Digital Component Selection Using Non-Observable Parameter Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing content distribution systems struggle with latency and inefficiency in selecting digital components for electronic documents due to reliance on observable parameters, neglecting non-observable parameters like vertical display position, which impact display effectiveness.

Innovation Solution

A content distribution system uses a parameter prediction model to predict non-observable parameters, such as vertical display position, by processing observable parameters, and integrates this prediction into a metric prediction model to enhance selection efficiency and relevance of digital components.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the content distribution system waits to obtain actual non-observable parameters (such as vertical display position) before selecting digital components, then the selection accuracy and display effectiveness improve, but the system latency and response time increase

Engineering Contradiction:

Improveselection accuracyVSAvoidsystem latency

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary prediction of non-observable parameters (such as vertical display position) using observable parameters available at request time. This preliminary action enables the content distribution system to make selection decisions without waiting for actual non-observable parameters to be determined, thereby reducing latency while maintaining reasonable selection accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system introduces a parameter prediction model as an intermediary between observable parameters and selection decisions. This intermediary component estimates non-observable parameters based on available data, allowing the system to bridge the gap between incomplete information and accurate selection requirements

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If the content distribution system includes all observable parameters in the request to improve selection accuracy, then the prediction precision improves, but the request size and network bandwidth usage increase

Engineering Contradiction:

Improveprediction precisionVSAvoidrequest size

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The system extracts and transmits only the most critical observable parameters (such as electronic document identifier, user agent information, and basic context data) in the request, rather than including all possible parameters. This selective extraction reduces request size and network bandwidth usage while maintaining sufficient prediction precision for effective content selection

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20250245284A1Predicting non-observable parameters for digital components

Publication Date: 2025.07.31 GOOGLE LLC

AI summary

Systems, methods, devices, and techniques for improving the efficiency of selecting digital components to present in electronic documents and reducing latency in rendering digital components in electronic documents. In some implementations, a content distribution system uses predicted metrics for a set of candidate components to determine items to present in an electronic document responsive to a request. A metric prediction model can generate predicted metrics with the aid of a parameter prediction sub-model that predicts a value of a non-observable parameter associated with a request for a digital component.