Learning Unit Adapts Specific Expressions for User Communication

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing information processing systems cannot effectively recognize and communicate using specific expressions that vary within groups, such as families or communities, leading to inefficient user interaction.

Innovation Solution

An information processing apparatus and method that includes a learning unit capable of associating recognition targets with specific expressions, using both sound and image inputs to adapt communication to match user-specific terminology, thereby enhancing user understanding and interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If general object recognition is used to acquire general expressions of objects, then the system can recognize and present information using standardized terminology, but it cannot acquire, use, or recognize specific expressions that vary within groups such as families

Engineering Contradiction:
Improveadaptability to user-specific expressionsVSAvoidloss of specific expression information
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent segments the expression system into two layers: general expressions for broad recognition and specific expressions for group-specific terminology. The learning unit separately acquires general expressions through object recognition and specific expressions through listening to user communications, allowing the system to handle both standardized and personalized terminology simultaneously.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary learning of specific expressions by continuously listening to and analyzing user communications before actual information presentation occurs. This advance acquisition of group-specific terminology enables the system to adapt its output to match user preferences without requiring real-time processing during information delivery.

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If the system uses only general expressions for information presentation, then communication is standardized and universally understandable, but communication smoothness and user familiarity are reduced

Engineering Contradiction:
Improvecommunication smoothnessVSAvoiduser understanding reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system uses feedback from analyzing user communications to continuously learn and update the specific expressions preferred by the user group. By monitoring how users naturally refer to objects in their conversations, the system adapts its terminology to match user expectations, thereby improving communication smoothness while maintaining accuracy through verified user preferences.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system dynamically changes the expression parameter from fixed general expressions to adaptable specific expressions based on learned user preferences. This parameter change allows the same object recognition core to produce different linguistic outputs depending on the target user group, enhancing both communication smoothness and understanding reliability.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11430429B2Information processing apparatus and information processing method
Publication Date: 2022.08.30 SONY GROUP CORP
  • US11430429B2 patent drawing
  • US11430429B2 patent drawing
  • US11430429B2 patent drawing

AI summary

To more smoothly communicate with a user, provided is an information processing apparatus including an output control unit that controls information presentation to a user, in which, in a case where a specific expression in a group including the user is applicable regarding content of information to be presented, the output control unit causes the information presentation including the specific expression to be executed using at least one of a sound or an image. Furthermore, provided is an information processing apparatus including a learning unit that learns a recognition target and a linguistic expression regarding the recognition target in association with each other, in which the linguistic expression includes a specific expression in a group including a user, and the learning unit learns the specific expression on the basis of at least one of a collected sound or a collected image.