Web Popularity Ranking via Textual Analysis and Query Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
TV content recommendation systems face challenges in acquiring first-hand popularity data for content entities, especially when they have limited knowledge of user past activities, and struggle to accurately update recommendations as popularity changes over time.
Innovation Solution
A computer-implemented method that performs textual analysis on predefined websites to identify reference web pages and search queries, determining content information and user interactions to calculate popularity rankings for content entities, which are then used to select content for display based on their popularity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual approaches are used to acquire popularity data, then data accuracy is improved, but the process becomes expensive and time-consuming
Solution Approach 1:
The patent replaces manual data collection methods with automated web crawling and data processing systems. The system automatically queries multiple data sources, parses web pages, and extracts popularity metrics without human intervention, thereby maintaining data accuracy while dramatically reducing time and cost requirements.
Solution Approach 2:
The system creates and maintains copies of popularity data from multiple external web sources simultaneously. By querying and caching data from various data providers in parallel, the system obtains comprehensive popularity information efficiently without relying on slow manual verification processes.
2Measurement precision
If the system waits for logged data to accumulate, then recommendation accuracy is improved, but the system cannot make accurate recommendations initially
Solution Approach 1:
The system performs preliminary actions by proactively collecting and processing popularity data from external web sources before any user interactions occur. This allows the system to build an initial recommendation capability using third-party popularity metrics, enabling it to provide accurate recommendations immediately upon launch rather than waiting for user data to accumulate.
Solution Approach 2:
The system uses third-party popularity data as an intermediary to bridge the gap during the cold start period. Instead of relying directly on user interaction data that doesn't yet exist, the system leverages external popularity signals from data providers as a mediator to generate initial recommendations, which are then refined as user data becomes available.
3Reliability
If comprehensive popularity data is collected from all sources, then recommendation quality is improved, but system complexity increases
Solution Approach 1:
The patent segments the data collection and processing system into distinct modular components: multiple independent data source queries, individual web page parsers for different data providers, and separate popularity metric calculation modules. This segmentation allows the system to handle comprehensive data from multiple sources while maintaining manageable complexity through clear separation of concerns and independent processing pipelines.
Data Source
AI summary
A computer-implemented method for ranking content entities by their associated web pages and search queries is disclosed. The method comprises: at a computer system having memory and one or more processors: performing a textual analysis on one or more predefined websites to identify a plurality of reference web pages, further including determining content information and one or more search queries for each reference web page; for a respective content entity: identifying a subset of the reference web pages and the corresponding search queries based on the content information of the reference web pages and query terms of the corresponding search queries; and determining a popularity ranking for the respective content entity based on user interactions with the identified subset of reference web pages and the corresponding search queries; and selecting at least a subset of the content entities for display to an end user in accordance with their respective popularity rankings.