Multi-Section Search UI with LLM Chat for Subjective Parameter Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing online systems are ineffective in identifying content based on subjective parameters such as topics or quality of content, as they rely on structured data and lack the ability to understand human intuition.

Innovation Solution

An online system that integrates a chat section with an automated chat system using a large-language model (LLM) to extract parameters from user messages, allowing users to set both quantifiable and subjective search parameters, which are then stored in a parameter data structure to guide content search.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the system uses structured user interface elements for parameter selection, then users can easily set quantifiable search parameters, but the system cannot effectively handle subjective parameters like topics or quality of content

Engineering Contradiction:

Improveease of setting search parametersVSAvoidability to handle subjective parameters

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The user interface is segmented into two distinct sections: a primary section for structured parameter input and a chat section for natural language input. This segmentation allows each section to optimize for its specific function while both contribute to the overall search parameter collection, resolving the contradiction between ease of operation for structured parameters and adaptability for subjective parameters.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent merges the outputs of two different input methods (structured UI elements and natural language chat) into a unified parameter data structure. The LLM processes both structured and unstructured inputs, combining their strengths to handle both quantifiable and subjective parameters effectively, thus resolving the contradiction between operational ease and parameter handling versatility.

Inventive Principle:

Principle #5Merging (Combining)

2Adaptability or versatility

If the system uses a chat section with LLM to extract parameters, then the system can understand subjective parameters, but the complexity of the user interface increases

Engineering Contradiction:

Improveability to extract subjective parametersVSAvoidcomplexity of user interface

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The chat section serves multiple functions: it allows users to input search queries, set subjective parameters, and even correct or refine structured parameter inputs. By making the chat interface multi-functional, the system reduces the need for separate complex interfaces for different parameter types, thereby managing interface complexity while maintaining high adaptability.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The LLM acts as an intermediary between the user's natural language inputs and the system's parameter processing mechanisms. This intermediary layer translates subjective, unstructured user intentions into structured parameter formats that the search system can process, reducing the apparent complexity of handling diverse parameter types without requiring complex direct processing mechanisms.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If the system integrates both chat section and primary section parameters, then the system can surface more relevant search results, but the processing time and computational resources increase

Engineering Contradiction:

Improverelevance of search resultsVSAvoidprocessing time for parameter extraction

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary processing by extracting and structuring parameters from the chat section inputs before they are combined with primary section parameters. The LLM pre-processes natural language inputs into structured formats in advance, so that when parameters are merged and search is executed, the processing burden is reduced, thereby improving result relevance while managing processing time.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250103668A1Multi-sectional user interfaces for LLM-integrated parameter selection for searches

Publication Date: 2025.03.27 NAVAN INC

AI summary

An online system provides a search user interface to users whereby users may search for content through elements in a primary section or through a chat section that interfaces with an automated chat system. The primary section of the search user interface displays the content that the user is searching for and includes user interface elements for setting parameters for the search for content. The chat section includes user interface elements for a chat session between the user and an automated chat system. The search user interface allows the user to set parameters for a search through both the primary section and the chat section of the search user interface. For example, the user may use the parameters elements in the primary section to set quantifiable search parameters while using the chat section to set more subjective search parameters.