Method, system, and non-transitory computer-readable recording medium for generating country-specific material safety data sheets

The method and system efficiently convert and generate country-specific MSDS using a trained parser model, addressing inefficiencies in existing methods by reducing time and costs while ensuring compliance and safety.

KR102991439B1Active Publication Date: 2026-07-15NEUROLINES CO LTD

Patent Information

Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
NEUROLINES CO LTD
Filing Date
2024-02-28
Publication Date
2026-07-15

AI Technical Summary

Technical Problem

Existing methods for generating and applying Material Safety Data Sheets (MSDS) across countries are inefficient, requiring significant time and costs, and often fail to comply with regulations and ensure worker safety.

Method used

A method and system for generating country-specific Material Safety Data Sheets (MSDS) using a trained parser model to extract and arrange data sets from a first country's MSDS, converting and augmenting them to meet the requirements of a second country's regulations and formats, utilizing a data generation system with components like a data set determination unit, material safety data sheet generation unit, and communication unit.

Benefits of technology

This approach reduces time and costs, enables quick and easy generation of MSDS suitable for each country's language and format, ensuring compliance with regulations and worker safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112024023250260-PAT00002_ABST
    Figure 112024023250260-PAT00002_ABST
Patent Text Reader

Abstract

According to one aspect of the present invention, a method for generating a country-specific Material Safety Data Sheet (MSDS) is provided, comprising the steps of: determining a second country data set regarding a target chemical substance by referring to information extracted by inputting a first country's Material Safety Data Sheet regarding a target chemical substance into a trained parser model; and generating the second country's Material Safety Data Sheet by arranging the second country data set regarding the target chemical substance to correspond to the composition information of the second country's Material Safety Data Sheet.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present invention relates to a method, system, and non-transient computer-readable recording medium for generating national material safety data sheets. Background Technology

[0002] A Material Safety Data Sheet (MSDS) is a document that provides information regarding the hazards and risks of chemical substances, emergency procedures, and handling methods. Just as purchasing household appliances like refrigerators comes with instructions on handling and precautions, and buying medicines provides information on ingredients, content, efficacy, and side effects, the Material Safety Data Sheet serves as a guide for the safe use of chemical substances.

[0003] As an example of prior art regarding this, the technology disclosed in Korean Patent Publication No. 10-2016-0112075 can be cited. According to this, the present invention introduces a technology for providing Material Safety Data Sheets, wherein the invention prints a Material Safety Data Sheet containing a QR code or barcode with information about a chemical substance, or attaches a QR code or barcode to a chemical substance container or packaging, and when a portable terminal recognizes the QR code or barcode, requests the Material Safety Data Sheet from a server, the server transmits the Material Safety Data Sheet data from a database where the Material Safety Data Sheets are stored to the portable terminal, and the portable terminal receives and displays the Material Safety Data Sheet transmitted from the server.

[0004] With the recent intensification of competition in the global market, sales of chemical products to various countries are increasing. In this process, Material Safety Data Sheets (MSDS) in the language of the importing country are required. Furthermore, since the classification and standards of chemical substances may vary by country, it is necessary to prepare MSDS that comply with the regulations of the importing country, even for the same chemical substance.

[0005] In particular, while domestic companies often already possess Material Safety Data Sheets prior to export, generating these for the target country remains a challenging task. Prior art literature

[0006] Published Patent Application No. 10-2016-0112075 (September 28, 2016) The problem to be solved

[0007] The present invention aims to solve all the problems of the aforementioned prior art.

[0008] In addition, the present invention has another objective of saving time and reducing related costs required to prepare national Material Safety Data Sheets.

[0009] In addition, another objective of the present invention is to quickly and easily generate Material Safety Data Sheets suitable for the language and format of each country.

[0010] In addition, the present invention has another objective of generating a material safety data sheet for a second country based on a material safety data sheet for a first country.

[0011] In addition, another objective of the present invention is to enable workers in the chemical industry and manufacturing sectors of each country to comply with regulations and ensure the safety of workers. means of solving the problem

[0012] A representative configuration of the present invention for achieving the above objective is as follows.

[0013] According to one aspect of the present invention, a method for generating a country-specific Material Safety Data Sheet (MSDS) is provided, comprising the steps of: determining a second country data set regarding a target chemical substance by referring to information extracted by inputting a first country's Material Safety Data Sheet regarding a target chemical substance into a trained parser model; and generating the second country's Material Safety Data Sheet by arranging the second country data set regarding the target chemical substance to correspond to the composition information of the second country's Material Safety Data Sheet.

[0014] According to another aspect of the present invention, a system for generating country-specific Material Safety Data Sheets (MSDS) is provided, comprising: a data set determining unit that determines a second country data set regarding a target chemical substance by referring to information extracted by inputting a first country's Material Safety Data Sheet regarding the target chemical substance into a learned parser model; and a Material Safety Data Sheet generating unit that generates the second country's Material Safety Data Sheet by arranging the second country's data set regarding the target chemical substance to correspond to the composition information of the second country's Material Safety Data Sheet.

[0015] In addition to this, other methods for implementing the present invention, other systems, and non-transient computer-readable recording media on which a computer program for executing said methods is recorded are further provided. Effects of the invention

[0016] According to the present invention, the time required to prepare national material safety data sheets can be saved and related costs can be reduced.

[0017] In addition, according to the present invention, material safety data sheets suitable for the language and format of each country can be generated quickly and easily.

[0018] In addition, according to the present invention, a material safety data sheet of a second country can be generated based on a material safety data sheet of a first country.

[0019] In addition, according to the present invention, workers in the chemical industry and manufacturing sectors of each country can comply with regulations and their safety can be ensured. Brief explanation of the drawing

[0020] FIG. 1 is a diagram showing the schematic configuration of an overall system for generating national material safety data sheets according to one embodiment of the present invention. FIG. 2 is a drawing illustrating in detail the internal configuration of a data generation system according to one embodiment of the present invention. FIGS. 3 and 4 are diagrams illustrating, in an exemplary manner, the process of extracting information from a material safety data sheet of a first country according to an embodiment of the present invention. FIG. 5 is a diagram exemplarily illustrating the process of augmenting a data set according to one embodiment of the present invention. FIG. 6 is a diagram exemplarily illustrating a database regarding country-specific chemical management block information according to one embodiment of the present invention. FIG. 7 is a diagram exemplarily showing a material safety data sheet of a second country generated according to one embodiment of the present invention. Specific details for implementing the invention

[0021] The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be modified from one embodiment to another without departing from the spirit and scope of the invention. It should also be understood that the location or arrangement of individual components within each embodiment may be modified without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not meant to be limiting, and the scope of the invention should be understood to encompass the scope claimed by the claims and all equivalents thereof. Similar reference numerals in the drawings indicate identical or similar components across various aspects.

[0022] Hereinafter, in order to enable a person skilled in the art to easily practice the present invention, various preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

[0023] Configuration of the entire system

[0024] FIG. 1 is a diagram showing the schematic configuration of an overall system for generating national material safety data sheets according to one embodiment of the present invention.

[0025] As illustrated in FIG. 1, the entire system according to one embodiment of the present invention may include a communication network (100), a data generation system (200), and a device (300).

[0026] First, a communication network (100) according to one embodiment of the present invention can be configured regardless of the mode of communication, such as wired communication or wireless communication, and can be configured as various communication networks such as a Local Area Network (LAN), a Metropolitan Area Network (MAN), or a Wide Area Network (WAN). Preferably, the communication network (100) referred to in this specification may be the known Internet or the World Wide Web (WWW). However, the communication network (100) may include at least a part of a known wired / wireless data communication network, a known telephone network, or a known wired / wireless television communication network, without being limited thereto.

[0027] For example, the communication network (100) may be a wireless data communication network and may implement conventional communication methods such as WiFi communication, WiFi-Direct communication, Long Term Evolution (LTE) communication, 5G communication, Bluetooth communication (including Bluetooth Low Energy (BLE) communication), infrared communication, ultrasonic communication, etc., in at least a part thereof.

[0028] Next, a data generation system (200) according to one embodiment of the present invention can perform the function of generating a material safety data of a second country by determining a second country data set by referring to information extracted by inputting a material safety data of a first country regarding a target chemical substance into a learned parser model, and arranging the second country data set to correspond to the composition information of the material safety data of the second country.

[0029] The configuration and function of the data generation system (200) according to the present invention will be examined in detail through the following detailed description.

[0030] Next, the device (300) according to one embodiment of the present invention is a digital device that includes a function to communicate after connecting to a data generation system (200). Any digital device equipped with memory means and equipped with a microprocessor to have computational capabilities, such as a smartphone, tablet, smart watch, smart band, smart glasses, desktop computer, laptop computer, workstation, PDA, web pad, etc., can be adopted as the device (300) according to the present invention. Such a device (300) may include an input means for inputting information (e.g., keyboard), a display means for displaying information (e.g., LCD, LED), etc.

[0031] In particular, the device (300) may include an application (not shown) that supports receiving functions according to the present invention from the data generation system (200). Such an application may be downloaded from the data generation system (200) or an external application distribution server (not shown). Meanwhile, the nature of such an application may generally be similar to the data set determination unit (210), material safety data generation unit (220), communication unit (230), and control unit (240) of the data generation system (200) as described below. Here, at least a part of the application may be replaced with a hardware device or firmware device capable of performing substantially the same or equivalent functions as needed.

[0032] Configuration of the data generation system

[0033] Below, we will examine the internal configuration of the data generation system (200) that performs important functions for the implementation of the present invention and the functions of each component.

[0034] FIG. 2 is a drawing illustrating in detail the internal configuration of a data generation system (200) according to one embodiment of the present invention.

[0035] As illustrated in FIG. 2, according to one embodiment of the present invention, a data generation system (200) may include a data set determination unit (210), a material safety data sheet generation unit (220), a communication unit (230), and a control unit (240). Additionally, according to one embodiment of the present invention, the data set determination unit (210), the material safety data sheet generation unit (220), the communication unit (230), and the control unit (240) may be program modules, at least some of which communicate with an external system (not shown). These program modules may be included in the data generation system (200) in the form of an operating system, an application program module, and other program modules, and may be physically stored on various known memory devices. Additionally, these program modules may be stored in a remote memory device capable of communicating with the data generation system (200). Meanwhile, these program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc., that perform specific tasks or execute specific abstract data types as described below according to the present invention.

[0036] Meanwhile, although the data generation system (200) has been described as above, this description is exemplary, and it is obvious to those skilled in the art that at least some of the components or functions of the data generation system (200) may be realized within a device (300) or server (not shown) or included within an external system (not shown) as needed.

[0037] First, a data set determination unit (210) according to one embodiment of the present invention can perform the function of determining a second country data set regarding a target chemical substance by referring to information extracted by inputting a material safety data of a first country regarding the target chemical substance into a learned (specifically, previously learned) parser model. Here, the second country data set may refer to data necessary to generate items constituting the material safety data of the second country (for example, if the second country is Korea, there may be 16 items such as information on chemical products and companies, hazards and risks, names and contents of constituent components, emergency response procedures, methods for dealing with explosions and fires, methods for dealing with leaks, handling and storage methods, exposure prevention and personal protective equipment, physicochemical properties, stability and reactivity, information on toxicity, environmental impact, precautions for disposal, information required for transportation, legal regulatory status, and other reference matters). Meanwhile, the items constituting the material safety data may vary by country, and the corresponding data set may also vary accordingly. In addition, the second country data set may be determined in the language of the second country (or the language required by the regulations regarding the Material Safety Data Sheet of the second country). To this end, a database or lookup table regarding each item of the Material Safety Data Sheet of the first country and the data constituting each item, composed in the language of the second country (or the language required by the regulations regarding the Material Safety Data Sheet of the second country), may be referenced.

[0038] Specifically, the data set determining unit (210) can train an artificial intelligence-based parser model to extract supplier information, chemical information, information regarding hazardous / risk codes (H codes), and information regarding precautionary codes (P codes) from a plurality of material safety data sheets of the first country (specifically, material safety data sheets processed for character recognition using OCR technology). For example, such a parser model may be a model trained to extract information regarding supplier information, chemical information, hazardous / risk codes (H codes), and precautionary codes (P codes) from the material safety data sheets of the first country based on the Doc2Vec algorithm or the Word2Vec algorithm. Meanwhile, the data set determining unit (210) may divide the material safety data of the first country into multiple chunks by referring to the document structure of the material safety data of the first country (e.g., the document structure may be determined based on specific phrases, table of contents, etc.), and may increase the processing speed by performing preprocessing to extract only the chunk among the multiple chunks in which information regarding supplier information, chemical substance information, hazardous / risk code (H code), and precautionary measure code (P code) is presumed to be located (e.g., extracted based on specific phrases, table of contents, etc.).

[0039] Next, the data set determination unit (210) can input the material safety data of the first country regarding the target chemical substance into the above-mentioned learned parser model to obtain supplier information, chemical substance information, information regarding hazardous / dangerous codes (H codes), and information regarding precautionary codes (P codes), and can determine the second country data set based on information that is associated with (or corresponds to) the items of the material safety data of the second country among the obtained information.

[0040] Meanwhile, in the material safety data sheet of the first country, hazardous codes (H codes), precautionary codes (P codes), or corresponding phrases (e.g., guidance phrases or explanatory phrases) may be listed in an abbreviated or arbitrary format. Accordingly, the data set determining unit (210) may convert the hazardous codes (H codes), precautionary codes (P codes), and corresponding phrases extracted from the parser model into standardized hazardous codes (H codes), standardized precautionary codes (P codes), and standardized phrases (e.g., guidance phrases or explanatory phrases) by referring to a GHS (Globally Harmonized System of Classification and Labelling of Chemicals) standard phrase database (e.g., a database of codes and corresponding phrases according to GHS standards).

[0041] For example, referring to FIG. 3, the data set determining unit (210) can divide the material safety data of the first country into multiple chunks (320, 321, 322) in response to the input of the material safety data (310) of the first country regarding the target chemical substance into a previously trained parser model, and can perform preprocessing to extract the chunk containing information regarding the hazardous / danger code (H code) and information regarding the precautionary measure code (P code) among the multiple chunks. Then, the data set determining unit (210) can extract information regarding the hazardous / danger code (H code) and information regarding the precautionary measure code (P code) from the above extracted chunks.

[0042] For another example, referring to FIG. 4, the data set determination unit (210) can extract information (420) regarding the product name (411), recommended use and usage restrictions (412), and the name and content of the constituents (413) from the material safety data sheet (A of 410) of the first country using a learned parser model. Additionally, the data set determination unit (210) can extract information (420) regarding the product name (414), recommended use and usage restrictions (415), and the name and content of the constituents (416) from the material safety data sheet (B of 410) of the first country using a learned parser model.

[0043] Additionally, the data set determination unit (210) can perform the function of augmenting a second country data set regarding a target chemical substance based on information extracted from a parser model.

[0044] Specifically, the data set determination unit (210) can extract supplier information and material information regarding the target chemical substance from the material safety data of the first country using a parser model, and can augment the above second country data set using extension information corresponding to the supplier information and material information.

[0045] For example, the data set determining unit (210) can determine extended information (e.g., toxicity information, physical property information, regulatory information, and transport information) corresponding to the above extracted supplier information and material information by referring to a database regarding toxicity information, physical property information, regulatory information, and transport information corresponding to supplier information and material information. Then, the data set determining unit (210) can augment the data set of the second country by using the above extended information to supplement the data set of the second country determined using the information extracted by inputting the material safety data of the first country into a model (specifically, the second country data that is insufficient to constitute the material safety data of the second country among the second country data sets).

[0046] As another example, the data set determining unit (210) may extract chemical management block information of a second country (e.g., GHS building block information) and legal regulation information of a second country corresponding to the above extracted substance information as extension information and use the extension information to augment the data set of the second country. In this case, the data set determining unit (210) may pre-configure a database (or lookup table) (see FIG. 6) regarding country-specific chemical management block information (e.g., GHS building block information) corresponding to each substance information and a database (or lookup table) regarding legal regulation information (e.g., legal regulation information regarding the management of chemicals), and may extract extension information corresponding to the substance information by referring to the database.

[0047] Additionally, the data set determination unit (210) can augment the second country data set regarding the target chemical substance using a code prediction model learned based on multiple material safety data sheets of the first country.

[0048] For example, it can be assumed that multiple material safety data sheets of the first country are in a form that contains only corresponding phrases (e.g., guidance phrases or explanatory phrases) without hazardous / danger codes (H codes) and precautionary codes (P codes), or in a form that contains only the above codes without corresponding phrases (e.g., guidance phrases or explanatory phrases). The data set determination unit (210) can train an artificial intelligence-based code prediction model using hazardous / danger codes (H codes) and corresponding phrases (e.g., guidance phrases or explanatory phrases) and precautionary codes (P codes) and corresponding phrases (e.g., guidance phrases or explanatory phrases) as training data. For example, such a code prediction model may be configured based on the Word2Vec algorithm and may be a model trained to output a phrase corresponding to the hazardous / risk code (H code) (e.g., a guidance phrase or an explanatory phrase; whereby the guidance phrase may be a standardized phrase such as a GHS standard phrase) in response to the input of the hazardous / risk code (H code), or to output the hazardous / risk code (H code) in response to the input of a phrase regarding the hazardous / risk code (H code) (e.g., a guidance phrase or an explanatory phrase), or to output a phrase corresponding to the preventive action code (P code) (e.g., a guidance phrase or an explanatory phrase; whereby the guidance phrase may be a standardized phrase such as a GHS standard phrase) in response to the input of the preventive action code (P code), or to output the preventive action code (P code) in response to the input of a phrase regarding the preventive action code (P code) (e.g., a guidance phrase or an explanatory phrase).

[0049] Next, the data set determination unit (210) can augment the second country data set regarding the target chemical substance by inputting multiple material safety data sheets of the first country into the above-mentioned learned code prediction model to generate a hazardous / dangerous code (H code), a phrase corresponding to the hazardous / dangerous code (H code) (e.g., a guidance phrase or an explanatory phrase), a precautionary code (P code), or a phrase corresponding to the precautionary code (P code) (e.g., a guidance phrase or an explanatory phrase) to supplement missing information.

[0050] For example, referring to FIG. 5, the data set determination unit (210) can determine the data set of the second country by using information extracted by inputting the material safety data of the first country regarding the target chemical substance into a learned parser model, and can augment the data set of the second country using extended information determined from the extracted information. Additionally, the data set determination unit (210) can augment the data set of the second country by inputting multiple material safety data of the first country into a learned code prediction model to generate a hazardous / danger code (H code), a phrase corresponding to the hazardous / danger code (H code) (e.g., guidance phrase or explanatory phrase), a precautionary code (P code), or a phrase corresponding to the precautionary code (P code) (e.g., guidance phrase or explanatory phrase) to supplement missing information. Then, the data set determination unit (210) can determine the augmented (specifically, augmented twice) data set of the second country as the data set of the second country regarding the target chemical substance.

[0051] More specifically, the data set determination unit (210) can determine the data set of the second country by using information extracted by inputting the material safety data of the first country regarding the target chemical substance into a learned parser model. Then, the data set determination unit (210) can augment the data set of the second country by referring to extension information corresponding to supplier information and material information extracted from the material safety data of the first country regarding the target chemical substance using the parser model (510, 520). Here, the augmented data set of the second country may be data necessary to constitute 1, 3, 9 to 16 of the constituent items (which may consist of a total of 16 items) of the material safety data of the second country. Next, the data set determination unit (210) may generate a hazardous / danger code (H code), a phrase corresponding to the hazardous / danger code (H code) (e.g., guidance phrase or explanatory phrase), a precautionary code (P code), or a phrase corresponding to the precautionary code (P code) (e.g., guidance phrase or explanatory phrase) from the material safety data sheet of the first country regarding the target chemical substance using a code prediction model, and may further enhance the above enhanced second country data set by referring to the above code or phrase (530, 540). Here, the further enhanced second country data set may be data necessary to constitute items 2 and 4 to 8 among the components of the material safety data sheet of the second country. Accordingly, the second country data set may be composed of data necessary to form all components of the material safety data sheet of the second country (550).

[0052] Next, a material safety data sheet generation unit (220) according to one embodiment of the present invention can generate a material safety data sheet of a second country by arranging a second country data set regarding a target chemical substance determined by a data set determination unit (210) to correspond to the composition of the material safety data sheet of the second country (e.g., table of contents, content, etc.).

[0053] For example, the material safety data generation unit (220) can generate a material safety data of the second country regarding the target chemical substance by matching and arranging the second country data set regarding the target chemical substance to each component item (e.g., 16 items) of the material safety data of the second country (see FIG. 7).

[0054] More specifically, the material safety data sheet generation unit (220) can generate a material safety data sheet of a second country by referencing a material safety data sheet template of a second country among the country-specific material safety data sheet templates (such templates may be formats required by the material safety data sheet regulations of each country) and matching and arranging the second country data set to each component item (e.g., 16 items) of the material safety data sheet of the second country.

[0055] Next, a communication unit (230) according to one embodiment of the present invention can perform the function of enabling data transmission and reception from / to a data set determining unit (210) and a material safety data generation unit (220).

[0056] Finally, a control unit (240) according to one embodiment of the present invention can perform the function of controlling the flow of data between the data set determination unit (210), the material safety data generation unit (220), and the communication unit (230). That is, by controlling the flow of data from / to the outside of the data generation system (200) or the flow of data between each component of the data generation system (200), the control unit (240) according to the present invention can control the data set determination unit (210), the material safety data generation unit (220), and the communication unit (230) to perform their respective unique functions.

[0057] Below, we will examine the process of generating a Material Safety Data Sheet for a second country regarding a target chemical substance in a situation where a Material Safety Data Sheet for a first country regarding the target chemical substance is not possessed, according to another embodiment of the present invention.

[0058] First, according to another embodiment of the present invention, a country (i.e., a second country) and a language for which a Material Safety Data Sheet (MSDS) is to be generated may be selected. Next, physical property information regarding the target chemical substance may be entered. Here, the physical property information may include physical state (gas, liquid, solid), pH, boiling point, flash point, solubility, presence of hydrocarbons, viscosity, etc. Next, information regarding the names and contents of components constituting the target chemical substance (e.g., CAS number, English name of the substance, representative (or minimum, maximum) content (%), etc.) may be entered. Next, information regarding the type of waste and transportation (e.g., risk class in transportation, container class, etc.) may be entered. Then, the Material Safety Data Sheet for the second country may be generated by processing and arranging the above entered information by referring to a database regarding the country-specific chemical management block information (e.g., GHS building block information) of the target chemical substance and a Material Safety Data Sheet template (e.g., form or template) of the second country.

[0059] The embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the computer-readable recording medium may be those specifically designed and configured for the present invention or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. Hardware devices may be modified into one or more software modules to perform processing according to the present invention, and vice versa.

[0060] Although the present invention has been described above with reference to specific details such as specific components, limited embodiments, and drawings, this is provided only to aid in a more comprehensive understanding of the invention, and the invention is not limited to the above embodiments, and a person skilled in the art to which the invention belongs can make various modifications and changes from this description.

[0061] Accordingly, the scope of the present invention should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present invention. Explanation of the symbols

[0062] 100: Communication network 200: Data Generation System 210: Data set determination unit 220: Material Safety Data Sheet Generation Section 230: Communications Department 240: Control unit 300: Device

Claims

Claim 1 A method implemented in a data generation system for generating country-specific Material Safety Data Sheets (MSDS), wherein - the data generation system includes a data set determination unit and a Material Safety Data Sheet generation unit -, wherein the data set determination unit includes the step of determining a second country data set regarding the target chemical substance by referring to information extracted by inputting the Material Safety Data Sheet of the first country regarding the target chemical substance into a trained parser model, and wherein the Material Safety Data Sheet generation unit includes the step of generating the Material Safety Data Sheet of the second country by arranging the second country data set regarding the target chemical substance to correspond to the composition information of the Material Safety Data Sheet of the second country, and wherein in the determining step, the data set determination unit augments the second country data set regarding the target chemical substance based on information extracted from the parser model, and wherein the data set determination unit extracts supplier information, substance information, hazard codes, and precautionary codes regarding the target chemical substance from the Material Safety Data Sheet of the first country regarding the target chemical substance using the parser model, and the extracted hazard codes, precautionary codes, and corresponding phrases are standardized hazard codes, standardized precautionary codes, and standardized A method for augmenting the second country data set regarding the target chemical substance by converting into phrases, wherein the data set determining unit augments the second country data set using extended information corresponding to the extracted supplier information and the extracted material information, and wherein, in the determining step, the data set determining unit augments the second country data set regarding the target chemical substance by supplementing missing information by generating the hazardous / risk code, the phrase corresponding to the hazardous / risk code, the precautionary code, or the phrase corresponding to the precautionary code using a code prediction model learned based on a plurality of material safety data sheets of the first country. Claim 2 In claim 1, the above parser model is a model trained to extract supplier information, chemical information, information regarding hazardous / risk codes and information regarding precautionary measures codes from the material safety data sheets of the first country based on the Doc2Vec algorithm. Claim 3 In paragraph 2, the data set determining unit performs a preprocessing method in which, by referring to the document structure of the material safety data of the first country, the material safety data of the first country regarding the target chemical substance is divided into multiple chunks, and only the chunk among the multiple chunks in which supplier information, chemical substance information, information regarding hazardous / risk codes and information regarding precautionary measures codes are presumed to be located. Claim 4 delete Claim 5 delete Claim 6 In paragraph 2, the data set determining unit extracts chemical management block information of the second country corresponding to the material information and legal regulation information of the second country as the extended information, and a method of augmenting the second country data set using the extended information. Claim 7 delete Claim 8 In claim 1, in the generating step, the material safety data sheet generating unit arranges the second country data set regarding the target chemical substance by referring to the material safety data sheet template of the second country among the country-specific material safety data sheet templates. Claim 9 A non-transient computer-readable recording medium on which a computer program for executing the method according to paragraph 1 is recorded. Claim 10 A system for generating country-specific Material Safety Data Sheets (MSDS) comprises: a data set determining unit that determines a second country data set regarding a target chemical substance by referring to information extracted from inputting a first country's Material Safety Data Sheet regarding the target chemical substance into a trained parser model; and a Material Safety Data generation unit that generates a second country's Material Safety Data Sheet by arranging the second country's data set regarding the target chemical substance to correspond to the composition information of the second country's Material Safety Data Sheet. The data set determining unit augments the second country's data set regarding the target chemical substance based on information extracted from the parser model; extracts supplier information, substance information, hazard codes, and precautionary codes regarding the target chemical substance from the first country's Material Safety Data Sheet regarding the target chemical substance using the parser model; converts the extracted hazard codes, precautionary codes, and corresponding phrases into standardized hazard codes, standardized precautionary codes, and standardized phrases; augments the second country's data set using extension information corresponding to the extracted supplier information and extracted substance information; and based on a plurality of Material Safety Data Sheets of the first country A system for augmenting the second country data set regarding the target chemical substance by using a learned code prediction model to generate the hazardous / risk code, the phrase corresponding to the hazardous / risk code, the precautionary measure code, or the phrase corresponding to the precautionary measure code to supplement missing information.