LLM-Powered Campaign Modification Interface for Sponsored Content

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing online systems face challenges in efficiently evaluating and modifying sponsored content items due to the time-intensive and resource-consuming process of analyzing large amounts of data, which hinders timely adjustments to improve performance.

Innovation Solution

An online system utilizes a trained large language model (LLM) to generate suggestions for modifying sponsored content campaigns based on stored data, including performance metrics and contextual information, reducing the need for manual review by generating interface elements for direct implementation of suggested actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If online systems capture and store large amounts of data describing presentation of sponsored content items, then performance evaluation accuracy is improved, but time required for reviewing and analyzing this data increases

Engineering Contradiction:

Improveperformance evaluation accuracyVSAvoidtime required for reviewing data

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an intermediary system that includes a processor and interface elements. This intermediary automatically processes the large amounts of captured data about sponsored content presentation and generates actionable suggestions for modification, eliminating the need for manual review of raw data while maintaining evaluation accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical process of reviewing and analyzing large datasets with an automated electronic system. The processor automatically analyzes performance metrics and contextual information to generate modification suggestions, substituting human manual analysis with computational processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If publishing users manually review stored information describing display of sponsored content items, then evaluation thoroughness is improved, but productivity decreases

Engineering Contradiction:

Improveevaluation thoroughnessVSAvoidspeed of campaign modification

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system enables self-service by automatically generating evaluation insights and modification suggestions without requiring publishing users to manually review raw data. The processor autonomously analyzes performance metrics and produces actionable recommendations that users can directly implement through interface elements.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary analysis of performance data and generates modification suggestions in advance, before users need to make decisions. This preliminary action includes automatically processing stored information, identifying performance issues, and formulating actionable recommendations.

Inventive Principle:

Principle #10Preliminary action

3Loss of information

If the system provides detailed performance metrics and contextual information, then decision-making quality is improved, but complexity of the system increases

Engineering Contradiction:

Improvedecision-making qualityVSAvoidsystem complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent extracts only the essential information needed for decision-making from the complex dataset. The processor filters and extracts key performance metrics and contextual factors, presenting them through simplified interface elements that convey critical insights without overwhelming users with raw data complexity.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies local quality by tailoring the presentation of performance information to specific decision contexts. Different interface elements provide customized views of performance metrics relevant to particular campaign modification scenarios, making the system adaptable to various decision-making needs without increasing overall complexity.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20250245693A1User Interface for Implementing Modifications to a Content Campaign Suggested by a Large Language Model

Publication Date: 2025.07.31 MAPLEBEAR INC

AI summary

An online system publishes sponsored content items to users. To enable a publishing user to evaluate performance of a campaign including sponsored content items and identify modifications to improve the campaign, the online system trains a large language model (LLM). Information about previous campaigns and their performance, previously asked questions about the campaigns, and actions for modifying the campaigns are used to train the LLM. For a particular ad campaign, the online system generates a prompt for the LLM to generate a list of suggestions and corresponding actions. The online system generates an interface including the suggestions in conjunction with interface elements causing performance of one or more of the actions when selected by the publishing user.