Score Calculation Unit for Character Likeness Data Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual data creation for generating interactive responses with specific character likeness is time-consuming and difficult to scale for large datasets.

Innovation Solution

An information processing apparatus that calculates a score indicating target character likeness based on feature amounts and associations, and extracts relevant data using a score calculation unit and extraction unit.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If manual data creation using crowdsourcing is used to increase utterance text with specific character likeness, then the quantity of data is improved, but the time required for data collection increases

Engineering Contradiction:

Improvequantity of utterance text dataVSAvoidtime required for data collection

Core Design Contradiction:

Quantity of substanceVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical data collection processes with automated computational methods. The score calculation unit automatically computes character likeness scores by analyzing feature amounts and association degrees from existing text data, eliminating the need for manual crowdsourcing while obtaining large quantities of character-specific utterance text efficiently

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically processing and filtering existing text data to extract character-specific utterances. The extraction unit autonomously selects data based on calculated scores without requiring human intervention, enabling rapid scaling of data collection

Inventive Principle:

Principle #25Self-service

2Quantity of substance

If manual data creation is used to collect large amounts of data, then the quantity of data is improved, but the productivity decreases

Engineering Contradiction:

Improvequantity of learning dataVSAvoiddata collection speed

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The patent replaces slow manual data creation with high-speed automated processing. The score calculation unit and extraction unit process large volumes of text data rapidly by computing feature amounts and association degrees algorithmically, achieving both high productivity and large data quantity simultaneously

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20240241899A1Information processing apparatus and information processing method

Publication Date: 2024.07.18 SONY GROUP CORP

AI summary

An information processing apparatus according to an embodiment includes: a score calculation unit (130) configured to calculate a score indicating a target character likeness of first content data based on a feature amount indicating a feature of the first content data and a degree of association of the target character with other characters different from the target character with respect to the first content data, and an extraction unit (140) configured to extract data to be associated with the target character among the first content data based on the score calculated by the score calculation unit.