Adaptive Search Results Layouts for Broad-Intent Queries

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional grid-based display of search results in online systems can be overwhelming for broad-intent search queries, making it difficult for users to efficiently locate relevant content.

Innovation Solution

An online system uses a model to select a layout template for a search results user interface based on a search query and user data, applying a search query model to identify matching results and a layout selection model to organize them in an explainable manner.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If traditional grid-based display is used to show search results, then the system can display a large number of results, but the user interface becomes overwhelming and difficult to navigate

Engineering Contradiction:
Improvenumber of search resultsVSAvoiduser interface usability
Core Design Contradiction:
Quantity of substanceVSEase of operation

Solution Approach 1:

The patent segments search results into multiple categories (e.g., products, services, information) and displays each category in a dedicated carousel section. This segmentation organizes the large quantity of results into manageable groups with clear visual separation, making the interface less overwhelming while preserving comprehensive result display.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a traditional two-dimensional grid layout to a multi-dimensional carousel-based interface with horizontal scrolling sections. Each carousel represents a dimensional layer for different result types, allowing users to navigate through results in a more structured spatial arrangement that reduces cognitive load.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If ranking algorithms sort results by relevance, then the most relevant content is shown first, but the display structure becomes rigid and less adaptable to different query types

Engineering Contradiction:
Improverelevance ranking accuracyVSAvoiddisplay layout flexibility
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic display system where the carousel configuration, section ordering, and result categorization automatically adjust based on the search query type, user preferences, and result characteristics. The system can switch between different carousel layouts (e.g., product carousels, service carousels, information carousels) to adapt to various search intents while maintaining relevance-based ranking.

Inventive Principle:
Principle #15Dynamics

3Ease of operation

If search results are grouped into carousels to organize content, then the interface becomes more manageable, but the system complexity increases

Engineering Contradiction:
Improvecontent organizationVSAvoidsystem architecture complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent employs a universal carousel component that serves multiple functions: displaying results, organizing categories, providing navigation, and presenting contextual information. This single reusable component handles diverse result types (products, services, info) without requiring separate display mechanisms, which simplifies the overall system architecture despite the sophisticated organization capabilities.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250328594A1Using a model of an online system to select layout template for search results user interface
Publication Date: 2025.10.23 MAPLEBEAR INC
  • US20250328594A1 patent drawing
  • US20250328594A1 patent drawing
  • US20250328594A1 patent drawing

AI summary

A trained model is used to select a layout template for a search results user interface displayed at a device associated with a user of the online system. Upon receiving a search query via a user interface of the device, the online system applies a search query model trained to identify, based on the search query and user data, a set of search results. Upon identifying the set of search results, the online system applies a layout selection model trained to identify, based at least in part on the set of search results, a layout for the search results user interface. The online system causes the device associated with the user to display the set of search results at the search results user interface using the identified layout for the search results user interface.