Unified Search Interface with ML Filter Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search and filtering systems lack integration of faceted filtering and keyword search within a single interface, leading to a fragmented user experience and inefficiencies in recommending relevant filter fields and values based on user inputs and characteristics.
Innovation Solution
A machine learning model is trained on historical query data to recommend filter fields and values, combining faceted filtering and keyword search, allowing for personalized suggestions based on user inputs and characteristics, and enabling users to select or modify recommended filter fields and values within a unified interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If faceted filtering and keyword search are kept as separate components, then each component can be independently optimized, but the user experience becomes fragmented and the system complexity increases
Solution Approach 1:
The patent combines faceted filtering and keyword search into a unified search interface where both functionalities coexist. The system integrates the filter field selection mechanism with keyword search, allowing users to perform both operations in a single unified search experience rather than switching between separate components.
2Measurement precision
If traditional keyword search is used without filter recommendations, then the search interface remains simple, but the relevance and precision of search results decrease
Solution Approach 1:
The system performs preliminary actions by automatically analyzing the user's search query and pre-selecting relevant filter fields and values based on the query context. This preliminary filtering recommendation occurs before the user finalizes their search, improving result relevance without requiring the user to manually explore multiple filter options.
Solution Approach 2:
The patent introduces an intermediary component that acts as a bridge between the user's keyword search and the filter application. This intermediary automatically suggests filter fields and values that match the search query, mediating between simple keyword input and complex filtered results, thereby improving precision without fully exposing the complexity to the user.
3Productivity
If manual filter selection is required for all searches, then filter application precision is high, but the time required to obtain search results increases
Solution Approach 1:
The system performs preliminary filter selection by automatically analyzing the search query and pre-recommending appropriate filter fields and values. This preliminary action occurs in the background before the user finalizes their search, significantly reducing the time required to obtain relevant search results while maintaining high precision through intelligent filter recommendations.
Data Source
AI summary
Techniques for suggesting a filter field based on a user input are disclosed. A system trains a machine learning model by obtaining historical data including sets of user search input, including a first search term and a first value for a first filter field. Based on the historical data, the system trains the machine learning model to associate the first filter field with the first search term. The system receives a first query for execution. The system applies the machine learning model to the first query to identify the first filter field as a suggestion. The system: recommends the first field for filtering a first set of search results corresponding to the first query. Responsive to receiving user input selecting a first value for the first filter field, the system filters using the first value to generate a set of filtered search results, and presents the filtered search results.