Household Viewership Deduplication Across Set-Top Boxes and Smart TVs

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies face challenges in accurately determining audience viewership measurements due to duplicative viewing data across multiple video devices within a household, leading to overrepresentation of viewing activity and skewing analysis results.

Innovation Solution

A system and method that analyzes viewing data from set-top boxes and smart TVs to identify and exclude duplicative portions, using machine learning models to determine viewership data based on demographic information and ensemble learning techniques, and employs automatic content recognition to enhance accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If viewing data is collected from multiple video devices (set-top boxes, smart TVs) at a household, then the quantity of viewing data increases, but the accuracy of viewership measurement deteriorates due to duplicative data

Engineering Contradiction:

Improvequantity of viewing dataVSAvoidaccuracy of viewership measurement

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The patent extracts and removes duplicative viewing data entries from the dataset. By identifying when the same viewing event is recorded by multiple devices (e.g., both set-top box and smart TV record the same program viewing) and removing these duplicates, the system maintains comprehensive data collection while ensuring measurement accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces a data processing system that acts as an intermediary between raw viewing data from multiple devices and the final viewership measurement. This intermediary layer compares and validates data from different devices, identifying and filtering duplicative entries before the data is used for analysis.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If viewing data from multiple devices is aggregated without filtering, then the completeness of viewing activity is improved, but the reliability of viewership data deteriorates due to overrepresentation

Engineering Contradiction:

Improvecompleteness of viewing activityVSAvoidreliability of viewership data

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system extracts only the necessary viewing data by removing duplicative entries. When the same viewing event is detected across multiple devices, the system retains one instance and removes the others, thereby maintaining completeness of viewing activity coverage while preventing overrepresentation that would compromise reliability.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent performs preliminary data cleaning and validation before aggregation. By pre-identifying and filtering duplicative viewing data entries before the data is aggregated into viewership measurements, the system ensures that the final data is both complete and reliable without requiring complex post-processing.

Inventive Principle:

Principle #10Preliminary action

3Device complexity

If duplicative viewing data is not excluded, then the simplicity of data processing is maintained, but the accuracy of viewership analysis deteriorates

Engineering Contradiction:

Improvesimplicity of data processingVSAvoidaccuracy of viewership analysis

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent introduces a dedicated data validation module that serves as an intermediary step between raw data collection and analysis. This module automatically identifies and removes duplicative viewing data entries using comparison logic, adding minimal complexity while significantly improving the accuracy of viewership analysis.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces manual or complex analytical methods with automated data processing algorithms. By using computational methods to automatically detect and filter duplicative viewing data based on device identifiers and viewing event characteristics, the system maintains processing simplicity while achieving high measurement precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20260082103A1Systems, methods, and devices for determining viewership data

Publication Date: 2026.03.19 COMCAST CABLE COMM LLC

AI summary

Systems, methods, and devices relating to determining viewership data are described herein. In a method, viewing data associated with a household is received. A first portion of the viewing data is indicative of video programming associated with a first video device and a second portion of the viewing data is indicative of video programming associated with a second video device. One or more characteristics associated with the first and second portions of the viewing data are determined. Based on the one or more characteristics and a comparison of the respective video programming associated with the first and second video devices, it is determined that the first portion of the viewing data is duplicative, at least in part, with the second portion of the viewing data.