User-Specific Context Data Structure for Conversational Building Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building management systems face challenges in generating precise data for service operations, as existing data generation methods are often imprecise, require manual intervention, and struggle with handling large amounts of unstructured data.
Innovation Solution
The system employs machine learning models, including language models, to generate data responsive to user prompts, process unstructured data, and present structured outputs, while also enabling real-time messaging and conversational interfaces for technicians.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are used to generate data for service operations, then data generation accuracy and timeliness are improved, but system complexity increases
Solution Approach 1:
The patent introduces a data structure as an intermediary between the machine learning model and the user interface. This data structure stores user-specific context information and enables the system to maintain state across interactions without requiring complex memory management or context tracking mechanisms in the ML model itself.
Solution Approach 2:
The system segments the data generation process into distinct components: the machine learning model generates responses based on prompts, while user-specific context information is stored separately in the data structure. This separation allows the ML model to remain simple and focused on generation, while user personalization is handled by the data structure.
2Manufacturing precision
If user-specific context information is maintained in a data structure, then service operation precision is improved, but data storage requirements increase
Solution Approach 1:
The patent applies local quality by storing user-specific context information only for active users in the data structure, rather than maintaining comprehensive historical data for all users. The data structure stores only the necessary context information (user profile, preferences, interaction history) needed for personalized service operations, minimizing storage requirements while maintaining precision.
3Adaptability or versatility
If machine learning models process unstructured data, then data processing capability is improved, but processing time increases
Solution Approach 1:
The system performs preliminary action by pre-processing and storing user-specific context information in the data structure before service operations begin. This allows the machine learning model to access prepared context data quickly during service operations without performing time-consuming data processing or parsing operations in real-time.
Data Source
AI summary
A method includes generating, using at least one machine learning model, an output responsive to a prompt received via a user interface of a client device, the user interface generated according to an identifier of a user, the prompt indicating a request to retrieve data regarding an item of equipment, the at least one machine learning model configured using training data comprising at least one of structured data or unstructured data regarding one or more items of equipment. The method further includes presenting, using the user interface, the output. The method further includes receiving, via the user interface, an input indicating a selection of the output. The method further includes assigning, responsive to receiving the input, an association between the output and the identifier of the user in a data structure assigned to the identifier of the user.