Multi-channel Communication Analysis System for Session Association
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing multi-channel communication systems struggle to accurately link and analyze communication sessions across different channels, leading to inefficiencies in tracking customer interactions and assessing marketing efforts, as they often fail to identify related sessions and incorrectly associate tasks or results.
Innovation Solution
A multi-channel analysis system that compares user data from various communication channels to determine confidence levels for associations between sessions, allowing for the updating of performance metrics and improved tracking of communication initiators and results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If communication sessions are matched based on customer contact data (phone numbers, email addresses), then the burden of tracking is reduced and communication sessions from the same contact are grouped, but the system fails to identify related sessions across different communication channels and may erroneously associate unrelated sessions
Solution Approach 1:
The system segments the session matching process into multiple independent analysis dimensions: contact data matching, task context analysis, and temporal pattern recognition. Each dimension independently evaluates aspects of session relatedness, allowing the system to avoid erroneous associations by requiring convergence across multiple segments rather than relying on a single matching criterion
Solution Approach 2:
The system introduces task context as an intermediary layer between contact data and session association. Instead of directly linking sessions based on contact information, the task context serves as a mediator that verifies whether sessions from different channels are genuinely related to the same customer objective, thereby improving association accuracy across communication channels
2Measurement precision
If reference numbers are provided to customers to link communication sessions, then related sessions can be identified, but the customer burden increases and communication sessions are delayed
Solution Approach 1:
The system implements self-service session linking by automatically analyzing task context and communication patterns to identify related sessions without requiring customer intervention. The system autonomously performs session association by examining task objectives, communication sequences, and contextual cues, eliminating the need for customers to manually provide reference numbers
Solution Approach 2:
The system performs preliminary analysis of communication patterns and task contexts during and immediately after sessions to establish associations proactively. By pre-processing and analyzing session data in real-time, the system prepares association results before customers need to reference them, eliminating delays that would occur if customers had to retrieve and recite reference numbers during subsequent communications
3Loss of information
If multiple communication channels are integrated into a single contact center, then comprehensive customer interaction data is captured, but the complexity of analyzing and linking sessions across channels increases
Solution Approach 1:
The system implements a universal task context analysis framework that functions across all communication channels (phone, email, chat, social media). This multi-functional approach uses consistent task-oriented semantics and contextual analysis rules regardless of the communication medium, allowing comprehensive multi-channel data integration without proportionally increasing analysis complexity
Solution Approach 2:
The system transforms multi-channel communication data into standardized task context parameters that capture the essential meaning and objective of interactions regardless of channel. By converting diverse channel-specific data into unified task-oriented parameters (such as task type, progress state, and intent), the system simplifies cross-channel session analysis while maintaining complete customer interaction information
Data Source
AI summary
Techniques described herein relate to determining associations between different interactive communication sessions performed between users and an organization, over multiple different communication channels. A multi-channel analysis system may receive and compare user data from communication records captured via different communication channel systems, such as phone systems, web servers, chat systems, etc. In some examples, the multi-channel analysis system may determine confidence levels for associations between different communication sessions, based on matches between different user data fields and/or other attributes of the communication sessions. Individual communication sessions may be associated with communication initiators and/or communication results, and the multi-channel analysis system may use associations between communication sessions and confidence levels to determine and update performance metrics associated with communication initiators and/or communication results.