Intelligent Screen Recording System Optimizing Storage via ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current contact center systems incur high storage costs due to random recording of agent interactions, leading to redundant recordings for low-performing agents and insufficient recordings for high-performing agents, necessitating a predictive approach to optimize screen recording storage.
Innovation Solution
A computerized system employing supervised classification machine learning to predict evaluation likelihood values and determine recording and storage policies for agent interactions, optimizing storage usage by selectively recording and deleting data items based on agent performance metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If random recording of agent interactions is performed at a predetermined percentage, then storage costs are incurred, but the quality of evaluation is insufficient for high-performing agents and redundant for low-performing agents
Solution Approach 1:
The system changes the recording parameter from a fixed random percentage to a dynamic probability value that varies per agent based on performance metrics. High-performing agents receive lower recording probabilities while low-performing agents receive higher probabilities, optimizing both evaluation quality and storage costs
Solution Approach 2:
The system performs preliminary classification of agents into performance groups before determining recording policies. This preliminary action allows the system to pre-calculate appropriate recording probabilities for each agent based on their historical performance, ensuring that evaluation needs are met while minimizing redundant recordings
2Loss of information
If screen recording is performed for all agent interactions, then complete evaluation data is available, but storage costs become excessively high
Solution Approach 1:
The system applies different recording qualities (probabilities) to different agents based on their local characteristics and performance levels. Instead of uniform recording for all agents, each agent receives a customized recording probability that matches their evaluation needs, reducing overall storage requirements while maintaining data completeness for those who need it
Solution Approach 2:
The system performs partial recording action by selecting only the necessary portion of interactions for recording based on agent performance. Rather than recording all interactions universally, the system applies recording action selectively to achieve sufficient evaluation data with minimal storage consumption
3Quantity of substance
If recording percentage is reduced to save storage costs, then storage efficiency improves, but evaluation reliability deteriorates
Solution Approach 1:
The system changes the recording parameter from a uniform percentage to agent-specific probability values. This parameter transformation ensures that storage efficiency is improved through selective recording while evaluation reliability is maintained by allocating higher recording probabilities to agents who need more evaluation coverage
Data Source
AI summary
A computerized system and method may determine the recording and/or storing and/or deleting of data items received from remotely connected computer systems, which may be for example interaction recordings associated with a plurality of agents as part of their activity within a given system or organization, using a supervised classification machine learning based approach. A computerized system comprising one or more processors, a communication interface to communicate via a communication network with remote computing devices, and a memory including a data store of a plurality of data items, may be used for extracting features from a plurality of data items; predicting evaluation likelihood values based on the features; deriving storing percentages for a plurality of remote computing devices; and, based on likelihood values and storing percentages, recording and/or storing and/or deleting a plurality of data items from a data store or database.