Action Indicators for Search Results Using Crowd-Sourced Badges

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current search systems face challenges in accurately predicting user actions from search results, making it difficult to determine which actions to facilitate with action indicators, and are prone to errors and resource-intensive machine learning processes.

Innovation Solution

The implementation of action indicators, or 'badges,' that provide users with information on frequently performed actions after selecting search operation output elements, using crowd-sourced user data to determine which indicators to display, based on aggregate user behavior, such as browsing, saving, or sharing, and comparing user action percentages to thresholds and standard deviations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If machine learning processes are used to predict user actions from search results, then prediction accuracy may be improved, but system complexity and resource consumption increase significantly

Engineering Contradiction:
Improveuser action prediction accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts and displays specific action indicators (such as shopping, saving, sharing) directly on search result elements without requiring complex machine learning models. This extraction approach simplifies the system by focusing on displaying pre-identified action patterns rather than predicting all possible user behaviors through complex algorithms

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent uses lightweight, simple action indicator badges that can be quickly generated and displayed without requiring heavy computational resources. These indicators are simple visual elements that convey action information without the need for continuous complex processing or retraining of machine learning models

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

2Measurement precision

If machine learning processes are used to predict user actions, then prediction capability is enhanced, but processing time and resource consumption increase

Engineering Contradiction:
Improveuser action prediction accuracyVSAvoidquery processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary analysis of user actions and prepares action indicators in advance, so that when a search query is executed, the system can quickly display pre-computed action indicators without requiring time-consuming machine learning inference during the actual query processing

Inventive Principle:
Principle #10Preliminary action

3Loss of information

If action indicators are provided for all search operation output elements, then user information completeness is improved, but information overload and user confusion may occur

Engineering Contradiction:
Improveuser information completenessVSAvoiduser interface clarity
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent applies action indicators selectively to specific search result elements based on their characteristics and the actions most relevant to each element type. Different visual indicators are used for different actions (shopping, saving, sharing), and indicators are displayed only where appropriate rather than uniformly across all elements

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent uses different visual representations (such as colored icons or badges) to indicate different user actions. This visual differentiation helps users quickly understand the available actions without text overload, maintaining interface clarity while providing comprehensive action information

Inventive Principle:
Principle #32Color changes

Data Source

PatentUS11132406B2Action indicators for search operation output elements
Publication Date: 2021.09.28 GOOGLE LLC
  • US11132406B2 patent drawing
  • US11132406B2 patent drawing
  • US11132406B2 patent drawing

AI summary

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, responsive to a search query from a user device, search operation output elements based on a search operation performed in response to the search query, wherein each search operation output element is an element that can be displayed in a search results environment in which search operation output elements responsive to the search query are displayed to a user of the user device, and are each individually selectable by the user, determining whether to provide an action indicator for each search operation output element, and providing, to the user device for display in the search results environment, the search operation output elements, and for each search operation output element for which one or more action indicators are to be provided, action indicator data for the search operation output element.