Dynamic Voice Menu Customization via Speech Feature Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional voice interaction systems provide static voice menus that are either too simplistic for advanced users or too complex for less advanced users, leading to user dissatisfaction due to a lack of customization.

Innovation Solution

A dynamic voice interaction system that customizes menu systems by extracting features from user speech, such as vocabulary and dialect, to assign users to specific user group models, allowing for tailored menu content, sequence, and tone adjustments based on perceived education levels, domain knowledge, and language literacy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a static voice menu system is provided to all users, then the system structure is simple and easy to implement, but the system lacks adaptability to different user capabilities leading to user dissatisfaction

Engineering Contradiction:
Improveadaptability to user capabilitiesVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The voice menu system transitions from a static structure to a dynamic one that adapts in real-time based on user characteristics. The system extracts features from user speech (vocabulary, dialect, sentence structure) and dynamically customizes menu content, sequence, and complexity to match the user's demonstrated capabilities, thereby achieving adaptability without requiring a completely complex system redesign

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes key parameters of the voice menu based on user analysis, including vocabulary complexity, sentence structure, dialect accommodation, and menu sequence ordering. By adjusting these parameters dynamically according to extracted user features, the system achieves versatility while maintaining a manageable structural framework

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If the voice menu provides comprehensive options, then advanced users find it too complex to navigate, but simplified menus make less advanced users frustrated

Engineering Contradiction:
Improveease of menu navigationVSAvoidcustomization to user level
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system applies different levels of menu complexity and vocabulary to different user groups based on their extracted features. Instead of a uniform menu structure, the system tailors the local quality of menu presentation (vocabulary choice, sentence complexity, option sequencing) to match each user's demonstrated capabilities, making navigation easier for each individual without sacrificing comprehensive functionality

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system performs preliminary analysis of user speech features (vocabulary, dialect, sentence structure) before presenting the voice menu. This preliminary action allows the system to pre-customize the menu characteristics to match the user's capabilities, ensuring ease of operation from the first interaction rather than requiring iterative adjustments

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12020691B2Dynamic vocabulary customization in automated voice systems
Publication Date: 2024.06.25 CAPITAL ONE SERVICES LLC
  • US12020691B2 patent drawing
  • US12020691B2 patent drawing
  • US12020691B2 patent drawing

AI summary

Techniques to dynamically customize a menu system presented to a user by a voice interaction system are provided. Audio data from a user that includes the speech of a user can be received. Features can be extracted from the received audio data, including a vocabulary of the speech of the user. The extracted features can be compared to features associated with a plurality of user group models. A user group model to assign to the user from the plurality of user group models can be determined based on the comparison. The user group models can cluster users together based on estimated characteristics of the users and can specify customized menu systems for each different user group. Audio data can then be generated and provided to the user in response to the received audio data based on the determined user group model assigned to the user.