FRONTEO Inc. (Headquarters: Minato-ku, Tokyo, President: Masahiro Morimoto, hereafter FRONTEO) has recently filed a lawsuit mainly in the United States for the document review tool "KIBIT Automator" equipped with the in-house developed AI "KIBIT". We are pleased to inform you that we have succeeded in improving the accuracy of Quality Control (hereinafter referred to as QC) by strengthening the "heat map function" that was often used for quality control in survey projects.

Discovery in US civil courts requires accurate discovery of evidence documents in a vast amount of documents within a limited amount of time. FRONTEO's AI-based document review tool "KIBIT Automator" is already in operation in the United States and Japan, reducing the amount of documents that require human review and significantly speeding up the amount of review documents per hour. We are achieving results such as improving.Larger deals require more documents to review and more document reviewers.As a result, the quality of reviews tends to vary, so improving the efficiency of QC is extremely important.To solve this, the heat map function is utilized.

The enhanced heat map function plays an important role in quality control, checking the consistency between AI and human judgment.In the survey, the reviewers check the documents scored by AI in order of priority, and perform a primary review that sorts out "relevant / irrelevant".After the completion of the primary review, the heat map function displays a document in which the judgment of the AI ​​and the judgment of the reviewer are different, so that the accuracy of the error detection rate is about 8 times higher than that of the extraction by random sampling. It has been realized.

Figure 1: Heatmap function-Compare the results of human checks with the results of AI (the darker the red, the more likely there is a difference between the results of human reviews and the AI ​​judgment).

With this enhancement, by further optimizing the algorithm of the heat map function, it is possible to cover documents with discrepancies and mistakes more quickly.In one survey example, about 2 documents

When a little over 1,000 judgments found the wrong document, the traditional heatmap required about 80 document checks to find 6,000% of the mistakes.On the other hand, when using the new heat map function, it can be achieved with only about 40 document checks, which is a 3,500% reduction.

This enhancement will help improve the efficiency of document review work in eDiscovery, reduce the burden on workers, and reduce costs.

As a pioneer in digital forensics / ediscovery, FRONTEO will continue to strive to improve and develop solutions that help streamline fraud investigations and litigation support.

■ About KIBIT Automator URL: https://legal.fronteo.com/products/kibit-automator/

"KIBIT Automator" improves the efficiency of document review work in e-discovery (electronic discovery), reduces the burden on workers, and reduces costs, among other discoveries required in the trial proceedings of US civil proceedings. An AI tool developed for the purpose, released in March 2019.We apply the research method used in discovery and utilize AI to examine and analyze large volumes of e-mails and electronic files that are evidence materials.In recent years, it has been utilized as one of the important processes of digital forensic surveys in the surveys of third-party committees in Japan, and it is expected to respond to the short-term information disclosure required by companies.

■ About KIBIT URL: https://www.fronteo.com/products/kibit/

"KIBIT" is an artificial intelligence that analyzes text without relying on keywords, using a unique machine learning algorithm that reproduces the "tacit knowledge" possessed by specialists and business experts.With high natural language processing technology, high-precision analysis can be performed in a short time with a small amount of teacher data, contributing to operational efficiency and sophistication in fields such as fraud investigation, intellectual property strategy, skill transfer, and risk prediction. doing.

■ About FRONTEO URL: https://www.fronteo.com/

FRONTEO uses the in-house developed AI engines "KIBIT", "Concept Encoder", and "Looca Cross" that specialize in natural language processing, and is meaningful and important from a huge amount of text data.
A data analysis company that extracts information and supports the business of the company. Since its establishment in August 2003, "e-discovery (electronic discovery)" and "digital forensic" have been supporting corporate international proceedings.
We have expanded our business globally to Japan, the United States, South Korea, and Taiwan, with a focus on legal tech businesses such as the “Survey”.Based on the AI ​​technology cultivated in this business, from 2014 for life science
By expanding the field of business to the field, business intelligence field, economic security, and using AI to "turn text data into knowledge", drug discovery support, dementia diagnosis support, finance / personnel /
We contribute to solving various corporate issues such as sales support. Listed on TSE Mothers on June 2007, 6. Obtained a first-class medical device manufacturing and sales license in January 26 (permit number: 2021B1X13), September of the same year
Reported the medical equipment sales business (Notification number: 3 Minato Misei Equipment No. 120).The capital is 2,973,975 thousand yen (as of March 2021, 3).

* FRONTEO, KIBIT, conceptencoder, and other product names are registered trademarks of FRONTEO in Japan.