Local ML Relevance Scoring for Mobile Data Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile electronic devices have limited screen real estate, making it difficult for users to find relevant information without extensive interaction, as existing technologies lack efficient methods for determining and presenting relevant data locally on the device.
Innovation Solution
The system employs a locally stored machine learning model on the user device to provide relevance scoring and ranking of data, using input signals from the user's environment and historical behavior to determine the relevance of information without relying on server facilitation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If information is displayed on a mobile electronic device with a small screen, then the device can provide information to the user, but the amount of information that can be displayed is limited and users need to interact extensively to find relevant information
Solution Approach 1:
The system performs preliminary actions by continuously monitoring user interactions and pre-determining relevant information before the user needs it. The machine learning model analyzes user behavior patterns in advance and prepares relevant information for immediate display, eliminating the need for users to extensively search through applications.
Solution Approach 2:
The system enables self-service by automatically determining and displaying relevant information based on user behavior without requiring active user search or interaction. The device serves itself by using its own monitored interaction data to train the machine learning model, which then autonomously selects and presents relevant information.
2Reliability
If a machine learning model is used to determine relevant information locally, then relevance scoring and ranking can be performed without server facilitation, but the device complexity increases
Solution Approach 1:
The system extracts the machine learning model from the server environment and places it locally on the mobile device. This extraction enables the device to independently perform relevance scoring and ranking operations without relying on server facilitation, thereby improving reliability and enabling offline functionality.
Solution Approach 2:
The system changes the operational parameters of the machine learning model by adapting it to run on resource-constrained mobile devices. The model is optimized to work with the specific hardware limitations of mobile devices while maintaining its ability to perform complex relevance determination tasks locally.
Data Source
AI summary
A system for determining relevant information based on user interactions may include a processor configured to receive data and associated relevance information from a data source and a set of signals describing a current environment of a user or historical user behavior information in which the data source being local to a computing device. The processor may be further configured to provide, using a machine learning model, a relevance score for each of multiple data items based at least in part on the received relevance information and the set of signals. The processor may be further configured to sort the data items based on a ranking of each relevance score for each data item. The processor may be further configured to provide, as output, the multiple data items based at least in part on the ranking.