Self-Learning RPA Bots for Telecom Expense Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Robotic Process Automation (RPA) systems struggle to adapt to dynamic changes in telecom expense management environments, requiring manual intervention and reprogramming due to frequent changes in carrier websites and data structures, which hampers efficient data collection and processing.
Innovation Solution
A system and method utilizing machine learning to generate and modify RPA bots from a simple template, enabling them to automatically adapt to changing carrier or vendor systems without human intervention, by employing synonyms, pseudonyms, and self-modification strategies to navigate and retrieve TEM data efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If traditional RPA bots follow recorded steps to gather data, then data collection is automated, but the bots cannot adapt to website changes and require manual reprogramming
Solution Approach 1:
The RPA bot automatically detects website structure changes and self-modifies its navigation logic by learning new paths through synonyms and pseudonyms without human intervention. The bot serves itself by adapting to environmental changes, eliminating the need for manual reprogramming when carrier websites are updated.
Solution Approach 2:
The bot transitions from static recorded steps to dynamic adaptive navigation. It continuously learns and updates its understanding of website structures by exploring new paths and storing successful navigation patterns, allowing it to adapt to changing website layouts and data locations in real-time.
2Adaptability or versatility
If manual intervention is used to reprogram bots when websites change, then bots can adapt to new structures, but productivity and efficiency are reduced due to continuous human involvement
Solution Approach 1:
The bot automatically detects when data retrieval fails due to website changes, explores alternative paths using synonyms and pseudonyms, and self-modifies its navigation logic without human intervention. This self-service capability maintains continuous productivity by eliminating downtime for manual reprogramming.
Solution Approach 2:
The bot implements a feedback loop where failed data retrieval attempts trigger automatic exploration of alternative navigation paths. Successful paths are stored and learned, creating a continuous improvement cycle that maintains productivity while adapting to website changes through automated feedback from retrieval outcomes.
3Reliability
If comprehensive data is collected from multiple carriers and sources, then better telecom service and cost reduction are achieved, but the complexity of managing multiple data sources increases
Solution Approach 1:
The RPA bot is designed with universal capabilities to navigate and extract data from multiple different carrier websites and data sources using a unified approach. It employs a comprehensive synonym and pseudonym library that works across different carriers, eliminating the need for carrier-specific programming and reducing overall system complexity while maintaining ability to collect diverse data.
Solution Approach 2:
The bot dynamically adapts its navigation strategy to each carrier's specific website structure while maintaining a consistent core functionality. It learns and stores carrier-specific paths and terminology, allowing it to efficiently manage multiple data sources with varying structures through adaptive rather than static configuration.
4Reliability
If frequent monitoring of carrier plans and equipment is performed, then optimal service selection is achieved, but computing resources and time are consumed
Solution Approach 1:
The bot pre-loads and caches carrier website structures, data locations, and terminology during off-peak times or initial setup. By preparing navigation paths and data extraction templates in advance, it reduces the time and computing resources required during frequent monitoring cycles, enabling rapid data collection when needed.
Solution Approach 2:
The bot maintains continuous operation by automatically recovering from website changes without interruption to the monitoring process. Its self-healing capability ensures uninterrupted data collection and analysis, eliminating downtime that would occur with manual intervention and maintaining continuous useful action for service optimization.
Data Source
AI summary
A system and method incorporating Robotic Processing Automation (RPA) and machine leaning to finding telecom expense management information accessed through a site or portal such that RPA bots are able to learn the most effective way to access the information using the minimum amount computing resources and allowing for the RPA bot to self-modify to optimize and adjust to changing environments on the site or portal with minimal or even no manual intervention.