Service Intelligence Search for Machine Anomaly Resolution Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current knowledge bases are not comprehensive and fail to identify different potential issues and resolutions, as they cannot reliably utilize machine logs or event records for knowledge searching, leading to ambiguity and difficulty in identifying the cause of system anomalies.
Innovation Solution
A service intelligence system that utilizes a processor to receive search queries, identify anomalous machine codes, select historical data elements based on similarity scores, and provide corrective actions or part replacements using natural language processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual knowledge systems are used to provide catalogs of issues and resolutions, then users can access documented solutions, but the systems are not comprehensive and cannot include all possible issues and resolution mappings
Solution Approach 1:
The system automatically processes machine logs and event records to generate knowledge base entries without manual intervention. The processor autonomously identifies anomalies, extracts patterns, and creates resolution mappings, enabling the system to continuously expand its comprehensiveness without proportional increases in manual maintenance complexity
Solution Approach 2:
Manual knowledge curation is replaced with automated machine learning algorithms that process machine logs and event records. The system uses natural language processing and pattern recognition to automatically generate issue-resolution mappings, substituting manual expert work with computational processes that scale more efficiently
2Reliability
If machine logs and event records are utilized for knowledge searching, then more comprehensive diagnostics can be achieved, but the complex information in logs is not readable or understandable by users
Solution Approach 1:
The system introduces an intermediary processing layer that translates complex machine logs and event records into user-friendly diagnostic information. The processor acts as a mediator between the raw technical data and the user interface, converting unreadable log entries into comprehensible issue descriptions and resolution recommendations
Solution Approach 2:
The system creates simplified copies or representations of the complex machine log data. Instead of presenting raw event records directly to users, it generates summarized diagnostic reports that capture the essential meaning while eliminating the complexity and technical jargon that makes the original logs unreadable
3Measurement precision
If the same symptom is mapped to multiple different root causes in the knowledge base, then more accurate diagnostics can be provided, but ambiguity arises regarding which resolution to apply
Solution Approach 1:
The system applies different weighting or priority levels to different potential resolutions based on the specific context of the anomaly. Instead of treating all possible resolutions equally, it assigns local quality characteristics to each resolution option based on the confidence score and contextual relevance, guiding users toward the most appropriate action for their specific situation
4Measurement precision
If manual annotation of event records is performed to distinguish normal and anomalous events, then accuracy can be improved, but it is impossible to annotate all event records using manual effort
Solution Approach 1:
The system performs self-annotation of event records using automated machine learning models. The processor autonomously classifies events as normal or anomalous based on patterns learned from training data, eliminating the need for manual annotation while maintaining high processing throughput and achieving acceptable accuracy levels
Data Source
AI summary
A service intelligence system is disclosed. The service intelligence system receives a search query, identifies anomalous machine codes for a machine associated with the search query, selects one or more historical data elements based on a similarity score between the identified anomalous machine codes and machine codes associated with the one or more historical data elements, ranks the one or more historical data elements based on the similarity score, selects a predetermined number of the one or more historical data elements based on descending rank order, and provides at least one corrective action or at least one part replacement associated with the tag for each of the predetermined number of highest ranked historical data elements in response to the search query. The machine codes are identified for a predetermined time period and each of the one or more historical data elements is associated with a tag.