Context-Aware Profile Completion via Machine Learning Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Social networking systems face challenges in encouraging users to complete their profiles fully, leading to inaccurate search results and user dissatisfaction, as users are reluctant to provide additional information during their online activities.

Innovation Solution

The implementation of machine learned models that determine the user's context and positivity of their experience, identifying missing profile data that would improve the experience and prompting users to add this data in a context-specific manner, with three machine learned models determining the relevance and likelihood of data completion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If users are prompted to complete profile data during online activities, then profile completeness improves, but user experience and satisfaction deteriorate due to interruptions

Engineering Contradiction:

Improveprofile data completenessVSAvoiduser experience

Core Design Contradiction:

Loss of informationVSEase of operation

Solution Approach 1:

The system performs preliminary analysis of user context and profile data before prompting the user. Machine learned models evaluate the current context, identify missing profile data, and determine the optimal timing for prompts, preparing the intervention in advance to minimize disruption while maximizing completion likelihood

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements a feedback mechanism where machine learned models continuously evaluate user context, profile completeness, and prompt effectiveness. Based on this feedback, the system adapts prompt timing, frequency, and content to optimize both profile completion and user experience, creating a closed-loop system that learns from user responses

Inventive Principle:

Principle #23Feedback

2Ease of operation

If profile data is left incomplete, then user resistance to interruption is maintained, but search result accuracy deteriorates

Engineering Contradiction:

Improveuser resistance to interruptionVSAvoidsearch result accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system introduces machine learned models as intermediaries between the user's online activities and the profile completion process. These models analyze context and determine when profile completion would benefit the user's current activity, acting as a smart mediator that protects users from unnecessary interruptions while ensuring critical profile data is collected

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically changes the parameters of profile data collection based on user context, current activity, and identified needs. Rather than requesting all missing data uniformly, the system prioritizes and adapts which profile fields to request based on real-time analysis, making the collection process more relevant and less intrusive

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If additional profile data is requested, then search result accuracy improves, but user productivity deteriorates due to time spent on data entry

Engineering Contradiction:

Improvesearch result accuracyVSAvoiduser productivity

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system applies partial action by requesting only the specific profile data that would most improve search results for the user's current context, rather than requiring all missing profile fields. The machine learned models identify and prioritize the most critical missing data points, reducing the burden on users while maintaining search accuracy improvements

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS10678997B2Machine learned models for contextual editing of social networking profiles

Publication Date: 2020.06.09 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

In an example, first and second machine learned models corresponding to a particular context of a social networking service are obtained, the first machine learned model trained via a first machine learning algorithm to output an indication of importance of a social networking profile field to obtaining results in the particular context, and the second machine learned model trained via a second machine learning algorithm to output a propensity of the user to edit a social networking profile field if requested. One or more missing fields in a social networking profile for the user are identified. For each of one or more of the one or more missing fields, the field and an identification of the user are passed through the first and second machine learned models, and outputs of the first and second machine learned models are combined to identify one or more top missing profile fields.