Geographical Feature Generation Model for POI Popularity Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing popularity scoring systems for Points of Interest (POIs) fail to accurately assign scores to new or less mentioned facilities, as they rely solely on social network mentions, resulting in inappropriate rankings.
Innovation Solution
A popularity estimation system that uses a geographical feature generation model to calculate a POI's popularity score based on the similarity of geographical features with known POIs, generating feature vectors from map images and applying machine learning to determine appropriate scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a popularity score is generated based on the number of mentions in SNS, then the popularity score reflects current social media activity, but new facilities with no or little SNS history cannot be given an appropriate popularity score
Solution Approach 1:
The patent introduces map images and geographical feature vectors as intermediary elements between the facility and its popularity score. Instead of directly using SNS mention counts, the system extracts geographical features from map images surrounding the facility location, generating feature vectors that serve as mediators to estimate popularity scores for facilities regardless of their SNS history.
Solution Approach 2:
The patent replaces the traditional mechanical counting method of SNS mentions with a machine learning-based system. A neural network model processes map images and generates feature vectors, substituting the direct social media mention mechanism with an automated image recognition and analysis system that can evaluate facilities based on their geographical context rather than social media activity.
2Reliability
If popularity scores are used to rank facility information, then retrieval results are appropriately ranked by popularity, but facilities not mentioned in SNS receive inappropriate low rankings
Solution Approach 1:
The system performs preliminary extraction of geographical features from map images before the popularity scoring process. By pre-processing the map images and generating feature vectors that capture the geographical context and characteristics of facilities, the system prepares information that can be used to estimate popularity scores even before SNS mentions are considered, ensuring new facilities are not disadvantaged in the ranking process.
Data Source
AI summary
A popularity estimation device includes: an acquisition unit configured to acquire a first map image including a first particular point and to acquire a plurality of second map images including a second particular point which is a particular point; a generation unit configured to generate a first feature vector and a second feature vector by inputting the first map image and the second map images to a geographical feature generation model with a map image as an input and with a feature vector indicating geographical features of the map image as an output; a score calculating unit configured to calculate a popularity score of the first particular point from a popularity score of the second particular point based on a degree of similarity between the first feature vector and the second feature vector; and an output unit configured to output the popularity score of the first particular point.