Automated IVR Tree Navigation for Shorter Assisted Calls

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing automated assistants struggle with efficiently navigating interactive voice response (IVR) systems, leading to prolonged resource usage and battery consumption during assisted telephone calls, as they often require user intervention and repeated calls to reach target states.

Innovation Solution

An automated assistant navigates IVR trees on behalf of users by synthesizing speech and emulating button presses, using stored IVR tree data and user inputs to determine target states, and adapts navigation based on client device interactions, reducing the need for user participation and subsequent calls.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If an automated assistant requires user intervention during IVR navigation, then the navigation can be more accurate and adapt to user preferences, but the call duration increases and device battery consumption rises

Engineering Contradiction:

Improvenavigation accuracyVSAvoidbattery consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs partial automation by handling routine IVR navigation tasks automatically while selectively engaging the user only when necessary for complex decisions or confirmations. This reduces overall user participation time and energy consumption while maintaining navigation accuracy for critical decisions.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The automated assistant pre-navigates the IVR tree to identify the target state and preparation steps before fully engaging the user. By performing preliminary navigation actions and only requiring user input at critical decision points, the system minimizes call duration and battery consumption while ensuring accurate navigation.

Inventive Principle:

Principle #10Preliminary action

2Use of energy by moving object

If the automated assistant performs full automatic navigation without user participation, then call duration and battery consumption are reduced, but the ability to handle complex or unexpected IVR scenarios decreases

Engineering Contradiction:

Improvebattery consumptionVSAvoidhandling complex scenarios

Core Design Contradiction:

Use of energy by moving objectVSAdaptability or versatility

Solution Approach 1:

The automated assistant independently navigates the IVR system by automatically listening to prompts, interpreting menu options, and selecting navigation paths without requiring continuous user intervention. The system serves itself by maintaining context and making autonomous decisions, reducing battery consumption while handling routine scenarios effectively.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system continuously monitors IVR system responses and user inputs, using this feedback to dynamically adjust its navigation strategy. By implementing feedback loops that allow the automated assistant to learn from interactions and adapt to unexpected scenarios, it maintains versatility while minimizing user participation and energy consumption.

Inventive Principle:

Principle #23Feedback

3Productivity

If the automated assistant stores and processes complete IVR tree data, then navigation efficiency improves, but device memory usage and data processing requirements increase

Engineering Contradiction:

Improvenavigation efficiencyVSAvoidmemory usage

Core Design Contradiction:

ProductivityVSQuantity of substance

Solution Approach 1:

The IVR tree data is segmented into hierarchical levels and stored in a structured format that allows the automated assistant to access only relevant portions during navigation. By dividing the complete IVR tree into manageable segments organized by department and function, the system improves navigation efficiency while reducing memory requirements through selective data access.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary processing of IVR tree data during off-peak times to pre-compute navigation paths and store optimized route information. By preparing navigation data in advance and caching frequently accessed IVR structures, the automated assistant achieves high navigation efficiency during calls without requiring large amounts of memory during active use.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250254239A1Automatic navigation of an interactive voice response (IVR) tree on behalf of human user(s)

Publication Date: 2025.08.07 GOOGLE LLC

AI summary

Implementations are directed to utilizing an assistant to automatically navigate an interactive voice response (IVR) tree to arrive at a target state during an assisted telephone call. The assistant can receive input to initiate the assisted telephone call, identify an entity to engage with, on behalf of the user, and during the assisted telephone call, based on the input, and identify an IVR tree stored in association with the entity. In various implementations, navigation of the IVR tree can be modified based on interaction(s) detected at a client device subsequent to initiating the assisted telephone call. In various implementations, the assisted telephone call can be initiated from a search interface, and the target state can be associated with a given search result. In various implementations, the IVR tree can be dynamic in that only a subset of candidate state(s) of the IVR tree may be available as the target state.