Brand Exclusivity Scoring via Entity Distribution Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for identifying brand exclusivity and user loyalty in social media are inefficient, as they rely on filtering exact keywords, resulting in a large data volume that is difficult to sift through to find important influencers and brand users.

Innovation Solution

A system and method that calculates a user's exclusivity to a brand by analyzing social media content, extracting and weighting entities related to the brand and the user, and determining a score based on the overlap and ranking of these entities, allowing for identification of loyal users and potential influencers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If exact keyword filtering is used to identify brand users, then the identification process is simple to implement, but the data volume remains large and difficult to sift through

Engineering Contradiction:
Improveease of implementationVSAvoiddata volume
Core Design Contradiction:
Ease of manufactureVSQuantity of substance

Solution Approach 1:

The patent transforms the identification approach from exact keyword matching to a probabilistic model based on entity distribution parameters. By calculating brand distribution (proportion of brand-related entities in user posts) and comparing it against threshold values, the system efficiently filters users without requiring manual review of large data volumes, thus reducing both implementation complexity and data processing burden.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent replaces the mechanical manual filtering process with an automated computational model. Instead of manually sifting through filtered keyword results, the system uses entity extraction, distribution calculation, and probabilistic threshold comparison to automatically identify brand users, eliminating the need for manual data sifting while maintaining identification accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If manual filtering of user comments is performed to identify important influencers, then the identification accuracy can be high, but the time and resources required are excessive

Engineering Contradiction:
Improveidentification accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary entity extraction and distribution calculation for all users before final identification. By pre-computing brand distribution metrics and establishing threshold-based filtering, the system prepares identification criteria in advance, allowing rapid and accurate identification of brand users without requiring time-consuming manual review of each user's comments.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system enables automated self-identification of brand users through the probabilistic model. Users are automatically classified based on their entity distribution patterns without requiring manual intervention. The model self-adjusts by comparing individual user brand distribution against established thresholds, eliminating the need for time-consuming manual identification while maintaining high accuracy.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If comprehensive entity extraction is performed to calculate user exclusivity, then the user loyalty measurement is accurate, but the computational complexity increases

Engineering Contradiction:
Improveexclusivity measurement accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the entity extraction and analysis process into distinct components: entity extraction from user posts, brand distribution calculation, user distribution calculation, and threshold-based comparison. By dividing the comprehensive analysis into these modular segments, the system achieves accurate exclusivity measurement through systematic entity comparison while managing computational complexity through structured, stepwise processing.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS10163116B2Determining brand exclusiveness of users
Publication Date: 2018.12.25 ADOBE INC
  • US10163116B2 patent drawing
  • US10163116B2 patent drawing
  • US10163116B2 patent drawing

AI summary

Embodiments of the present invention relate to a determination of a user's exclusiveness toward a particular brand. User-specific entities are extracted from social media content associated with a user. At least a portion of the user-specific entities are brand-related entities that are specifically relevant to a particular brand. These brand-related entities are analyzed with respect to the user-specific entities extracted from the social media content to determine a level of exclusivity of the user to the brand.