Product Network for Accurate Ad Targeting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing online advertising systems lack the ability to accurately determine the interest of customers in related products, leading to inefficient ad placement and reduced revenue, as they rely on limited data such as previous searches and demographics without access to customer purchase history.

Innovation Solution

A system where a service provider maintains a product network based on customer purchase history, using a propensity model to calculate a recommended bid amount for third-party entities, allowing for more accurate ad targeting by identifying related products that customers are likely to be interested in.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If online advertising systems use limited data such as previous searches and demographics for ad targeting, then the system complexity remains low, but the accuracy of determining customer interest in related products deteriorates

Engineering Contradiction:
Improveaccuracy of determining customer interestVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by maintaining a product network based on customer purchase history before ad targeting decisions are made. The product network pre-establishes relationships between products and customers, enabling more accurate interest determination without increasing real-time processing complexity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces a product network as an intermediary structure that connects customer purchase history with ad targeting decisions. This intermediary layer processes and structures the data relationships, allowing accurate customer interest determination while managing system complexity through organized data representation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the system processes bid requests in real-time without pre-computed product networks, then the processing speed is high, but the accuracy of ad targeting deteriorates

Engineering Contradiction:
Improveaccuracy of ad targetingVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary computation by maintaining product networks based on customer purchase history in advance. This pre-computation stores structured relationships between products and customers, enabling fast and accurate ad targeting decisions when bid requests are received without requiring complex real-time analysis.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If third-party entities perform all bid request processing independently, then the system architecture remains simple, but processing congestion increases and efficiency deteriorates

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidsystem architecture complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent merges the product network maintenance function into the service provider's infrastructure, combining data processing capabilities across multiple entities. This consolidation allows third-party entities to leverage pre-computed product networks, reducing their individual processing loads and eliminating congestion while maintaining architectural simplicity through shared resources.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS11810155B1Maintaining a product graph network based on customer purchase history
Publication Date: 2023.11.07 AMAZON TECH INC
  • US11810155B1 patent drawing
  • US11810155B1 patent drawing
  • US11810155B1 patent drawing

AI summary

A system for maintaining product networks to provide recommendations for bid amounts to third party entity devices. A service provider entity device tracks product purchase history for customers and determines relationships associated with products purchased by the customers. When a webpage is loaded by a customer device, a third party entity device receives a bid request from a publisher device and transmits a bid recommendation request to the service provider entity device. The service provider entity device determines input features including a base bid, a propensity score, and a pacing score based on the relationships. The service provider entity device transmits a bid recommendation response with a recommended bid amount to the third party entity device, based on the input features.