Predictive Service for Smart Routing in Cellular Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current user support services in cellular networks face challenges in efficiently routing user issues to the most appropriate agent or resource, leading to increased resolution times due to the lack of effective data analysis and intelligent routing systems.
Innovation Solution
A system that leverages data collected from cellular devices and network sensors to predict user issues, analyze patterns, and route user contacts to the most suitable support agents or resources based on the nature of the issue, device type, and agent expertise, utilizing a database to match issue parameters with previous successful resolutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional user support routing methods are used, then all user contacts are directed to a general support queue, but this leads to increased resolution times due to mismatched agent expertise and issue complexity
Solution Approach 1:
The system performs preliminary analysis of user contacts by analyzing device data, network data, and contact data before routing occurs. The predictive service pre-determines the likely subject of the contact and identifies the most suitable support group or agent in advance, so that when the contact is made, routing can happen immediately without delays from manual triage or mismatched assignments
Solution Approach 2:
A predictive service acts as an intermediary between the user contact and the support agents. This intermediary analyzes multiple data sources (device data from cellular devices, network data from the cellular network, contact data from the user) and uses machine learning models to predict the contact subject and determine optimal routing, thereby resolving the contradiction by introducing intelligence that reduces time loss while managing complexity through automated decision-making
2Measurement precision
If data from multiple cellular devices and network sensors is collected and analyzed, then accurate predictions of user issues can be made, but this increases system complexity and data processing requirements
Solution Approach 1:
The data analysis system is segmented into multiple specialized components: device data collection from cellular devices, network data collection from the cellular network, contact data collection from users, and separate machine learning model components for predicting contact subjects and routing decisions. This segmentation allows each component to process specific types of data efficiently, improving prediction accuracy while managing overall system complexity through modular architecture
Solution Approach 2:
The predictive service system is designed as a multi-functional platform that simultaneously performs device monitoring, network analysis, contact prediction, and intelligent routing. By creating a universal system that handles multiple functions through integrated data analysis and machine learning, the patent achieves high prediction accuracy while avoiding the need for separate specialized systems for each function, thereby managing complexity
3Productivity
If user contacts are routed to specialized agents based on predicted issues, then resolution efficiency increases, but this requires sophisticated predictive modeling and data matching capabilities
Solution Approach 1:
The system implements feedback loops where outcome data from resolved contacts is fed back into the machine learning models to continuously improve prediction accuracy. The predictive service learns from historical data about which agents successfully resolved which types of issues, and uses this feedback to refine future routing decisions. This feedback mechanism enables sophisticated automated routing that improves productivity while the automation level increases through iterative learning
Solution Approach 2:
The system performs preliminary predictive modeling and data matching before routing occurs, analyzing device data, network data, and contact data to predict the subject of the contact and identify the most suitable agent in advance. This preliminary action enables sophisticated routing decisions to be made automatically without requiring complex real-time decision-making during the actual contact, thereby increasing both productivity and automation level
Data Source
AI summary
Techniques for identifying a likely subject of a user contact with a user support network and routing the user contact to an agent or an application that is determined to have relevant experience with the subject or issue the user is experiencing. To identify a likely subject of the user contact, data is gathered from a user device as well as from secondary user devices located near the user device. Also, data related to network resources the user device is using, history data of a user's previous contacts with the user support network, and account data associated with the user device is also collected. As a result, the user contact is routed to a knowledgeable agent who is likely to resolve the user's issue without further routing or consultation, thus saving network bandwidth, user device resources, agent time, user time, etc.