Date: 2025.11.27 MAPLEBEAR INC

AI summary

A chat interface supported by language models is used for generating a group order at an online system based on a conversation between multiple users. Upon receiving, via the chat interface, input data with information about the conversation, the online system requests a first language model to generate, based on the input data, a list of ingredients. The online system then requests a second language model to map the list of ingredients into a list of items at a retailer associated with the online system. Upon generation of the list of items, the online system causes the chat interface to display content prompting approval by the users for conversion of the list of items. Responsive to the approval, the online system places the group order that includes the list of items for delivery to a user of the online system.