Context Signal Accuracy via Blended Data Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems face challenges in canonicalizing contextual signals, such as IP addresses and Wi-Fi signals, due to inconsistencies across data sources, leading to inaccurate location-based information, which complicates application logic and requires large, impractical mapping tables to ensure accuracy.

Innovation Solution

A method that processes user feedback to determine the accuracy of data sources, segmenting them based on user satisfaction, and creating a 'blended' data source for improved accuracy, using user interaction data to log and analyze correctness measures and adjust scores for each data source segment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If large mapping tables are used to ensure accurate canonicalization of contextual signals, then mapping accuracy is improved, but device complexity and storage requirements increase significantly

Engineering Contradiction:
Improvemapping accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the monolithic mapping table into multiple smaller, specialized data sources or lookup tables. Each segment handles a specific type of contextual signal (e.g., IP addresses, Wi-Fi MAC addresses, cell tower IDs) or a specific geographic region. This segmentation reduces the complexity of individual tables while maintaining comprehensive coverage through coordinated use of multiple segments.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary canonicalization service that sits between the application layer and the mapping data sources. This service handles the complexity of coordinating multiple data sources, managing updates, and resolving conflicts, thereby shielding applications from the underlying system complexity while maintaining high mapping accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If multiple data sources are used to provide contextual information, then information completeness is improved, but data consistency and accuracy deteriorate due to conflicting mappings

Engineering Contradiction:
Improveinformation completenessVSAvoiddata consistency
Core Design Contradiction:
Loss of informationVSReliability

Solution Approach 1:

The patent implements feedback mechanisms where the system monitors the performance and accuracy of each data source. Usage patterns, success rates, and conflict frequencies are tracked and fed back into the system to dynamically adjust data source weighting, prioritize more reliable sources, and identify sources that need updating or removal. This feedback loop maintains data consistency while utilizing multiple sources for completeness.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent changes the parameters of data source utilization by introducing confidence scores, freshness metrics, and source-specific weighting factors. Instead of treating all data sources equally, the system dynamically adjusts parameters based on source reliability, data recency, and contextual relevance, thereby resolving conflicts while maintaining information completeness from multiple sources.

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If comprehensive mapping tables are maintained to cover all possible contextual signals, then coverage is improved, but difficulty in evaluating and maintaining accuracy increases

Engineering Contradiction:
Improvesignal coverageVSAvoidaccuracy evaluation difficulty
Core Design Contradiction:
Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent performs preliminary actions by establishing data quality metrics, validation rules, and accuracy benchmarks before deploying mapping tables. Confidence scores and reliability indicators are pre-calculated and embedded in the data structures, enabling automated quality assessment without requiring manual evaluation of each mapping entry. This preliminary preparation simplifies ongoing maintenance while maintaining comprehensive coverage.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2791823B1Increasing the accuracy of information returned for context signals
Publication Date: 2019.07.31 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP2791823B1 patent drawingFigure 1
  • EP2791823B1 patent drawingFigure 2
  • EP2791823B1 patent drawingFigure 3

AI summary

The subject disclosure is directed towards a technology by which the accuracy of context-based information provided by at least one data source for received context data is increased. Correctness information received in association with usage of looked up context-based information is logged. The correctness information may be processed to increase the overall accuracy by correcting a data source, and/or by creating a blended data source that includes the most likely accurate portions (segments) from among multiple data sources as determined via the correctness information.