Chat-Powered Search Query Refinement for Relevant Asset Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional search engines struggle to provide relevant image results due to users' inability to articulate complex search intents effectively, leading to irrelevant or no results, despite advancements in vector-based search technologies.
Innovation Solution
A chat-powered search system using AI that engages users in an interactive conversational process to refine search queries, leveraging a large language model to elicit detailed information and construct precise search queries that align with user intent.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional keyword matching search is used, then the search system is simple and fast, but the search results are irrelevant or do not align with user intent
Solution Approach 1:
The patent introduces a chatbot as an intermediary between the user and the search system. The chatbot engages users in conversation to elicit additional details about their search intent, then uses these refined details to construct more precise search queries. This mediator resolves the contradiction by improving search relevance through natural language interaction without requiring complex changes to the underlying search infrastructure.
Solution Approach 2:
The system performs preliminary actions by engaging users in a conversational process before executing the actual search. Through the chatbot, the system proactively solicits additional information about user needs, preferences, and context, preparing a refined search query in advance. This preliminary information gathering enables more accurate search results without increasing the complexity of the search engine itself.
2Measurement precision
If users provide detailed search queries, then the search results are more relevant, but users struggle to articulate their search intent effectively
Solution Approach 1:
The chatbot enables users to self-serve by guiding them through a conversational process that helps them articulate their own search intent more clearly. Through natural language interaction, the system prompts users to provide additional details they may not have initially considered, allowing users to independently refine their search queries without requiring expertise in search optimization or complex query formulation.
Solution Approach 2:
The system implements feedback mechanisms where the chatbot responds to user inputs by asking clarifying questions and guiding users to provide more specific information. This iterative conversational feedback loop helps users progressively refine their search intent, transforming vague initial queries into precise search criteria through natural dialogue rather than requiring users to manually construct complex queries.
3Measurement precision
If vector-based search technologies are used, then the system can understand context and meaning, but crafting effective queries remains challenging for users
Solution Approach 1:
The chatbot serves as an intermediary that bridges the gap between users and vector-based search technology. It translates users' natural language inputs into refined search queries that leverage the contextual understanding capabilities of vector-based search, without requiring users to understand or manually craft complex vector queries. The chatbot handles the complexity of query formulation while users simply engage in natural conversation.
Solution Approach 2:
The system replaces the mechanical process of manual query crafting with an automated conversational agent. Instead of requiring users to manually construct complex search queries that leverage vector-based search capabilities, the chatbot automatically engages users in dialogue, extracts relevant information, and formulates optimized search queries using natural language processing and machine learning techniques.
Data Source
AI summary
Methods, systems, and storage media for refining search queries through interactive conversational exchange are disclosed. Exemplary implementations may receive a first search input from a user describing a desired asset such as an image. Aspects implementations may also interact with the user via a chat interface to solicit additional details about the desired asset in response to the first search input, construct a search query based on the first search input and the additional details solicited from the user, and submit the search query to a search service to retrieve relevant asset data for the user.