Speech Processing Content Restriction for Child Users

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Speech processing systems lack effective mechanisms to restrict access to inappropriate content and actions for child users, potentially allowing them to inadvertently or intentionally access explicit or inappropriate materials and services.

Innovation Solution

A system and method that utilize automatic speech recognition (ASR) and natural language understanding (NLU) to identify child users and enforce access policies, restricting their access to certain skills and content based on device identifiers or user profiles, ensuring only child-appropriate responses are provided.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If speech processing systems allow unrestricted access to all content and skills, then system versatility and user freedom are improved, but child users may inadvertently or intentionally access inappropriate or explicit content

Engineering Contradiction:
Improvesystem versatilityVSAvoidinappropriate content access
Core Design Contradiction:
Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary identification of child users through device identifiers or user profiles before content delivery. Access policies are pre-configured to restrict certain skills and content for child users, preventing inappropriate content access before it can occur. This proactive approach allows the system to maintain versatility for adult users while protecting child users.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

An intermediary access policy mechanism is introduced between the speech processing system and the content/skills. This intermediary layer evaluates user identity and applies appropriate restrictions, allowing the system to maintain full versatility while filtering inappropriate content for child users. The intermediary does not reduce overall system capability but selectively applies constraints.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If access policies are implemented to restrict content for child users, then protection from inappropriate content is improved, but system complexity increases due to additional identification and policy enforcement mechanisms

Engineering Contradiction:
Improveinappropriate content accessVSAvoidsystem complexity
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The system utilizes self-service mechanisms by leveraging existing device identifiers or user profiles that are already associated with child users. Rather than requiring complex new identification systems, the speech processing system automatically detects and applies access policies based on information already available in the ecosystem, minimizing additional complexity while maintaining effective protection.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If device identifiers or user profiles are used to identify child users, then accuracy of child user identification is improved, but loss of user privacy increases due to data collection and processing

Engineering Contradiction:
Improvechild user identification accuracyVSAvoiduser privacy
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The system performs preliminary identification of child users using device identifiers or user profiles that are already established in the ecosystem. By leveraging pre-existing identification mechanisms rather than creating new data collection systems, the approach maintains high identification accuracy while minimizing additional privacy intrusion. The access policies are applied based on this preliminary identification without requiring further personal information.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3676831B1Natural language user input processing restriction
Publication Date: 2024.04.17 AMAZON TECH INC
  • EP3676831B1 patent drawingFigure 1
  • EP3676831B1 patent drawingFigure 2
  • EP3676831B1 patent drawingFigure 3

AI summary

Techniques for restricting content, available to a speech processing system, from certain users of the system are described. The system may include child devices and child profiles. When a user provides input to a child device, the system may process the input to determine child appropriate content based on the invoked device being a child device. When a user provides input to a device, the system may identify the user, determine an age of the user, and process the input to determine content appropriate for the user's age. The system may be configured such that child user may be restricted to invoking certain intents, speechlets, skills, and the like. The system may include restrictions that apply uniformly to each child user and/or child device. In addition, the system may include restrictions that are unique to a specific child user and/or device.