Realtime IT Support Chatbots Using Remote Session Training Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional chatbot applications lack reliable training data based on real-time customer/user footprints, leading to inaccurate resolutions and frequent escalation of queries to more experienced support representatives.

Innovation Solution

A chatbot support system trains a machine learning system with remote session data from first client systems, capturing user journeys and actions to provide accurate, timely resolutions, eliminating the need for query escalation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional chatbot applications are trained with traditional training data, then the system can provide automated support, but the resolutions are inaccurate and queries are frequently escalated to experienced support representatives

Engineering Contradiction:

Improveaccuracy of resolutionsVSAvoidlack of real-time customer footprint data

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The system proactively captures and stores real-time customer footprint data, user journeys, and interaction histories before they are needed for training. This preliminary data collection enables the machine learning system to be trained with current, relevant information about actual customer behaviors and issues, improving resolution accuracy without waiting for traditional feedback loops

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements a feedback mechanism where real-time customer interaction data is continuously collected, analyzed, and used to retrain the machine learning model. This closed-loop feedback ensures the chatbot learns from actual customer footprints and resolves issues accurately, reducing escalations to human representatives

Inventive Principle:

Principle #23Feedback

2Productivity

If real-time remote session data is collected and used for training, then accurate resolutions can be provided, but the system complexity increases

Engineering Contradiction:

Improvecustomer support efficiencyVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The machine learning system is designed to handle multiple functions: it processes real-time remote session data, analyzes user journeys, generates accurate resolutions, and continuously learns from new data. This multi-functional approach consolidates what could be separate complex systems into a unified platform, improving productivity while managing complexity through integration

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system introduces an intermediary data processing layer that captures real-time customer footprint information and transforms it into training data for the machine learning model. This intermediary layer simplifies the overall architecture by handling data collection, processing, and model training as a coordinated workflow, making the system more manageable despite the increased capabilities

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20250245558A1Realtime Data Based Automated IT Support

Publication Date: 2025.07.31 DELL PROD LP

AI summary

Methods, system, and non-transitory processor-readable storage medium for a chatbot support system are provided herein. An example method includes the chatbot support system training a machine learning system, where the machine learning system is trained with remote session data obtained on a first client system. A chatbot application on a second client system receives a support request from a user. The chatbot application obtains a resolution for the support request from the machine learning system, and outputs on the second client system the resolution for the user.