Dynamic Multi-Class Selection for Series Data Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing information processing techniques for classifying series data often fail to accurately determine the likelihood of data belonging to multiple classes, leading to inflexible classification outcomes.

Innovation Solution

An information processing apparatus and method that calculates a classification index based on multiple elements of series data, selecting and outputting K classes from N classification candidates, where K is determined by the index, allowing for flexible classification based on the likelihood of class membership.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a single class is selected from multiple classification candidates, then the classification outcome is simple and clear, but the flexibility and accuracy in determining class membership is reduced

Engineering Contradiction:

Improvesimplicity of classification outcomeVSAvoidflexibility in determining class membership

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent applies dynamics by allowing the number of selected classes (K) to be variable rather than fixed. The selection unit can dynamically determine K based on the classification index calculated from series data elements, enabling the system to adapt between single-class and multi-class selection scenarios depending on the data characteristics and application requirements.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes the parameter of classification output from a fixed single class to a variable number of classes (K). By calculating a classification index based on multiple elements and using this index to determine K, the system can adjust the number of selected classes based on data quality and complexity, resolving the contradiction between simplicity and flexibility.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If multiple classes are selected based on classification likelihood, then the accuracy and flexibility of class membership determination is improved, but the complexity of the classification process increases

Engineering Contradiction:

Improveaccuracy of class membership determinationVSAvoidcomplexity of classification process

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the classification process into distinct functional components: an acquisition unit that obtains series data elements, a calculation unit that computes the classification index based on at least two elements, and a selection unit that selects K classes based on the index. This segmentation reduces overall process complexity by making each component's function clear and independent.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The classification index serves as an intermediary that bridges the raw series data elements and the final class selection. By calculating this intermediate index from multiple elements, the system simplifies the relationship between complex data patterns and class membership determination, making the overall process more manageable while maintaining accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If classification is based on multiple elements and their likelihoods, then the reliability of classification results is improved, but the computational requirements and processing time increase

Engineering Contradiction:

Improvereliability of classification resultsVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent applies partial action by requiring only at least two elements from the series data to calculate the classification index, rather than processing all elements. This partial approach maintains sufficient reliability for accurate classification while significantly reducing computational time and processing requirements compared to using all available elements.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20240020574A1Information processing apparatus, information processing method, and computer program

Publication Date: 2024.01.18 NEC CORP

AI summary

An information processing apparatus includes: an acquisition unit that obtains a plurality of elements included in series data; a calculation unit that calculates a classification index indicating a likelihood of a class to which the series data belong, on the basis of at least two elements of the plurality of elements; and a selection unit that selects and outputs, from N classes that are classification candidates of the series data (where N is a natural number), K classes to which the series data are likely to belong (where K is a natural number that is less than or equal to N and that is greater than or equal to 1), on the basis of the classification index. According to the information processing apparatus, it is possible to select a plurality of classes to which the series data are likely to belong.