system

Abstract

The system according to this embodiment aims to automate and efficiently manage information on hazardous materials. [Solution] The system according to the embodiment comprises an analysis unit, an acquisition unit, and an extraction unit. The analysis unit analyzes product information. The acquisition unit acquires hazardous materials information based on the information analyzed by the analysis unit. The extraction unit extracts necessary information based on the information acquired by the acquisition unit.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the management of dangerous goods information depends on the information provided by suppliers and manufacturers, and visual inspection is required for extracting necessary information, so there is a problem that efficient management is difficult.

[0005] The system according to the embodiment aims to automate and efficiently perform the management of dangerous goods information.

Means for Solving the Problems

[0006] The system according to the embodiment includes an analysis unit, an acquisition unit, and an extraction unit. The analysis unit analyzes product information. The acquisition unit acquires dangerous goods information based on the information analyzed by the analysis unit. The extraction unit extracts necessary information based on the information acquired by the acquisition unit. [Effects of the Invention]

[0007] The system according to this embodiment can automate and efficiently manage hazardous materials information. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The hazardous materials management system according to an embodiment of the present invention is a system that solves the challenges of hazardous materials management for inventory-based e-commerce companies using a generating AI agent. In this hazardous materials management system, the generating AI agent analyzes product information and determines whether or not it is a hazardous material. Next, the generating AI agent obtains hazardous materials information using web scraping. Furthermore, the generating AI agent performs pattern analysis and extracts necessary hazardous materials management information. This mechanism eliminates the need for conventional manual operation and potential risks, contributing to strengthening corporate compliance. For example, the generating AI agent analyzes product information. In this case, the product information is analyzed in both text and image formats. For example, it analyzes information written on product labels and instruction manuals to determine whether or not it is a hazardous material. This enables accurate understanding of hazardous materials information. Next, the generating AI agent obtains hazardous materials information using web scraping. For example, it automatically downloads information about hazardous materials from the manufacturer's website. If the necessary information is not available on the website, the generating AI agent automatically requests the information from the manufacturer. This streamlines the acquisition of hazardous materials information. Furthermore, the generating AI agent performs pattern analysis and extracts necessary hazardous materials management information. For example, it can accurately extract necessary information from various PDF formats, such as SDS (Safety Data Sheets), test result reports, and product labels. The generating AI agent learns patterns in these documents and automatically extracts the necessary information. This improves the accuracy of information extraction and reduces the risk of management omissions. As a result, proper management of hazardous materials information ensures that periodic inspections based on fire safety laws are carried out reliably, reducing the risk of fires and explosions. Furthermore, proper management of hazardous materials improves corporate credibility and contributes to increased customer satisfaction. In this way, the hazardous materials management system can eliminate traditional manual operations and potential risks, contributing to strengthening corporate compliance.

[0029] The hazardous materials management system according to this embodiment comprises an analysis unit, an acquisition unit, and an extraction unit. The analysis unit analyzes product information. Product information includes, but is not limited to, product specifications, ingredient information, and usage instructions. The analysis unit analyzes product information using, for example, text mining technology. The analysis unit can also analyze product information using image recognition technology. For example, the analysis unit analyzes information written on product labels and instructions to determine whether or not a product is a hazardous material. The acquisition unit acquires hazardous materials information based on the information analyzed by the analysis unit. The acquisition unit automatically downloads information about hazardous materials from, for example, the manufacturer's website. The acquisition unit can acquire information using web scraping technology. The acquisition unit can also automatically request information from the manufacturer if the necessary information is not available on the website. For example, the acquisition unit requests information using automated email or API requests. The extraction unit extracts the necessary information based on the information acquired by the acquisition unit. The extraction unit accurately extracts the necessary information from various PDF formats, such as SDS, test result reports, and product labels. The extraction unit can extract information using PDF analysis technology. For example, it can extract lists of chemical substances and hazard assessments from Safety Data Sheets (SDS). It can also extract key points of test results from test result reports. This allows the hazardous materials management system to automate the analysis of product information, acquisition of hazardous materials information, and extraction of necessary information, thereby improving accuracy.

[0030] The analysis department analyzes product information. Product information includes, but is not limited to, product specifications, ingredient information, and usage instructions. For example, the analysis department analyzes product information using text mining technology. Text mining technology is a technique that uses natural language processing (NLP) to extract useful information from large amounts of text data. Specifically, it extracts keywords from product descriptions and ingredient lists and evaluates the hazards of the product based on these keywords. The analysis department can also analyze product information using image recognition technology. Image recognition technology is a technique that uses machine learning algorithms to analyze image data and identify specific patterns and features. For example, it can acquire information written on product labels and instructions as images and analyze them to determine whether or not the product is a hazardous material. By using image recognition technology, information can be accurately read even if it includes handwritten labels or complex diagrams. Furthermore, by combining these technologies, the analysis department can comprehensively analyze information from both text and images to perform more accurate hazardous material assessments. For example, by comparing ingredient information extracted using text mining technology with label information analyzed using image recognition technology and checking for matches, the reliability of the information can be improved. This allows the analysis department to efficiently and accurately analyze diverse product information and identify and evaluate hazardous materials.

[0031] The acquisition unit obtains hazardous materials information based on the information analyzed by the analysis unit. For example, the acquisition unit automatically downloads information about hazardous materials from a manufacturer's website. By using web scraping technology, it can analyze the HTML structure of web pages and extract the necessary information. Specifically, the acquisition unit accesses the manufacturer's website, identifies product pages and links to Safety Data Sheets (SDS), and collects information about hazardous materials from these pages. The acquisition unit can also automatically request information from the manufacturer if the necessary information is not available on the website. For example, the acquisition unit uses an automated email sending function to send an email to the manufacturer requesting the necessary information. The email content is generated based on a predefined template and specifically includes the required information. Furthermore, the acquisition unit can also obtain information directly from the manufacturer's database using API requests. An API request is a method of sending an HTTP request to a specific endpoint and receiving the necessary data as a response. This allows the acquisition unit to perform information acquisition using APIs in addition to web scraping and automated email sending, improving the efficiency and accuracy of information collection. By using a combination of these methods, the acquisition unit can quickly and accurately acquire necessary hazardous materials information, thereby strengthening information management throughout the entire system.

[0032] The extraction unit extracts necessary information based on the information acquired by the acquisition unit. For example, the extraction unit accurately extracts necessary information from various PDF formats, such as SDSs, test result reports, and product labels. By using PDF analysis technology, it can analyze the structure of PDF files and extract specific information. Specifically, the extraction unit extracts lists of chemical substances and hazard assessments from SDSs. SDSs are documents that provide information on the safety of chemical substances, including ingredient information, hazard assessments, and first-aid procedures. The extraction unit automatically extracts this information and stores it in a database. The extraction unit can also extract key points of test results from test result reports. Test result reports contain test results regarding product safety and performance, and the extraction unit extracts important data from these reports and manages the information in cooperation with the analysis and acquisition units. Furthermore, the extraction unit can also extract necessary information from product labels. Product labels contain ingredient information, usage instructions, and precautions, and the extraction unit accurately extracts this information to contribute to the overall information management of the system. This allows the extraction unit to efficiently extract necessary information from diverse sources, improving the accuracy and reliability of the hazardous materials management system. By utilizing these technologies, the extraction unit can process the acquired information quickly and accurately, strengthening information management throughout the entire system.

[0033] The analysis unit can analyze product information using both text and images. For example, the analysis unit can analyze product information using a text analysis algorithm. For instance, the analysis unit can analyze the text information contained in the product's instruction manual to determine whether or not it is a hazardous material. The analysis unit can also analyze product information using image recognition technology. For example, the analysis unit can analyze the image information contained on the product's label to determine whether or not it is a hazardous material. This allows for accurate identification of hazardous materials by analyzing product information using both text and images. Some or all of the above-described processes in the analysis unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the analysis unit can input the text information contained in the product's instruction manual into a generation AI, which can then analyze the text information to determine whether or not it is a hazardous material.

[0034] The acquisition unit can automatically download information about hazardous materials from the manufacturer's website. The acquisition unit can acquire information using, for example, web scraping technology. For example, the acquisition unit can automatically download SDS and test result reports from the manufacturer's website. The acquisition unit can also acquire information using APIs. For example, the acquisition unit can acquire information about hazardous materials using the manufacturer's API. This improves the efficiency of information acquisition by automatically downloading information about hazardous materials from the manufacturer's website. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the acquisition unit can have a generation AI execute web scraping technology, and the generation AI can acquire information from the manufacturer's website.

[0035] The acquisition unit can automatically request information from manufacturers if the necessary information is not available on the website. For example, the acquisition unit can request information using automated email sending. For example, the acquisition unit can automatically send an email to the manufacturer requesting the necessary information. The acquisition unit can also request information using API requests. For example, the acquisition unit can request information using the manufacturer's API. This improves the reliability of information acquisition by automatically requesting information from manufacturers if the necessary information is not available on the website. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the acquisition unit can use a generation AI to execute automated email sending, and the generation AI can request information from the manufacturer.

[0036] The extraction unit can accurately extract necessary information from PDFs in various formats, such as SDSs, test result reports, and product labels. The extraction unit extracts information using, for example, a PDF analysis algorithm. For instance, it can extract a list of chemical substances and hazard assessments from an SDS. It can also extract key points of test results from a test result report. Furthermore, it can extract usage precautions from a product label. This improves the accuracy of information extraction by accurately extracting necessary information from PDFs in various formats, such as SDSs, test result reports, and product labels. Some or all of the above-described processes in the extraction unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the extraction unit can have a generation AI execute a PDF analysis algorithm, allowing the generation AI to extract the necessary information from the PDF.

[0037] The analysis department can perform analyses while considering the product's usage environment and storage conditions. For example, the analysis department can collect information on the product's usage environment and incorporate it into the analysis. For instance, if the product is used in a high-temperature environment, the analysis department will focus on analyzing its resistance to high temperatures. The analysis department can also collect information on the product's storage conditions and incorporate it into the analysis. For example, if the product is stored in a high-humidity environment, the analysis department will focus on analyzing its resistance to humidity. Furthermore, the analysis department can perform analyses while comprehensively considering the product's usage environment and storage conditions. For example, if the product is used in a high-vibration environment, the analysis department will focus on analyzing its resistance to vibration. By performing analyses while considering the product's usage environment and storage conditions, more practical analysis results can be provided. Some or all of the above-described processes in the analysis department may be performed using a generation AI, or they may be performed without a generation AI. For example, the analysis department can input information on the product's usage environment into a generation AI, which can then perform the analysis while considering the usage environment.

[0038] The analysis unit can improve the accuracy of its hazardous materials classification by referring to past accident data. For example, the analysis unit can identify products with a high fire risk by referring to past fire accident data. For example, the analysis unit can obtain past fire accident data from a database and identify products with a high fire risk. The analysis unit can also identify products with a high explosion risk by referring to past explosion accident data. For example, the analysis unit can analyze past explosion accident data and identify products with a high explosion risk. Furthermore, the analysis unit can identify products with a high leakage risk by referring to past leakage accident data. For example, the analysis unit can analyze past leakage accident data and identify products with a high leakage risk. In this way, the accuracy of hazardous materials classification is improved by referring to past accident data. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the analysis unit can input past accident data into a generation AI, and the generation AI can analyze the accident data to improve the accuracy of hazardous materials classification.

[0039] The analysis department can perform analyses while taking into account information about the product's manufacturing process. For example, the analysis department can perform analyses while taking into account information about chemical substances used in the product's manufacturing process. For example, the analysis department can collect information about chemical substances used in the manufacturing process and incorporate it into the analysis. The analysis department can also perform analyses while taking into account information about by-products generated in the manufacturing process. For example, the analysis department can collect information about by-products generated in the manufacturing process and incorporate it into the analysis. Furthermore, the analysis department can also perform analyses while taking into account information about the machinery used in the manufacturing process. For example, the analysis department can collect information about the machinery used in the manufacturing process and incorporate it into the analysis. By performing analyses while taking into account information about the product's manufacturing process, more accurate analysis results can be provided. Some or all of the above processing in the analysis department may be performed using a generating AI, or it may be performed without using a generating AI. For example, the analysis department can input manufacturing process information into a generating AI, and the generating AI can perform analyses while taking the manufacturing process information into account.

[0040] The analysis unit can perform analysis while considering the product's transportation history. For example, the analysis unit can perform analysis while considering information about the impact the product received during transportation. For example, the analysis unit can collect information about the impact received during transportation and incorporate it into the analysis. The analysis unit can also perform analysis while considering information about temperature changes received during transportation. For example, the analysis unit can collect information about temperature changes received during transportation and incorporate it into the analysis. Furthermore, the analysis unit can also perform analysis while considering information about humidity changes received during transportation. For example, the analysis unit can collect information about humidity changes received during transportation and incorporate it into the analysis. By performing analysis while considering the product's transportation history, more accurate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the analysis unit can input transportation history information into a generation AI, and the generation AI can perform analysis while considering the transportation history.

[0041] The acquisition unit can evaluate the reliability of information and select the information to acquire. For example, the acquisition unit can evaluate the reliability of information sources and prioritize the acquisition of highly reliable information. For example, the acquisition unit can evaluate the past performance of information sources and acquire highly reliable information. The acquisition unit can also evaluate the frequency of information updates and prioritize the acquisition of the latest information. For example, the acquisition unit can evaluate the frequency of information updates of information sources and acquire the latest information. Furthermore, the acquisition unit can evaluate the accuracy of information and acquire highly reliable information. For example, the acquisition unit can evaluate the accuracy of information from information sources and acquire highly reliable information. In this way, highly reliable information can be acquired by evaluating the reliability of information and selecting the information to acquire. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the acquisition unit can have a generation AI evaluate the reliability of information sources, and the generation AI can select and acquire highly reliable information.

[0042] The acquisition unit can acquire information by integrating it from multiple sources. For example, the acquisition unit can acquire and integrate information from the websites of multiple manufacturers. For example, the acquisition unit can acquire and integrate SDSs and test result reports from the websites of multiple manufacturers. The acquisition unit can also acquire and integrate information from the databases of multiple government agencies. For example, the acquisition unit can acquire and integrate information on hazardous materials from the databases of multiple government agencies. Furthermore, the acquisition unit can acquire and integrate information from reports of multiple research institutions. For example, the acquisition unit can acquire information on hazardous materials from reports of multiple research institutions. This improves the comprehensiveness of the information by integrating and acquiring information from multiple sources. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the acquisition unit can have a generation AI integrate information from multiple sources, and the generation AI can integrate and acquire the information.

[0043] The data acquisition unit can select information to acquire by considering the frequency of information updates. For example, the data acquisition unit may prioritize acquiring information that is updated frequently. For example, the data acquisition unit may prioritize acquiring information that is updated regularly. The data acquisition unit can also acquire information that is updated infrequently as needed. For example, the data acquisition unit may acquire information that is updated infrequently as needed. Furthermore, the data acquisition unit can acquire information with a good balance between high and low update frequencies. For example, the data acquisition unit may acquire information with a good balance between high and low update frequencies. By selecting information to acquire by considering the frequency of information updates, the latest information can be obtained. Some or all of the above processing in the data acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the data acquisition unit may have a generation AI evaluate the frequency of information updates, and the generation AI may select information by considering the frequency of updates.

[0044] The acquisition unit can evaluate the reliability of the information provider and select the information to acquire. For example, the acquisition unit can evaluate the provider's past performance and acquire highly reliable information. The acquisition unit can also evaluate the provider's information update frequency and acquire the latest information. Furthermore, the acquisition unit can evaluate the accuracy of the provider's information and acquire highly reliable information. In this way, highly reliable information can be acquired by evaluating the reliability of the information provider and selecting the information to acquire. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the acquisition unit can have a generation AI evaluate the reliability of the provider, and the generation AI can select and acquire highly reliable information.

[0045] The extraction unit can adjust the level of detail of the extraction based on the importance of the information. For example, the extraction unit extracts highly important information in detail. The extraction unit can also extract less important information concisely. Furthermore, the extraction unit can adjust the level of detail of the extraction in stages according to the importance of the information. This allows for the appropriate extraction of necessary information by adjusting the level of detail of the extraction based on the importance of the information. Some or all of the above processing in the extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can have a generation AI evaluate the importance of the information, and the generation AI can adjust the level of detail of the extraction based on the importance.

[0046] The extraction unit can evaluate the relevance of information and select the information to extract. For example, the extraction unit can prioritize extracting highly relevant information. The extraction unit can also extract less relevant information as needed. Furthermore, the extraction unit can extract both highly and less relevant information in a balanced manner. This allows for the priority extraction of highly relevant information by evaluating the relevance of information and selecting the information to extract. Some or all of the above processing in the extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can have a generation AI evaluate the relevance of information, and the generation AI can select and extract highly relevant information.

[0047] The extraction unit can apply different extraction algorithms depending on the format of the information. For example, the extraction unit can apply a natural language processing algorithm to text-formatted information. The extraction unit can also apply an image recognition algorithm to image-formatted information. Furthermore, the extraction unit can apply a PDF analysis algorithm to PDF-formatted information. This improves the accuracy of information extraction by applying the most suitable extraction algorithm according to the format of the information. Some or all of the above processing in the extraction unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the extraction unit can have the generative AI apply different extraction algorithms depending on the format of the information, and the generative AI can extract the information.

[0048] The extraction unit can evaluate the reliability of the information provider and select the information to extract. For example, the extraction unit can evaluate the provider's past performance and extract highly reliable information. The extraction unit can also evaluate the frequency of information updates from the provider and extract the latest information. Furthermore, the extraction unit can evaluate the accuracy of the information from the provider and extract highly reliable information. In this way, highly reliable information can be extracted by evaluating the reliability of the information provider and selecting the information to extract. Some or all of the above processing in the extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can have a generation AI evaluate the reliability of the provider, and the generation AI can select and extract highly reliable information.

[0049] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0050] The analysis department can conduct analyses while considering the product's usage environment and storage conditions. For example, it can collect information on the product's usage environment and incorporate it into the analysis. For instance, if the product is used in a high-temperature environment, it will focus on analyzing its resistance to high temperatures. It can also collect information on the product's storage conditions and incorporate it into the analysis. For example, if the product is stored in a high-humidity environment, it will focus on analyzing its resistance to humidity. Furthermore, it can conduct analyses while comprehensively considering the product's usage environment and storage conditions. For example, if the product is used in a high-vibration environment, it will focus on analyzing its resistance to vibration. By considering the product's usage environment and storage conditions, it is possible to provide more practical analysis results.

[0051] The information acquisition unit can evaluate the reliability of the information and select the information to acquire. For example, it can evaluate the reliability of the information source and prioritize the acquisition of highly reliable information. For example, it can evaluate the past performance of the information source and acquire highly reliable information. It can also evaluate the frequency of information updates and prioritize the acquisition of the latest information. For example, it can evaluate the frequency of information updates of the information source and acquire the latest information. Furthermore, it can evaluate the accuracy of the information and acquire highly reliable information. For example, it can evaluate the accuracy of the information source and acquire highly reliable information. In this way, by evaluating the reliability of the information and selecting the information to acquire, highly reliable information can be obtained.

[0052] The extraction unit can apply different extraction algorithms depending on the format of the information. For example, a natural language processing algorithm can be applied to text-formatted information. Similarly, an image recognition algorithm can be applied to image-formatted information. Furthermore, a PDF analysis algorithm can be applied to PDF-formatted information. This allows for the application of the most suitable extraction algorithm for each information format, thereby improving the accuracy of information extraction.

[0053] The analysis department can improve the accuracy of its hazardous materials classification by referring to past accident data. For example, it can identify products with a high fire risk by referring to past fire accident data. For example, it can identify products with a high fire risk by obtaining past fire accident data from a database. It can also identify products with a high explosion risk by referring to past explosion accident data. For example, it can identify products with a high explosion risk by analyzing past explosion accident data. Furthermore, it can identify products with a high leakage risk by referring to past leakage accident data. For example, it can identify products with a high leakage risk by analyzing past leakage accident data. In this way, the accuracy of hazardous materials classification is improved by referring to past accident data.

[0054] The information acquisition unit can acquire and integrate information from multiple sources. For example, it can acquire and integrate information from the websites of multiple manufacturers. For example, it can acquire and integrate SDSs and test result reports from the websites of multiple manufacturers. It can also acquire and integrate information from databases of multiple government agencies. For example, it can acquire and integrate information on hazardous materials from databases of multiple government agencies. Furthermore, it can acquire and integrate information from reports of multiple research institutions. For example, it can acquire and integrate information on hazardous materials from reports of multiple research institutions. By integrating and acquiring information from multiple sources, the comprehensiveness of the information is improved.

[0055] The extraction unit can adjust the level of detail of the extraction based on the importance of the information. For example, highly important information can be extracted in detail. Less important information can also be extracted concisely. Furthermore, the level of detail of the extraction can be adjusted in stages according to the importance of the information. This allows for the appropriate extraction of necessary information by adjusting the level of detail based on the importance of the information.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The analysis department analyzes product information. This information includes product specifications, ingredient information, and usage instructions. The analysis department uses text mining and image recognition technologies to analyze the product information and determine whether the product is classified as a hazardous material by analyzing the information on the product label and instructions. Step 2: The acquisition unit acquires hazardous materials information based on the information analyzed by the analysis unit. The acquisition unit automatically downloads information on hazardous materials from the manufacturer's website and acquires the information using web scraping technology. If the necessary information is not available on the website, it requests the information from the manufacturer using automated email or API requests. Step 3: The extraction unit extracts the necessary information based on the information acquired by the acquisition unit. The extraction unit uses PDF analysis technology to accurately extract the necessary information from various PDF formats such as SDS, test result reports, and product labels. For example, it extracts a list of chemical substances and hazard assessments from SDSs, and extracts the key points of test results from test result reports.

[0058] (Example of form 2) The hazardous materials management system according to an embodiment of the present invention is a system that solves the challenges of hazardous materials management for inventory-based e-commerce companies using a generating AI agent. In this hazardous materials management system, the generating AI agent analyzes product information and determines whether or not it is a hazardous material. Next, the generating AI agent obtains hazardous materials information using web scraping. Furthermore, the generating AI agent performs pattern analysis and extracts necessary hazardous materials management information. This mechanism eliminates the need for conventional manual operation and potential risks, contributing to strengthening corporate compliance. For example, the generating AI agent analyzes product information. In this case, the product information is analyzed in both text and image formats. For example, it analyzes information written on product labels and instruction manuals to determine whether or not it is a hazardous material. This enables accurate understanding of hazardous materials information. Next, the generating AI agent obtains hazardous materials information using web scraping. For example, it automatically downloads information about hazardous materials from the manufacturer's website. If the necessary information is not available on the website, the generating AI agent automatically requests the information from the manufacturer. This streamlines the acquisition of hazardous materials information. Furthermore, the generating AI agent performs pattern analysis and extracts necessary hazardous materials management information. For example, it can accurately extract necessary information from various PDF formats, such as SDS (Safety Data Sheets), test result reports, and product labels. The generating AI agent learns patterns in these documents and automatically extracts the necessary information. This improves the accuracy of information extraction and reduces the risk of management omissions. As a result, proper management of hazardous materials information ensures that periodic inspections based on fire safety laws are carried out reliably, reducing the risk of fires and explosions. Furthermore, proper management of hazardous materials improves corporate credibility and contributes to increased customer satisfaction. In this way, the hazardous materials management system can eliminate traditional manual operations and potential risks, contributing to strengthening corporate compliance.

[0059] The hazardous materials management system according to this embodiment comprises an analysis unit, an acquisition unit, and an extraction unit. The analysis unit analyzes product information. Product information includes, but is not limited to, product specifications, ingredient information, and usage instructions. The analysis unit analyzes product information using, for example, text mining technology. The analysis unit can also analyze product information using image recognition technology. For example, the analysis unit analyzes information written on product labels and instructions to determine whether or not a product is a hazardous material. The acquisition unit acquires hazardous materials information based on the information analyzed by the analysis unit. The acquisition unit automatically downloads information about hazardous materials from, for example, the manufacturer's website. The acquisition unit can acquire information using web scraping technology. The acquisition unit can also automatically request information from the manufacturer if the necessary information is not available on the website. For example, the acquisition unit requests information using automated email or API requests. The extraction unit extracts the necessary information based on the information acquired by the acquisition unit. The extraction unit accurately extracts the necessary information from various PDF formats, such as SDS, test result reports, and product labels. The extraction unit can extract information using PDF analysis technology. For example, it can extract lists of chemical substances and hazard assessments from Safety Data Sheets (SDS). It can also extract key points of test results from test result reports. This allows the hazardous materials management system to automate the analysis of product information, acquisition of hazardous materials information, and extraction of necessary information, thereby improving accuracy.

[0060] The analysis department analyzes product information. Product information includes, but is not limited to, product specifications, ingredient information, and usage instructions. For example, the analysis department analyzes product information using text mining technology. Text mining technology is a technique that uses natural language processing (NLP) to extract useful information from large amounts of text data. Specifically, it extracts keywords from product descriptions and ingredient lists and evaluates the hazards of the product based on these keywords. The analysis department can also analyze product information using image recognition technology. Image recognition technology is a technique that uses machine learning algorithms to analyze image data and identify specific patterns and features. For example, it can acquire information written on product labels and instructions as images and analyze them to determine whether or not the product is a hazardous material. By using image recognition technology, information can be accurately read even if it includes handwritten labels or complex diagrams. Furthermore, by combining these technologies, the analysis department can comprehensively analyze information from both text and images to perform more accurate hazardous material assessments. For example, by comparing ingredient information extracted using text mining technology with label information analyzed using image recognition technology and checking for matches, the reliability of the information can be improved. This allows the analysis department to efficiently and accurately analyze diverse product information and identify and evaluate hazardous materials.

[0061] The acquisition unit obtains hazardous materials information based on the information analyzed by the analysis unit. For example, the acquisition unit automatically downloads information about hazardous materials from a manufacturer's website. By using web scraping technology, it can analyze the HTML structure of web pages and extract the necessary information. Specifically, the acquisition unit accesses the manufacturer's website, identifies product pages and links to Safety Data Sheets (SDS), and collects information about hazardous materials from these pages. The acquisition unit can also automatically request information from the manufacturer if the necessary information is not available on the website. For example, the acquisition unit uses an automated email sending function to send an email to the manufacturer requesting the necessary information. The email content is generated based on a predefined template and specifically includes the required information. Furthermore, the acquisition unit can also obtain information directly from the manufacturer's database using API requests. An API request is a method of sending an HTTP request to a specific endpoint and receiving the necessary data as a response. This allows the acquisition unit to perform information acquisition using APIs in addition to web scraping and automated email sending, improving the efficiency and accuracy of information collection. By using a combination of these methods, the acquisition unit can quickly and accurately acquire necessary hazardous materials information, thereby strengthening information management throughout the entire system.

[0062] The extraction unit extracts necessary information based on the information acquired by the acquisition unit. For example, the extraction unit accurately extracts necessary information from various PDF formats, such as SDSs, test result reports, and product labels. By using PDF analysis technology, it can analyze the structure of PDF files and extract specific information. Specifically, the extraction unit extracts lists of chemical substances and hazard assessments from SDSs. SDSs are documents that provide information on the safety of chemical substances, including ingredient information, hazard assessments, and first-aid procedures. The extraction unit automatically extracts this information and stores it in a database. The extraction unit can also extract key points of test results from test result reports. Test result reports contain test results regarding product safety and performance, and the extraction unit extracts important data from these reports and manages the information in cooperation with the analysis and acquisition units. Furthermore, the extraction unit can also extract necessary information from product labels. Product labels contain ingredient information, usage instructions, and precautions, and the extraction unit accurately extracts this information to contribute to the overall information management of the system. This allows the extraction unit to efficiently extract necessary information from diverse sources, improving the accuracy and reliability of the hazardous materials management system. By utilizing these technologies, the extraction unit can process the acquired information quickly and accurately, strengthening information management throughout the entire system.

[0063] The analysis unit can analyze product information using both text and images. For example, the analysis unit can analyze product information using a text analysis algorithm. For instance, the analysis unit can analyze the text information contained in the product's instruction manual to determine whether or not it is a hazardous material. The analysis unit can also analyze product information using image recognition technology. For example, the analysis unit can analyze the image information contained on the product's label to determine whether or not it is a hazardous material. This allows for accurate identification of hazardous materials by analyzing product information using both text and images. Some or all of the above-described processes in the analysis unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the analysis unit can input the text information contained in the product's instruction manual into a generation AI, which can then analyze the text information to determine whether or not it is a hazardous material.

[0064] The acquisition unit can automatically download information about hazardous materials from the manufacturer's website. The acquisition unit can acquire information using, for example, web scraping technology. For example, the acquisition unit can automatically download SDS and test result reports from the manufacturer's website. The acquisition unit can also acquire information using APIs. For example, the acquisition unit can acquire information about hazardous materials using the manufacturer's API. This improves the efficiency of information acquisition by automatically downloading information about hazardous materials from the manufacturer's website. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the acquisition unit can have a generation AI execute web scraping technology, and the generation AI can acquire information from the manufacturer's website.

[0065] The acquisition unit can automatically request information from manufacturers if the necessary information is not available on the website. For example, the acquisition unit can request information using automated email sending. For example, the acquisition unit can automatically send an email to the manufacturer requesting the necessary information. The acquisition unit can also request information using API requests. For example, the acquisition unit can request information using the manufacturer's API. This improves the reliability of information acquisition by automatically requesting information from manufacturers if the necessary information is not available on the website. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the acquisition unit can use a generation AI to execute automated email sending, and the generation AI can request information from the manufacturer.

[0066] The extraction unit can accurately extract necessary information from PDFs in various formats, such as SDSs, test result reports, and product labels. The extraction unit extracts information using, for example, a PDF analysis algorithm. For instance, it can extract a list of chemical substances and hazard assessments from an SDS. It can also extract key points of test results from a test result report. Furthermore, it can extract usage precautions from a product label. This improves the accuracy of information extraction by accurately extracting necessary information from PDFs in various formats, such as SDSs, test result reports, and product labels. Some or all of the above-described processes in the extraction unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the extraction unit can have a generation AI execute a PDF analysis algorithm, allowing the generation AI to extract the necessary information from the PDF.

[0067] The analysis unit can estimate the user's emotions and adjust the product information analysis method based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions using an emotion analysis algorithm. For example, the analysis unit can estimate the user's emotions by analyzing the user's facial expressions and voice. The analysis unit can also estimate emotions based on user feedback. For example, the analysis unit can estimate the user's emotions by analyzing the results of a user survey. This allows for more appropriate analysis results to be provided by adjusting the product information analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can input user facial expression data into a generative AI, which can then estimate the user's emotions and adjust the product information analysis method.

[0068] The analysis department can perform analyses while considering the product's usage environment and storage conditions. For example, the analysis department can collect information on the product's usage environment and incorporate it into the analysis. For instance, if the product is used in a high-temperature environment, the analysis department will focus on analyzing its resistance to high temperatures. The analysis department can also collect information on the product's storage conditions and incorporate it into the analysis. For example, if the product is stored in a high-humidity environment, the analysis department will focus on analyzing its resistance to humidity. Furthermore, the analysis department can perform analyses while comprehensively considering the product's usage environment and storage conditions. For example, if the product is used in a high-vibration environment, the analysis department will focus on analyzing its resistance to vibration. By performing analyses while considering the product's usage environment and storage conditions, more practical analysis results can be provided. Some or all of the above-described processes in the analysis department may be performed using a generation AI, or they may be performed without a generation AI. For example, the analysis department can input information on the product's usage environment into a generation AI, which can then perform the analysis while considering the usage environment.

[0069] The analysis unit can improve the accuracy of its hazardous materials classification by referring to past accident data. For example, the analysis unit can identify products with a high fire risk by referring to past fire accident data. For example, the analysis unit can obtain past fire accident data from a database and identify products with a high fire risk. The analysis unit can also identify products with a high explosion risk by referring to past explosion accident data. For example, the analysis unit can analyze past explosion accident data and identify products with a high explosion risk. Furthermore, the analysis unit can identify products with a high leakage risk by referring to past leakage accident data. For example, the analysis unit can analyze past leakage accident data and identify products with a high leakage risk. In this way, the accuracy of hazardous materials classification is improved by referring to past accident data. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the analysis unit can input past accident data into a generation AI, and the generation AI can analyze the accident data to improve the accuracy of hazardous materials classification.

[0070] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, the analysis unit estimates the user's emotions using an emotion analysis algorithm. For example, the analysis unit analyzes the user's facial expressions and voice to estimate the user's emotions. The analysis unit can also estimate emotions based on user feedback. For example, the analysis unit analyzes the user's survey results to estimate the user's emotions. This allows for a more appropriate display method by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can input user facial expression data into a generative AI, which can then estimate the user's emotions and adjust the display method of the analysis results.

[0071] The analysis department can perform analyses while taking into account information about the product's manufacturing process. For example, the analysis department can perform analyses while taking into account information about chemical substances used in the product's manufacturing process. For example, the analysis department can collect information about chemical substances used in the manufacturing process and incorporate it into the analysis. The analysis department can also perform analyses while taking into account information about by-products generated in the manufacturing process. For example, the analysis department can collect information about by-products generated in the manufacturing process and incorporate it into the analysis. Furthermore, the analysis department can also perform analyses while taking into account information about the machinery used in the manufacturing process. For example, the analysis department can collect information about the machinery used in the manufacturing process and incorporate it into the analysis. By performing analyses while taking into account information about the product's manufacturing process, more accurate analysis results can be provided. Some or all of the above processing in the analysis department may be performed using a generating AI, or it may be performed without using a generating AI. For example, the analysis department can input manufacturing process information into a generating AI, and the generating AI can perform analyses while taking the manufacturing process information into account.

[0072] The analysis unit can perform analysis while considering the product's transportation history. For example, the analysis unit can perform analysis while considering information about the impact the product received during transportation. For example, the analysis unit can collect information about the impact received during transportation and incorporate it into the analysis. The analysis unit can also perform analysis while considering information about temperature changes received during transportation. For example, the analysis unit can collect information about temperature changes received during transportation and incorporate it into the analysis. Furthermore, the analysis unit can also perform analysis while considering information about humidity changes received during transportation. For example, the analysis unit can collect information about humidity changes received during transportation and incorporate it into the analysis. By performing analysis while considering the product's transportation history, more accurate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the analysis unit can input transportation history information into a generation AI, and the generation AI can perform analysis while considering the transportation history.

[0073] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring hazardous materials information based on the estimated user emotions. The acquisition unit can estimate the user's emotions, for example, by using an emotion analysis algorithm. For example, the acquisition unit can analyze the user's facial expressions and voice to estimate the user's emotions. The acquisition unit can also estimate emotions based on user feedback. For example, the acquisition unit can analyze the user's survey results to estimate the user's emotions. By adjusting the timing of acquiring hazardous materials information according to the user's emotions, information can be acquired at a more appropriate time. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the acquisition unit may be performed using the generative AI or not. For example, the acquisition unit can input user facial expression data into the generative AI, and the generative AI can estimate the user's emotions and adjust the timing of acquiring hazardous materials information.

[0074] The acquisition unit can evaluate the reliability of information and select the information to acquire. For example, the acquisition unit can evaluate the reliability of information sources and prioritize the acquisition of highly reliable information. For example, the acquisition unit can evaluate the past performance of information sources and acquire highly reliable information. The acquisition unit can also evaluate the frequency of information updates and prioritize the acquisition of the latest information. For example, the acquisition unit can evaluate the frequency of information updates of information sources and acquire the latest information. Furthermore, the acquisition unit can evaluate the accuracy of information and acquire highly reliable information. For example, the acquisition unit can evaluate the accuracy of information from information sources and acquire highly reliable information. In this way, highly reliable information can be acquired by evaluating the reliability of information and selecting the information to acquire. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the acquisition unit can have a generation AI evaluate the reliability of information sources, and the generation AI can select and acquire highly reliable information.

[0075] The acquisition unit can acquire information by integrating it from multiple sources. For example, the acquisition unit can acquire and integrate information from the websites of multiple manufacturers. For example, the acquisition unit can acquire and integrate SDSs and test result reports from the websites of multiple manufacturers. The acquisition unit can also acquire and integrate information from the databases of multiple government agencies. For example, the acquisition unit can acquire and integrate information on hazardous materials from the databases of multiple government agencies. Furthermore, the acquisition unit can acquire and integrate information from reports of multiple research institutions. For example, the acquisition unit can acquire information on hazardous materials from reports of multiple research institutions. This improves the comprehensiveness of the information by integrating and acquiring information from multiple sources. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the acquisition unit can have a generation AI integrate information from multiple sources, and the generation AI can integrate and acquire the information.

[0076] The data acquisition unit can estimate the user's emotions and determine the priority of information to acquire based on the estimated user emotions. For example, the data acquisition unit can estimate the user's emotions using an emotion analysis algorithm. For example, the data acquisition unit can estimate the user's emotions by analyzing the user's facial expressions and voice. The data acquisition unit can also estimate emotions based on user feedback. For example, the data acquisition unit can estimate the user's emotions by analyzing the results of a user survey. This allows for the prioritization of information to be acquired according to the user's emotions, thereby prioritizing the acquisition of more important information. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data acquisition unit may be performed using a generative AI or not. For example, the data acquisition unit can input user facial expression data into a generative AI, which can then estimate the user's emotions and determine the priority of information to acquire.

[0077] The data acquisition unit can select information to acquire by considering the frequency of information updates. For example, the data acquisition unit may prioritize acquiring information that is updated frequently. For example, the data acquisition unit may prioritize acquiring information that is updated regularly. The data acquisition unit can also acquire information that is updated infrequently as needed. For example, the data acquisition unit may acquire information that is updated infrequently as needed. Furthermore, the data acquisition unit can acquire information with a good balance between high and low update frequencies. For example, the data acquisition unit may acquire information with a good balance between high and low update frequencies. By selecting information to acquire by considering the frequency of information updates, the latest information can be obtained. Some or all of the above processing in the data acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the data acquisition unit may have a generation AI evaluate the frequency of information updates, and the generation AI may select information by considering the frequency of updates.

[0078] The acquisition unit can evaluate the reliability of the information provider and select the information to acquire. For example, the acquisition unit can evaluate the provider's past performance and acquire highly reliable information. The acquisition unit can also evaluate the provider's information update frequency and acquire the latest information. Furthermore, the acquisition unit can evaluate the accuracy of the provider's information and acquire highly reliable information. In this way, highly reliable information can be acquired by evaluating the reliability of the information provider and selecting the information to acquire. Some or all of the above processing in the acquisition unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the acquisition unit can have a generation AI evaluate the reliability of the provider, and the generation AI can select and acquire highly reliable information.

[0079] The extraction unit can estimate the user's emotions and determine the priority of information to extract based on the estimated user emotions. The extraction unit can estimate the user's emotions using, for example, an emotion analysis algorithm. For example, the extraction unit can analyze the user's facial expressions and voice to estimate the user's emotions. The extraction unit can also estimate emotions based on user feedback. For example, the extraction unit can analyze the user's survey results to estimate the user's emotions. By determining the priority of information to extract according to the user's emotions, more important information can be extracted preferentially. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using a generative AI or not. For example, the extraction unit can input user facial expression data into a generative AI, and the generative AI can estimate the user's emotions and determine the priority of information to extract.

[0080] The extraction unit can adjust the level of detail of the extraction based on the importance of the information. For example, the extraction unit extracts highly important information in detail. The extraction unit can also extract less important information concisely. Furthermore, the extraction unit can adjust the level of detail of the extraction in stages according to the importance of the information. This allows for the appropriate extraction of necessary information by adjusting the level of detail of the extraction based on the importance of the information. Some or all of the above processing in the extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can have a generation AI evaluate the importance of the information, and the generation AI can adjust the level of detail of the extraction based on the importance.

[0081] The extraction unit can evaluate the relevance of information and select the information to extract. For example, the extraction unit can prioritize extracting highly relevant information. The extraction unit can also extract less relevant information as needed. Furthermore, the extraction unit can extract both highly and less relevant information in a balanced manner. This allows for the priority extraction of highly relevant information by evaluating the relevance of information and selecting the information to extract. Some or all of the above processing in the extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can have a generation AI evaluate the relevance of information, and the generation AI can select and extract highly relevant information.

[0082] The extraction unit can estimate the user's emotions and adjust the display method of the extraction results based on the estimated user emotions. The extraction unit can estimate the user's emotions using, for example, an emotion analysis algorithm. For example, the extraction unit can analyze the user's facial expressions and voice to estimate the user's emotions. The extraction unit can also estimate emotions based on user feedback. For example, the extraction unit can analyze the user's survey results to estimate the user's emotions. This allows for a more appropriate display method by adjusting the display method of the extraction results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using the generative AI or not. For example, the extraction unit can input user facial expression data into the generative AI, which can then estimate the user's emotions and adjust the display method of the extraction results.

[0083] The extraction unit can apply different extraction algorithms depending on the format of the information. For example, the extraction unit can apply a natural language processing algorithm to text-formatted information. The extraction unit can also apply an image recognition algorithm to image-formatted information. Furthermore, the extraction unit can apply a PDF analysis algorithm to PDF-formatted information. This improves the accuracy of information extraction by applying the most suitable extraction algorithm according to the format of the information. Some or all of the above processing in the extraction unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the extraction unit can have the generative AI apply different extraction algorithms depending on the format of the information, and the generative AI can extract the information.

[0084] The extraction unit can evaluate the reliability of the information provider and select the information to extract. For example, the extraction unit can evaluate the provider's past performance and extract highly reliable information. The extraction unit can also evaluate the frequency of information updates from the provider and extract the latest information. Furthermore, the extraction unit can evaluate the accuracy of the information from the provider and extract highly reliable information. In this way, highly reliable information can be extracted by evaluating the reliability of the information provider and selecting the information to extract. Some or all of the above processing in the extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can have a generation AI evaluate the reliability of the provider, and the generation AI can select and extract highly reliable information.

[0085] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0086] The analysis department can estimate user emotions and adjust the product information analysis method based on the estimated user emotions. For example, the analysis department can estimate user emotions by analyzing the user's facial expressions and voice. It can also estimate emotions based on user feedback. This allows for more appropriate analysis results by adjusting the product information analysis method according to the user's emotions. For example, if the user is feeling anxious, the analysis department can adjust to provide more detailed information. If the user is satisfied, it can adjust to provide concise information. Furthermore, it can also adjust how the analysis results are displayed based on the user's emotions. For example, if the user is feeling stressed, the analysis results can be displayed in a visually easy-to-understand manner. This enables flexible responses that respond to the user's emotions.

[0087] The information acquisition unit can estimate the user's emotions and adjust the timing of acquiring hazardous materials information based on the estimated emotions. For example, the unit can analyze the user's facial expressions and voice to estimate their emotions. It can also estimate emotions based on user feedback. This allows for information to be acquired at a more appropriate time by adjusting the timing of acquiring hazardous materials information according to the user's emotions. For example, if the user is anxious, the unit can adjust to acquire information quickly. If the user is relaxed, the unit can acquire information at the normal timing. Furthermore, the method of acquiring information can also be adjusted based on the user's emotions. For example, if the user is feeling anxious, the unit can adjust to acquire information from reliable sources. This enables flexible responses that respond to the user's emotions.

[0088] The extraction unit can estimate the user's emotions and determine the priority of information to extract based on those estimated emotions. For example, the extraction unit can analyze the user's facial expressions and voice to estimate their emotions. It can also estimate emotions based on user feedback. This allows the system to prioritize information extraction according to the user's emotions, thereby prioritizing the extraction of more important information. For example, if the user is tense, the extraction unit can adjust to prioritize the extraction of important information. If the user is relaxed, the extraction unit can extract information with the usual priority. Furthermore, the system can adjust how the extraction results are displayed based on the user's emotions. For example, if the user is stressed, the extraction results can be displayed in a visually easy-to-understand manner. This enables flexible responses that respond to the user's emotions.

[0089] The analysis department can conduct analyses while considering the product's usage environment and storage conditions. For example, it can collect information on the product's usage environment and incorporate it into the analysis. For instance, if the product is used in a high-temperature environment, it will focus on analyzing its resistance to high temperatures. It can also collect information on the product's storage conditions and incorporate it into the analysis. For example, if the product is stored in a high-humidity environment, it will focus on analyzing its resistance to humidity. Furthermore, it can conduct analyses while comprehensively considering the product's usage environment and storage conditions. For example, if the product is used in a high-vibration environment, it will focus on analyzing its resistance to vibration. By considering the product's usage environment and storage conditions, it is possible to provide more practical analysis results.

[0090] The information acquisition unit can evaluate the reliability of the information and select the information to acquire. For example, it can evaluate the reliability of the information source and prioritize the acquisition of highly reliable information. For example, it can evaluate the past performance of the information source and acquire highly reliable information. It can also evaluate the frequency of information updates and prioritize the acquisition of the latest information. For example, it can evaluate the frequency of information updates of the information source and acquire the latest information. Furthermore, it can evaluate the accuracy of the information and acquire highly reliable information. For example, it can evaluate the accuracy of the information source and acquire highly reliable information. In this way, by evaluating the reliability of the information and selecting the information to acquire, highly reliable information can be obtained.

[0091] The extraction unit can apply different extraction algorithms depending on the format of the information. For example, a natural language processing algorithm can be applied to text-formatted information. Similarly, an image recognition algorithm can be applied to image-formatted information. Furthermore, a PDF analysis algorithm can be applied to PDF-formatted information. This allows for the application of the most suitable extraction algorithm for each information format, thereby improving the accuracy of information extraction.

[0092] The analysis department can improve the accuracy of its hazardous materials classification by referring to past accident data. For example, it can identify products with a high fire risk by referring to past fire accident data. For example, it can identify products with a high fire risk by obtaining past fire accident data from a database. It can also identify products with a high explosion risk by referring to past explosion accident data. For example, it can identify products with a high explosion risk by analyzing past explosion accident data. Furthermore, it can identify products with a high leakage risk by referring to past leakage accident data. For example, it can identify products with a high leakage risk by analyzing past leakage accident data. In this way, the accuracy of hazardous materials classification is improved by referring to past accident data.

[0093] The information acquisition unit can acquire and integrate information from multiple sources. For example, it can acquire and integrate information from the websites of multiple manufacturers. For example, it can acquire and integrate SDSs and test result reports from the websites of multiple manufacturers. It can also acquire and integrate information from databases of multiple government agencies. For example, it can acquire and integrate information on hazardous materials from databases of multiple government agencies. Furthermore, it can acquire and integrate information from reports of multiple research institutions. For example, it can acquire and integrate information on hazardous materials from reports of multiple research institutions. By integrating and acquiring information from multiple sources, the comprehensiveness of the information is improved.

[0094] The extraction unit can adjust the level of detail of the extraction based on the importance of the information. For example, highly important information can be extracted in detail. Less important information can also be extracted concisely. Furthermore, the level of detail of the extraction can be adjusted in stages according to the importance of the information. This allows for the appropriate extraction of necessary information by adjusting the level of detail based on the importance of the information.

[0095] The extraction unit can estimate the user's emotions and adjust the display method of the extraction results based on the estimated emotions. For example, it can analyze the user's facial expressions and voice to estimate their emotions. It can also estimate emotions based on user feedback. This allows for a more appropriate display method by adjusting the display method of the extraction results according to the user's emotions. For example, if the user is feeling stressed, the extraction results can be displayed in a visually easy-to-understand manner. If the user is relaxed, a concise display method can be provided. Furthermore, the display content can be adjusted based on the user's emotions. For example, if the user is feeling anxious, detailed information can be displayed. This enables a flexible response that responds to the user's emotions.

[0096] The following briefly describes the processing flow for example form 2.

[0097] Step 1: The analysis department analyzes product information. This information includes product specifications, ingredient information, and usage instructions. The analysis department uses text mining and image recognition technologies to analyze the product information and determine whether the product is classified as a hazardous material by analyzing the information on the product label and instructions. Step 2: The acquisition unit acquires hazardous materials information based on the information analyzed by the analysis unit. The acquisition unit automatically downloads information on hazardous materials from the manufacturer's website and acquires the information using web scraping technology. If the necessary information is not available on the website, it requests the information from the manufacturer using automated email or API requests. Step 3: The extraction unit extracts the necessary information based on the information acquired by the acquisition unit. The extraction unit uses PDF analysis technology to accurately extract the necessary information from various PDF formats such as SDS, test result reports, and product labels. For example, it extracts a list of chemical substances and hazard assessments from SDSs, and extracts the key points of test results from test result reports.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0100] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0101] Each of the multiple elements described above, including the analysis unit, acquisition unit, and extraction unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 and analyzes product information using text mining and image recognition technologies. The acquisition unit is implemented by the identification processing unit 290 of the data processing device 12 and automatically downloads hazardous materials information from the manufacturer's website. The extraction unit is implemented by the identification processing unit 290 of the data processing device 12 and accurately extracts necessary information from SDS and test result reports. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0102] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0103] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0104] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0105] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0106] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0108] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0109] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0110] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0111] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0112] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0117] Each of the multiple elements described above, including the analysis unit, acquisition unit, and extraction unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 and analyzes product information using text mining and image recognition technologies. The acquisition unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and automatically downloads hazardous materials information from the manufacturer's website. The extraction unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and accurately extracts necessary information from SDS and test result reports. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0118] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0119] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0121] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0122] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0124] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0125] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0126] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0127] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0128] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements described above, including the analysis unit, acquisition unit, and extraction unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 and analyzes product information using text mining and image recognition technologies. The acquisition unit is implemented by the identification processing unit 290 of the data processing unit 12 and automatically downloads hazardous materials information from the manufacturer's website. The extraction unit is implemented by the identification processing unit 290 of the data processing unit 12 and accurately extracts necessary information from SDS and test result reports. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0134] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0135] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0136] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0137] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0138] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0140] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0141] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0142] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0143] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0144] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0145] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0147] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0149] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the analysis unit, acquisition unit, and extraction unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 and analyzes product information using text mining and image recognition technologies. The acquisition unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and automatically downloads hazardous materials information from the manufacturer's website. The extraction unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and accurately extracts necessary information from SDS and test result reports. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0151] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0152] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0153] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0154] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0155] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0156] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0157] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0158] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0159] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0160] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0161] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0162] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0163] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0164] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0165] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0166] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0167] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0168] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0169] (Note 1) The analysis department analyzes product information, An acquisition unit that acquires hazardous materials information based on the information analyzed by the aforementioned analysis unit, An extraction unit extracts necessary information based on the information acquired by the acquisition unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned analysis unit is Analyze product information using both text and images. The system described in Appendix 1, characterized by the features described herein. (Note 3) The acquisition unit is, Automatically downloads information about hazardous materials from the manufacturer's website. The system described in Appendix 1, characterized by the features described herein. (Note 4) The acquisition unit is, If the necessary information is not available on the website, the system will automatically request the manufacturer to provide it. The system described in Appendix 1, characterized by the features described herein. (Note 5) The extraction unit is It accurately extracts necessary information from various PDF formats, such as SDS, test result reports, and product labels. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit is We estimate user sentiment and adjust the product information analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit is The analysis will take into account the product's usage environment and storage conditions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit is By referring to past accident data, we can improve the accuracy of determining whether a material is classified as hazardous. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit is The analysis will be conducted taking into account the product's manufacturing process information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit is The analysis will take into account the product's transportation history. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, The system estimates the user's emotions and adjusts the timing of acquiring hazardous materials information based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The acquisition unit is, Evaluate the reliability of the information and select the information to acquire. The system described in Appendix 1, characterized by the features described herein. (Note 14) The acquisition unit is, Integrate and obtain information from multiple sources. The system described in Appendix 1, characterized by the features described herein. (Note 15) The acquisition unit is, It estimates the user's emotions and determines the priority of information to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The acquisition unit is, Select the information to acquire, taking into account the frequency of information updates. The system described in Appendix 1, characterized by the features described herein. (Note 17) The acquisition unit is, Evaluate the reliability of the information provider and select the information to be obtained. The system described in Appendix 1, characterized by the features described herein. (Note 18) The extraction unit is It estimates the user's emotions and determines the priority of information to extract based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The extraction unit is Adjust the level of detail in the extraction based on the importance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 20) The extraction unit is Evaluate the relevance of the information and select the information to extract. The system described in Appendix 1, characterized by the features described herein. (Note 21) The extraction unit is It estimates the user's emotions and adjusts how the extraction results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The extraction unit is Apply different extraction algorithms depending on the format of the information. The system described in Appendix 1, characterized by the features described herein. (Note 23) The extraction unit is Evaluate the reliability of the information providers and select the information to extract. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis department analyzes product information, An acquisition unit that acquires hazardous materials information based on the information analyzed by the aforementioned analysis unit, An extraction unit extracts necessary information based on the information acquired by the acquisition unit, Equipped with A system characterized by the following features.

2. The aforementioned analysis unit is Analyze product information using both text and images. The system according to feature 1.

3. The acquisition unit is, Automatically downloads information about hazardous materials from the manufacturer's website. The system according to feature 1.

4. The acquisition unit is, If the necessary information is not available on the website, the system will automatically request the manufacturer to provide it. The system according to feature 1.

5. The extraction unit is It accurately extracts necessary information from various PDF formats, such as SDS, test result reports, and product labels. The system according to feature 1.

6. The aforementioned analysis unit is We estimate user sentiment and adjust the product information analysis method based on the estimated user sentiment. The system according to feature 1.

7. The aforementioned analysis unit is The analysis will take into account the product's usage environment and storage conditions. The system according to feature 1.

8. The aforementioned analysis unit is By referring to past accident data, we can improve the accuracy of determining whether a material is classified as hazardous. The system according to feature 1.

Images