Personalized Query Response System Using User Preference Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional question and answer systems provide uniform search results for the same query regardless of user differences, failing to consider individual user preferences and characteristics.
Innovation Solution
An electronic apparatus and method that determine keywords from user queries, incorporate user preference information to select relevant words from hierarchical structures, and update scores based on user interactions to provide tailored search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional question and answer systems provide uniform search results for the same query, then the system structure remains simple, but user satisfaction and relevance deteriorate due to inability to consider individual user preferences
Solution Approach 1:
The system performs preliminary actions by storing user preference information in advance and using it to pre-filter and rank search results before the user actually queries. This allows the system to adapt to user preferences without adding complex real-time processing during the query execution phase.
Solution Approach 2:
The patent introduces user preference information as an intermediary element that mediates between the query and the search results. This intermediary layer allows the system to personalize results without fundamentally changing the core search architecture, thus maintaining simplicity while improving adaptability.
2Ease of operation
If the system provides personalized search results based on user preferences, then user satisfaction improves, but the number of processing steps and system complexity increases
Solution Approach 1:
The patent segments the search process into distinct phases: preference extraction, preference storage, query processing, and result generation. By segmenting the complexity into separate modules, the system can personalize results without overwhelming processing complexity in any single phase.
Solution Approach 2:
The system performs self-service by automatically extracting and storing user preference information without requiring explicit user input or configuration. This automation reduces the operational burden on users while managing the complexity internally through automated preference learning mechanisms.
3Measurement precision
If the same search results are provided for identical queries from different users, then the system operation remains simple, but information relevance deteriorates as it fails to account for individual user characteristics
Solution Approach 1:
The patent applies local quality by tailoring search results to individual users based on their specific preferences and characteristics. Instead of providing uniform results for all users, the system adjusts the quality and relevance of results locally for each user, improving measurement precision without requiring complete system redesign.
Data Source
AI summary
An electronic apparatus and a controlling method thereof are provided. The electronic apparatus includes a memory configured to store at least one instruction, and a processor configured to execute the at least one instruction to control the electronic apparatus to: determine a keyword from a query based on the query being input, obtain a word related to the keyword based on information on a user preference, and provide a response to the user query based on the keyword and the word. The processor may be configured to control the electronic apparatus to obtain at least one word from among a plurality of candidate words corresponding to the keyword as a word related to the keyword based on the user preference information. For example, at least part of a method of providing a response to a query by the electronic apparatus may use an AI model that is trained using at least one of machine learning, neural network or deep learning algorithm.