AI Chat Assistant Determining Workplace Accommodations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional job-search platforms do not consider workplace accommodations for individuals with disabilities, limiting their ability to find suitable job opportunities.
Innovation Solution
An artificial intelligence model integrated into an automated chat assistant determines workplace accommodations by using multiple large language models (LLMs) to analyze queries, rephrase them based on chat history, identify relevant accommodations, and formulate responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional job-search platforms are used, then job searching is simple and accessible, but workplace accommodations for individuals with disabilities are not considered
Solution Approach 1:
An automated chat assistant serves as an intermediary between users and the job-search platform, handling accommodation-related queries and information delivery. The chat assistant processes natural language questions about workplace accommodations and retrieves relevant information from the knowledge base, shielding users from the underlying system complexity while providing specialized accommodation information.
Solution Approach 2:
The system segments accommodation information into structured knowledge bases organized by disability type, accommodation category, and job role. This segmentation allows the chat assistant to efficiently retrieve and present relevant accommodation information without requiring users to navigate complex databases, thereby enhancing adaptability while managing complexity.
2Measurement precision
If multiple large language models are used to determine accommodations, then accommodation recommendation accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-processing and structuring accommodation information into organized knowledge bases before user queries arrive. Accommodation data is pre-categorized by disability type, accommodation category, and job role, allowing the chat assistant to quickly retrieve and combine relevant information without requiring extensive real-time computation for each query.
Solution Approach 2:
The system extracts only the most relevant accommodation information from the knowledge base based on the user's specific query and context. Rather than processing all accommodation data, the chat assistant identifies and retrieves only the necessary subset of information related to the user's disability type and accommodation needs, reducing processing time while maintaining accuracy.
Data Source
AI summary
A computer-implemented method including determining whether a query is part of a conversation having a chat history before the query. When the query is part of the conversation, the method can include rephrasing the query, using a first large language model (LLM), based on context from the chat history. The method also can include determining, using a second LLM, whether or not the query is related to accommodations or disabilities. When the query is related to accommodations or disabilities, the method further can include determining one or more accommodations responsive to the query using a third LLM; and formulating a response to the query using a fourth LLM based on the one or more accommodations. Other embodiments are described.