IoT-Based Search Result Positioning for Whole Page Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern search engines fail to optimize the placement of search results beyond static ranking, resulting in suboptimal whole page relevance, as they do not consider data from Internet of Things (IoT) devices that users interact with, which can provide valuable context for improving user interaction efficiency.
Innovation Solution
Collect and process data from IoT devices to create an IoT entity index, using trained machine learning models to enhance ranking and positioning of search results based on user-specific IoT features, thereby improving whole page relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If static ranking methods are used for search results, then the implementation is simple and fast, but the whole page relevance is suboptimal
Solution Approach 1:
The patent segments the search result processing into multiple independent components: static ranking layer, IoT feature extraction layer, machine learning model layer, and positioning layer. Each component handles specific tasks independently, allowing the system to achieve high whole page relevance through layered processing while maintaining implementation simplicity at each stage.
Solution Approach 2:
The patent performs preliminary extraction and processing of IoT device features before the actual ranking process. By pre-processing user context data from IoT devices and creating feature representations in advance, the system prepares personalized context information that enhances relevance without adding complexity during the real-time ranking execution.
2Adaptability or versatility
If IoT device data is collected and processed, then user-specific context is obtained for better personalization, but data processing complexity increases
Solution Approach 1:
The patent creates a universal IoT entity index that serves multiple functions: it stores user context information, provides features for ranking models, and supports various types of personalization queries. This multi-functional index structure enables the system to handle diverse personalization needs through a single processed data repository, reducing overall data processing complexity.
Solution Approach 2:
The patent introduces an intermediary machine learning model that transforms raw IoT device data into standardized feature representations. This intermediary layer processes and normalizes data from various IoT devices, converting heterogeneous user context information into a unified format that can be efficiently used by the ranking system without requiring complex handling of raw device data.
3Measurement precision
If machine learning models are used for ranking, then positioning accuracy is improved, but computational resources increase
Solution Approach 1:
The patent applies partial action by using machine learning models selectively - primarily for re-ranking and positioning the top candidate results rather than processing all search results. This approach achieves high positioning accuracy for the most relevant results while avoiding the excessive computational cost of applying complex models to every single result, thus optimizing resource consumption.
Data Source
AI summary
Representative embodiments disclose mechanisms to assign search results associated with a user query to locations based in part on features associated with the user's Internet of Things (IoT) devices. This results in a search page that presents results in an order and prominence that improves user understanding and information accessibility. Features from IoT devices are used to train a machine learning model that receives as an input information from an IoT entity index, the query, and results from the search engine along with their static rankings. The resultant IoT positioning scores are used to assign an initial location on the search results page. A second machine learning model trained using IoT features is then used to assign a final location on the page. The system causes display of the page to the user.