Context Engine Matching Inferred Contexts to Calendar Labels

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The challenge in accurately and reliably determining the context of electronic devices due to the large number of potential contexts, which hinders effective implementation of context-aware functionalities in communication devices.

Innovation Solution

A method involving accessing context information associated with a mobile device, identifying an inferred context, matching it with raw calendar data labels, and updating the device based on the association to improve context awareness, using a combination of sensor and application data analyzed by a context engine.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If context information is collected from multiple sensors and applications, then the quantity and variety of context data increases, but the accuracy and reliability of context estimation decreases due to the large number of potential contexts

Engineering Contradiction:
Improvequantity of context dataVSAvoidaccuracy of context estimation
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent segments the large set of potential contexts into smaller, more manageable context categories. By dividing the context space into distinct segments, the system can more effectively process and analyze context information from multiple sensors without being overwhelmed by the sheer number of potential contexts, thereby improving both the quantity of data processed and the accuracy of estimation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-defining context categories and criteria for classification before actual context estimation occurs. This preliminary structuring of context information allows the system to efficiently organize sensor data into predefined categories, improving the reliability of context estimation by reducing the complexity of real-time analysis.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If manual labeling of calendar events is required, then the precision of context information improves, but the time and effort required for data processing increases

Engineering Contradiction:
Improveprecision of context informationVSAvoidtime for data processing
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system implements self-service by automatically inferring context labels for calendar events using sensor data and classification algorithms, eliminating the need for manual user input. The device serves itself by autonomously processing context information, matching sensor-derived contexts with calendar events, and maintaining updated context data without requiring user time or effort, while still achieving high precision through multiple classification criteria.

Inventive Principle:
Principle #25Self-service

3Productivity

If inferred contexts are matched with calendar data without validation, then the speed of context determination increases, but the accuracy of context labeling decreases

Engineering Contradiction:
Improvespeed of context determinationVSAvoidaccuracy of context labeling
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system incorporates feedback mechanisms by validating inferred contexts against multiple criteria including sensor data consistency, calendar event characteristics, and temporal relationships. This feedback loop allows the system to verify the accuracy of context labels after rapid determination, ensuring that speed does not compromise precision. The validation process provides corrective feedback when mismatches are detected, improving overall labeling accuracy.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP2847978B1Calendar matching of inferred contexts and label propagation
Publication Date: 2019.10.16 QUALCOMM INC
  • EP2847978B1 patent drawingFigure 1A
  • EP2847978B1 patent drawingFigure 1B
  • EP2847978B1 patent drawingFigure 2

AI summary

Methods, systems, computer-readable media, and apparatuses for calendar matching of inferred contexts are described. In one potential embodiment, a mobile device may use context information to generate a calendar of inferred contexts. Label information from raw calendar data may be used to update an inferred context within a calendar of inferred contexts. Additionally, the label may be propagated to future contexts and entries in an inferred context calendar.