Automated Keyword Grouping for Campaign Bid Customization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional systems face challenges in managing large numbers of keywords for content campaigns, making it difficult for sponsors to customize bids effectively due to the complexity and computational resource demands, especially when trying to optimize for reach and impressions.

Innovation Solution

An online system automatically groups keywords based on categories like popularity or relevance, using a trained computer model to predict groupings and estimate performance metrics, allowing sponsors to set override bids for these groups without individual keyword interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If sponsors manually manage and customize bids for each individual keyword in large campaigns, then bid customization precision is improved, but device complexity and ease of operation deteriorate due to the large number of keywords making management unwieldy

Engineering Contradiction:

Improvebid customization precisionVSAvoidcampaign management complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system automatically segments keywords into groups based on shared characteristics such as relevance to the sponsored content, popularity metrics, and predicted likelihood of requiring bid modifications. This segmentation allows sponsors to manage subsets of keywords rather than individual keywords, reducing complexity while maintaining customization capability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary automated grouping mechanism that sits between the sponsor and the large set of keywords. This intermediary automatically creates meaningful keyword groups and presents them to the sponsor, acting as a mediator that simplifies the interface between human decision-making and large-scale keyword management.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Manufacturing precision

If sponsors manually manage and customize bids for each individual keyword in large campaigns, then bid customization precision is improved, but ease of operation deteriorates due to the large number of keywords making management unwieldy

Engineering Contradiction:

Improvebid customization precisionVSAvoidcampaign management ease

Core Design Contradiction:

Manufacturing precisionVSEase of operation

Solution Approach 1:

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If the system provides detailed information for each individual keyword, then measurement precision is improved, but loss of time increases due to the sponsor needing to review and make decisions for hundreds or thousands of keywords

Engineering Contradiction:

Improvekeyword performance measurement precisionVSAvoidtime to review and modify bids

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by automatically analyzing keyword performance data, predicting which keywords are likely to need bid modifications, and pre-grouping them before presenting to the sponsor. This preliminary processing reduces the time the sponsor needs to spend on review and decision-making.

Inventive Principle:

Principle #10Preliminary action

4Productivity

If the system processes and optimizes for each individual keyword to achieve fine-grained bid optimization, then productivity is improved, but use of energy and computational resources worsens due to the large number of keywords requiring processing

Engineering Contradiction:

Improvebid optimization productivityVSAvoidcomputational resource consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system merges the processing of individual keywords by grouping them based on shared characteristics and predicted bid modification needs. Instead of processing each keyword independently, the system processes groups of keywords together, reducing redundant computational operations while maintaining optimization effectiveness.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system applies partial action by focusing computational resources on keyword groups that are predicted to require bid modifications, rather than uniformly processing all keywords. This selective approach reduces overall computational resource consumption while maintaining productivity for the most impactful keywords.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20240330977A1Automatic keyword grouping for campaign bid customization

Publication Date: 2024.10.03 MAPLEBEAR INC

AI summary

A keyword campaign automatically groups keywords for customized override bids for the keyword group. The keywords of a campaign may be analyzed by a computer model to predict membership in a category in addition to the likelihood that the bid of the keyword will be modified. The keyword groups may be automatically generated based on the predictions, and performance metrics are evaluated for the keyword groups at one or more modified bids. The performance metrics of the keyword groups at the modified bids may then be used to set override bids. The automatically generated keyword groups and performance metrics permit a sponsor to intelligently group and customize keyword bids with reduced interface interactions and without requiring individual keyword bid adjustments.