Automation Routine Mining System for Contact Center Workload Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing process mining tools face challenges in discovering automation routines efficiently due to lengthy data gathering processes, incomplete data, and disconnection between system event logs and actual employee actions, limiting the types of routines that can be identified and automated.
Innovation Solution
An automation routine type mining system that mines usage data from agents, represents it as binary vectors, screens for viability, and creates new automation routines based on frequently occurring sequences, which can then be turned into code, using user-definable constraints to filter and identify relevant patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If process mining tools use system event logs to identify automation opportunities, then they can present complete end-to-end flow and identify bottlenecks, but the data gathering process becomes lengthy and resource intensive
Solution Approach 1:
The patent introduces an intermediary layer (the mining system) that sits between the enterprise applications and the analysis tools. This intermediary automatically captures and structures data from multiple application types (databases, file systems, web applications, desktop applications) into a unified format, eliminating the need for lengthy manual data gathering while ensuring complete process flow information is captured.
Solution Approach 2:
The system performs preliminary data collection and structuring operations before the actual mining process. By pre-capturing data from various sources and organizing it into a standardized format in advance, the system eliminates the need for time-consuming data gathering during the analysis phase, while ensuring all necessary process flow information is available.
2Loss of information
If process mining tools rely on log events from enterprise applications, then they can identify process-level patterns, but they lack connection to actual employee actions and require customer cooperation
Solution Approach 1:
The mining system is designed to work universally with multiple types of applications and data sources (databases, file systems, web applications, desktop applications) without requiring application-specific configurations or customer cooperation. It captures both process-level information and actual employee actions through a unified interface that works across different application types.
Solution Approach 2:
The system acts as an intermediary that bridges the gap between enterprise applications and analysis tools, capturing data automatically without requiring customer cooperation. It monitors and records actual employee actions across multiple application types, translating them into structured process information that can be analyzed.
3Productivity
If pattern mining techniques are used to identify repeating patterns in agent behavior, then automation routines can be generated, but certain routine types remain difficult to discover due to preprocessing challenges
Solution Approach 1:
The system segments the complex data preprocessing task into distinct modules that handle different application types (databases, file systems, web applications, desktop applications) separately. Each module transforms data from its specific format into a standardized structure, making the overall preprocessing process more manageable and enabling discovery of diverse routine types that would be difficult to identify with monolithic preprocessing approaches.
Data Source
AI summary
A system to create new automation routines includes a processor to: Over time, store a group of actions taken by a group of agents within applications. From the stored group of actions, identify a repeating pattern of actions in a subset of the applications, and construct a binary vector, each position within the binary vector storing a 1 for an occurrence of any action within any application of the subset, and a 0 otherwise. From the binary vector and the repeating pattern, extract a sentence including at least one action within at least one application. Based on the repeating pattern, an application type, or a business goal, create a constraint. If the sentence meets the constraint, accept the sentence and add it to a pool of accepted sentences. From the pool of accepted sentences, identify a pattern of occurrences of the accepted sentence, and create a new automation routine.