Local User Profile Filtering for Message Relevancy and Privacy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing message delivery systems fail to maximize the relevance and receptiveness of messages, particularly advertisements, as they rely on user profiling and activity tracking, which can compromise privacy and may not adapt effectively to real-time user contexts.

Innovation Solution

A method that determines a user's profile locally on their device, considering time, location, and event modes, filters messages based on user interest levels, and updates profiles in real-time without requiring server communication, ensuring privacy and relevance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If user profiling and activity tracking are performed on servers, then message selection can be based on comprehensive user data, but user privacy is compromised and data security risks increase

Engineering Contradiction:
Improvemessage relevancyVSAvoidprivacy compromise
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent extracts the user profiling and message selection functionality from the server and relocates it to the end-user device. The device locally determines user profiles based on collected data and selects messages without transmitting personal information to the server, thereby maintaining message relevancy while eliminating privacy compromises associated with server-based processing

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The end-user device performs self-service by autonomously determining user profiles and selecting messages based on locally stored data. The device independently evaluates message relevancy using its own resources and logic, eliminating the need for server intervention and ensuring that personal data remains private while still achieving accurate message selection

Inventive Principle:
Principle #25Self-service

2Adaptability or versatility

If real-time adaptation to user context is implemented, then message receptiveness increases, but system complexity increases due to continuous profile updates and local processing

Engineering Contradiction:
Improvereal-time adaptationVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by pre-defining user profiles with multiple parameters (demographic data, interests, location, time preferences) and storing them locally on the device. These pre-configured profiles enable rapid real-time adaptation without requiring complex on-the-fly computations, as the device simply matches incoming messages against pre-existing profile structures

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent segments the user profile into distinct parameters and categories (demographic information, interests, location data, temporal preferences). This segmentation allows the system to handle real-time adaptation through modular comparisons of individual parameters rather than processing complex holistic data structures, reducing computational complexity while maintaining adaptability

Inventive Principle:
Principle #1Segmentation

3Object-affected harmful factors

If all data processing occurs locally on the device, then user privacy is protected, but the device requires higher computational resources and storage capacity

Engineering Contradiction:
Improveprivacy protectionVSAvoidcomputational resources
Core Design Contradiction:
Object-affected harmful factorsVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by processing only the minimal necessary data locally - specifically, user profile parameters and message metadata - rather than processing all possible data types. The device maintains privacy by keeping personal information local while using computational resources efficiently by focusing calculations only on the specific parameters needed for message selection, such as matching user interests with message categories

Inventive Principle:
Principle #16Partial or excessive action

4Measurement precision

If continuous profile updates are performed, then message relevancy is maintained, but data communication requirements increase

Engineering Contradiction:
Improvemessage relevancyVSAvoiddata communication
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The device performs self-service by continuously updating its own user profile based on local observations of user behavior and context without requiring server communication. The device autonomously monitors user interactions, location changes, and temporal patterns to dynamically refine profiles, eliminating the need for continuous data transmission while maintaining high message relevancy through localized adaptive learning

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP2391090B1System and method for increasing relevancy of messages delivered to a device over a network
Publication Date: 2013.08.21 PRIMVISION
  • EP2391090B1 patent drawingFigure 1~2
  • EP2391090B1 patent drawingFigure 3
  • EP2391090B1 patent drawingFigure 4

AI summary

System and method for increasing relevancy of messages delivered to a device over a network Prim'Vision A system for increasing relevancy of messages delivered to a device (100) over network (300), characterized in that the device (100) comprises: ● a profile module (110) arranged for determining a user's profile, the user's profile comprising: a plurality of classes; a least a level of interest associated to each class, the level of interest depending on the class and on at least one of the following parameters: the time, the place of the user, an event mode, the event mode indicating if a detected event must be initiated by an application of the device (100) itself or if a detected event must be initiated by the user or by another device, ● a profile file comprising storage means for storing said user's profile; ● reception means (102) for receiving from a server via a network (300) messages, each message comprising a content and a header, the header comprising a class that relates to the content; the profile module (110) being arranged for: ● defining from the user's profile a probability of interest associated the class of the message; ● determining a threshold of interest; ● filtering the received message through storing the message in storage means of the device (100) in case the probability of interest associated to the class of the message is higher than the threshold; rejecting the message from the device (100) in case the probability of interest associated to the class of the message is lower than the threshold; ● detecting an event and determining whether said event matches at least one event type of a list of event types stored in the device (100); ● if said event matches at least one event type, then retrieving data related to at least one of the following parameters: the current time, a parameter related to the current place of the user, an event mode of said detected event; ● based on the retrieved data, selecting in the user's profile the class having the highest level of interest; ● selecting a message stored in the device (100) and having a header comprising said selected class; the device (100) comprising: ● display means for displaying on the device (100) a message invitation, the message invitation requesting from the user a consent to display on the device (100) the content of the message, ● a user interface for receiving from the user a response to the request, the device (100) being arranged for updating in the user's profile (110) the level of interest of the selected class taking into account the response.