TV Sports Recommendations Using Cross-Provider Score Normalization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle to effectively compare and rank user affinity for sports-related media content across different media content providers using diverse scoring models, and to integrate sports-related content with non-sports-related content for personalized recommendations on television platforms.

Innovation Solution

Implementing an inter-ranking algorithm to normalize scores from different providers and a co-ranking algorithm to merge user affinities for sports and non-sports content, using machine learning models trained on user activities to generate personalized recommendations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple diverse scoring models from different media content providers are used to evaluate user affinity, then the coverage and variety of sports content recommendations are improved, but the complexity of comparing and ranking scores across different providers increases

Engineering Contradiction:

Improvecoverage of sports content recommendationsVSAvoidcomplexity of score comparison and ranking

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent transforms diverse scoring models from different media content providers into a unified ranking system by normalizing scores to a common scale (0-100) and applying weighted combinations based on user preferences. This parameter transformation allows comparison across providers while maintaining the benefits of diverse scoring approaches.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediary processing layer that receives scores from multiple providers, normalizes them, and generates a unified ranking. This intermediary system handles the complexity of cross-provider comparison while presenting a simplified interface to users, effectively mediating between diverse scoring models and the recommendation output.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If machine learning models are trained on extensive user activity data from multiple sources, then the precision of personalized recommendations is improved, but the time and computational resources required for model training and processing increase

Engineering Contradiction:

Improveprecision of user affinity measurementVSAvoidtime for model training and data processing

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-training machine learning models on historical user activity data from multiple sources before actual recommendation generation. This pre-processing creates ready-to-use models that can quickly generate recommendations without requiring extensive real-time computation, thus reducing processing time while maintaining high precision.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses partial action by selectively processing only the most relevant user activity data and features for model training, rather than processing all available data. This approach achieves sufficient precision for personalized recommendations while significantly reducing the time and computational resources required compared to exhaustive data processing.

Inventive Principle:

Principle #16Partial or excessive action

3Adaptability or versatility

If sports-related content and non-sports-related content are integrated into a unified recommendation system, then the versatility of content recommendations is improved, but the difficulty of merging different user affinity models increases

Engineering Contradiction:

Improveversatility of content recommendationsVSAvoidcomplexity of merging affinity models

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal recommendation framework that handles both sports and non-sports content through a single unified model. This multi-functional system uses common data structures and processing logic for different content types, reducing the complexity that would otherwise arise from maintaining separate affinity models for sports and non-sports content.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent applies segmentation by separating the recommendation process into distinct modules: one for processing sports content affinity and another for non-sports content affinity, which are then combined in a unified ranking system. This modular approach reduces the complexity of merging different affinity models while maintaining versatility across content types.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12542950B2Personalized recommendations for television sports content

Publication Date: 2026.02.03 GOOGLE LLC

AI summary

According to an aspect, a method may generate an activity timeline of a user based on data indicative of a search history, a watch history, and activity of the user with a television application. The method may generate a sports score using a sports model based on the activity timeline of the user, may generate a ranked list of sports related media content items for recommending to the user based on the sports score, and may associate a respective selectable information item with each of the sports related media content items included in the ranked list. The method may send, to a network-connected display device, the ranked list of sports related media content items that includes each respective selectable information item for displaying each respective selectable information item in a user interface of the television application executing on the network-connected display device.