Scoring Server for Influencer Targeting Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional advertising and influencer marketing systems lack the ability to precisely target users based on their interests, concerns, and behavioral characteristics, and fail to effectively recalculate influence scores post-promotion distribution, leading to inefficient advertising and limited control over target numbers and conditions.
Innovation Solution
A scoring server connected to subscriber terminals, SNS servers, and content provision terminals that calculates and recalculate user information communicativity scores using action history and response data, allowing for more precise targeting and feedback-driven advertising strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional advertising systems use basic influence scores based on follower count and activity level, then advertisement distribution can be performed, but the precision of targeting users based on interests, concerns, and behavioral characteristics is insufficient
Solution Approach 1:
The scoring system is segmented into multiple independent modules: basic score calculation module (using follower count and activity level), interest/concern score module (using SNS posting analysis), and behavioral characteristic score module (using action history). These modules work together to provide comprehensive targeting precision while maintaining system manageability through modular design.
Solution Approach 2:
The system transitions from traditional single-dimension influence scoring (based only on follower count) to multi-dimensional scoring by adding vertical dimensions: interest/concern dimensions (derived from SNS content analysis) and behavioral characteristic dimensions (derived from action history). This dimensional expansion enables precise targeting without excessive complexity.
2Measurement precision
If advertisement distribution is performed without feedback mechanism, then promotion can be distributed, but the ability to improve precision by feeding back effects and results is lost
Solution Approach 1:
The system implements a closed-loop feedback mechanism where advertising effects and user responses are collected after promotion distribution, analyzed to update interest/concern profiles and behavioral characteristics, and used to recalculate influence scores. This continuous feedback loop improves scoring precision and advertising efficiency by adapting to actual user responses rather than relying on static initial scores.
3Ease of operation
If advertisers want to arbitrarily narrow down influencers matching specific promotion conditions, then targeting control is improved, but the ability to effectively search and filter suitable influencers is reduced
Solution Approach 1:
The system performs preliminary action by pre-calculating comprehensive influence scores for all potential influencers before the advertising campaign begins. These pre-calculated scores incorporate follower metrics, SNS content analysis, and historical behavior patterns. When advertisers need to narrow down targets, they can efficiently filter from this pre-processed pool using simple score thresholds rather than conducting complex searches from scratch, thus improving both ease of operation and search efficiency.
4Adaptability or versatility
If basic influence scoring is used without re-creation mechanism, then initial advertisement distribution can be performed, but the score cannot be updated to reflect current user behavior and interests
Solution Approach 1:
The system implements periodic action by automatically recalculating influence scores at predetermined intervals (e.g., daily, weekly, or monthly) and triggered by significant events (e.g., major SNS postings or behavioral changes). This periodic recalculation ensures scores remain adaptive to current user behavior and interests while avoiding excessive computational complexity by using scheduled batch processing rather than continuous real-time recalculation.
Data Source
AI summary
A scoring server makes it possible for a provider of advertising or other content to arbitrarily search for an influencer who is suited to a promotion and to easily control target numbers or target conditions, and is capable of making effects and results from distribution of the promotion feedback into impact and information communicativity and improving precision. This server is connected by a network to a subscriber terminal, an SNS server, and a content provision terminal. Said server: communicates with the SNS server and creates a score of a subscriber's information communicativity; provides content to the subscriber terminal which has been provided from the content provision terminal; and re-creates the score using an action history with respect to the SNS server in relation to the content of the subscriber terminal, and the response to the actions, as feedback elements.