Personalized Application Recommendation System Using Big Data Analytics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The increasing number of mobile applications makes it time-consuming and inefficient for users to select relevant applications, as existing search tools rely on generic parameters like downloads, release dates, and customer ratings, which do not adequately account for user-specific needs.

Innovation Solution

A system utilizing big data analytics to recommend user applications based on past user experiences, location, device usage patterns, and behavior, generating keywords to prioritize applications that match user interests, and displaying them in a user-friendly interface without requiring manual keyword input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If existing search tools are used to sort user applications based on general popularity parameters, then applications can be organized and displayed, but the selection process becomes time-consuming and inefficient

Engineering Contradiction:

Improveapplication selection efficiencyVSAvoidtime required for application selection

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of user data, usage patterns, and application metadata before the user needs to select an application. By pre-processing and storing this information in a structured format, the system can quickly generate personalized recommendations without requiring the user to manually search through large numbers of applications, thus reducing selection time and improving efficiency

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system automatically generates personalized application recommendations based on user behavior patterns, preferences, and contextual information without requiring active user input during the selection process. The system serves itself by autonomously analyzing data and presenting relevant applications, freeing the user from manual searching and sorting operations

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If known search tools sort applications based on generic parameters like downloads and ratings, then applications can be organized, but the results do not adequately account for user-specific needs

Engineering Contradiction:

Improverelevance of application recommendations to user needsVSAvoiduser-specific information utilization

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system transitions from generic, uniform application sorting to localized, personalized recommendations tailored to each user's specific needs. By analyzing individual user behavior patterns, preferences, and contextual data, the system generates customized application lists that reflect the unique requirements of each user, thereby improving relevance and reducing information loss about user-specific needs

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes the sorting parameters from static, generic metrics (total downloads, average ratings) to dynamic, user-specific parameters derived from individual usage patterns, preferences, and contextual information. This parameter transformation enables the system to adapt application recommendations to each user's unique needs while utilizing relevant user-specific information that was previously lost in generic sorting approaches

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9247014B1Methods, devices, and mediums associated with recommending user applications

Publication Date: 2016.01.26 INTELLECTUAL VENTURES FUND 79 LLC

AI summary

A method, device, and/or medium may be associated with identifying user information associated with user behavior and generating keywords based, at least in part, on the user information. The keywords may be compared to metadata associated with user applications, and the user applications may be prioritized according to a correlation of the metadata with the keywords based, at least in part, on the comparison.