Information processing device, information processing method, and computer program
A neural network model using phrases for corporate evaluation addresses inaccuracies in ESG scoring by focusing on contextual relevance and adaptability, ensuring precise corporate evaluation values.
JP7883264B2Active Publication Date: 2026-07-01KYUSHU UNIV +1
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- KYUSHU UNIV
- Filing Date
- 2024-03-07
- Publication Date
- 2026-07-01
AI Technical Summary
Technical Problem
Existing corporate evaluation methods based on news article word frequency and similarity analysis lead to inaccurate ESG risk scores, especially for companies not frequently mentioned in the news, and repetitive word usage inflates scores.
Method used
A neural network-based corporate evaluation model using phrases of two or more words related to specific evaluation items, trained on fragment data, calculates relevance scores by incorporating context through BERT, and updates with frequently occurring relevant phrases.
Benefits of technology
Accurately calculates corporate evaluation values by considering contextual relevance and adaptability to changing trends, providing reliable ESG risk assessments.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure 0007883264000002 
Figure 0007883264000003 
Figure 0007883264000004
Abstract
To provide an information processing device for performing accurate corporation evaluation on the basis of document data on a corporation.SOLUTION: An information processing device has: a corporation evaluation phrase storage unit for storing a corporation evaluation phrase composed of two or more words related to corporation evaluation; a text data preprocessing unit for acquiring documents on a corporation, extracting text data from the documents, and generating a plurality of fragment data by dividing the extracted text data by the number of prescribed words; and a corporation evaluation unit for calculating a corporation evaluation value by a corporation evaluation model being a learned neural network where learning is performed so as to calculate the corporation evaluation value on the basis of the corporation evaluation phrase.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art