Contact Center Routing Using External Sensor Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Contact centers fail to leverage the full capabilities of IoT devices to provide an enhanced user experience, as they currently lack efficient integration and routing of communication sessions based on external sensor data.

Innovation Solution

A system that uses a machine learning model to identify external sensors and route communication sessions in a contact center based on received sensor information, prioritizing sessions to high-priority queues instead of traditional IVR systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional IVR systems are used for routing communication sessions, then system simplicity is maintained, but customer satisfaction and routing efficiency deteriorate

Engineering Contradiction:
Improverouting efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system segments the routing decision-making process into multiple components: IVR system handles initial call intake, machine learning model analyzes sensor data and communication patterns, and routing engine directs calls to appropriate queues. This segmentation allows each component to specialize in specific tasks, improving overall routing efficiency without requiring complete system replacement.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A machine learning model acts as an intermediary between the IVR system and the routing engine. The ML model receives sensor data from IoT devices and communication session information, then provides enhanced routing recommendations to the IVR system. This intermediary layer enables intelligent routing decisions without directly modifying the existing IVR infrastructure.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If external sensor data is integrated into routing decisions, then routing personalization and customer satisfaction improve, but system complexity and data processing requirements worsen

Engineering Contradiction:
Improverouting personalizationVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The machine learning model serves multiple functions simultaneously: it processes sensor data from various IoT devices, analyzes communication session patterns, generates routing recommendations, and adapts to different customer scenarios. This multi-functionality enables personalized routing without requiring separate systems for each function, thereby limiting the increase in system complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system changes routing parameters dynamically based on sensor data inputs. Instead of static routing rules, the ML model adjusts routing decisions in real-time based on environmental context, customer behavior patterns, and device sensor information. This parameter adaptation enables personalized routing while using the same underlying system infrastructure.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If machine learning models are used to analyze sensor data, then routing accuracy and customer experience improve, but computational requirements and processing time worsen

Engineering Contradiction:
Improverouting accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The machine learning model is trained in advance on historical sensor data and communication patterns to learn optimal routing strategies. During actual call routing, the pre-trained model quickly matches current sensor inputs against learned patterns, enabling accurate routing decisions without requiring complex real-time computation. This preliminary training action reduces processing time during live operations.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system processes only the most relevant sensor data and communication attributes needed for routing decisions, rather than analyzing all available data. The ML model selectively focuses on key features that have the highest impact on routing accuracy, performing partial analysis that achieves sufficient precision without excessive processing time.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3661180B1System and method for providing enhanced routing in a contact center
Publication Date: 2021.07.07 AVAYA INC
  • EP3661180B1 patent drawingFigure 1
  • EP3661180B1 patent drawingFigure 2
  • EP3661180B1 patent drawingFigure 3

AI summary

A first request to establish a communication session with a contact center is received from a user communication device. A request to establish a voice communication session is received at the contact center. A machine learning model uses prior communication sessions with the contact center to identify a first set of one or more sensors that are external to the user communication device. External sensor information is received e.g., during the request to establish the communication session, by the contact center. The external sensor information is from the first set of one or more sensors that are external to the user communication device. The communication session in the contact center is routed based on the received external sensor information. For example, instead of the communication session being routed to an Interactive Voice Response (IVR) system, the communication session is routed to a high priority contact center queue.