Adaptive Browser Tab Loading via User Behavior Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing browser technologies load pages in either the current tab or a new tab, failing to adaptively adjust based on user usage habits, leading to complex operations and inefficient browsing experiences.
Innovation Solution
A page loading method that collects user history browsing behaviors, trains a learning model to determine the correspondence between visited pages and browsing manners, and adaptively selects the loading manner for each page based on the trained model, allowing pages to be loaded in either the current or new tab according to user habits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the browser fixedly loads the search result in the current tab or new tab, then the page loading manner is simple, but the browsing efficiency and user experience deteriorate due to inability to adapt to user habits
Solution Approach 1:
The browser automatically learns and adapts to user browsing habits through the trained model, making decisions about tab loading without requiring user intervention. The system collects historical browsing data, trains a learning model to predict user preferences, and automatically applies these predictions to determine whether to load pages in current or new tabs, thereby improving browsing efficiency while maintaining operational simplicity.
Solution Approach 2:
The browser dynamically changes the page loading parameter (current tab vs. new tab) based on the prediction output from the trained model. Instead of using a fixed loading manner, the system adjusts the loading behavior parameter according to learned user preferences for different webpage types, search engines, and contexts, thereby optimizing browsing efficiency without requiring complex manual configuration.
2Adaptability or versatility
If the browser provides fixed loading options, then the operation process is simple, but the adaptability to different user habits deteriorates
Solution Approach 1:
The browser performs self-learning by automatically collecting browsing history data and training the model without user intervention. The system autonomously identifies user preferences for different webpage types and search engines, then applies this knowledge to adaptively determine loading behavior. This self-service approach enables high adaptability to user habits while keeping the operation process simple and transparent to the user.
Solution Approach 2:
The system continuously collects feedback from user browsing behaviors and uses this feedback to refine the trained model's predictions. By monitoring which loading choices users make and correlating them with webpage characteristics, the model learns and adapts to user preferences over time, improving adaptability while maintaining ease of operation through automatic adjustment.
3Ease of operation
If manual selection of tab loading is required, then the loading mechanism remains simple, but the user operation becomes complex and time-consuming
Solution Approach 1:
The browser performs preliminary learning by collecting browsing history data and training the model in advance, so that when a user clicks a search result, the appropriate tab loading decision is already determined by the pre-trained model. This preliminary action eliminates the need for real-time user selection, reducing operation complexity and saving time during actual browsing activities.
Solution Approach 2:
The system automatically makes tab loading decisions without requiring user input or selection. By leveraging the trained model to predict user preferences and automatically applying these predictions, the browser eliminates the manual selection step entirely, thereby simplifying operations and reducing the time users spend on tab management while improving overall browsing efficiency.
Data Source
AI summary
The present disclosure provides a page loading method and an electronic device. The method includes: collecting history browsing behaviors of a user during using a browser, and obtaining visited pages involved in the history browsing behaviors and browsing manners used by the user; training a learning model based on the visited pages and the browsing manners used by the user, such that the learning model learns a correspondence relationship between the visited pages and the browsing manners; in response to receiving a page visiting request, analyzing a target page to be visited based on the trained learning model, so as to determine a target browsing manner from the manner of browsing in a current tab and the manner of browsing in a new tab; and loading the target page according to the target browsing manner.