Dialogue-Based Recommendation System for Ambiguous User Intent
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Internet shopping sites fail to effectively determine user preferences and provide personalized recommendations, as they lack the ability to infer user preferences from ambiguous search terms and do not engage users in dialogue to understand their preferences, leading to inadequate presentation of relevant commodities.
Innovation Solution
An information provision system that includes an input reception device, a response determination device, and a user type determination device, which engages users in dialogue to determine their preferences and presents relevant commodities based on user type, category selection, purchase history, and attributes, updating user types as preferences change over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing recommendation functions present commodities purchased by other users, then commodities can be presented to users, but user preferences and attributes cannot be determined, leading to inadequate personalization
Solution Approach 1:
The system implements feedback loops where user responses to recommendation questions are continuously analyzed to refine user type determination. The natural language processing component processes user feedback in real-time, adjusting preference profiles and improving future recommendation accuracy based on accumulated interaction data
Solution Approach 2:
The patent introduces an intermediary natural language processing system that mediates between the recommendation engine and user preferences. This intermediary extracts semantic meaning from ambiguous user inputs, enabling accurate preference determination without requiring users to directly articulate their preferences
2Measurement precision
If the system engages users in dialogue to determine preferences, then user preferences can be accurately determined, but system complexity increases
Solution Approach 1:
The natural language processing component serves multiple functions simultaneously: it parses user input, determines user type, extracts preferences, and generates appropriate responses. This multi-functional approach reduces overall system complexity by consolidating what could be separate modules into a single versatile processing unit
Solution Approach 2:
The system automatically analyzes user responses and updates preference profiles without requiring manual intervention or complex configuration. The self-service nature of the preference determination process reduces operational complexity while maintaining high accuracy through automated natural language analysis
3Manufacturing precision
If the system presents recommended commodities based on user type, then recommendation quality improves, but processing time increases due to dialogue and analysis
Solution Approach 1:
The system performs preliminary user type determination and preference analysis during initial user interactions, establishing a baseline profile before full recommendation processing is needed. This preliminary action reduces processing time for subsequent recommendations by having preference data pre-analyzed and ready
Solution Approach 2:
The system dynamically adjusts processing parameters based on user engagement level and interaction history. For highly engaged users with established profiles, the system reduces analysis depth and processing time, while allocating more resources to new or less engaged users who require more comprehensive preference determination
4Adaptability or versatility
If the system analyzes ambiguous search words through inference, then relevant commodities can be presented, but measurement precision of user intent decreases
Solution Approach 1:
The system uses feedback from user responses to ambiguous search queries to refine intent interpretation. By analyzing how users respond to initial recommendations based on inferred intent, the system adjusts its inference algorithms to improve accuracy over time, turning ambiguous inputs into progressively more precise understanding
Data Source
AI summary
Provided is an information provision system which determines preference of a user based on a dialogue with the user utilizing an Internet shopping site and determines a recommended commodity based on the determined preference. An information provision server in an information provision system receives utterance (input) by a user utilizing an Internet shopping site via a user terminal and provides a response thereto onto the user terminal, thereby performing control so as to have a conversation with the user. Further, based on the input by the user and user attributes, the information provision server determines a user type of the user and when a recommended commodity is presented to the user, determines the recommended commodity from among commodities purchased by other user whose user type is the same as the user type of the user.