Information Processing Device for Adaptive Feature Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The inefficiency in collecting and processing patient information for personalized medicine and related applications, such as treatment method selection, training, exercise, and dieting, due to the time and cost involved in gathering bio-information features.
Innovation Solution
An information processing device configured with an acquisition unit to generate models for each elapsed period, a collection unit to gather and compare first and second outputs from feature value inputs, and a setting unit to associate types with the model based on these outputs, enhancing the efficiency of information collection for measure proposals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If comprehensive bio-information is collected for personalized medicine, then measurement precision is improved, but loss of time and cost increase
Solution Approach 1:
The patent segments the information collection process by dividing feature values into different types (first type and second type). The system collects first type feature values immediately and second type feature values later, allowing treatment method selection to proceed without waiting for complete information gathering. This segmentation resolves the contradiction by enabling timely decisions with available data while preserving the option to refine assessments later.
Solution Approach 2:
The system performs preliminary action by pre-collecting first type feature values that can be obtained quickly and using them to generate initial treatment method selections. This preliminary assessment allows prompt treatment decisions to be made without delaying for comprehensive data collection, while the system retains the capability to incorporate second type feature values later for refined assessments.
2Measurement precision
If comprehensive bio-information is collected for personalized medicine, then measurement precision is improved, but cost increases
Solution Approach 1:
The patent segments the information collection process by dividing feature values into different types (first type and second type). The system collects first type feature values immediately and second type feature values later, allowing treatment method selection to proceed without waiting for complete information gathering. This segmentation resolves the contradiction by enabling timely decisions with available data while preserving the option to refine assessments later.
Solution Approach 2:
The system applies partial action by collecting only the necessary first type feature values required for initial treatment method selection, rather than collecting all possible feature values upfront. This partial collection approach reduces immediate costs and time investment while maintaining sufficient precision for making treatment decisions, with the option to collect additional second type feature values if needed for refined assessments.
3Reliability
If all types of feature values are input to the model, then reliability of treatment selection is improved, but device complexity increases
Solution Approach 1:
The patent implements dynamics by making the feature value collection process adaptive and flexible. The system dynamically determines which types of feature values to collect based on the specific treatment selection context and available data. This dynamic approach allows the system to maintain reliability by collecting necessary feature values while avoiding the complexity of a rigid, comprehensive collection framework, as the system adapts its data gathering to actual needs.
Solution Approach 2:
The system applies local quality by differentiating between first type and second type feature values with distinct collection characteristics. First type feature values have specific properties (quickly obtainable, essential for initial assessment) while second type feature values have different properties (taken later, supplementary). This local differentiation allows the system to optimize the collection process for each type, maintaining reliability through appropriate data quality while reducing overall complexity by treating different feature value types differently rather than applying a uniform complex collection mechanism.
Data Source
AI summary
An information processing device 100 of the present disclosure includes: an acquisition unit 121 that acquires a model that is generated for each elapsed period, and has learned by machine learning to output a measure for a human by receiving input of a plurality of types of feature value representing a condition of the human; a collection unit 122 that collects first output that is obtained when a predetermined number of types of feature value are input to the model of each elapsed period, and second output that is obtained when some types of feature value in the predetermined number of types of feature value are input to the model of each elapsed period; and a setting unit 123 that sets, on the basis of the first output and the second output, types to be associated with the model of each elapsed period. Thereby, the information processing device 100 can be used for assistance of decision-making by a user, or the like.