Multi-Block Model Input Data Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing model generation techniques are limited in flexibility, particularly for models with multiple blocks, as they primarily involve serial connections and lack the ability to efficiently utilize input data features.
Innovation Solution
An information processing method that selects and combines different types of input data for each block in a model using a genetic algorithm to optimize the generation of models, allowing for flexible input data usage and improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a model with multiple blocks is generated using only serial connections, then the model structure is simple, but the flexibility in using input data is limited
Solution Approach 1:
The model is divided into multiple independent blocks, each capable of receiving different types of input data. This segmentation allows each block to be optimized for specific data types while maintaining overall model flexibility.
Solution Approach 2:
The patent introduces a new dimension of parallel connections between blocks, moving beyond the traditional single serial path. This allows multiple data types to flow through different block combinations simultaneously, enhancing flexibility without proportionally increasing complexity.
2Measurement precision
If different types of input data are used for each block, then the model accuracy is improved, but the complexity of data management increases
Solution Approach 1:
The model architecture is designed with universal block structures that can handle multiple data types through parallel connections. Each block type is designed to be multi-functional, capable of processing different input types without requiring entirely separate processing paths.
Solution Approach 2:
The patent dynamically adjusts which blocks receive which data types based on the input characteristics. This parameter-based routing allows the model to optimize accuracy for different data combinations without hardcoding complex management rules.
Data Source
AI summary
An information processing method including: acquiring learning data used for learning of a model having a plurality of blocks including a first block to which an output from a first input layer is input and a second block to which an output from a second input layer different from the first input layer is input, the learning data including a plurality of types of information; and selecting a type included in data input to each of the plurality of blocks in learning using the learning data, and generating the model by using first data in which a combination of types selected among the plurality of types is a first combination as an input from the first input layer to the first block and second data in which a combination of types selected is a second combination as an input from the second input layer to the second block.