Building Service Data Coupling for Accurate AI Equipment Diagnostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building management systems face challenges in generating precise data for responding to equipment issues due to the complexity of interactions between equipment, users, and technicians, with existing AI systems often producing incorrect or irrelevant data that requires manual input adjustments and lacks integration with diverse data sources.
Innovation Solution
A system utilizing machine learning models, including generative AI, to process unstructured service data from various sources, such as engineering and operational data, to identify patterns and generate structured outputs for precise equipment servicing, leveraging ontological models and digital twins for data integration and correlation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If existing AI systems are used to generate data for equipment servicing, then data generation speed is improved, but data accuracy and relevance deteriorate
Solution Approach 1:
The patent introduces unstructured service data (technician observations, photos, videos) as an intermediary to bridge equipment data and user information. This intermediary enables existing AI systems to generate relevant data by processing real-world service context, thereby maintaining data generation speed while improving accuracy through ground-truth information from actual service scenarios.
Solution Approach 2:
The system implements feedback loops where service data from technicians is continuously collected and used to train and refine AI models. This feedback mechanism allows the AI systems to learn from actual service outcomes and improve data generation accuracy over time while maintaining efficient automated processing.
2Measurement precision
If manual input adjustments are required for AI-generated data, then data accuracy is improved, but time consumption increases
Solution Approach 1:
The system enables self-service by allowing AI models to automatically generate service data with high accuracy through training on unstructured service data. The models autonomously process equipment data and generate relevant service information without requiring manual adjustments, thereby maintaining data accuracy while eliminating time-consuming manual intervention.
Solution Approach 2:
The system performs preliminary action by pre-training AI models on extensive unstructured service data before actual service operations. This preliminary training equips the models with the knowledge to generate accurate data automatically, preventing the need for manual adjustments during time-critical service situations.
3Measurement precision
If diverse data sources are integrated for comprehensive equipment analysis, then diagnostic accuracy is improved, but system complexity increases
Solution Approach 1:
The patent segments diverse data sources into distinct categories: equipment data (structured), service data (unstructured), and user information. Each segment is processed by specialized AI models trained for specific data types, reducing overall system complexity while maintaining comprehensive diagnostic capability through modular architecture.
Solution Approach 2:
The system implements multi-functionality by using a unified AI platform that processes multiple data types (structured and unstructured) through various model architectures. This universal approach consolidates diverse data processing capabilities into a single system, reducing complexity compared to having separate systems for each data type while maintaining comprehensive diagnostic accuracy.
Data Source
AI summary
A method includes receiving, by one or more processors, unstructured service data corresponding to one or more service requests handled by technicians for servicing building equipment of a building. The method may include detecting, by the one or more processors, an identifier of the building equipment, a space of the building, or a customer associated with the building using the unstructured service data. The method may include retrieving, by the one or more processors based on the identifier of the building equipment, the space, or the customer, additional data associated with the building equipment, the space, or the customer from one or more additional data sources separate from the unstructured service data. The method may include training, by the one or more processors, a generative AI model using training data including the unstructured service data and the additional data.