--To the press -
FRONTEO announces new version of paper search AI "Amanogawa"
Achieves comprehensiveness and improved search speed, and adds a function to output a high-ranking list of search results.
Masahiro Morimoto, President and CEO
東京 都 港区 港 南 2-12-23
(Code number: 2158 TSE Mothers)
FRONTEO Inc. (Headquarters: Minato-ku, Tokyo, President: Masahiro Morimoto, hereinafter FRONTEO) has announced "Amanogawa Ver. 22.214.171.124".
"Amanogawa" uses artificial intelligence "Concept Encoder" and PubMed.*This is a system that detects and analyzes articles related to sentences such as keywords, hypotheses, and abstracts entered by searchers from the articles published in.It has been introduced to multiple pharmaceutical companies and universities since the release of Ver. 2020 in July 7, because it is highly evaluated for its ability to find the desired treatise in a short time from a huge number and its high searchability. I will.In this version, the following three functions have been improved and new functions have been added.
(6000) The number of papers displayed as a result has increased from 2 to XNUMX.
② Search speed is increased by about 1.5 times
(100) Implemented a function to output a list of the top XNUMX articles with high similarity to search terms and sentences.
"Amanogawa" treatise search screen.Each point shows a treatise
The number of articles plotted on the "Space Map" that displays the search results has more than tripled, greatly improving the comprehensiveness of the literature and making it easier to understand the cluster and overall picture of related articles. I did.In addition, the analysis speed has been shortened, further improving work efficiency.In addition, from the search results, the top 3 reports with high relevance / similarity to search terms / sentences (keyword search results, vector search results, 100 reports each based on keyword / vector hybrid search results, total 100 Added the function to output the list of papers in Excel format.In the previous version, these papers were displayed in card format together with the abstract (abstract), but with the addition of the list output function, the listability has been improved, and search results can be saved and information can be shared with collaborators. It has become easier to do.
FRONTEO will continue to contribute to improving the quality of medical care and the QOL of patients through the development of AI systems that contribute to improving the efficiency and success rate of drug discovery research and reducing the development period and cost.
* A database that allows you to search for articles in the field of biomedical science.Created by the National Center for Biological Sciences in the National Library of Medicine
■ About Amanogawa
"Amanogawa (trademark / patent pending)" is a paper search AI system equipped with FRONTEO's original AI engine "Concept Encoder (registered trademark: concept encoder, reading: concept encoder)".When a researcher inputs a sentence such as a word or hypothesis of interest, "Concept Encoder" instantly detects the article related to the input content from the large number of articles published in PubMed.
Since the search results are plotted in a map according to the similarity between the articles, you can check the relevance at a glance, and drag the article information detected on the map to narrow down the search, which is a visual that has never been seen before. You can search for articles.In addition, you can sort the search results in order of relevance and list their abstracts, greatly streamlining your article search.This makes it possible to discover events and new drug targets from a perspective that is difficult for humans to notice.
■ About Concept Encoder
"Concept Encoder (registered trademark: concept encoder, reading: concept encoder)" is a natural language analysis AI (artificial intelligence) developed by FRONTEO specially in the life science field.It was developed in 2018 with the aim of effectively analyzing and utilizing medical data containing a large amount of free-form text data based on evidence. "Concept Encoder" can be co-analyzed with data other than text, and we are conducting research on co-analysis with numerical data such as gene expression information, vitals and various test values accumulated in the life science field.Patent registration number: Patent No. 6346367
■FRONTEO URL: https://www.fronteo.com/
FRONTEO uses the in-house developed AI engine "KIBIT" and "concept encoder" specializing in natural language processing to extract meaningful and important information from a huge amount of text data to support corporate business. A data analysis company. Since its establishment in August 2003, it has been expanding globally to Japan, the United States, South Korea, and Taiwan, focusing on legal tech businesses such as "e-discovery (electronic discovery)" and "digital forensic investigation" that support international litigation of companies. Has been deployed.Based on the AI technology cultivated in the legal tech business, we expanded the business field to the life science field, business intelligence field, and OSINT from 8, and created by using AI to "turn text data into knowledge". We contribute to solving various corporate issues such as drug support, dementia diagnosis support, financial, human resources, and sales support. Listed on TSE Mothers on June 2014, 2007. January 6, 26 Obtained a first-class medical device manufacturing and sales license (permit number: 2021B1X13).The capital is 13 thousand yen (as of March 1, 10350).
* FRONTEO, KIBIT, and concept encoder are registered trademarks of FRONTEO in Japan.