Aided Call Transfer System Using Speech Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Call centers face inefficiencies in transferring calls due to complex organizational structures, requiring agents to manually search for appropriate departments using keyword-based search tools, which is time-consuming and prone to errors, leading to incorrect transfers and reduced customer satisfaction.

Innovation Solution

A system utilizing a speech recognition engine to automatically identify keywords from user-agent conversations, dynamically adjusting confidence scores for potential transfer options, and providing agents with a user-friendly interface to efficiently route calls to the most suitable department or agent.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If agents manually search for appropriate departments using keyword-based search tools, then they can transfer calls to specific departments, but the process becomes time-consuming and prone to errors

Engineering Contradiction:

Improveaccuracy of call transferVSAvoidtime spent on call transfer

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables automatic call transfer by allowing the caller's speech to directly trigger transfer actions without requiring manual agent intervention. The speech recognition engine processes caller statements in real-time and automatically routes calls based on identified intent and keywords, making the system self-serve the transfer decision-making process.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of agents typing keywords and navigating search tools with an automated speech recognition system. The speech recognition engine converts spoken words into text, identifies intent and entities, and triggers transfers automatically, substituting the manual search mechanism with an automated linguistic processing system.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If agents use complex keyword-based search tools to find appropriate departments, then calls can be routed accurately, but the operational complexity increases

Engineering Contradiction:

Improveaccuracy of call transferVSAvoidcomplexity of transfer system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The speech recognition engine serves multiple functions within a single system: it transcribes speech to text, identifies caller intent, extracts key entities (names, locations, products), and triggers appropriate transfer actions. This multi-functional approach consolidates what would otherwise require separate tools and processes into one universal system.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The speech recognition engine acts as an intermediary layer between the caller and the call transfer system. It translates natural language speech into structured data (intent, entities, keywords) that the transfer system can process, mediating between human communication and automated routing without requiring agents to directly interact with complex search interfaces.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If agents manually process call transfers, then they can handle complex organizational structures, but productivity decreases

Engineering Contradiction:

Improveability to handle organizational structureVSAvoidcall transfer efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system changes the parameters of call transfer by transitioning from manual text-based keyword searching to automated speech-based intent recognition. This parameter change enables the system to process transfer decisions based on natural language understanding rather than manual keyword matching, significantly improving processing speed while maintaining adaptability to complex organizational structures through configurable routing rules.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11272054B1Aided call transfer system

Publication Date: 2022.03.08 UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)

AI summary

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a transfer option for transferring a call. One of the methods includes: dynamically capturing, by the at least one processor, during a call between a first individual and a second individual, one or more keywords from a verbal conversation between the first individual and the second individual during the call; automatically determining, by the at least one processor, a transfer option for transferring the call based on the captured one or more keywords; and transferring, by the at least one processor, the call to a transfer unit specified by the determined transfer option.