Content Orchestration Engine for Automated Record Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Remote network management platforms face challenges in efficiently searching and retrieving relevant records to diagnose and resolve frequently occurring technical problems, leading to prolonged troubleshooting times and resource constraints for agents.
Innovation Solution
A content orchestration engine is introduced to determine whether input text contains 'solved' or 'unsolved' content, using natural language processing and machine learning techniques to classify and retrieve relevant records from databases, thereby reducing the time required to address user issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a querying procedure is applied to search through millions of records in databases, then relevant text-based descriptions can be found to resolve user problems, but the search process becomes computationally intensive and time-consuming
Solution Approach 1:
The patent applies preliminary action by pre-processing text-based descriptions from records and storing them in optimized data structures before queries are executed. This allows the system to quickly retrieve and compare pre-processed information during actual problem-solving, avoiding the need to process raw text during time-critical query operations.
Solution Approach 2:
The patent creates simplified copies or representations of the original text-based descriptions in optimized formats. These copies enable fast comparison and matching during queries while the original detailed records remain stored for reference when needed, balancing retrieval speed with information completeness.
2Quantity of substance
If traditional text-based searching is used to find relevant records, then the system can handle large volumes of records, but the searching process returns many non-useful results requiring additional manual filtering
Solution Approach 1:
The patent applies local quality by extracting and emphasizing specific key features or characteristics from text-based descriptions that are most relevant to problem resolution. Instead of treating all text equally, the system identifies and weights locally important features, enabling more precise matching while maintaining the ability to search through large record volumes.
Solution Approach 2:
The patent transforms text-based descriptions into different parameter representations or feature vectors that capture essential information in a structured format. This parameter transformation enables efficient computational comparison and filtering, allowing the system to rapidly identify useful results among millions of records by comparing key parameters rather than processing full text.
3Device complexity
If agents manually examine ticket text to identify solutions, then no additional automated processing is needed, but the troubleshooting process takes days or weeks
Solution Approach 1:
The patent introduces an intermediary automated processing layer between the ticket submission and agent examination. This intermediary system performs preliminary analysis, searches relevant databases, and prepares candidate solutions before presenting them to agents, significantly reducing the time agents need to spend on each ticket while maintaining system simplicity through modular architecture.
Solution Approach 2:
The patent enables self-service by implementing automated systems that can independently perform initial problem analysis, search for relevant solutions in historical records, and present recommended resolutions. This allows many routine problems to be resolved automatically without agent intervention, while agents focus on complex cases requiring human judgment.
Data Source
AI summary
A system could include persistent storage units. Each persistent storage unit could contain: (i) records including descriptions related to technology-related problems, and (ii) term frequency (TF) metrics for tokens within the descriptions. The system could include processors configured to perform operations. The operations may include receiving input text and determining that the input text is subject to a querying procedure. The operations could also include, in response to the determining, identifying a classification for the input text and based on the classification, selecting at least one of the persistent storage units. The operations could further include tokenizing the input text to form input tokens and calculating, for the input tokens, input TF metrics. The operations could additionally include determining similarity metrics between: (i) the input TF metrics, and (ii) TF metrics for records within the at least one persistent storage unit and, based on the similarity metrics, retrieving relevant records.