Customer Journey Graph Query Re-Ranking for Relevant GUI Suggestions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines often provide results that do not meet user expectations, leading to additional queries and system burden, and existing query suggestion systems can further frustrate users and reduce efficiency.
Innovation Solution
A system that builds a customer journey graph based on historical user activity information to re-rank suggested queries and display them via a graphical user interface, using a composite scoring system to optimize query suggestions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a query suggestion system is employed to provide suggested queries to the user, then the user may receive additional query options, but the results may further frustrate the user and reduce system efficiency
Solution Approach 1:
The system monitors user interactions with search results and suggested queries in real-time, using this feedback to dynamically adjust and re-rank suggestions. This continuous feedback loop ensures that query suggestions adapt to user preferences and behavior patterns, improving relevance while reducing unnecessary computations for poorly performing suggestions
Solution Approach 2:
The system changes the ranking parameters of suggested queries based on observed user behavior patterns and interaction data. By dynamically adjusting relevance scores and display priorities according to actual user preferences rather than static algorithms, the system improves suggestion quality while optimizing computational resource utilization
2Reliability
If search engines provide results that do not meet user expectations, then comprehensive search capabilities are maintained, but additional queries are required burdening the computing system
Solution Approach 1:
The system performs preliminary analysis of user search patterns and behavior during the current session to proactively generate and prioritize query suggestions before the user needs to formulate additional queries. This preliminary action anticipates user needs and provides relevant suggestions in advance, reducing the time required for iterative searching
Solution Approach 2:
The system introduces an intermediary layer between the user's initial query and the search results that actively monitors user interactions and dynamically adjusts query suggestions. This intermediary analyzes user behavior patterns and serves as a mediator to refine and re-rank suggestions in real-time, bridging the gap between initial search intent and actual user needs
3Ease of operation
If existing query suggestion systems display suggested queries, then users receive query alternatives, but user frustration increases and efficiency decreases
Solution Approach 1:
The system transforms static query suggestion displays into dynamic, adaptive interfaces that continuously adjust based on real-time user interactions. Suggested queries are re-ranked and re-prioritized during the user session based on observed behavior patterns, ensuring that the most relevant suggestions are prominently displayed while maintaining operational ease
Solution Approach 2:
The system implements real-time feedback mechanisms that monitor user interactions with suggested queries and search results, using this information to dynamically adjust the display and ranking of future suggestions. This feedback-driven approach ensures that query assistance improves over time while optimizing for actual user efficiency rather than merely providing additional options
Data Source
AI summary
A system including one or more processors and one or more non-transitory computer readable media storing computing instructions that, when executed on the one or more processors, perform: receiving historical in-session user activity information; building a customer journey graph based on the historical in-session user activity information; generating suggested queries based on the customer journey graph; and in response to identifying an input query for a user session of a user: re-ranking the suggested queries; and displaying the suggested queries, as re-ranked, to the user via a graphical user interface (GUI). Other embodiments are described.