Information Pushing Using User Behavior Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information push systems often deliver irrelevant information to users, as they lack personalization and relevance, pushing unnecessary event or advertisement information alongside subscribed content.
Innovation Solution
A method and apparatus that analyze user search and browsing records to determine keywords, matching them with a preset information stream data set using probability models, and generate targeted data for push notifications based on user preferences and behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the server pushes other information (event information, advertisement information) to the user in addition to subscribed information stream data, then the information quantity increases, but the relevance and pertinence of the information decreases
Solution Approach 1:
The patent applies local quality by analyzing user-specific attributes (search history, browsing behavior, device type, browser type) to determine personalized push strategies for each user. The system dynamically adjusts which information to push based on local user characteristics rather than applying a uniform push strategy to all users, thereby maintaining information relevance while increasing quantity.
Solution Approach 2:
The system changes parameters by using probability determination models that calculate the likelihood of user interest based on multiple factors (account information, device type, browser type, search history, browsing records). These parameter changes enable the system to dynamically adjust information push relevance, selecting and presenting information that matches user preferences and behavior patterns.
2Device complexity
If the server pushes generic information to all users, then the system complexity is low, but the user experience and information pertinence deteriorate
Solution Approach 1:
The system performs preliminary action by pre-collecting and storing user attribute data (search history, browsing records, device information, browser type) before the information push occurs. Probability determination models are pre-trained based on historical data, enabling the system to quickly and accurately personalize information pushes without complex real-time processing, thus improving user experience while controlling system complexity.
Solution Approach 2:
The system implements feedback mechanisms by analyzing user interactions with pushed information and using this data to refine probability determination models. The models learn from user behavior patterns (clicks, views, searches) to continuously improve the accuracy of information selection, creating a closed-loop system that enhances user experience over time while maintaining manageable complexity through automated learning.
Data Source
AI summary
Embodiments can include an information pushing method and device. An embodiment of the method can include: receiving an information stream data acquisition request sent by a terminal, wherein the information stream data acquisition request comprises query information; performing a query according to the query information to obtain first information stream data; acquiring at least one of a search record or a browsing record of an account associated with the terminal with respect to a predetermined time period; determining, based on the at least one of the search record or the browsing record, a keyword; determining second information stream data located in a preset information stream data set and matching the key word; generating, based on the first information stream data and the determined second information stream data, data to be pushed; and pushing to the terminal the data to be pushed. The embodiment can achieve targeted information pushing.