Information Processing Device Learning Setting Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In deep learning, selecting a suitable learning setting is time-consuming, as it requires extensive processing to obtain the necessary indices for selection.

Innovation Solution

An information processing device and method that acquire and recommend a learning setting based on the similarity with previous learning processing, using a data acquisition unit and display control unit to expedite the selection process by suggesting settings from a search history database.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If learning processing is executed to obtain indices for selecting a learning setting, then the selection accuracy is improved, but the time required increases significantly

Engineering Contradiction:

Improveselection accuracyVSAvoidtime required

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system pre-executes learning processing to obtain indices and store them in advance in a database. When a user needs to select a learning setting, the pre-computed indices are retrieved from the database rather than computing them on-demand, thereby resolving the contradiction between obtaining accurate selection indices and the time required to do so.

Inventive Principle:

Principle #10Preliminary action

2Loss of time

If a learning setting is selected without executing learning processing, then the time required is reduced, but the selection accuracy deteriorates

Engineering Contradiction:

Improvetime requiredVSAvoidselection accuracy

Core Design Contradiction:

Loss of timeVSMeasurement precision

Solution Approach 1:

The system creates a database that stores copies of learning processing results (indices) obtained from previous learning executions. Instead of performing full learning processing each time a selection is needed, the system retrieves pre-stored copies of indices from the database, thus reducing time while maintaining selection accuracy through access to pre-computed reliable data.

Inventive Principle:

Principle #26Copying

3Reliability

If extensive learning processing is performed to obtain comprehensive indices, then the reliability of learning setting selection is improved, but the complexity of the system increases

Engineering Contradiction:

Improvereliability of selectionVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system divides the learning processing into two separate components: (1) learning processing execution that generates indices, and (2) index retrieval from the stored database. This segmentation allows the system to maintain high reliability through comprehensive learning processing while reducing operational complexity by separating the time-consuming learning execution from the quick index retrieval operation.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11593635B2Information processing device, method of processing information, and method of providing information

Publication Date: 2023.02.28 SONY GROUP CORP

AI summary

There is provide an information processing device capable of reducing the time taken for selection of the learning setting, the information processing device including: a data acquisition unit configured to acquire a learning setting corresponding to information related to previous learning processing in which a degree of similarity with information related to learning processing specified by a user is higher than a predetermined degree of similarity as a learning setting to be recommended to the user; and a display control unit configured to control display corresponding to the learning setting to be recommended.