Chat History-Augmented Support Plans for Accurate Self-Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often struggle to independently diagnose or resolve technical problems and require additional instructions from automated or human technical support services, leading to inefficiencies and increased reliance on expert assistance.
Innovation Solution
An automated system utilizing a machine-learning language model generates technical support plans by querying a chat history database with user prompts, incorporating user and product information to provide accurate and efficient diagnostic and troubleshooting instructions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users attempt to independently diagnose or resolve technical problems, then user autonomy is improved, but diagnostic accuracy deteriorates due to lack of technical expertise
Solution Approach 1:
The patent introduces an automated technical support system as an intermediary between users and technical problem resolution. The system includes a language model that generates natural language responses, a chat history database for contextual information, and a query processing mechanism. This intermediary provides expert-level diagnostic accuracy while maintaining user autonomy, as users can independently interact with the system without requiring human technical support agents.
2Measurement precision
If automated technical support services are implemented, then diagnostic accuracy is improved, but system complexity increases due to need for sophisticated language models and databases
Solution Approach 1:
The patent utilizes a language model that has been trained on technical support interactions to generate responses. The system copies and adapts patterns from historical chat data stored in the chat history database, allowing the system to provide accurate diagnostic information without requiring complex real-time analysis infrastructure. The language model captures expert knowledge in a reusable format that simplifies the overall system architecture.
Solution Approach 2:
The system performs preliminary actions by pre-processing and storing technical support interactions in the chat history database before they are needed. Chat history segments are queried and prepared in advance, allowing the language model to generate accurate responses without requiring complex real-time processing. This preliminary organization of knowledge reduces the computational complexity during actual technical support interactions.
3Measurement precision
If human technical support agents are used, then diagnostic accuracy is improved, but operational cost and response time deteriorate
Solution Approach 1:
The patent implements a self-service technical support system where users can obtain diagnostic information and troubleshooting guidance without human intervention. The automated system processes user queries, retrieves relevant information from the chat history database, and generates natural language responses using the language model. This eliminates the need for human technical support agents while maintaining diagnostic accuracy and improving response efficiency.
Data Source
AI summary
A method of automated technical support includes receiving a natural-language prompt from a user device and a user identifier corresponding to a user of the user device. The natural-language prompt includes a natural-language description of at least one technical problem. The method additionally includes querying a chat history database with a query including at least one of the user identifier, a representation of the natural-language response, and at least one keyword extracted from the natural-language prompt. At least one chat history segment from the chat history database is received in response to the query, and an augmented prompt is generated based on the natural-language prompt and the chat history segment. A natural-language technical support plan responsive to the at least one technical problem is then generated through execution of a language model based on the augmented prompt.