Conversational Interface for Building Automation Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building automation systems (BAS) face challenges in user interaction, requiring extensive training due to complex navigation and data filtering, leading to frustration and inefficiency, especially for new users who need to repeatedly access and manage data from multiple menus and pages.
Innovation Solution
A conversational user interface that responds naturally to user inputs, determining context and parameters such as user ID, location, and desired actions, allowing for customized and efficient interactions, including natural dialogue and adaptive responses based on user skill level and access rights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional BAS user interface with multiple menus and pages is used, then comprehensive data access is achieved, but user interaction complexity and training requirements increase
Solution Approach 1:
The patent introduces a conversational interface (chatbot) as an intermediary between the user and the complex BAS system. This intermediary translates natural language user intents into system commands and retrieves data through multiple internal processing layers, shielding users from the underlying complexity while maintaining comprehensive data access capabilities.
Solution Approach 2:
The patent replaces the traditional mechanical navigation through menus and pages with a natural language processing system. Instead of requiring users to physically navigate through hierarchical interfaces, the system uses speech recognition and natural language understanding to interpret user requests and execute appropriate actions directly.
2Loss of information
If comprehensive data access through multiple menus is provided, then complete information retrieval is achieved, but time consumption and user frustration increase
Solution Approach 1:
The system performs preliminary actions by maintaining context across conversation turns and pre-processing user intents. The conversation history is analyzed and stored, allowing the system to anticipate follow-up questions and retrieve related data proactively without requiring users to navigate through multiple menus for each piece of information.
Solution Approach 2:
The conversational interface serves multiple functions simultaneously: it can query sensor data, control equipment, provide system status, and answer historical questions all through a single unified interface. This multi-functional approach eliminates the need for users to switch between different menus and pages for different types of data access.
3Reliability
If standardized BAS interface is used, then system stability is maintained, but adaptability to different user skill levels decreases
Solution Approach 1:
The conversational interface dynamically adapts its responses and information depth based on user skill level detection. The system analyzes user questions and adjusts the complexity of explanations, the level of technical detail provided, and the types of suggestions offered, all while maintaining stable underlying system operations and data access protocols.
Solution Approach 2:
The system incorporates feedback mechanisms that monitor user interactions and adjust its behavior accordingly. By analyzing user questions, response patterns, and correction feedback, the system adapts to individual user skill levels and preferences, providing appropriate levels of detail and guidance while maintaining system stability through consistent core functionality.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system for user interaction with a building automation system (BAS). The system includes a user device configured to accept vocal inputs and produce audio outputs, and a server in communication with the user device and a BAS controller. The server is configured to translate a vocal input to input text, and determine and store a conversation context based on the input text. The server is further configured to determine a desired output corresponding to the input text. Additionally, the server is configured to receive, from the BAS controller, BAS data corresponding to the desired output, and generate at least one audio output from the BAS data. The user device outputs the at least one audio output, and the server is configured to apply the conversation context to a subsequent vocal input.