Context-Aware Input Re-Formatting via Statistical Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies fail to effectively provide context-relevant alternatives for re-formatting input, either by presenting irrelevant options or requiring separate models for each context, such as email and text messaging applications.
Innovation Solution
A statistical model is applied to score context-independent outputs based on historical user behavior, domain contexts, and general contexts, allowing for the selection of relevant alternatives to re-format input by combining knowledge sources across different contexts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If separate models are used for each context (email, text messaging, etc.), then context-specific accuracy is improved, but device complexity increases
Solution Approach 1:
The patent applies a single statistical model that can handle multiple contexts (email, text messaging, search queries, etc.) by incorporating context indicators and weights, eliminating the need for separate models for each context while maintaining context-specific accuracy
Solution Approach 2:
The patent changes parameters within a single model by adjusting context weights and indicators dynamically based on the input context, allowing the model to adapt to different contexts without requiring separate model structures
2Device complexity
If context-independent outputs are provided, then device complexity is reduced, but relevance to user context deteriorates
Solution Approach 1:
The patent introduces context indicators and weights as intermediaries between the single statistical model and the output suggestions, allowing the model to generate context-relevant suggestions without requiring multiple separate models
Solution Approach 2:
The patent makes the model dynamic by adjusting context weights and indicators based on the specific input context, allowing a single static model structure to produce dynamic, context-appropriate suggestions
3Measurement precision
If multiple context-specific models are implemented, then suggestion accuracy is improved, but data scarcity in individual contexts becomes more problematic
Solution Approach 1:
The patent merges data from multiple contexts into a single statistical model by incorporating context indicators and weights, allowing the model to learn from aggregate data across all contexts while still providing context-specific suggestions, thereby mitigating data scarcity in individual contexts
Data Source
AI summary
Various components provide options to re-format an input based on one or more contexts. The input is received that has been submitted to an application (e.g., messaging application, mobile application, word-processing application, web browser, search tool, etc.), and one or more outputs are identified that are possibilities to be provided as options for re-formatting. A respective score of each output is determined by applying a statistical model to a respective combination of the input and each output, the respective score comprising a plurality of context scores that quantify a plurality of contexts of the respective combination. Exemplary contexts include historical-user contexts, domain contexts, and general contexts. One or more suggested outputs are selected from among the one or more outputs based on the respective scores and are provided as options to re-format the input.