Adaptive Conversational User Journeys via Dynamic Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conversational user journeys in existing systems are static and lack adaptability, failing to dynamically evolve based on user interactions, which limits their ability to provide a personalized and relevant experience.
Innovation Solution
A computer-implemented method and system that stores user journeys and intents in databases, allowing for dynamic modification of link weightings based on user interactions, enabling the system to evolve and present relevant journeys to users by determining their intents and adapting the journey structure in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If user journeys are made static and fixed in existing systems, then the system structure is simple and easy to manage, but the system lacks adaptability and cannot provide personalized experiences
Solution Approach 1:
The patent implements dynamics by allowing user journeys to evolve over time through weight modifications. Links between intents have associated weights that can be adjusted based on user interactions, enabling the journey to adapt its structure dynamically rather than remaining static. This resolves the contradiction by introducing adaptability while managing complexity through controlled, incremental changes rather than complete redesigns.
Solution Approach 2:
The patent applies parameter changes by modifying the weight values associated with links between intents. These weight parameters can be adjusted based on user behavior patterns, allowing the same journey structure to adapt to different users and contexts. This enables personalization and adaptability without requiring fundamentally different journey structures for each user scenario.
2Reliability
If the system provides detailed and comprehensive user journeys, then the relevance and user engagement are improved, but the system becomes more complex and harder to manage
Solution Approach 1:
The patent implements feedback mechanisms where user interactions with the system are used to modify the weights of links between intents. This feedback loop allows the system to learn from actual user behavior and adjust journey structures to improve relevance. The feedback-driven weight modification enables comprehensive and relevant journeys to emerge organically from user interactions rather than requiring manual creation of every possible scenario.
Solution Approach 2:
The system performs self-service by automatically adjusting journey structures based on aggregated user interaction data. Rather than requiring manual reconfiguration of journeys for each user type, the system self-adapts through weight modifications driven by observed user behavior patterns. This enables comprehensive and relevant personalized journeys while reducing the manual complexity of system management.
3Ease of operation
If the system uses fixed user journeys for all users, then the implementation is simple, but user engagement and personalization are reduced
Solution Approach 1:
The patent applies dynamics by transitioning from static fixed journeys to dynamic adaptive journeys. The same journey framework can adapt its structure based on individual user characteristics and interactions through weight modifications. This enables personalization while maintaining the ease of operation by using a unified framework that automatically adjusts rather than requiring separate manual configurations for different user types.
Data Source
AI summary
A computer-implemented system and method for searching comprises, in an initial training phase, storing a plurality of user journeys in a stored journey database (SJDB), and storing a plurality of intents in a stored intents database (SIDB). The plurality of user journeys comprise a plurality of intents linked together by weighted links. In a first use phase, the method comprises determining a first intent of a first user or a second user, and modifying a first weighting of the weightings based on the first intent. In a second use phase, the method comprises receiving, from the second user, a second user question, determining a second intent from the second user question, and locating a user journey from the plurality of user journeys in the SJDB related to the second intent.