FRONTEO Inc. (Headquarters: Minato-ku, Tokyo, President: Masahiro Morimoto, hereafter FRONTEO) is a business of the in-house developed AI engine "Concept Encoder (trademark: conceptencoder, reading: concept encoder)" that has been used in the medical field. We are pleased to announce the new AI solution "Word Sonar (trademark pending, reading: Word Sonar)" to be used in the intelligence field.As the first step, we have started to provide the AI ​​system "Word Sonar for Accident View" (trademark pending, reading: Word Sonar for Accident View) that discovers and predicts risks related to safety measures at construction and manufacturing sites.

WordSonar for AccidentView centrally aggregates and analyzes a huge amount of text data such as daily reports, work reports, accident reports, etc. owned by construction / manufacturing companies using Concept Encoder, and presents them in a format that is easy to grasp and utilize. It is an AI system.Detects risk factors at worksites that were difficult to identify at the right time with conventional text mining and image analysis, and predicts accidents a few days before the occurrence.By analyzing a large amount of data with AI, in addition to reducing the burden of risk assessment of site managers and workers and confirmation / aggregation work of daily reports, it is objective and comprehensive without being affected by individual subjectivity and knowledge. Risk judgment is possible.In addition to daily reports, it is also possible to perform analysis while incorporating the latest data including meteorological data and seasonal data, so risk level evaluation in response to changes in site conditions and appropriate alerts to workers , Achieve continuous improvement in prediction accuracy.

Concept Encoder was developed in 2 as FRONTEO's second AI engine, and is currently widely used in the life science field for diagnostic support, fall prediction of inpatients, drug discovery support, and so on.One of the solutions equipped with the engine, the fall prediction AI system "Coroban," analyzes nursing records written in electronic medical records and predicts patients who may fall 2018 days before their onset. The high risk assessment accuracy and the effectiveness of fall prevention have been evaluated, and the introduction is currently progressing mainly in hospitals. FRONTEO will apply the risk assessment technology and know-how cultivated through this product through text analysis using AI to develop solutions that meet the needs of risk detection / prediction and accident prevention in various fields.

In companies, text data written in natural language such as reports is a huge and valuable source of information for business improvement.However, since it is difficult to handle it as homogeneous data for analysis, its utilization is currently limited. Since Concept Encoder vectorizes and analyzes the meaning of text, it is possible to comprehensively analyze such data.In addition, similar keywords that cannot be detected by simple keyword search are grouped, visualized, and presented.For example, if you want to investigate the risk of occupational accidents during snowfall at a construction / manufacturing site, enter "snow" in WordSonar for AccidentView, and include past cases including highly relevant words such as "freezing" and "freezing". You can also see cases that were detected and could be overlooked in the keyword search.

■ Figure 1: Display example when searching for "snow" as a keyword in WordSonar for Accident View

Figure XNUMX: Flow of using WordSonar for AccidentView

Figure XNUMX: Accident cases for each work content using a map　　

Figure XNUMX: Risk analysis chart for the work in charge

In the construction and manufacturing industry, while the working population is declining, the number of fatalities and injuries is increasing year by year.According to the Ministry of Health, Labor and Welfare's "Breaking News on Occupational Accidents" (as of January 4), the number of fatalities and injuries in 1 was 2021, about 13% (about 5,358%) in four years. 4) is also increasing¹⁾..According to the Statistics Bureau of the Ministry of Internal Affairs and Communications, "Japan Statistics 2021", the manufacturing industry has the highest number of occupational accident casualties among all industries, followed by the commerce, transportation, and construction industries, and the main causes are. "Pinched, caught", "falling", "falling, falling", etc.²⁾..These occupational accidents are often caused by small mistakes and lack of communication that could have been avoided with appropriate alerts. It is important to build a mechanism for prediction and prevention that causes as few cases as possible.In occupational safety and health efforts, each company has accumulated a large number of records such as the occurrence of accidents and disasters, and the situation of hiyari hats through reports in the format specified by the government and safety activities such as KYK (danger prediction activity).However, these records are only stored and not fully utilized, they are the personal know-how of the department in charge, the site manager / worker, and the situation is such that the site becomes accustomed and the countermeasures become a mere ghost. There is also an urgent need to implement effective occupational accident prevention and safety measures.　

WordSonar for AccidentView provides information that leads to disaster prediction, prevention, and business improvement from data that cannot be used in a timely manner at the workplace of a company.DetectionHowever, by making effective use of it, we support the prediction of occupational accident risks in companies and the improvement of workplace safety measures.In addition, FRONTEO will continue to expand the WordSonar series to various industries, starting with this solution for the construction and manufacturing industries, improve business efficiency, reduce costs and improve customer satisfaction. Will be provided.

XNUMX) Ministry of Health, Labor and Welfare: "Working accident occurrence situation (breaking news)" Reiwa XNUMXrd year

2021) Statistics Bureau, Ministry of Internal Affairs and Communications "Statistics of Japan 29" Chapter XNUMX Disasters / Accidents

■FRONTEOabout　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 to extract meaningful and important information from a huge amount of text data, and is a company. It is a data analysis company that supports the business of. 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 corporate international litigation. Has been deployed.Based on the AI ​​technology cultivated in this business, we will expand the business field to the life science field, business intelligence field, and economic security from 8, and by using AI to "turn text data into knowledge", We contribute to solving various corporate issues such as drug discovery support, dementia diagnosis support, financial, personnel, and sales support. Listed on TSE Mothers on June 2014, 2007. Obtained a first-class medical device manufacturing and sales business license in January 6 (permit number: 26B2021X1), and notified the managed medical device sales business in September of the same year (notification number: 13 Minato Misei Equipment No. 1).The capital is 10350 thousand yen (as of March 9, 3).

* FRONTEO, KIBIT, conceptencoder, and Coroban are registered trademarks of FRONTEO in Japan.