Personal Assistant Function Sequence Recommendation via Task Flow Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The vast number of available app functions makes it difficult for users to find and access the desired functionalities, as existing recommendation systems typically recommend single app functions rather than functional sequences, which are often needed to fulfill user intentions.
Innovation Solution
A method and system that utilize user intention analysis, task flow graphs, and function flow graphs to recommend optimal function sequences based on user usage data, employing graph theoretical algorithms to derive and rank function sequences for personalized recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If direct access to functions is provided to users, then user convenience is improved, but the tremendous number of functions makes it very hard to perform
Solution Approach 1:
The patent introduces a recommendation system as an intermediary between users and the vast number of app functions. This system analyzes user intentions, historical behavior data, and function relationships to generate personalized function sequences, thereby mediating the complexity gap between users and the overwhelming number of available functions while maintaining ease of access
2Device complexity
If existing recommendation systems recommend single function pages or apps, then recommendation simplicity is maintained, but it makes it even harder for the user to find desired apps
Solution Approach 1:
The patent segments the user intention into multiple tasks and organizes functions into structured sequences rather than recommending single isolated functions. By dividing the recommendation into task-level components and arranging them in logical sequences, the system provides a more comprehensive solution that helps users find complete workflows while maintaining manageable recommendation structures
Solution Approach 2:
The patent transitions from recommending single functions (one-dimensional) to recommending function sequences (multi-dimensional). By adding the temporal and logical sequence dimension to function recommendations, the system provides users with ordered workflows that better reflect real-world task completion patterns, making it easier to find desired apps and functions in context
Data Source
AI summary
A method is provided for recommending a desired func sequence to a user. The method includes obtaining a user intention list including at least one user intention; separating the user intention into a plurality of tasks; and creating a task flow graph for the plurality of tasks based on user usage data. Each vertex in the task flow graph represents a task and indicating an importance of the task. The method also includes creating a func flow graph based on the user usage data and temporal sequences of the tasks and funcs, and each vertex in the func flow graph represents a func and indicating an importance of the func. Further, the method includes determining a desired func sequence to fulfill the user intention based on the user usage data, the task flow graph, and the func flow graph; and recommending the desired func sequence to the user.