Travel Plan Recommendation via Multi-Dimensional Feature Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing travel plan recommendation methods have low accuracy and poor stability due to the diversity of users and travel environments, failing to meet user requirements.
Innovation Solution
A travel plan recommendation method that generates a travel feature vector based on user persona information, travel mode distribution, current travel environment, and starting/destination point features, which is input into a classification model trained to calculate scores for candidate travel plans, thereby improving recommendation accuracy and stability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional recommendation methods (fastest/lowest cost) are used, then the recommendation process is simple, but the recommendation accuracy and stability are low
Solution Approach 1:
The patent transforms the recommendation approach by changing from simple parameter comparison (time, cost) to multi-dimensional feature vector representation. User preferences, travel modes, environment features, and POI features are converted into vector embeddings that capture nuanced relationships, enabling more accurate recommendations while managing complexity through efficient vector operations
Solution Approach 2:
The patent introduces vector embeddings as an intermediary layer between raw features and recommendation decisions. These embeddings serve as a mediator that transforms discrete features into continuous representations, allowing the system to handle diversity in user preferences and travel environments more effectively while maintaining computational efficiency
2Reliability
If comprehensive user and environment features are considered, then the recommendation accuracy improves, but the computational complexity increases
Solution Approach 1:
The patent merges multiple feature types (user preferences, travel modes, environment features, POI features) into a unified vector space. By combining these diverse features into integrated feature vectors and using attention mechanisms to weigh their relative importance, the system achieves stable recommendations across diverse scenarios without proportionally increasing computational complexity
Solution Approach 2:
The patent implements dynamic feature weighting through attention mechanisms that adaptively adjust the importance of different features based on the specific travel scenario. This dynamic approach allows the system to focus computational resources on the most relevant features for each recommendation, improving stability while managing complexity
Data Source
AI summary
Embodiments of the present disclosure provide a travel plan recommendation method, an apparatus, a device and a computer readable storage medium. In the method according to the embodiments of the present disclosure, the travel plan classification model is obtained by training with the comprehensive consideration of the diversity of users, the diversity of the travel environment in time and space and dynamics of the user's travel preference, and the travel feature vector is generated according to the user persona information and the travel mode distribution information of the user, the current travel environment feature information and the feature information of the starting point and the destination point of the current travel, the travel feature vector is inputted into the travel plan classification model to calculate the scores of the candidate travel plans, and the travel plan recommended to the user according to the scores of the candidate travel plans.