System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information on past accidents and oversights; means for preprocessing the collected data and converting the data into an analyzable format; means for extracting a risk pattern from the preprocessed data using natural language processing; means for receiving requirement definition information of a new project; means for evaluating a risk by comparing the requirement definition information of the new project with the risk pattern; and means for feeding back a risk item to a user based on the evaluation result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a need for a system that can prevent risks in new projects by effectively utilizing information on past accidents and fire ant misses within a company. In particular, a challenge is to effectively identify risks that are likely to occur during the new requirements definition and design stages based on information on similar accidents and fire ant misses that have occurred in the past. Furthermore, current methods tend to delay risk evaluation and feedback, which can result in inadequate risk management in new projects. A system that can solve these issues is needed. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system having the following features: A system including: means for collecting information on past accidents and fire ant misses; means for preprocessing the collected data and converting it into an analyzable format; means for extracting risk patterns from the preprocessed data using natural language processing; means for receiving requirements definition information for a new project; means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns; and means for providing feedback on risk items to a user based on the evaluation results. Furthermore, by further including means for clustering information on past accidents and fire ant misses to generate related risk patterns, and means for generating a report including risk indications based on the collected data and providing the report to a user, risk management for new projects can be effectively performed.

[0006] "Means of collection" refers to means that have the function of obtaining information on past accidents and fire ant hats from a database and collecting related information.

[0007] The "preprocessing means" is a means having a function for cleansing collected data and converting it into an analyzable format.

[0008] "Natural language processing" is a technology that analyzes text data and extracts risk patterns and commonalities.

[0009] "Risk patterns" refer to common risk elements and patterns extracted from past accidents and fire ant hat information.

[0010] The "receiving means" is a means having the function of acquiring requirement definition information for a new project and receiving it as data.

[0011] The "means for matching" is a means that has the function of comparing the requirements definition information of a new project with past risk patterns and evaluating the degree of similarity.

[0012] The "means for assessing risk" is a means having a function for assessing the risk in a new project based on the collation results and calculating a risk score.

[0013] "Feedback means" refers to a means that has the function of notifying the user of identified risks based on the evaluation results.

[0014] "Clustering" is a technique for grouping collected data based on similarity and generating associated risk patterns.

[0015] The "means for generating a report" is a means having a function for automatically generating a report summarizing identified risk items and providing it to the user. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0028] 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. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] System Configuration

[0038] This invention relates to a system that collects and analyzes information on past accidents and fire ant incidents, with the aim of preventing risks in new projects. The system is mainly composed of three elements: a server, a terminal, and a user.

[0039] 1. Server: Responsible for the main processing of data collection, pre-processing, analysis using natural language processing, risk assessment, risk feedback and report generation.

[0040] 2. Terminal: Serves as an interface for users to enter requirements for new projects and receive feedback and reports from the server.

[0041] 3. User: The entity that inputs the requirements definition for a new project and improves the project design based on the risk findings and reports provided by the server.

[0042] Program processing (overview)

[0043] The system's program is configured to achieve the following main functions:

[0044] Data collection

[0045] The server collects information on past accident reports and fire ant hats within the company. This collection is done via database queries and file system access. For example, it retrieves a report on a "fault in function A" that occurred in "project A."

[0046] Data Preprocessing

[0047] The server converts the collected data into an analyzable format, specifically by performing text cleansing to remove unnecessary white space and special characters, and using morphological analysis to extract important keywords and phrases.

[0048] Data analysis using natural language processing

[0049] The server performs natural language processing on the preprocessed data, extracting important keywords and risk patterns and clustering information on similar accidents and fire ant incidents. For example, if a "fault with user authentication" appears in multiple reports, it will be identified as a single risk pattern.

[0050] risk assessment

[0051] When a user inputs a requirement definition for a new project into a terminal, the terminal sends this information to the server, which analyzes the information and compares it with past risk patterns, thereby evaluating the potential risks in the new project.

[0052] Risk Feedback

[0053] The server provides real-time feedback to the user on risk issues based on the evaluation results, such as "There have been many problems with password encryption in the past, so you should recheck the encryption specifications for the user authentication function."

[0054] Report Generation

[0055] The server generates a report summarizing the risk assessment and feedback and provides it to the user. The report includes past cases, recommended countermeasures, details of the risk assessment, etc. For example, it generates a detailed report on "Past cases of accidents related to user authentication functions and recommended countermeasures."

[0056] Specific examples

[0057] Scenario 1: Data collection and preprocessing

[0058] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0059] Scenario 2: Data Analysis with Natural Language Processing

[0060] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0061] Scenario 3: Risk Assessment and Feedback

[0062] When a user inputs a requirement such as "Implementing user authentication functionality in the development of a new web application" from a terminal, the server compares this information with past risk patterns and proactively identifies the risk of "frequent password encryption errors."

[0063] Scenario 4: Report Generation

[0064] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0065] In this way, the present invention provides an effective system for effectively utilizing information on past accidents and fire ant hats to prevent risks in new projects.

[0066] The processing flow will be explained below.

[0067] Step 1: Data collection

[0068] The server connects to the company's internal database to retrieve past accident reports and fire ant hat information. It uses a database query to extract the required records and downloads the data in a format such as JSON or CSV. For example, it executes the query "SELECT FROM incidents WHERE date > '2020-01-01'" on the database.

[0069] Step 2: Data Preprocessing

[0070] The server preprocesses the collected data. Specifically, it performs text cleansing to remove unnecessary white space and special characters. It then performs morphological analysis to break down sentences into tokens and extract important keywords and phrases. This converts the data into a format that is easy to analyze.

[0071] Step 3: Data analysis using natural language processing

[0072] The server performs natural language processing on the preprocessed data, analyzing frequently occurring words and co-occurrence networks to extract risk patterns. For example, risk patterns such as "insufficient code review" and "insufficient testing" are extracted. The server then clusters the data using similarity calculations to identify related risk factors.

[0073] Step 4: Risk Assessment

[0074] A user inputs requirements definition information for a new project into a terminal. For example, a requirement might be "Implement user authentication functionality in a new web application." The terminal then sends this information to the server. The server compares the received requirements definition information with past risk patterns and performs a risk assessment. A risk score is calculated based on the comparison results, and potential problems are identified.

[0075] Step 5: Risk feedback

[0076] The server provides the results of the risk assessment to the user in real time. For example, it may provide specific feedback via the terminal, such as, "There have been many instances of password encryption errors in the past in the user authentication function, so the encryption specifications should be rechecked." Based on this feedback, the user can revise the project requirements definition and design.

[0077] Step 6: Generate reports

[0078] The server generates a detailed report containing risk findings. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a specific report such as "Past incidents related to user authentication functions and recommended countermeasures" is created. The report is provided to the user via their device in a downloadable format.

[0079] In this way, by executing each step sequentially, the system can efficiently identify risks in new projects in advance and provide users with the necessary guidance and countermeasures.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] Conventional project management systems have difficulty effectively utilizing information on past accidents and fire ant hats to prevent risks in new projects. Furthermore, they lack the means to convert collected information into an analyzable format and extract risk patterns using natural language processing, resulting in issues with the accuracy and speed of risk assessment. Furthermore, they lack the means to provide specific feedback to users based on risk assessment results, or to provide detailed reports of that information.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes means for collecting information on past accidents and fire ant hats, means for preprocessing the collected information and converting it into an analyzable format, means for extracting risk patterns from the preprocessed information using natural language processing, means for receiving requirements definition information for a new project, means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns, means for providing feedback on risk items to a user based on the evaluation results, and means for generating a report summarizing the risk evaluation results and the feedback content and providing it to the user. This makes it possible to effectively utilize past information, identify risks in new projects in advance, and take measures.

[0085] "Past accident and fire ant information" refers to reports of troubles that have occurred within companies and organizations and information on hazard predictions.

[0086] "Means of collection" refers to the method of obtaining information via database queries or file system access.

[0087] "Means for preprocessing and converting into an analyzable format" refers to methods for formatting data using text cleansing and morphological analysis and converting it into a format suitable for analysis.

[0088] "Natural language processing" refers to the technology of analyzing text data using a computer and extracting meaning and patterns.

[0089] "Means for extracting risk patterns" refers to methods for identifying and extracting common risk elements from pre-processed data.

[0090] "Requirements definition information for a new project" refers to information about the functions, specifications, and requirements of a newly started project.

[0091] "Means for receiving" refers to the method by which the server receives information input by the user.

[0092] "Means for cross-checking and assessing risks" refers to a method for comparing the requirements definition information of a new project with existing risk patterns to identify potential risks.

[0093] "Means for providing feedback on risk items to users" refers to a method for providing information on identified risks to users in real time.

[0094] "Means for generating a report and providing it to the user" refers to a method for creating a report summarizing the evaluation results and feedback content and delivering it to the user.

[0095] "Clustering" refers to a machine learning technique that groups similar data.

[0096] "Risk findings" refer to potential risks identified for a new project based on past examples.

[0097] "Text cleansing" refers to the process of cleaning and removing unnecessary white space and special characters from text data.

[0098] "Methods for extracting important keywords and phrases" refers to methods for selecting particularly meaningful words and phrases from text data.

[0099] The present invention relates to a system that collects and analyzes information on past accidents and fire ant incidents, and aims to prevent risks in new projects. Specific embodiments of the present invention will be described in detail below.

[0100] System Configuration

[0101] The system of the present invention is mainly composed of three elements: a server, a terminal, and a user.

[0102] 1. Server: Responsible for the main processing of data collection, pre-processing, analysis using natural language processing, risk assessment, risk feedback and report generation.

[0103] 2. Terminal: Serves as an interface for users to enter requirements for new projects and receive feedback and reports from the server.

[0104] 3. User: The entity that inputs the requirements definition for a new project and improves the project design based on the risk findings and reports provided by the server.

[0105] Hardware and software used

[0106] The server uses Python's psycopg2 library to retrieve information from a PostgreSQL database to collect past accident reports and fire ant hat information from within the company. This allows for efficient collection of past accident and fire ant hat information. Python's NLTK library is used for data preprocessing, which performs text cleansing and morphological analysis to convert the data into an analyzable format.

[0107] Next, we use the Python sklearn library for natural language processing. Specifically, we use TF-IDF vectorization and K-means clustering to extract important keywords and risk patterns. This allows us to identify common risk elements from past accident reports and extract them as risk patterns.

[0108] The user inputs the requirements definition for a new project into the terminal, and the information is sent to the server. The server compares the information with risk patterns collected and processed in the past and evaluates potential risks. Based on the evaluation results, specific risk indications are fed back to the user in real time.

[0109] The risk assessment and feedback are then compiled into a detailed report that includes the assessment results, feedback, past similar incidents, and countermeasures taken. The report is generated using the Python FPDF library.

[0110] Specific examples

[0111] Specific examples of data collection and preprocessing

[0112] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0113] Specific examples of data analysis using natural language processing

[0114] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0115] Examples of risk assessment and feedback

[0116] When a user enters the requirements definition for a new project, such as "Implementing user authentication functionality in the development of a new web application," into a terminal, the server compares this information with past risk patterns and identifies the risk of "frequent password encryption errors" in advance.

[0117] Example of report generation

[0118] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0119] Prompt Sentence Examples

[0120] "We are developing a new web app and are planning to implement user authentication. However, we have seen many issues with user authentication in past projects. Please use this information to identify potential risks and provide specific feedback."

[0121] As described above, the present invention provides an effective system for preventing risks in new projects by effectively utilizing information on past accidents and fire ant sightings.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1: Data collection

[0124] The server retrieves past accident reports and fire ant information from the database. Specifically, it uses Python's psycopg2 library to send queries to the PostgreSQL database and collect information for the target period (for example, from 2020 onwards). The input is an SQL query, and the output is a dataset of accident reports and fire ant information. For example, it retrieves a report about a "fault in function A" related to "project A."

[0125] Step 2: Data Preprocessing

[0126] The server performs preprocessing to convert the collected data into an analyzable format. Specifically, it uses Python's NLTK library to perform text cleansing (removing unnecessary white space and special characters) and morphological analysis. This allows important keywords and phrases to be extracted. The input is the collected data, and the output is cleansed text data. For example, keywords such as "code review," "bug," and "deficiency" are extracted.

[0127] Step 3: Data analysis using natural language processing

[0128] The server performs natural language processing on the preprocessed data. Specifically, it performs TF-IDF vectorization using Python's sklearn library and extracts risk patterns using K-means clustering. The input is cleansed text data, and the output is a cluster of risk patterns. For example, it identifies patterns such as "insufficient code reviews" and "insufficient testing."

[0129] Step 4: Risk Assessment

[0130] When a user inputs the requirements definition for a new project into a terminal, it is sent to the server. The server preprocesses this information and compares it with previously extracted risk patterns. The input is the requirements definition information for the new project, and the output is a potential risk assessment based on the comparison. For example, if a requirement such as "Implement user authentication functionality in new web application development" is input, the server will evaluate the risk of "frequent password encryption errors."

[0131] Step 5: Risk feedback

[0132] The server provides the user with specific feedback based on the risk assessment results in real time. The input is the risk assessment results, and the output is a specific feedback message to the user. For example, it generates a message saying, "There have been many problems with password encryption in the past, so you should recheck the encryption specifications of the user authentication function."

[0133] Step 6: Generate reports

[0134] The server generates a report summarizing the risk assessment and feedback and provides it to the user. Specifically, it creates a PDF report using Python's FPDF library. The input is the risk assessment results and feedback, and the output is a PDF report. For example, it generates a detailed report on "Past accidents related to user authentication functions and recommended countermeasures."

[0135] By following the above processing steps, this system effectively utilizes information on past accidents and fire ant hats, and provides specific actions to prevent risks in new projects.

[0136] (Application example 1)

[0137] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0138] At work sites such as factories, it is difficult to assess risks in real time based on information on past accidents and fire ant incidents, leaving many workers exposed to potential danger. Rather than simply using past accident data as a record, it is necessary to effectively utilize this data to immediately warn workers and assess risks while they are working on-site, thereby preventing accidents and fire ant incidents from occurring.

[0139] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0140] In this invention, the server includes means for collecting information on past accidents and fire ant hats, means for preprocessing the collected data and converting it into an analyzable format, means for extracting risk patterns from the preprocessed data using natural language processing, means for receiving requirements definition information for a new project, means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns, means for providing feedback on risk items to the user based on the evaluation results, means for recognizing the actions of workers and comparing them with a past accident database in real time, and means for providing feedback on warnings to the user when danger is detected. This enables real-time risk evaluation and warnings based on past accident data during work.

[0141] An "accident" refers to an unexpected problem or trouble that occurs at a work site or project.

[0142] "Fire ant hat information" refers to events or experiences that did not result in an accident but were close calls or startling events that almost led to danger.

[0143] "Collection means" refers to methods and systems for collecting information on past accidents and fire ant incidents from databases and documents.

[0144] "Preprocessing means" refers to data cleansing and formatting work to convert collected data into an analyzable format.

[0145] "Natural language processing methods" is a general term for machine learning and statistical methods used to analyze text data and extract meaning and patterns.

[0146] "Risk patterns" refer to common risk elements and models extracted from past accidents and fire ant hat information.

[0147] "Requirements definition information" refers to the conditions and specifications required when starting a new project.

[0148] An "assessment means" is a method or system for assessing risks by comparing the requirements definition information of a new project with risk patterns.

[0149] "Feedback means" refers to a method or system for notifying users of risk items based on the evaluation results and providing them with points for improvement or caution.

[0150] "Movement recognition means" refers to the technology or means for detecting and analyzing the actions and movements of workers using sensors, etc.

[0151] A "real-time comparison means" is a system that instantly compares the recognized actions of workers with a database of past accidents to assess risk.

[0152] "Warning feedback means" refers to a method or system for issuing a warning to a worker when a hazard is detected.

[0153] The system for implementing this invention consists of three main elements: a server, a terminal, and a user.

[0154] Server Configuration

[0155] The server is a combination of the following:

[0156] 1. Data collection method: Collect information on past accidents and fire ant hats from the company's database or file system. For example, retrieve accident reports using a database query.

[0157] 2. Preprocessing: Convert the collected data into an analyzable format, using text cleansing to remove unnecessary whitespace and special characters, and morphological analysis to extract keywords and phrases.

[0158] 3. Natural language processing: Natural language processing is performed on the preprocessed data to extract important keywords and risk patterns. Clustering is performed to identify common risk factors.

[0159] 4. Evaluation method: Receives new project requirements definition information and evaluates the risks by comparing them with past risk patterns, thereby revealing potential risks in the project.

[0160] 5. Feedback method: Based on the evaluation results, risk items are fed back to the user. In addition, the system recognizes the worker's actions and compares them with a database of past accidents in real time.

[0161] 6. Warning feedback means: If a danger is detected, a warning is sent to the user and specific countermeasures are presented.

[0162] Device configuration

[0163] The terminal acts as an interface for users to input requirements for new projects and receive feedback and warnings from the server, and also functions as a display for workers wearing smart glasses to receive real-time risk assessments and warnings.

[0164] Hardware and Software Use

[0165] Hardware: smart glasses (e.g. Google Glass), servers, PCs

[0166] Software: SQLite (database management system), Janome (Python morphological analysis library), scikit-learn (machine learning library)

[0167] Data processing and calculation

[0168] The server collects accident information from the database and performs preprocessing using text cleansing and morphological analysis. It then uses natural language processing technology to extract risk patterns and perform clustering. When it receives requirement definition information for a new project, it compares it with past risk patterns and evaluates and provides feedback on the risks. When it recognizes worker movements, it analyzes data from sensors in real time and immediately issues an alert if a danger is detected.

[0169] Specific examples

[0170] For example, consider a case where a worker is wearing smart glasses while handling materials at height in a factory. If the camera detects that the worker is not wearing a safety belt, the system will display a warning based on past accident data, such as:

[0171] "In the past, similar accidents have occurred due to failure to fasten seat belts. Please fasten your seat belt."

[0172] Prompt Sentence Examples

[0173] "New tasks in factory work: material handling when working at height"

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The server collects past accident and fire ant information from a database. The input is a database of accident reports, and the output is a list of collected accident reports. Specifically, it executes a database query to retrieve accident reports.

[0177] Step 2:

[0178] The server preprocesses the collected data and converts it into an analyzable format. The input is a list of collected accident reports, and the output is preprocessed text data. Specifically, it performs text cleansing to remove unnecessary white space and special characters, and uses morphological analysis to extract important keywords and phrases.

[0179] Step 3:

[0180] The server performs natural language processing on the preprocessed data. The input is preprocessed text data, and the output is extracted risk patterns. Specifically, natural language processing technology is used to analyze the data, extract important keywords and phrases, and perform clustering to identify risk patterns.

[0181] Step 4:

[0182] The server receives the requirements definition information of the new project and compares it with past risk patterns. The input is the requirements definition information of the new project, and the output is the risk assessment results. Specifically, the information of the new project is input into a clustering model, and potential risks are evaluated by comparing it with past risk patterns.

[0183] Step 5:

[0184] The server provides feedback to the user on risk items based on the evaluation results. The input is the risk evaluation results, and the output is a feedback message to the user. Specifically, the server generates risk items based on the evaluation results and notifies the user.

[0185] Step 6:

[0186] The terminal recognizes the worker's movements and sends them to the server. The input is the worker's movement data, and the output is the movement recognition results. Specifically, the terminal analyzes data acquired from the camera in the smart glasses and recognizes the worker's movements.

[0187] Step 7:

[0188] The server compares the action recognition results with a past accident database in real time. The inputs are the action recognition results and the accident database, and the output is risk warning information. Specifically, the action recognition results are compared with past accident data, and a risk warning is generated if a risk is detected.

[0189] Step 8:

[0190] If a risk is detected, the device provides a warning to the user. The input is risk warning information, and the output is a warning message displayed to the user. Specifically, the warning message is displayed on the smart glasses display to alert the user.

[0191] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0192] System Configuration

[0193] This invention relates to a system that collects and analyzes information on past accidents and fire ant incidents to prevent risks in new projects. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide appropriate feedback based on the user's emotional state. This system consists of three main components: a server, a terminal, and a user.

[0194] 1. Server: Responsible for the core processing of data collection, pre-processing, analysis using natural language processing, risk assessment, emotion recognition, risk feedback and report generation.

[0195] 2. Terminal: This serves as an interface for users to input requirements for new projects and receive feedback and reports from the server. It also collects user sentiment data.

[0196] 3. User: Enters requirements for a new project and improves the project design based on risk findings and reports provided by the server. Sentiment data is also provided.

[0197] Program processing (overview)

[0198] The system's program is configured to achieve the following main functions:

[0199] Data collection

[0200] The server retrieves past accident reports and fire ant information from the company's database. This collection is done via database queries and file system access. For example, it retrieves a report on a "fault in function A" related to "project A."

[0201] Data Preprocessing

[0202] The server preprocesses the collected data, specifically by performing text cleansing to remove unnecessary white space and special characters, and then performs morphological analysis to break down the sentences into tokens and extract important keywords and phrases.

[0203] Data analysis using natural language processing

[0204] The server performs natural language processing on the preprocessed data, analyzing frequently occurring words and co-occurrence networks to extract risk patterns. For example, risk patterns such as "insufficient code review" and "insufficient testing" are extracted. The server then clusters the data using similarity calculations to identify related risk factors.

[0205] risk assessment

[0206] A user inputs requirements definition information for a new project into a terminal. For example, a requirement might be "Implement user authentication functionality in a new web application." The terminal then sends this information to the server. The server compares the received requirements definition information with past risk patterns and performs a risk assessment. A risk score is calculated based on the comparison results, and potential problems are identified.

[0207] emotion recognition

[0208] The server acquires the user's emotional data through the device. To do this, it uses voice and facial recognition technology to analyze the user's emotional state. For example, if the user is feeling stressed, the emotion engine will detect this.

[0209] Risk Feedback

[0210] The server adjusts the feedback based on the results of the risk assessment and the user's emotional state. For example, if the user is feeling stressed, the server will point out the risks in a gentle tone. Specific feedback may include the following: "There have been many instances of password encryption errors in the past with the user authentication function, so you should recheck the encryption specifications."

[0211] Report Generation

[0212] The server generates a detailed report containing risk findings. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a specific report such as "Past incidents related to user authentication functions and recommended countermeasures" is created. The report is provided to the user via their device in a downloadable format.

[0213] Specific examples

[0214] Scenario 1: Data collection and preprocessing

[0215] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0216] Scenario 2: Data Analysis with Natural Language Processing

[0217] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0218] Scenario 3: Risk Assessment and Feedback

[0219] When a user inputs a requirement such as "Implementing user authentication functionality in the development of a new web application" from a terminal, the server compares this information with past risk patterns and proactively identifies the risk of "frequent password encryption errors."

[0220] Scenario 4: Emotion recognition and feedback regulation

[0221] The server obtains the user's emotional data from the device, detects when the user is feeling stressed, and provides feedback in a gentle tone, saying, "There have been many instances of password encryption errors in the past with the user authentication function, so please carefully recheck the encryption specifications."

[0222] Scenario 5: Report Generation

[0223] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0224] In this way, the present invention provides an effective system for efficiently preventing risks in new projects by utilizing information on past accidents and fire ant incidents as well as the user's emotional state.

[0225] The processing flow will be explained below.

[0226] Step 1: Data collection

[0227] The server connects to the company's database and retrieves past accident reports and fire alarm information. For example, it executes a query such as "SELECT FROM incident_reports WHERE date > '2020-01-01'" and downloads the corresponding records in JSON format. Alternatively, it can read past CSV files from the file system.

[0228] Step 2: Data Preprocessing

[0229] The server preprocesses the collected data. Specifically, it cleanses the data and removes unnecessary white space and special characters. Next, it performs morphological analysis, breaking down sentences into tokens and extracting important keywords and phrases. For example, it extracts words such as "insufficient code review" and "insufficient testing."

[0230] Step 3: Data analysis using natural language processing

[0231] The server performs natural language processing on the preprocessed data, extracting risk patterns from accident and fire ant reports. It analyzes frequently occurring words and co-occurrence networks, and then clusters the data using similarity calculations to identify related risk elements. For example, it identifies a risk pattern related to "insufficient code reviews" that is common to multiple reports.

[0232] Step 4: Receive requirements for the new project

[0233] The user inputs the requirements definition for a new project into the terminal. For example, the user inputs the requirement information "Implement user authentication function in a new web application." The terminal then sends this information to the server.

[0234] Step 5: Risk Assessment

[0235] The server analyzes the received requirements definition information for the new project. It then compares it with existing past risk patterns and performs a risk assessment. This identifies potential risks in the new project and calculates a risk score. For example, it assesses the risk of user authentication functions based on past "password encryption errors."

[0236] Step 6: Obtaining emotion data

[0237] The server acquires the user's emotional data from the device. For example, it analyzes the user's tone of voice and facial expressions when inputting information, and uses an emotion engine to determine the user's emotional state (e.g., stress, relaxation).

[0238] Step 7: Emotion-Based Risk Feedback

[0239] The server combines the risk assessment results with the user's emotional state to generate appropriate feedback. For example, if the user is feeling stressed, the server may notify the user in a gentle tone, saying, "There have been many instances of password encryption errors in the past in the user authentication function, so please recheck the encryption specifications." The server then sends the risk feedback to the user via their device.

[0240] Step 8: Generate reports

[0241] The server generates a detailed report summarizing the identified risks. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a report on "Past incidents and recommended countermeasures for user authentication functions" is created. The report is provided to the user via their device, along with a downloadable link.

[0242] In this way, by executing each step sequentially, a system including an emotion engine can efficiently identify risks in new projects in advance and provide users with necessary guidance and countermeasures. Furthermore, by providing feedback that takes into account the user's emotional state, it reduces the burden on the user and achieves effective risk management.

[0243] Example 2

[0244] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0245] Conventional risk management systems are unable to fully utilize accident reports and fire ant information, and are unable to provide feedback that takes into account the user's emotional state, making it difficult to prevent risks in new projects.Furthermore, there is also the problem that providing specific risk feedback can easily cause stress to users.

[0246] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0247] In this invention, the server includes a means for collecting information on past accidents and fire ant incidents, a means for preprocessing the collected data and converting it into an analyzable format, and a means for extracting risk patterns from the preprocessed data using natural language processing, thereby enabling the collected information to be effectively analyzed and risks associated with new projects to be identified.

[0248] The server further includes means for receiving requirements definition information for a new project, means for comparing the requirements definition information for the new project with the risk pattern to evaluate risks, means for providing risk items as feedback to the user based on the evaluation results, means for acquiring emotional data of the user using voice recognition and face recognition technology to recognize emotions, and means for adjusting the content of the risk feedback based on the emotional data. This makes it possible to provide appropriate risk feedback according to the user's emotional state and reduce stress.

[0249] "Past accident and fire ant information" refers to records of accidents and incidents that have occurred within a company or organization, and is data collected to prevent risks before they occur.

[0250] A "means of collection" is a method for gathering the required information, such as using a database query or file system access.

[0251] "Means of preprocessing and converting into an analyzable format" refers to methods of removing noise from raw data, performing morphological analysis and tokenization, and preparing the data in an appropriate format for analysis.

[0252] "Natural language processing" is a technology that processes text data so that it can be analyzed by machines, and analyzes frequently occurring words and co-occurrence networks to extract important keywords and risk patterns.

[0253] "Risk patterns" are risk factors discovered through data analysis and the characteristics of associated error patterns.

[0254] "Requirements definition information for a new project" is information that describes the technical and functional requirements needed for a new project.

[0255] "Means for assessing risk" is a method for comparing past risk patterns with the requirements of a new project to measure potential danger.

[0256] "Feedback methods" are methods for notifying users of the results of risk assessment and providing specific improvements and points of caution for the project.

[0257] "Speech recognition technology" is a technology that analyzes voice data collected by microphones and other devices to understand the speaker's emotions and content.

[0258] "Facial recognition technology" is a technology that analyzes facial expressions captured by a camera or other device to determine the emotional state of the subject.

[0259] "Emotion data" is information about the user's emotional state obtained using voice recognition or face recognition technology.

[0260] The "means for emotion recognition" is a method for analyzing collected emotion data and determining the user's emotional state.

[0261] The "means for adjusting the content of feedback" refers to a method for appropriately changing the content of notifications and the tone of feedback to the user based on the results of emotion recognition.

[0262] This invention is a system that collects and analyzes information on past accidents and fire ant hats to prevent risks in new projects. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide appropriate feedback based on the user's emotional state. This system consists of three main components: a server, a terminal, and a user.

[0263] server

[0264] The server is responsible for data collection, pre-processing, natural language processing, risk assessment, emotion recognition, risk feedback and report generation.

[0265] 1. The server retrieves past accident reports and fire alarm information from within the company using database queries and file system access. For example, it executes an SQL query such as "SELECT FROM accident_reports WHERE project_id = 'A';".

[0266] 2. The server performs text cleansing on the collected data. This process uses a text analysis library (e.g., Python's regular expression library) and a morphological analysis tool (e.g., MeCab) to extract important keywords. For example, from the sentence "This bug occurred due to a lack of code review," keywords such as "bug," "code review," and "lack" are extracted.

[0267] 3. The server performs natural language processing on the preprocessed data using an NLP library (e.g., spaCy, NLTK). For example, it uses TF-IDF to analyze and extract risk patterns such as "insufficient testing" and "lack of code reviews."

[0268] 4. The server receives the requirements definition information of the new project and performs risk assessment by comparing it with past risk patterns. In this process, a risk score is calculated based on the requirements information of the new project and potential problems are identified.

[0269] 5. The server acquires the user's emotional data using voice recognition and facial recognition technology (e.g., OpenCV, Affectiva) and performs emotion recognition. For example, it captures the user's facial expressions with a camera and analyzes their emotional state.

[0270] 6. The server adjusts the content of the risk feedback based on the results of the risk assessment and the user's emotional state. For example, if the user is feeling stressed, the server provides feedback in a gentle tone. It also provides specific instructions such as, "There have been many instances of password encryption errors in the past with the user authentication function, so please carefully recheck the encryption specifications."

[0271] 7. The server generates a PDF report containing past incidents, detailed risk assessments, and recommended countermeasures. For example, a report titled "Past incidents related to user authentication functions and recommended countermeasures" is created and notified to the user via their device.

[0272] Terminal

[0273] The terminal functions as an interface for users to input requirements for new projects and receive feedback and reports from the server, and also collects user emotional data and sends it to the server.

[0274] User

[0275] Users input requirements for new projects and improve the project design based on risk findings and reports provided by the server. They also provide sentiment data, which contributes to the system's feedback adjustments.

[0276] Prompt Sentence Examples

[0277] "Write a program that analyzes past accident reports and generates risk findings for new projects."

[0278] "Please explain the algorithms used by the system to analyze user emotional data and adjust feedback."

[0279] In this way, the system can prevent risks in the next new project, and by providing feedback according to the user's emotional state, risk management can be more effective.

[0280] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0281] Step 1: Data collection

[0282] The server uses database queries and file system access to retrieve past accident reports and fire ant information stored within the company. As input, it uses a query statement or file path to execute an SQL query. As a specific example, it executes the SQL query "SELECT FROM accident_reports WHERE project_id = 'A';". As output, it obtains a dataset of collected accident reports and fire ant information.

[0283] Step 2: Data Preprocessing

[0284] The server performs text cleansing on the collected data. It uses the collected accident report dataset as input. Specifically, it uses Python's regular expression library to remove unnecessary whitespace and special characters. It then uses a morphological analysis tool (e.g., MeCab) to break it down into tokens and extract important keywords and phrases. The cleansed and analyzed dataset is obtained as output.

[0285] Step 3: Data analysis using natural language processing

[0286] The server performs natural language processing on the preprocessed data using an NLP library (e.g., spaCy, NLTK). The preprocessed dataset is used as input. Specifically, it extracts frequently occurring words using TF-IDF and analyzes co-occurrence networks. Clustering techniques are used to extract risk patterns. The output is risk patterns such as "insufficient testing" and "lack of code review" and related risk factors.

[0287] Step 4: Receive requirements for your new project

[0288] The user inputs the requirements definition information for the new project through the terminal. As input, the project requirements manually entered by the user (e.g., "Implement user authentication functionality in a new web application") are used. The terminal sends the input information to the server. As output, the requirements definition information for the new project is obtained and sent to the server.

[0289] Step 5: Risk Assessment

[0290] The server receives the requirements definition information for a new project and compares it with past risk patterns to perform a risk assessment. The received project requirements definition information and past risk patterns are used as input. Specifically, a similarity calculation algorithm is used to compare the information and calculate a risk score. The output is the results of the risk assessment and potential problems.

[0291] Step 6: Emotion Recognition

[0292] The device collects the user's emotional data using a camera and microphone. The input is the user's audio and video data. The server analyzes this data to determine the user's emotional state. Specific operations include using voice recognition and facial recognition technology (e.g., OpenCV, Affectiva). The output is data related to the user's emotional state.

[0293] Step 7: Risk Feedback

[0294] The server adjusts the content of risk feedback taking into account the results of risk assessment and the user's emotional state. It uses the risk assessment results and emotion recognition data as input. Specific behavior involves generating a feedback message, providing it in a gentle tone if the user is feeling stressed. Specific feedback messages (e.g., "There have been many instances of password encryption errors in the past in the user authentication function, so please carefully recheck the encryption specifications") are obtained as output.

[0295] Step 8: Generate reports

[0296] The server generates a detailed report containing risk findings. It uses the collected and analyzed data, risk assessment results, and feedback as input. Specific operations include creating a report in PDF format and notifying the user via their terminal. The output is a detailed report (e.g., "Past incidents related to user authentication functions and recommended countermeasures").

[0297] The above are the specific processing steps of the program of this system.

[0298] (Application example 2)

[0299] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0300] In conventional manufacturing lines, there is a need for a system that can efficiently collect and analyze information on past accidents and near misses to prevent potential risks in new projects. However, current systems have the problem of providing uniform feedback without taking the user's emotional state into consideration, which often leads to stress for workers and results in workers not receiving appropriate feedback. Furthermore, they lack the functionality to automatically generate detailed risk reports, making it difficult for users to take adequate measures. These issues need to be resolved.

[0301] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0302] In this invention, the server includes means for collecting information on past accidents and near misses, means for preprocessing the collected data and converting it into an analyzable format, and means for extracting risk patterns from the preprocessed data using natural language processing. This makes it possible to evaluate the risks of a new project based on information on past accidents and near misses, adjust the feedback provided to the user according to the user's emotional state, and automatically generate a detailed risk report.

[0303] "Accident information" is a detailed record of past accidents that have occurred on production lines or projects.

[0304] "Near miss information" refers to information about close calls or startling experiences or moments when people felt danger, even though they did not result in an accident.

[0305] "Emotion data" is data that represents the user's emotional state and is acquired through voice recognition, face recognition, or the like.

[0306] "Risk patterns" are data that are analyzed based on past accident and near-miss information and show trends in risks that occur repeatedly under specific conditions or situations.

[0307] "Requirements definition information" is information that describes the functions and specifications required for a new project, as well as their details.

[0308] "Clustering" is a data analysis technique for grouping data with similar characteristics and identifying common risk patterns.

[0309] "Feedback" refers to information about the results of risk assessment, points to note, and improvement suggestions that the system provides to the user.

[0310] The "report" is a summary of detailed information such as risk assessment results, past accident examples, and recommended countermeasures.

[0311] This invention is a system for preventing risks on production lines and providing appropriate feedback according to the emotional state of workers. The system consists of three main components: a server, a terminal, and a user.

[0312] System Overview

[0313] The system has the following main functions:

[0314] 1. Collecting information on past accidents and near misses

[0315] 2. Analysis of preprocessed data using natural language processing

[0316] 3. Receive requirements for a new project

[0317] 4. Risk assessment and feedback of risk assessment results

[0318] 5. Acquisition and Analysis of Emotion Data

[0319] 6. Adjust feedback based on emotional data

[0320] 7. Generate detailed reports

[0321] server

[0322] The server is responsible for the core processing of the system. Specifically, it is responsible for the following:

[0323] 1. Collecting information on past accidents and near misses:

[0324] The server collects information on past accidents and near misses from the company's database and various files. For example, it collects reports on "malfunctions of function A" related to "production line A."

[0325] 2. Data Preprocessing:

[0326] The server preprocesses the collected data and converts it into an analyzable format, specifically by performing text cleansing to remove unnecessary spaces and special characters, and then performing morphological analysis to extract important keywords and phrases.

[0327] 3. Data analysis using natural language processing:

[0328] Natural language processing is performed on the preprocessed data, and risk patterns are extracted by analyzing frequently occurring words and co-occurrence networks. This allows risk patterns such as "insufficient code reviews" and "insufficient testing" to be identified.

[0329] 4. Risk Assessment:

[0330] Based on the requirements definition information of a new project, risk assessment is performed by comparing it with past risk patterns. For example, a requirement to "introduce a new safety system" is received as project information, and a risk score is calculated by comparing it with past risk information.

[0331] 5. Acquiring and analyzing emotion data:

[0332] The system acquires user emotion data from the device and analyzes it using emotion recognition technology. For example, if a worker is feeling stressed, this can be detected using voice and facial recognition technology.

[0333] 6. Feedback adjustment:

[0334] Tailor feedback based on risk assessment and emotional data, for example, softening the tone of feedback if the user is stressed.

[0335] 7. Report Generation:

[0336] Generate detailed reports containing risk findings and provide them to users. For example, create a report containing "Past incidents and recommended countermeasures for new safety systems."

[0337] Terminal

[0338] The terminal acts as an interface for users to input requirements for new projects and receive feedback and reports from the server, and also collects emotion data using voice and facial recognition technology.

[0339] User

[0340] Users input requirements definition information for new projects and improve the project design based on risk findings and reports provided by the server. Users also have the role of providing their own emotional data.

[0341] Examples of specific examples and prompts

[0342] For example, a user inputs a project requirement, such as "introduce a safety system to a new manufacturing line," into a terminal and provides a facial image (worker_image.jpg) through the terminal. The server uses this information to perform risk assessment and analyze the user's emotional state.

[0343] Prompt Sentence Examples

[0344] New project description:

[0345] Introducing safety systems to new production lines

[0346] Path to worker's face image:

[0347] worker_image.jpg

[0348] Based on this information, the system performs risk assessment, provides appropriate feedback, and generates detailed reports, allowing users to effectively prevent project risks before they occur.

[0349] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0350] Step 1:

[0351] The server collects past accident and near-miss information from the company's database and various files. The input is past accident reports and near-miss information, and the output is the collected raw data. Specifically, it uses SQL queries and file access to collect reports related to "Production Line A."

[0352] Step 2:

[0353] The server preprocesses the collected data. The input is the raw data collected in step 1, and the output is cleansed text data. Specifically, it removes unnecessary spaces and special characters and performs morphological analysis to extract important keywords and phrases.

[0354] Step 3:

[0355] The server extracts risk patterns from the preprocessed data using natural language processing. The input is the text data preprocessed in step 2, and the output is the extracted risk patterns. Specifically, it analyzes frequently occurring words and co-occurrence networks to identify risk trends.

[0356] Step 4:

[0357] The user inputs the requirements definition information for a new project into a terminal. The input is the project requirements information entered by the user, and the output is the requirements information for the new project received by the terminal. For example, the user inputs information such as "Introduce a safety system to a new manufacturing line."

[0358] Step 5:

[0359] The terminal transmits the requirement definition information received from the user to the server. The input is the project requirement information entered by the user, and the output is the requirement information of the new project transmitted to the server.

[0360] Step 6:

[0361] The server compares the received requirements definition information of the new project with past risk patterns to evaluate the risk. The input is the requirements definition information and risk patterns of the new project, and the output is the risk evaluation results. Specifically, it calculates a risk score using similarity calculations and identifies potential problems.

[0362] Step 7:

[0363] The device acquires the user's emotional data using voice and facial recognition technology. The input is the user's voice data and facial image, and the output is analyzed emotional data. Specifically, the device uses voice recognition technology to determine whether the user is feeling stressed.

[0364] Step 8:

[0365] The server adjusts the feedback based on the risk assessment result and emotional data. The input is the risk assessment result and emotional data, and the output is the adjusted feedback content. Specifically, it provides gentle feedback to a user who is feeling stressed.

[0366] Step 9:

[0367] The server generates a detailed report including risk findings and provides it to the user via a terminal. The input is the risk assessment results and past accident report data, and the output is a detailed risk report. Specifically, a report is created that includes "past accident examples and recommended countermeasures for the new safety system" and is provided to the user in a downloadable format.

[0368] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0369] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0370] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0371] [Second embodiment]

[0372] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0373] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0374] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0375] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, 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. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0376] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0377] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0378] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0379] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0380] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0381] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0382] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0383] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0384] System Configuration

[0385] This invention relates to a system that collects and analyzes information on past accidents and fire ant incidents, with the aim of preventing risks in new projects. The system is mainly composed of three elements: a server, a terminal, and a user.

[0386] 1. Server: Responsible for the main processing of data collection, pre-processing, analysis using natural language processing, risk assessment, risk feedback and report generation.

[0387] 2. Terminal: Serves as an interface for users to enter requirements for new projects and receive feedback and reports from the server.

[0388] 3. User: The entity that inputs the requirements definition for a new project and improves the project design based on the risk findings and reports provided by the server.

[0389] Program processing (overview)

[0390] The system's program is configured to achieve the following main functions:

[0391] Data collection

[0392] The server collects information on past accident reports and fire ant hats within the company. This collection is done via database queries and file system access. For example, it retrieves a report on a "fault in function A" that occurred in "project A."

[0393] Data Preprocessing

[0394] The server converts the collected data into an analyzable format, specifically by performing text cleansing to remove unnecessary white space and special characters, and using morphological analysis to extract important keywords and phrases.

[0395] Data analysis using natural language processing

[0396] The server performs natural language processing on the preprocessed data, extracting important keywords and risk patterns and clustering information on similar accidents and fire ant incidents. For example, if a "fault with user authentication" appears in multiple reports, it will be identified as a single risk pattern.

[0397] risk assessment

[0398] When a user inputs a requirement definition for a new project into a terminal, the terminal sends this information to the server, which analyzes the information and compares it with past risk patterns, thereby evaluating the potential risks in the new project.

[0399] Risk Feedback

[0400] The server provides real-time feedback to the user on risk issues based on the evaluation results, such as "There have been many problems with password encryption in the past, so you should recheck the encryption specifications for the user authentication function."

[0401] Report Generation

[0402] The server generates a report summarizing the risk assessment and feedback and provides it to the user. The report includes past cases, recommended countermeasures, details of the risk assessment, etc. For example, it generates a detailed report on "Past cases of accidents related to user authentication functions and recommended countermeasures."

[0403] Specific examples

[0404] Scenario 1: Data collection and preprocessing

[0405] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0406] Scenario 2: Data Analysis with Natural Language Processing

[0407] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0408] Scenario 3: Risk Assessment and Feedback

[0409] When a user inputs a requirement such as "Implementing user authentication functionality in the development of a new web application" from a terminal, the server compares this information with past risk patterns and proactively identifies the risk of "frequent password encryption errors."

[0410] Scenario 4: Report Generation

[0411] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0412] In this way, the present invention provides an effective system for effectively utilizing information on past accidents and fire ant hats to prevent risks in new projects.

[0413] The processing flow will be explained below.

[0414] Step 1: Data collection

[0415] The server connects to the company's internal database to retrieve past accident reports and fire ant hat information. It uses a database query to extract the required records and downloads the data in a format such as JSON or CSV. For example, it executes the query "SELECT FROM incidents WHERE date > '2020-01-01'" on the database.

[0416] Step 2: Data Preprocessing

[0417] The server preprocesses the collected data. Specifically, it performs text cleansing to remove unnecessary white space and special characters. It then performs morphological analysis to break down sentences into tokens and extract important keywords and phrases. This converts the data into a format that is easy to analyze.

[0418] Step 3: Data analysis using natural language processing

[0419] The server performs natural language processing on the preprocessed data, analyzing frequently occurring words and co-occurrence networks to extract risk patterns. For example, risk patterns such as "insufficient code review" and "insufficient testing" are extracted. The server then clusters the data using similarity calculations to identify related risk factors.

[0420] Step 4: Risk Assessment

[0421] A user inputs requirements definition information for a new project into a terminal. For example, a requirement might be "Implement user authentication functionality in a new web application." The terminal then sends this information to the server. The server compares the received requirements definition information with past risk patterns and performs a risk assessment. A risk score is calculated based on the comparison results, and potential problems are identified.

[0422] Step 5: Risk feedback

[0423] The server provides the results of the risk assessment to the user in real time. For example, it may provide specific feedback via the terminal, such as, "There have been many instances of password encryption errors in the past in the user authentication function, so the encryption specifications should be rechecked." Based on this feedback, the user can revise the project requirements definition and design.

[0424] Step 6: Generate reports

[0425] The server generates a detailed report containing risk findings. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a specific report such as "Past incidents related to user authentication functions and recommended countermeasures" is created. The report is provided to the user via their device in a downloadable format.

[0426] In this way, by executing each step sequentially, the system can efficiently identify risks in new projects in advance and provide users with the necessary guidance and countermeasures.

[0427] Example 1

[0428] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0429] Conventional project management systems have difficulty effectively utilizing information on past accidents and fire ant hats to prevent risks in new projects. Furthermore, they lack the means to convert collected information into an analyzable format and extract risk patterns using natural language processing, resulting in issues with the accuracy and speed of risk assessment. Furthermore, they lack the means to provide specific feedback to users based on risk assessment results, or to provide detailed reports of that information.

[0430] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0431] In this invention, the server includes means for collecting information on past accidents and fire ant hats, means for preprocessing the collected information and converting it into an analyzable format, means for extracting risk patterns from the preprocessed information using natural language processing, means for receiving requirements definition information for a new project, means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns, means for providing feedback on risk items to a user based on the evaluation results, and means for generating a report summarizing the risk evaluation results and the feedback content and providing it to the user. This makes it possible to effectively utilize past information, identify risks in new projects in advance, and take measures.

[0432] "Past accident and fire ant information" refers to reports of troubles that have occurred within companies and organizations and information on hazard predictions.

[0433] "Means of collection" refers to the method of obtaining information via database queries or file system access.

[0434] "Means for preprocessing and converting into an analyzable format" refers to methods for formatting data using text cleansing and morphological analysis and converting it into a format suitable for analysis.

[0435] "Natural language processing" refers to the technology of analyzing text data using a computer and extracting meaning and patterns.

[0436] "Means for extracting risk patterns" refers to methods for identifying and extracting common risk elements from pre-processed data.

[0437] "Requirements definition information for a new project" refers to information about the functions, specifications, and requirements of a newly started project.

[0438] "Means for receiving" refers to the method by which the server receives information input by the user.

[0439] "Means for cross-checking and assessing risks" refers to a method for comparing the requirements definition information of a new project with existing risk patterns to identify potential risks.

[0440] "Means for providing feedback on risk items to users" refers to a method for providing information on identified risks to users in real time.

[0441] "Means for generating a report and providing it to the user" refers to a method for creating a report summarizing the evaluation results and feedback content and delivering it to the user.

[0442] "Clustering" refers to a machine learning technique that groups similar data.

[0443] "Risk findings" refer to potential risks identified for a new project based on past examples.

[0444] "Text cleansing" refers to the process of cleaning and removing unnecessary white space and special characters from text data.

[0445] "Methods for extracting important keywords and phrases" refers to methods for selecting particularly meaningful words and phrases from text data.

[0446] The present invention relates to a system that collects and analyzes information on past accidents and fire ant incidents, and aims to prevent risks in new projects. Specific embodiments of the present invention will be described in detail below.

[0447] System Configuration

[0448] The system of the present invention is mainly composed of three elements: a server, a terminal, and a user.

[0449] 1. Server: Responsible for the main processing of data collection, pre-processing, analysis using natural language processing, risk assessment, risk feedback and report generation.

[0450] 2. Terminal: Serves as an interface for users to enter requirements for new projects and receive feedback and reports from the server.

[0451] 3. User: The entity that inputs the requirements definition for a new project and improves the project design based on the risk findings and reports provided by the server.

[0452] Hardware and software used

[0453] The server uses Python's psycopg2 library to retrieve information from a PostgreSQL database to collect past accident reports and fire ant hat information from within the company. This allows for efficient collection of past accident and fire ant hat information. Python's NLTK library is used for data preprocessing, which performs text cleansing and morphological analysis to convert the data into an analyzable format.

[0454] Next, we use the Python sklearn library for natural language processing. Specifically, we use TF-IDF vectorization and K-means clustering to extract important keywords and risk patterns. This allows us to identify common risk elements from past accident reports and extract them as risk patterns.

[0455] The user inputs the requirements definition for a new project into the terminal, and the information is sent to the server. The server compares the information with risk patterns collected and processed in the past and evaluates potential risks. Based on the evaluation results, specific risk indications are fed back to the user in real time.

[0456] The risk assessment and feedback are then compiled into a detailed report that includes the assessment results, feedback, past similar incidents, and countermeasures taken. The report is generated using the Python FPDF library.

[0457] Specific examples

[0458] Specific examples of data collection and preprocessing

[0459] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0460] Specific examples of data analysis using natural language processing

[0461] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0462] Examples of risk assessment and feedback

[0463] When a user enters the requirements definition for a new project into a terminal, such as "Implementing user authentication functionality in the development of a new web application," the server compares this information with past risk patterns and identifies the risk of "frequent password encryption errors" in advance.

[0464] Example of report generation

[0465] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0466] Prompt Sentence Examples

[0467] "We are developing a new web app and are planning to implement user authentication. However, we have seen many issues with user authentication in past projects. Please use this information to identify potential risks and provide specific feedback."

[0468] As described above, the present invention provides an effective system for preventing risks in new projects by effectively utilizing information on past accidents and fire ant sightings.

[0469] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0470] Step 1: Data collection

[0471] The server retrieves past accident reports and fire ant information from the database. Specifically, it uses Python's psycopg2 library to send queries to the PostgreSQL database and collect information for the target period (for example, from 2020 onwards). The input is an SQL query, and the output is a dataset of accident reports and fire ant information. For example, it retrieves a report about a "fault in function A" related to "project A."

[0472] Step 2: Data Preprocessing

[0473] The server performs preprocessing to convert the collected data into an analyzable format. Specifically, it uses Python's NLTK library to perform text cleansing (removing unnecessary white space and special characters) and morphological analysis. This allows important keywords and phrases to be extracted. The input is the collected data, and the output is cleansed text data. For example, keywords such as "code review," "bug," and "deficiency" are extracted.

[0474] Step 3: Data analysis using natural language processing

[0475] The server performs natural language processing on the preprocessed data. Specifically, it performs TF-IDF vectorization using Python's sklearn library and extracts risk patterns using K-means clustering. The input is cleansed text data, and the output is a cluster of risk patterns. For example, it identifies patterns such as "insufficient code reviews" and "insufficient testing."

[0476] Step 4: Risk Assessment

[0477] When a user inputs the requirements definition for a new project into a terminal, it is sent to the server. The server preprocesses this information and compares it with previously extracted risk patterns. The input is the requirements definition information for the new project, and the output is a potential risk assessment based on the comparison. For example, if a requirement such as "Implement user authentication functionality in new web application development" is input, the server will evaluate the risk of "frequent password encryption errors."

[0478] Step 5: Risk feedback

[0479] The server provides the user with specific feedback based on the risk assessment results in real time. The input is the risk assessment results, and the output is a specific feedback message to the user. For example, it generates a message saying, "There have been many problems with password encryption in the past, so you should recheck the encryption specifications of the user authentication function."

[0480] Step 6: Generate reports

[0481] The server generates a report summarizing the risk assessment and feedback and provides it to the user. Specifically, it creates a PDF report using Python's FPDF library. The input is the risk assessment results and feedback, and the output is a PDF report. For example, it generates a detailed report on "Past accidents related to user authentication functions and recommended countermeasures."

[0482] By following the above processing steps, this system effectively utilizes information on past accidents and fire ant hats, and provides specific actions to prevent risks in new projects.

[0483] (Application example 1)

[0484] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0485] At work sites such as factories, it is difficult to assess risks in real time based on information on past accidents and fire ant incidents, leaving many workers exposed to potential danger. Rather than simply using past accident data as a record, it is necessary to effectively utilize this data to immediately warn workers and assess risks while they are working on-site, thereby preventing accidents and fire ant incidents from occurring.

[0486] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0487] In this invention, the server includes means for collecting information on past accidents and fire ant hats, means for preprocessing the collected data and converting it into an analyzable format, means for extracting risk patterns from the preprocessed data using natural language processing, means for receiving requirements definition information for a new project, means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns, means for providing feedback on risk items to the user based on the evaluation results, means for recognizing the actions of workers and comparing them with a past accident database in real time, and means for providing feedback on warnings to the user when danger is detected. This enables real-time risk evaluation and warnings based on past accident data during work.

[0488] An "accident" refers to an unexpected problem or trouble that occurs at a work site or project.

[0489] "Fire ant hat information" refers to events or experiences that did not result in an accident but were close calls or startling events that almost led to danger.

[0490] "Collection means" refers to methods and systems for collecting information on past accidents and fire ant incidents from databases and documents.

[0491] "Preprocessing means" refers to data cleansing and formatting work to convert collected data into an analyzable format.

[0492] "Natural language processing methods" is a general term for machine learning and statistical methods used to analyze text data and extract meaning and patterns.

[0493] "Risk patterns" refer to common risk elements and models extracted from past accidents and fire ant hat information.

[0494] "Requirements definition information" refers to the conditions and specifications required when starting a new project.

[0495] An "assessment means" is a method or system for assessing risks by comparing the requirements definition information of a new project with risk patterns.

[0496] "Feedback means" refers to a method or system for notifying users of risk items based on the evaluation results and providing them with points for improvement or caution.

[0497] "Movement recognition means" refers to the technology or means for detecting and analyzing the actions and movements of workers using sensors, etc.

[0498] A "real-time comparison means" is a system that instantly compares the recognized actions of workers with a database of past accidents to assess risk.

[0499] "Warning feedback means" refers to a method or system for issuing a warning to a worker when a hazard is detected.

[0500] The system for implementing this invention consists of three main elements: a server, a terminal, and a user.

[0501] Server Configuration

[0502] The server is a combination of the following:

[0503] 1. Data collection method: Collect information on past accidents and fire ant incidents from the company's database or file system. For example, retrieve accident reports using a database query.

[0504] 2. Preprocessing: Convert the collected data into an analyzable format, using text cleansing to remove unnecessary whitespace and special characters, and morphological analysis to extract keywords and phrases.

[0505] 3. Natural language processing: Natural language processing is performed on the preprocessed data to extract important keywords and risk patterns. Clustering is performed to identify common risk factors.

[0506] 4. Evaluation method: Receives new project requirements definition information and evaluates the risks by comparing them with past risk patterns, thereby revealing potential risks in the project.

[0507] 5. Feedback method: Based on the evaluation results, risk items are fed back to the user. In addition, the system recognizes the worker's actions and compares them with a database of past accidents in real time.

[0508] 6. Warning feedback means: If a danger is detected, a warning is sent to the user and specific countermeasures are presented.

[0509] Device configuration

[0510] The terminal acts as an interface for users to input requirements for new projects and receive feedback and warnings from the server, and also functions as a display for workers wearing smart glasses to receive real-time risk assessments and warnings.

[0511] Hardware and Software Use

[0512] Hardware: smart glasses (e.g. Google Glass), servers, PCs

[0513] Software: SQLite (database management system), Janome (Python morphological analysis library), scikit-learn (machine learning library)

[0514] Data processing and calculation

[0515] The server collects accident information from the database and performs preprocessing using text cleansing and morphological analysis. It then uses natural language processing technology to extract risk patterns and perform clustering. When it receives requirement definition information for a new project, it compares it with past risk patterns and evaluates and provides feedback on the risks. When it recognizes worker movements, it analyzes data from sensors in real time and immediately issues an alert if a danger is detected.

[0516] Specific examples

[0517] For example, consider a case where a worker is wearing smart glasses while handling materials at height in a factory. If the camera detects that the worker is not wearing a safety belt, the system will display a warning based on past accident data, such as:

[0518] "In the past, similar accidents have occurred due to failure to fasten seat belts. Please fasten your seat belt."

[0519] Prompt Sentence Examples

[0520] "New tasks in factory work: material handling when working at height"

[0521] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0522] Step 1:

[0523] The server collects past accident and fire ant information from a database. The input is a database of accident reports, and the output is a list of collected accident reports. Specifically, it executes a database query to retrieve accident reports.

[0524] Step 2:

[0525] The server preprocesses the collected data and converts it into an analyzable format. The input is a list of collected accident reports, and the output is preprocessed text data. Specifically, it performs text cleansing to remove unnecessary white space and special characters, and uses morphological analysis to extract important keywords and phrases.

[0526] Step 3:

[0527] The server performs natural language processing on the preprocessed data. The input is preprocessed text data, and the output is extracted risk patterns. Specifically, natural language processing technology is used to analyze the data, extract important keywords and phrases, and perform clustering to identify risk patterns.

[0528] Step 4:

[0529] The server receives the requirements definition information of the new project and compares it with past risk patterns. The input is the requirements definition information of the new project, and the output is the risk assessment results. Specifically, the information of the new project is input into a clustering model, and potential risks are evaluated by comparing it with past risk patterns.

[0530] Step 5:

[0531] The server provides feedback to the user on risk items based on the evaluation results. The input is the risk evaluation results, and the output is a feedback message to the user. Specifically, the server generates risk items based on the evaluation results and notifies the user.

[0532] Step 6:

[0533] The terminal recognizes the worker's movements and sends them to the server. The input is the worker's movement data, and the output is the movement recognition results. Specifically, the terminal analyzes data acquired from the camera in the smart glasses and recognizes the worker's movements.

[0534] Step 7:

[0535] The server compares the action recognition results with a past accident database in real time. The inputs are the action recognition results and the accident database, and the output is risk warning information. Specifically, the action recognition results are compared with past accident data, and a risk warning is generated if a risk is detected.

[0536] Step 8:

[0537] If a risk is detected, the device provides a warning to the user. The input is risk warning information, and the output is a warning message displayed to the user. Specifically, the warning message is displayed on the smart glasses display to alert the user.

[0538] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0539] System Configuration

[0540] This invention relates to a system that collects and analyzes information on past accidents and fire ant incidents to prevent risks in new projects. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide appropriate feedback based on the user's emotional state. This system consists of three main components: a server, a terminal, and a user.

[0541] 1. Server: Responsible for the core processing of data collection, pre-processing, analysis using natural language processing, risk assessment, emotion recognition, risk feedback and report generation.

[0542] 2. Terminal: This serves as an interface for users to input requirements for new projects and receive feedback and reports from the server. It also collects user sentiment data.

[0543] 3. User: Enters requirements for a new project and improves the project design based on risk findings and reports provided by the server. Sentiment data is also provided.

[0544] Program processing (overview)

[0545] The system's program is configured to achieve the following main functions:

[0546] Data collection

[0547] The server retrieves past accident reports and fire ant information from the company's database. This collection is done via database queries and file system access. For example, it retrieves a report on a "fault in function A" related to "project A."

[0548] Data Preprocessing

[0549] The server preprocesses the collected data, specifically by performing text cleansing to remove unnecessary white space and special characters, and then performs morphological analysis to break down the sentences into tokens and extract important keywords and phrases.

[0550] Data analysis using natural language processing

[0551] The server performs natural language processing on the preprocessed data, analyzing frequently occurring words and co-occurrence networks to extract risk patterns. For example, risk patterns such as "insufficient code review" and "insufficient testing" are extracted. The server then clusters the data using similarity calculations to identify related risk factors.

[0552] risk assessment

[0553] A user inputs requirements definition information for a new project into a terminal. For example, a requirement might be "Implement user authentication functionality in a new web application." The terminal then sends this information to the server. The server compares the received requirements definition information with past risk patterns and performs a risk assessment. A risk score is calculated based on the comparison results, and potential problems are identified.

[0554] emotion recognition

[0555] The server acquires the user's emotional data through the device. To do this, it uses voice and facial recognition technology to analyze the user's emotional state. For example, if the user is feeling stressed, the emotion engine will detect this.

[0556] Risk Feedback

[0557] The server adjusts the feedback based on the results of the risk assessment and the user's emotional state. For example, if the user is feeling stressed, the server will point out the risks in a gentle tone. Specific feedback may include the following: "There have been many instances of password encryption errors in the past with the user authentication function, so you should recheck the encryption specifications."

[0558] Report Generation

[0559] The server generates a detailed report containing risk findings. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a specific report such as "Past incidents related to user authentication functions and recommended countermeasures" is created. The report is provided to the user via their device in a downloadable format.

[0560] Specific examples

[0561] Scenario 1: Data collection and preprocessing

[0562] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0563] Scenario 2: Data Analysis with Natural Language Processing

[0564] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0565] Scenario 3: Risk Assessment and Feedback

[0566] When a user inputs a requirement such as "Implementing user authentication functionality in the development of a new web application" from a terminal, the server compares this information with past risk patterns and proactively identifies the risk of "frequent password encryption errors."

[0567] Scenario 4: Emotion recognition and feedback regulation

[0568] The server obtains the user's emotional data from the device, detects when the user is feeling stressed, and provides feedback in a gentle tone, saying, "There have been many instances of password encryption errors in the past with the user authentication function, so please carefully recheck the encryption specifications."

[0569] Scenario 5: Report Generation

[0570] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0571] In this way, the present invention provides an effective system for efficiently preventing risks in new projects by utilizing information on past accidents and fire ant incidents as well as the user's emotional state.

[0572] The processing flow will be explained below.

[0573] Step 1: Data collection

[0574] The server connects to the company's database and retrieves past accident reports and fire alarm information. For example, it executes a query such as "SELECT FROM incident_reports WHERE date > '2020-01-01'" and downloads the corresponding records in JSON format. Alternatively, it can read past CSV files from the file system.

[0575] Step 2: Data Preprocessing

[0576] The server preprocesses the collected data. Specifically, it cleanses the data and removes unnecessary white space and special characters. Next, it performs morphological analysis, breaking down sentences into tokens and extracting important keywords and phrases. For example, it extracts words such as "insufficient code review" and "insufficient testing."

[0577] Step 3: Data analysis using natural language processing

[0578] The server performs natural language processing on the preprocessed data, extracting risk patterns from accident and fire ant reports. It analyzes frequently occurring words and co-occurrence networks, and then clusters the data using similarity calculations to identify related risk elements. For example, it identifies a risk pattern related to "insufficient code reviews" that is common to multiple reports.

[0579] Step 4: Receive requirements for the new project

[0580] The user inputs the requirements definition for a new project into the terminal. For example, the user inputs the requirement information "Implement user authentication function in a new web application." The terminal then sends this information to the server.

[0581] Step 5: Risk Assessment

[0582] The server analyzes the received requirements definition information for the new project. It then compares it with existing past risk patterns and performs a risk assessment. This identifies potential risks in the new project and calculates a risk score. For example, it assesses the risk of user authentication functions based on past "password encryption errors."

[0583] Step 6: Obtaining emotion data

[0584] The server acquires the user's emotional data from the device. For example, it analyzes the user's tone of voice and facial expressions when inputting information, and uses an emotion engine to determine the user's emotional state (e.g., stress, relaxation).

[0585] Step 7: Emotion-Based Risk Feedback

[0586] The server combines the risk assessment results with the user's emotional state to generate appropriate feedback. For example, if the user is feeling stressed, the server may notify the user in a gentle tone, saying, "There have been many instances of password encryption errors in the past in the user authentication function, so please recheck the encryption specifications." The server then sends the risk feedback to the user via their device.

[0587] Step 8: Generate reports

[0588] The server generates a detailed report summarizing the identified risks. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a report on "Past incidents and recommended countermeasures for user authentication functions" is created. The report is provided to the user via their device, along with a downloadable link.

[0589] In this way, by executing each step sequentially, a system including an emotion engine can efficiently identify risks in new projects in advance and provide users with necessary guidance and countermeasures. Furthermore, by providing feedback that takes into account the user's emotional state, it reduces the burden on the user and achieves effective risk management.

[0590] Example 2

[0591] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0592] Conventional risk management systems are unable to fully utilize accident reports and fire ant information, and are unable to provide feedback that takes into account the user's emotional state, making it difficult to prevent risks in new projects.Furthermore, there is also the problem that providing specific risk feedback can easily cause stress to users.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0594] In this invention, the server includes a means for collecting information on past accidents and fire ant incidents, a means for preprocessing the collected data and converting it into an analyzable format, and a means for extracting risk patterns from the preprocessed data using natural language processing, thereby enabling the collected information to be effectively analyzed and risks associated with new projects to be identified.

[0595] The server further includes means for receiving requirements definition information for a new project, means for comparing the requirements definition information for the new project with the risk pattern to evaluate risks, means for providing risk items as feedback to the user based on the evaluation results, means for acquiring emotional data of the user using voice recognition and face recognition technology to recognize emotions, and means for adjusting the content of the risk feedback based on the emotional data. This makes it possible to provide appropriate risk feedback according to the user's emotional state and reduce stress.

[0596] "Past accident and fire ant information" refers to records of accidents and incidents that have occurred within a company or organization, and is data collected to prevent risks before they occur.

[0597] A "means of collection" is a method for gathering the required information, such as using a database query or file system access.

[0598] "Means of preprocessing and converting into an analyzable format" refers to methods of removing noise from raw data, performing morphological analysis and tokenization, and preparing the data in an appropriate format for analysis.

[0599] "Natural language processing" is a technology that processes text data so that it can be analyzed by machines, and analyzes frequently occurring words and co-occurrence networks to extract important keywords and risk patterns.

[0600] "Risk patterns" are risk factors discovered through data analysis and the characteristics of associated error patterns.

[0601] "Requirements definition information for a new project" is information that describes the technical and functional requirements needed for a new project.

[0602] "Means for assessing risk" is a method for comparing past risk patterns with the requirements of a new project to measure potential danger.

[0603] "Feedback methods" are methods for notifying users of the results of risk assessment and providing specific improvements and points of caution for the project.

[0604] "Speech recognition technology" is a technology that analyzes voice data collected by microphones and other devices to understand the speaker's emotions and content.

[0605] "Facial recognition technology" is a technology that analyzes facial expressions captured by a camera or other device to determine the emotional state of the subject.

[0606] "Emotion data" is information about the user's emotional state obtained using voice recognition or face recognition technology.

[0607] The "means for emotion recognition" is a method for analyzing collected emotion data and determining the user's emotional state.

[0608] The "means for adjusting the content of feedback" refers to a method for appropriately changing the content of notifications and the tone of feedback to the user based on the results of emotion recognition.

[0609] This invention is a system that collects and analyzes information on past accidents and fire ant hats to prevent risks in new projects. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide appropriate feedback based on the user's emotional state. This system consists of three main components: a server, a terminal, and a user.

[0610] server

[0611] The server is responsible for data collection, pre-processing, natural language processing, risk assessment, emotion recognition, risk feedback and report generation.

[0612] 1. The server retrieves past accident reports and fire alarm information from within the company using database queries and file system access. For example, it executes an SQL query such as "SELECT FROM accident_reports WHERE project_id = 'A';".

[0613] 2. The server performs text cleansing on the collected data. This process uses a text analysis library (e.g., Python's regular expression library) and a morphological analysis tool (e.g., MeCab) to extract important keywords. For example, from the sentence "This bug occurred due to a lack of code review," keywords such as "bug," "code review," and "lack" are extracted.

[0614] 3. The server performs natural language processing on the preprocessed data using an NLP library (e.g., spaCy, NLTK). For example, it uses TF-IDF to analyze and extract risk patterns such as "insufficient testing" and "lack of code reviews."

[0615] 4. The server receives the requirements definition information of the new project and performs risk assessment by comparing it with past risk patterns. In this process, a risk score is calculated based on the requirements information of the new project and potential problems are identified.

[0616] 5. The server acquires the user's emotional data using voice recognition and facial recognition technology (e.g., OpenCV, Affectiva) and performs emotion recognition. For example, it captures the user's facial expressions with a camera and analyzes their emotional state.

[0617] 6. The server adjusts the content of the risk feedback based on the results of the risk assessment and the user's emotional state. For example, if the user is feeling stressed, the server provides feedback in a gentle tone. It also provides specific instructions such as, "There have been many instances of password encryption errors in the past with the user authentication function, so please carefully recheck the encryption specifications."

[0618] 7. The server generates a PDF report containing past incidents, detailed risk assessments, and recommended countermeasures. For example, a report titled "Past incidents related to user authentication functions and recommended countermeasures" is created and notified to the user via their device.

[0619] Terminal

[0620] The terminal functions as an interface for users to input requirements for new projects and receive feedback and reports from the server, and also collects user emotional data and sends it to the server.

[0621] User

[0622] Users input requirements for new projects and improve the project design based on risk findings and reports provided by the server. They also provide sentiment data, which contributes to the system's feedback adjustments.

[0623] Prompt Sentence Examples

[0624] "Write a program that analyzes past accident reports and generates risk findings for new projects."

[0625] "Please explain the algorithms used by the system to analyze user emotional data and adjust feedback."

[0626] In this way, the system can prevent risks in the next new project, and by providing feedback according to the user's emotional state, risk management can be more effective.

[0627] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0628] Step 1: Data collection

[0629] The server uses database queries and file system access to retrieve past accident reports and fire ant information stored within the company. As input, it uses a query statement or file path to execute an SQL query. As a specific example, it executes the SQL query "SELECT FROM accident_reports WHERE project_id = 'A';". As output, it obtains a dataset of collected accident reports and fire ant information.

[0630] Step 2: Data Preprocessing

[0631] The server performs text cleansing on the collected data. It uses the collected accident report dataset as input. Specifically, it uses Python's regular expression library to remove unnecessary whitespace and special characters. It then uses a morphological analysis tool (e.g., MeCab) to break it down into tokens and extract important keywords and phrases. The cleansed and analyzed dataset is obtained as output.

[0632] Step 3: Data analysis using natural language processing

[0633] The server performs natural language processing on the preprocessed data using an NLP library (e.g., spaCy, NLTK). The preprocessed dataset is used as input. Specifically, it extracts frequently occurring words using TF-IDF and analyzes co-occurrence networks. Clustering techniques are used to extract risk patterns. The output is risk patterns such as "insufficient testing" and "lack of code review" and related risk factors.

[0634] Step 4: Receive requirements for your new project

[0635] The user inputs the requirements definition information for the new project through the terminal. As input, the project requirements manually entered by the user (e.g., "Implement user authentication functionality in a new web application") are used. The terminal sends the input information to the server. As output, the requirements definition information for the new project is obtained and sent to the server.

[0636] Step 5: Risk Assessment

[0637] The server receives the requirements definition information for a new project and compares it with past risk patterns to perform a risk assessment. The received project requirements definition information and past risk patterns are used as input. Specifically, a similarity calculation algorithm is used to compare the information and calculate a risk score. The output is the results of the risk assessment and potential problems.

[0638] Step 6: Emotion Recognition

[0639] The device collects the user's emotional data using a camera and microphone. The input is the user's audio and video data. The server analyzes this data to determine the user's emotional state. Specific operations include using voice recognition and facial recognition technology (e.g., OpenCV, Affectiva). The output is data related to the user's emotional state.

[0640] Step 7: Risk Feedback

[0641] The server adjusts the content of risk feedback taking into account the results of risk assessment and the user's emotional state. It uses the risk assessment results and emotion recognition data as input. Specific behavior involves generating a feedback message, providing it in a gentle tone if the user is feeling stressed. Specific feedback messages (e.g., "There have been many instances of password encryption errors in the past in the user authentication function, so please carefully recheck the encryption specifications") are obtained as output.

[0642] Step 8: Generate reports

[0643] The server generates a detailed report containing risk findings. It uses the collected and analyzed data, risk assessment results, and feedback as input. Specific operations include creating a report in PDF format and notifying the user via their terminal. The output is a detailed report (e.g., "Past incidents related to user authentication functions and recommended countermeasures").

[0644] The above are the specific processing steps of the program of this system.

[0645] (Application example 2)

[0646] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0647] In conventional manufacturing lines, there is a need for a system that can efficiently collect and analyze information on past accidents and near misses to prevent potential risks in new projects. However, current systems have the problem of providing uniform feedback without taking the user's emotional state into consideration, which often leads to stress for workers and results in workers not receiving appropriate feedback. Furthermore, they lack the functionality to automatically generate detailed risk reports, making it difficult for users to take adequate measures. These issues need to be resolved.

[0648] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0649] In this invention, the server includes means for collecting information on past accidents and near misses, means for preprocessing the collected data and converting it into an analyzable format, and means for extracting risk patterns from the preprocessed data using natural language processing. This makes it possible to evaluate the risks of a new project based on information on past accidents and near misses, adjust the feedback provided to the user according to the user's emotional state, and automatically generate a detailed risk report.

[0650] "Accident information" is a detailed record of past accidents that have occurred on production lines or projects.

[0651] "Near miss information" refers to information about close calls or startling experiences or moments when people felt danger, even though they did not result in an accident.

[0652] "Emotion data" is data that represents the user's emotional state and is acquired through voice recognition, face recognition, or the like.

[0653] "Risk patterns" are data that are analyzed based on past accident and near-miss information and show trends in risks that occur repeatedly under specific conditions or situations.

[0654] "Requirements definition information" is information that describes the functions and specifications required for a new project, as well as their details.

[0655] "Clustering" is a data analysis technique for grouping data with similar characteristics and identifying common risk patterns.

[0656] "Feedback" refers to information about the results of risk assessment, points to note, and improvement suggestions that the system provides to the user.

[0657] The "report" is a summary of detailed information such as risk assessment results, past accident examples, and recommended countermeasures.

[0658] This invention is a system for preventing risks on production lines and providing appropriate feedback according to the emotional state of workers. The system consists of three main components: a server, a terminal, and a user.

[0659] System Overview

[0660] The system has the following main functions:

[0661] 1. Collecting information on past accidents and near misses

[0662] 2. Analysis of preprocessed data using natural language processing

[0663] 3. Receive requirements for a new project

[0664] 4. Risk assessment and feedback of risk assessment results

[0665] 5. Acquisition and Analysis of Emotion Data

[0666] 6. Adjust feedback based on emotional data

[0667] 7. Generate detailed reports

[0668] server

[0669] The server is responsible for the core processing of the system. Specifically, it is responsible for the following:

[0670] 1. Collecting information on past accidents and near misses:

[0671] The server collects information on past accidents and near misses from the company's database and various files. For example, it collects reports on "malfunctions of function A" related to "production line A."

[0672] 2. Data Preprocessing:

[0673] The server preprocesses the collected data and converts it into an analyzable format, specifically by performing text cleansing to remove unnecessary spaces and special characters, and then performing morphological analysis to extract important keywords and phrases.

[0674] 3. Data analysis using natural language processing:

[0675] Natural language processing is performed on the preprocessed data, and risk patterns are extracted by analyzing frequently occurring words and co-occurrence networks. This allows risk patterns such as "insufficient code reviews" and "insufficient testing" to be identified.

[0676] 4. Risk Assessment:

[0677] Based on the requirements definition information of a new project, risk assessment is performed by comparing it with past risk patterns. For example, a requirement to "introduce a new safety system" is received as project information, and a risk score is calculated by comparing it with past risk information.

[0678] 5. Acquiring and analyzing emotion data:

[0679] The system acquires user emotion data from the device and analyzes it using emotion recognition technology. For example, if a worker is feeling stressed, this can be detected using voice and facial recognition technology.

[0680] 6. Feedback adjustment:

[0681] Tailor feedback based on risk assessment and emotional data, for example, softening the tone of feedback if the user is stressed.

[0682] 7. Report Generation:

[0683] Generate detailed reports containing risk findings and provide them to users. For example, create a report containing "Past incidents and recommended countermeasures for new safety systems."

[0684] Terminal

[0685] The terminal acts as an interface for users to input requirements for new projects and receive feedback and reports from the server, and also collects emotion data using voice and facial recognition technology.

[0686] User

[0687] Users input requirements definition information for new projects and improve the project design based on risk findings and reports provided by the server. Users also have the role of providing their own emotional data.

[0688] Examples of specific examples and prompts

[0689] For example, a user inputs a project requirement, such as "introduce a safety system to a new manufacturing line," into a terminal and provides a facial image (worker_image.jpg) through the terminal. The server uses this information to perform risk assessment and analyze the user's emotional state.

[0690] Prompt Sentence Examples

[0691] New project description:

[0692] Introducing safety systems to new production lines

[0693] Path to worker's face image:

[0694] worker_image.jpg

[0695] Based on this information, the system performs risk assessment, provides appropriate feedback, and generates detailed reports, allowing users to effectively prevent project risks before they occur.

[0696] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0697] Step 1:

[0698] The server collects past accident and near-miss information from the company's database and various files. The input is past accident reports and near-miss information, and the output is the collected raw data. Specifically, it uses SQL queries and file access to collect reports related to "Production Line A."

[0699] Step 2:

[0700] The server preprocesses the collected data. The input is the raw data collected in step 1, and the output is cleansed text data. Specifically, it removes unnecessary spaces and special characters and performs morphological analysis to extract important keywords and phrases.

[0701] Step 3:

[0702] The server extracts risk patterns from the preprocessed data using natural language processing. The input is the text data preprocessed in step 2, and the output is the extracted risk patterns. Specifically, it analyzes frequently occurring words and co-occurrence networks to identify risk trends.

[0703] Step 4:

[0704] The user inputs the requirements definition information for a new project into a terminal. The input is the project requirements information entered by the user, and the output is the requirements information for the new project received by the terminal. For example, the user inputs information such as "Introduce a safety system to a new manufacturing line."

[0705] Step 5:

[0706] The terminal transmits the requirement definition information received from the user to the server. The input is the project requirement information entered by the user, and the output is the requirement information of the new project transmitted to the server.

[0707] Step 6:

[0708] The server compares the received requirements definition information of the new project with past risk patterns to evaluate the risk. The input is the requirements definition information and risk patterns of the new project, and the output is the risk evaluation results. Specifically, it calculates a risk score using similarity calculations and identifies potential problems.

[0709] Step 7:

[0710] The device acquires the user's emotional data using voice and facial recognition technology. The input is the user's voice data and facial image, and the output is analyzed emotional data. Specifically, the device uses voice recognition technology to determine whether the user is feeling stressed.

[0711] Step 8:

[0712] The server adjusts the feedback based on the risk assessment result and emotional data. The input is the risk assessment result and emotional data, and the output is the adjusted feedback content. Specifically, it provides gentle feedback to a user who is feeling stressed.

[0713] Step 9:

[0714] The server generates a detailed report including risk findings and provides it to the user via a terminal. The input is the risk assessment results and past accident report data, and the output is a detailed risk report. Specifically, a report is created that includes "past accident examples and recommended countermeasures for the new safety system" and is provided to the user in a downloadable format.

[0715] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0716] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0717] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0718] [Third embodiment]

[0719] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0720] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0721] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0722] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. 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. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0723] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0724] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0725] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0726] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0727] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0728] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0729] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0730] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0731] System Configuration

[0732] This invention relates to a system that collects and analyzes information on past accidents and fire ant incidents, with the aim of preventing risks in new projects. The system is mainly composed of three elements: a server, a terminal, and a user.

[0733] 1. Server: Responsible for the main processing of data collection, pre-processing, analysis using natural language processing, risk assessment, risk feedback and report generation.

[0734] 2. Terminal: Serves as an interface for users to enter requirements for new projects and receive feedback and reports from the server.

[0735] 3. User: The entity that inputs the requirements definition for a new project and improves the project design based on the risk findings and reports provided by the server.

[0736] Program processing (overview)

[0737] The system's program is configured to achieve the following main functions:

[0738] Data collection

[0739] The server collects information on past accident reports and fire ant hats within the company. This collection is done via database queries and file system access. For example, it retrieves a report on a "fault in function A" that occurred in "project A."

[0740] Data Preprocessing

[0741] The server converts the collected data into an analyzable format, specifically by performing text cleansing to remove unnecessary white space and special characters, and using morphological analysis to extract important keywords and phrases.

[0742] Data analysis using natural language processing

[0743] The server performs natural language processing on the preprocessed data, extracting important keywords and risk patterns and clustering information on similar accidents and fire ant incidents. For example, if a "fault with user authentication" appears in multiple reports, it will be identified as a single risk pattern.

[0744] risk assessment

[0745] When a user inputs a requirement definition for a new project into a terminal, the terminal sends this information to the server, which analyzes the information and compares it with past risk patterns, thereby evaluating the potential risks in the new project.

[0746] Risk Feedback

[0747] The server provides real-time feedback to the user on risk issues based on the evaluation results, such as "There have been many problems with password encryption in the past, so you should recheck the encryption specifications for the user authentication function."

[0748] Report Generation

[0749] The server generates a report summarizing the risk assessment and feedback and provides it to the user. The report includes past cases, recommended countermeasures, details of the risk assessment, etc. For example, it generates a detailed report on "Past cases of accidents related to user authentication functions and recommended countermeasures."

[0750] Specific examples

[0751] Scenario 1: Data collection and preprocessing

[0752] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0753] Scenario 2: Data Analysis with Natural Language Processing

[0754] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0755] Scenario 3: Risk Assessment and Feedback

[0756] When a user inputs a requirement such as "Implementing user authentication functionality in the development of a new web application" from a terminal, the server compares this information with past risk patterns and proactively identifies the risk of "frequent password encryption errors."

[0757] Scenario 4: Report Generation

[0758] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0759] In this way, the present invention provides an effective system for effectively utilizing information on past accidents and fire ant hats to prevent risks in new projects.

[0760] The processing flow will be explained below.

[0761] Step 1: Data collection

[0762] The server connects to the company's internal database to retrieve past accident reports and fire ant hat information. It uses a database query to extract the required records and downloads the data in a format such as JSON or CSV. For example, it executes the query "SELECT FROM incidents WHERE date > '2020-01-01'" on the database.

[0763] Step 2: Data Preprocessing

[0764] The server preprocesses the collected data. Specifically, it performs text cleansing to remove unnecessary white space and special characters. It then performs morphological analysis to break down sentences into tokens and extract important keywords and phrases. This converts the data into a format that is easy to analyze.

[0765] Step 3: Data analysis using natural language processing

[0766] The server performs natural language processing on the preprocessed data, analyzing frequently occurring words and co-occurrence networks to extract risk patterns. For example, risk patterns such as "insufficient code review" and "insufficient testing" are extracted. The server then clusters the data using similarity calculations to identify related risk factors.

[0767] Step 4: Risk Assessment

[0768] A user inputs requirements definition information for a new project into a terminal. For example, a requirement might be "Implement user authentication functionality in a new web application." The terminal then sends this information to the server. The server compares the received requirements definition information with past risk patterns and performs a risk assessment. A risk score is calculated based on the comparison results, and potential problems are identified.

[0769] Step 5: Risk feedback

[0770] The server provides the results of the risk assessment to the user in real time. For example, it may provide specific feedback via the terminal, such as, "There have been many instances of password encryption errors in the past in the user authentication function, so the encryption specifications should be rechecked." Based on this feedback, the user can revise the project requirements definition and design.

[0771] Step 6: Generate reports

[0772] The server generates a detailed report containing risk findings. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a specific report such as "Past incidents related to user authentication functions and recommended countermeasures" is created. The report is provided to the user via their device in a downloadable format.

[0773] In this way, by executing each step sequentially, the system can efficiently identify risks in new projects in advance and provide users with the necessary guidance and countermeasures.

[0774] Example 1

[0775] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0776] Conventional project management systems have difficulty effectively utilizing information on past accidents and fire ant hats to prevent risks in new projects. Furthermore, they lack the means to convert collected information into an analyzable format and extract risk patterns using natural language processing, resulting in issues with the accuracy and speed of risk assessment. Furthermore, they lack the means to provide specific feedback to users based on risk assessment results, or to provide detailed reports of that information.

[0777] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0778] In this invention, the server includes means for collecting information on past accidents and fire ant hats, means for preprocessing the collected information and converting it into an analyzable format, means for extracting risk patterns from the preprocessed information using natural language processing, means for receiving requirements definition information for a new project, means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns, means for providing feedback on risk items to a user based on the evaluation results, and means for generating a report summarizing the risk evaluation results and the feedback content and providing it to the user. This makes it possible to effectively utilize past information, identify risks in new projects in advance, and take measures.

[0779] "Past accident and fire ant information" refers to reports of troubles that have occurred within companies and organizations and information on hazard predictions.

[0780] "Means of collection" refers to the method of obtaining information via database queries or file system access.

[0781] "Means for preprocessing and converting into an analyzable format" refers to methods for formatting data using text cleansing and morphological analysis and converting it into a format suitable for analysis.

[0782] "Natural language processing" refers to the technology of analyzing text data using a computer and extracting meaning and patterns.

[0783] "Means for extracting risk patterns" refers to methods for identifying and extracting common risk elements from pre-processed data.

[0784] "Requirements definition information for a new project" refers to information about the functions, specifications, and requirements of a newly started project.

[0785] "Means for receiving" refers to the method by which the server receives information input by the user.

[0786] "Means for cross-checking and assessing risks" refers to a method for comparing the requirements definition information of a new project with existing risk patterns to identify potential risks.

[0787] "Means for providing feedback on risk items to users" refers to a method for providing information on identified risks to users in real time.

[0788] "Means for generating a report and providing it to the user" refers to a method for creating a report summarizing the evaluation results and feedback content and delivering it to the user.

[0789] "Clustering" refers to a machine learning technique that groups similar data.

[0790] "Risk findings" refer to potential risks identified for a new project based on past examples.

[0791] "Text cleansing" refers to the process of cleaning and removing unnecessary white space and special characters from text data.

[0792] "Methods for extracting important keywords and phrases" refers to methods for selecting particularly meaningful words and phrases from text data.

[0793] The present invention relates to a system that collects and analyzes information on past accidents and fire ant incidents, and aims to prevent risks in new projects. Specific embodiments of the present invention will be described in detail below.

[0794] System Configuration

[0795] The system of the present invention is mainly composed of three elements: a server, a terminal, and a user.

[0796] 1. Server: Responsible for the main processing of data collection, pre-processing, analysis using natural language processing, risk assessment, risk feedback and report generation.

[0797] 2. Terminal: Serves as an interface for users to enter requirements for new projects and receive feedback and reports from the server.

[0798] 3. User: The entity that inputs the requirements definition for a new project and improves the project design based on the risk findings and reports provided by the server.

[0799] Hardware and software used

[0800] The server uses Python's psycopg2 library to retrieve information from a PostgreSQL database to collect past accident reports and fire ant hat information from within the company. This allows for efficient collection of past accident and fire ant hat information. Python's NLTK library is used for data preprocessing, which performs text cleansing and morphological analysis to convert the data into an analyzable format.

[0801] Next, we use the Python sklearn library for natural language processing. Specifically, we use TF-IDF vectorization and K-means clustering to extract important keywords and risk patterns. This allows us to identify common risk elements from past accident reports and extract them as risk patterns.

[0802] The user inputs the requirements definition for a new project into the terminal, and the information is sent to the server. The server compares the information with risk patterns collected and processed in the past and evaluates potential risks. Based on the evaluation results, specific risk indications are fed back to the user in real time.

[0803] The risk assessment and feedback are then compiled into a detailed report that includes the assessment results, feedback, past similar incidents, and countermeasures taken. The report is generated using the Python FPDF library.

[0804] Specific examples

[0805] Specific examples of data collection and preprocessing

[0806] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0807] Specific examples of data analysis using natural language processing

[0808] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0809] Examples of risk assessment and feedback

[0810] When a user enters the requirements definition for a new project into a terminal, such as "Implementing user authentication functionality in the development of a new web application," the server compares this information with past risk patterns and identifies the risk of "frequent password encryption errors" in advance.

[0811] Example of report generation

[0812] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0813] Prompt Sentence Examples

[0814] "We are developing a new web app and are planning to implement user authentication. However, we have seen many issues with user authentication in past projects. Please use this information to identify potential risks and provide specific feedback."

[0815] As described above, the present invention provides an effective system for preventing risks in new projects by effectively utilizing information on past accidents and fire ant sightings.

[0816] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0817] Step 1: Data collection

[0818] The server retrieves past accident reports and fire ant information from the database. Specifically, it uses Python's psycopg2 library to send queries to the PostgreSQL database and collect information for the target period (for example, from 2020 onwards). The input is an SQL query, and the output is a dataset of accident reports and fire ant information. For example, it retrieves a report about a "fault in function A" related to "project A."

[0819] Step 2: Data Preprocessing

[0820] The server performs preprocessing to convert the collected data into an analyzable format. Specifically, it uses Python's NLTK library to perform text cleansing (removing unnecessary white space and special characters) and morphological analysis. This allows important keywords and phrases to be extracted. The input is the collected data, and the output is cleansed text data. For example, keywords such as "code review," "bug," and "deficiency" are extracted.

[0821] Step 3: Data analysis using natural language processing

[0822] The server performs natural language processing on the preprocessed data. Specifically, it performs TF-IDF vectorization using Python's sklearn library and extracts risk patterns using K-means clustering. The input is cleansed text data, and the output is a cluster of risk patterns. For example, it identifies patterns such as "insufficient code reviews" and "insufficient testing."

[0823] Step 4: Risk Assessment

[0824] When a user inputs the requirements definition for a new project into a terminal, it is sent to the server. The server preprocesses this information and compares it with previously extracted risk patterns. The input is the requirements definition information for the new project, and the output is a potential risk assessment based on the comparison. For example, if a requirement such as "Implement user authentication functionality in new web application development" is input, the server will evaluate the risk of "frequent password encryption errors."

[0825] Step 5: Risk feedback

[0826] The server provides the user with specific feedback based on the risk assessment results in real time. The input is the risk assessment results, and the output is a specific feedback message to the user. For example, it generates a message saying, "There have been many problems with password encryption in the past, so you should recheck the encryption specifications of the user authentication function."

[0827] Step 6: Generate reports

[0828] The server generates a report summarizing the risk assessment and feedback and provides it to the user. Specifically, it creates a PDF report using Python's FPDF library. The input is the risk assessment results and feedback, and the output is a PDF report. For example, it generates a detailed report on "Past accidents related to user authentication functions and recommended countermeasures."

[0829] By following the above processing steps, this system effectively utilizes information on past accidents and fire ant hats, and provides specific actions to prevent risks in new projects.

[0830] (Application example 1)

[0831] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0832] At work sites such as factories, it is difficult to assess risks in real time based on information on past accidents and fire ant incidents, leaving many workers exposed to potential danger. Rather than simply using past accident data as a record, it is necessary to effectively utilize this data to immediately warn workers and assess risks while they are working on-site, thereby preventing accidents and fire ant incidents from occurring.

[0833] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0834] In this invention, the server includes means for collecting information on past accidents and fire ant hats, means for preprocessing the collected data and converting it into an analyzable format, means for extracting risk patterns from the preprocessed data using natural language processing, means for receiving requirements definition information for a new project, means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns, means for providing feedback on risk items to the user based on the evaluation results, means for recognizing the actions of workers and comparing them with a past accident database in real time, and means for providing feedback on warnings to the user when danger is detected. This enables real-time risk evaluation and warnings based on past accident data during work.

[0835] An "accident" refers to an unexpected problem or trouble that occurs at a work site or project.

[0836] "Fire ant hat information" refers to events or experiences that did not result in an accident but were close calls or startling events that almost led to danger.

[0837] "Collection means" refers to methods and systems for collecting information on past accidents and fire ant incidents from databases and documents.

[0838] "Preprocessing means" refers to data cleansing and formatting work to convert collected data into an analyzable format.

[0839] "Natural language processing methods" is a general term for machine learning and statistical methods used to analyze text data and extract meaning and patterns.

[0840] "Risk patterns" refer to common risk elements and models extracted from past accidents and fire ant hat information.

[0841] "Requirements definition information" refers to the conditions and specifications required when starting a new project.

[0842] An "assessment means" is a method or system for assessing risks by comparing the requirements definition information of a new project with risk patterns.

[0843] "Feedback means" refers to a method or system for notifying users of risk items based on the evaluation results and providing them with points for improvement or caution.

[0844] "Movement recognition means" refers to the technology or means for detecting and analyzing the actions and movements of workers using sensors, etc.

[0845] A "real-time comparison means" is a system that instantly compares the recognized actions of workers with a database of past accidents to assess risk.

[0846] "Warning feedback means" refers to a method or system for issuing a warning to a worker when a hazard is detected.

[0847] The system for implementing this invention consists of three main elements: a server, a terminal, and a user.

[0848] Server Configuration

[0849] The server is a combination of the following:

[0850] 1. Data collection method: Collect information on past accidents and fire ant incidents from the company's database or file system. For example, retrieve accident reports using a database query.

[0851] 2. Preprocessing: Convert the collected data into an analyzable format, using text cleansing to remove unnecessary whitespace and special characters, and morphological analysis to extract keywords and phrases.

[0852] 3. Natural language processing: Natural language processing is performed on the preprocessed data to extract important keywords and risk patterns. Clustering is performed to identify common risk factors.

[0853] 4. Evaluation method: Receives new project requirements definition information and evaluates the risks by comparing them with past risk patterns, thereby revealing potential risks in the project.

[0854] 5. Feedback method: Based on the evaluation results, risk items are fed back to the user. In addition, the system recognizes the worker's actions and compares them with a database of past accidents in real time.

[0855] 6. Warning feedback means: If a danger is detected, a warning is sent to the user and specific countermeasures are presented.

[0856] Device configuration

[0857] The terminal acts as an interface for users to input requirements for new projects and receive feedback and warnings from the server, and also functions as a display for workers wearing smart glasses to receive real-time risk assessments and warnings.

[0858] Hardware and Software Use

[0859] Hardware: smart glasses (e.g. Google Glass), servers, PCs

[0860] Software: SQLite (database management system), Janome (Python morphological analysis library), scikit-learn (machine learning library)

[0861] Data processing and calculation

[0862] The server collects accident information from the database and performs preprocessing using text cleansing and morphological analysis. It then uses natural language processing technology to extract risk patterns and perform clustering. When it receives requirement definition information for a new project, it compares it with past risk patterns and evaluates and provides feedback on the risks. When it recognizes worker movements, it analyzes data from sensors in real time and immediately issues an alert if a danger is detected.

[0863] Specific examples

[0864] For example, consider a case where a worker is wearing smart glasses while handling materials at height in a factory. If the camera detects that the worker is not wearing a safety belt, the system will display a warning based on past accident data, such as:

[0865] "In the past, similar accidents have occurred due to failure to fasten seat belts. Please fasten your seat belt."

[0866] Prompt Sentence Examples

[0867] "New tasks in factory work: material handling when working at height"

[0868] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0869] Step 1:

[0870] The server collects past accident and fire ant information from a database. The input is a database of accident reports, and the output is a list of collected accident reports. Specifically, it executes a database query to retrieve accident reports.

[0871] Step 2:

[0872] The server preprocesses the collected data and converts it into an analyzable format. The input is a list of collected accident reports, and the output is preprocessed text data. Specifically, it performs text cleansing to remove unnecessary white space and special characters, and uses morphological analysis to extract important keywords and phrases.

[0873] Step 3:

[0874] The server performs natural language processing on the preprocessed data. The input is preprocessed text data, and the output is extracted risk patterns. Specifically, natural language processing technology is used to analyze the data, extract important keywords and phrases, and perform clustering to identify risk patterns.

[0875] Step 4:

[0876] The server receives the requirements definition information of the new project and compares it with past risk patterns. The input is the requirements definition information of the new project, and the output is the risk assessment results. Specifically, the information of the new project is input into a clustering model, and potential risks are evaluated by comparing it with past risk patterns.

[0877] Step 5:

[0878] The server provides feedback to the user on risk items based on the evaluation results. The input is the risk evaluation results, and the output is a feedback message to the user. Specifically, the server generates risk items based on the evaluation results and notifies the user.

[0879] Step 6:

[0880] The terminal recognizes the worker's movements and sends them to the server. The input is the worker's movement data, and the output is the movement recognition results. Specifically, the terminal analyzes data acquired from the camera in the smart glasses and recognizes the worker's movements.

[0881] Step 7:

[0882] The server compares the action recognition results with a past accident database in real time. The inputs are the action recognition results and the accident database, and the output is risk warning information. Specifically, the action recognition results are compared with past accident data, and a risk warning is generated if a risk is detected.

[0883] Step 8:

[0884] If a risk is detected, the device provides a warning to the user. The input is risk warning information, and the output is a warning message displayed to the user. Specifically, the warning message is displayed on the smart glasses display to alert the user.

[0885] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0886] System Configuration

[0887] This invention relates to a system that collects and analyzes information on past accidents and fire ant incidents to prevent risks in new projects. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide appropriate feedback based on the user's emotional state. This system consists of three main components: a server, a terminal, and a user.

[0888] 1. Server: Responsible for the core processing of data collection, pre-processing, analysis using natural language processing, risk assessment, emotion recognition, risk feedback and report generation.

[0889] 2. Terminal: This serves as an interface for users to input requirements for new projects and receive feedback and reports from the server. It also collects user sentiment data.

[0890] 3. User: Enters requirements for a new project and improves the project design based on risk findings and reports provided by the server. Sentiment data is also provided.

[0891] Program processing (overview)

[0892] The system's program is configured to achieve the following main functions:

[0893] Data collection

[0894] The server retrieves past accident reports and fire ant information from the company's database. This collection is done via database queries and file system access. For example, it retrieves a report on a "fault in function A" related to "project A."

[0895] Data Preprocessing

[0896] The server preprocesses the collected data, specifically by performing text cleansing to remove unnecessary white space and special characters, and then performs morphological analysis to break down the sentences into tokens and extract important keywords and phrases.

[0897] Data analysis using natural language processing

[0898] The server performs natural language processing on the preprocessed data, analyzing frequently occurring words and co-occurrence networks to extract risk patterns. For example, risk patterns such as "insufficient code review" and "insufficient testing" are extracted. The server then clusters the data using similarity calculations to identify related risk factors.

[0899] risk assessment

[0900] A user inputs requirements definition information for a new project into a terminal. For example, a requirement might be "Implement user authentication functionality in a new web application." The terminal then sends this information to the server. The server compares the received requirements definition information with past risk patterns and performs a risk assessment. A risk score is calculated based on the comparison results, and potential problems are identified.

[0901] emotion recognition

[0902] The server acquires the user's emotional data through the device. To do this, it uses voice and facial recognition technology to analyze the user's emotional state. For example, if the user is feeling stressed, the emotion engine will detect this.

[0903] Risk Feedback

[0904] The server adjusts the feedback based on the results of the risk assessment and the user's emotional state. For example, if the user is feeling stressed, the server will point out the risks in a gentle tone. Specific feedback may include the following: "There have been many instances of password encryption errors in the past with the user authentication function, so you should recheck the encryption specifications."

[0905] Report Generation

[0906] The server generates a detailed report containing risk findings. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a specific report such as "Past incidents related to user authentication functions and recommended countermeasures" is created. The report is provided to the user via their device in a downloadable format.

[0907] Specific examples

[0908] Scenario 1: Data collection and preprocessing

[0909] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[0910] Scenario 2: Data Analysis with Natural Language Processing

[0911] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[0912] Scenario 3: Risk Assessment and Feedback

[0913] When a user inputs a requirement such as "Implementing user authentication functionality in the development of a new web application" from a terminal, the server compares this information with past risk patterns and proactively identifies the risk of "frequent password encryption errors."

[0914] Scenario 4: Emotion recognition and feedback regulation

[0915] The server obtains the user's emotional data from the device, detects when the user is feeling stressed, and provides feedback in a gentle tone, saying, "There have been many instances of password encryption errors in the past with the user authentication function, so please carefully recheck the encryption specifications."

[0916] Scenario 5: Report Generation

[0917] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[0918] In this way, the present invention provides an effective system for efficiently preventing risks in new projects by utilizing information on past accidents and fire ant incidents as well as the user's emotional state.

[0919] The processing flow will be explained below.

[0920] Step 1: Data collection

[0921] The server connects to the company's database and retrieves past accident reports and fire alarm information. For example, it executes a query such as "SELECT FROM incident_reports WHERE date > '2020-01-01'" and downloads the corresponding records in JSON format. Alternatively, it can read past CSV files from the file system.

[0922] Step 2: Data Preprocessing

[0923] The server preprocesses the collected data. Specifically, it cleanses the data and removes unnecessary white space and special characters. Next, it performs morphological analysis, breaking down sentences into tokens and extracting important keywords and phrases. For example, it extracts words such as "insufficient code review" and "insufficient testing."

[0924] Step 3: Data analysis using natural language processing

[0925] The server performs natural language processing on the preprocessed data, extracting risk patterns from accident and fire ant reports. It analyzes frequently occurring words and co-occurrence networks, and then clusters the data using similarity calculations to identify related risk elements. For example, it identifies a risk pattern related to "insufficient code reviews" that is common to multiple reports.

[0926] Step 4: Receive requirements for the new project

[0927] The user inputs the requirements definition for a new project into the terminal. For example, the user inputs the requirement information "Implement user authentication function in a new web application." The terminal then sends this information to the server.

[0928] Step 5: Risk Assessment

[0929] The server analyzes the received requirements definition information for the new project. It then compares it with existing past risk patterns and performs a risk assessment. This identifies potential risks in the new project and calculates a risk score. For example, it assesses the risk of user authentication functions based on past "password encryption errors."

[0930] Step 6: Obtaining emotion data

[0931] The server acquires the user's emotional data from the device. For example, it analyzes the user's tone of voice and facial expressions when inputting information, and uses an emotion engine to determine the user's emotional state (e.g., stress, relaxation).

[0932] Step 7: Emotion-Based Risk Feedback

[0933] The server combines the risk assessment results with the user's emotional state to generate appropriate feedback. For example, if the user is feeling stressed, the server may notify the user in a gentle tone, saying, "There have been many instances of password encryption errors in the past in the user authentication function, so please recheck the encryption specifications." The server then sends the risk feedback to the user via their device.

[0934] Step 8: Generate reports

[0935] The server generates a detailed report summarizing the identified risks. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a report on "Past incidents and recommended countermeasures for user authentication functions" is created. The report is provided to the user via their device, along with a downloadable link.

[0936] In this way, by executing each step sequentially, a system including an emotion engine can efficiently identify risks in new projects in advance and provide users with necessary guidance and countermeasures. Furthermore, by providing feedback that takes into account the user's emotional state, it reduces the burden on the user and achieves effective risk management.

[0937] Example 2

[0938] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0939] Conventional risk management systems are unable to fully utilize accident reports and fire ant information, and are unable to provide feedback that takes into account the user's emotional state, making it difficult to prevent risks in new projects.Furthermore, there is also the problem that providing specific risk feedback can easily cause stress to users.

[0940] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0941] In this invention, the server includes a means for collecting information on past accidents and fire ant incidents, a means for preprocessing the collected data and converting it into an analyzable format, and a means for extracting risk patterns from the preprocessed data using natural language processing, thereby enabling the collected information to be effectively analyzed and risks associated with new projects to be identified.

[0942] The server further includes means for receiving requirements definition information for a new project, means for comparing the requirements definition information for the new project with the risk pattern to evaluate risks, means for providing risk items as feedback to the user based on the evaluation results, means for acquiring emotional data of the user using voice recognition and face recognition technology to recognize emotions, and means for adjusting the content of the risk feedback based on the emotional data. This makes it possible to provide appropriate risk feedback according to the user's emotional state and reduce stress.

[0943] "Past accident and fire ant information" refers to records of accidents and incidents that have occurred within a company or organization, and is data collected to prevent risks before they occur.

[0944] A "means of collection" is a method for gathering the required information, such as using a database query or file system access.

[0945] "Means of preprocessing and converting into an analyzable format" refers to methods of removing noise from raw data, performing morphological analysis and tokenization, and preparing the data in an appropriate format for analysis.

[0946] "Natural language processing" is a technology that processes text data so that it can be analyzed by machines, and analyzes frequently occurring words and co-occurrence networks to extract important keywords and risk patterns.

[0947] "Risk patterns" are risk factors discovered through data analysis and the characteristics of associated error patterns.

[0948] "Requirements definition information for a new project" is information that describes the technical and functional requirements needed for a new project.

[0949] "Means for assessing risk" is a method for comparing past risk patterns with the requirements of a new project to measure potential danger.

[0950] "Feedback methods" are methods for notifying users of the results of risk assessment and providing specific improvements and points of caution for the project.

[0951] "Speech recognition technology" is a technology that analyzes voice data collected by microphones and other devices to understand the speaker's emotions and content.

[0952] "Facial recognition technology" is a technology that analyzes facial expressions captured by a camera or other device to determine the emotional state of the subject.

[0953] "Emotion data" is information about the user's emotional state obtained using voice recognition or face recognition technology.

[0954] The "means for emotion recognition" is a method for analyzing collected emotion data and determining the user's emotional state.

[0955] The "means for adjusting the content of feedback" refers to a method for appropriately changing the content of notifications and the tone of feedback to the user based on the results of emotion recognition.

[0956] This invention is a system that collects and analyzes information on past accidents and fire ant hats to prevent risks in new projects. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide appropriate feedback based on the user's emotional state. This system consists of three main components: a server, a terminal, and a user.

[0957] server

[0958] The server is responsible for data collection, pre-processing, natural language processing, risk assessment, emotion recognition, risk feedback and report generation.

[0959] 1. The server retrieves past accident reports and fire alarm information from within the company using database queries and file system access. For example, it executes an SQL query such as "SELECT FROM accident_reports WHERE project_id = 'A';".

[0960] 2. The server performs text cleansing on the collected data. This process uses a text analysis library (e.g., Python's regular expression library) and a morphological analysis tool (e.g., MeCab) to extract important keywords. For example, from the sentence "This bug occurred due to a lack of code review," keywords such as "bug," "code review," and "lack" are extracted.

[0961] 3. The server performs natural language processing on the preprocessed data using an NLP library (e.g., spaCy, NLTK). For example, it uses TF-IDF to analyze and extract risk patterns such as "insufficient testing" and "lack of code reviews."

[0962] 4. The server receives the requirements definition information of the new project and performs risk assessment by comparing it with past risk patterns. In this process, a risk score is calculated based on the requirements information of the new project and potential problems are identified.

[0963] 5. The server acquires the user's emotional data using voice recognition and facial recognition technology (e.g., OpenCV, Affectiva) and performs emotion recognition. For example, it captures the user's facial expressions with a camera and analyzes their emotional state.

[0964] 6. The server adjusts the content of the risk feedback based on the results of the risk assessment and the user's emotional state. For example, if the user is feeling stressed, the server provides feedback in a gentle tone. It also provides specific instructions such as, "There have been many instances of password encryption errors in the past with the user authentication function, so please carefully recheck the encryption specifications."

[0965] 7. The server generates a PDF report containing past incidents, detailed risk assessments, and recommended countermeasures. For example, a report titled "Past incidents related to user authentication functions and recommended countermeasures" is created and notified to the user via their device.

[0966] Terminal

[0967] The terminal functions as an interface for users to input requirements for new projects and receive feedback and reports from the server, and also collects user emotional data and sends it to the server.

[0968] User

[0969] Users input requirements for new projects and improve the project design based on risk findings and reports provided by the server. They also provide sentiment data, which contributes to the system's feedback adjustments.

[0970] Prompt Sentence Examples

[0971] "Write a program that analyzes past accident reports and generates risk findings for new projects."

[0972] "Please explain the algorithms used by the system to analyze user emotional data and adjust feedback."

[0973] In this way, the system can prevent risks in the next new project, and by providing feedback according to the user's emotional state, risk management can be more effective.

[0974] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0975] Step 1: Data collection

[0976] The server uses database queries and file system access to retrieve past accident reports and fire ant information stored within the company. As input, it uses a query statement or file path to execute an SQL query. As a specific example, it executes the SQL query "SELECT FROM accident_reports WHERE project_id = 'A';". As output, it obtains a dataset of collected accident reports and fire ant information.

[0977] Step 2: Data Preprocessing

[0978] The server performs text cleansing on the collected data. It uses the collected accident report dataset as input. Specifically, it uses Python's regular expression library to remove unnecessary whitespace and special characters. It then uses a morphological analysis tool (e.g., MeCab) to break it down into tokens and extract important keywords and phrases. The cleansed and analyzed dataset is obtained as output.

[0979] Step 3: Data analysis using natural language processing

[0980] The server performs natural language processing on the preprocessed data using an NLP library (e.g., spaCy, NLTK). The preprocessed dataset is used as input. Specifically, it extracts frequently occurring words using TF-IDF and analyzes co-occurrence networks. Clustering techniques are used to extract risk patterns. The output is risk patterns such as "insufficient testing" and "lack of code review" and related risk factors.

[0981] Step 4: Receive requirements for your new project

[0982] The user inputs the requirements definition information for the new project through the terminal. As input, the project requirements manually entered by the user (e.g., "Implement user authentication functionality in a new web application") are used. The terminal sends the input information to the server. As output, the requirements definition information for the new project is obtained and sent to the server.

[0983] Step 5: Risk Assessment

[0984] The server receives the requirements definition information for a new project and compares it with past risk patterns to perform a risk assessment. The received project requirements definition information and past risk patterns are used as input. Specifically, a similarity calculation algorithm is used to compare the information and calculate a risk score. The output is the results of the risk assessment and potential problems.

[0985] Step 6: Emotion Recognition

[0986] The device collects the user's emotional data using a camera and microphone. The input is the user's audio and video data. The server analyzes this data to determine the user's emotional state. Specific operations include using voice recognition and facial recognition technology (e.g., OpenCV, Affectiva). The output is data related to the user's emotional state.

[0987] Step 7: Risk Feedback

[0988] The server adjusts the content of risk feedback taking into account the results of risk assessment and the user's emotional state. It uses the risk assessment results and emotion recognition data as input. Specific behavior involves generating a feedback message, providing it in a gentle tone if the user is feeling stressed. Specific feedback messages (e.g., "There have been many instances of password encryption errors in the past in the user authentication function, so please carefully recheck the encryption specifications") are obtained as output.

[0989] Step 8: Generate reports

[0990] The server generates a detailed report containing risk findings. It uses the collected and analyzed data, risk assessment results, and feedback as input. Specific operations include creating a report in PDF format and notifying the user via their terminal. The output is a detailed report (e.g., "Past incidents related to user authentication functions and recommended countermeasures").

[0991] The above are the specific processing steps of the program of this system.

[0992] (Application example 2)

[0993] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0994] In conventional manufacturing lines, there is a need for a system that can efficiently collect and analyze information on past accidents and near misses to prevent potential risks in new projects. However, current systems have the problem of providing uniform feedback without taking the user's emotional state into consideration, which often leads to stress for workers and results in workers not receiving appropriate feedback. Furthermore, they lack the functionality to automatically generate detailed risk reports, making it difficult for users to take adequate measures. These issues need to be resolved.

[0995] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0996] In this invention, the server includes means for collecting information on past accidents and near misses, means for preprocessing the collected data and converting it into an analyzable format, and means for extracting risk patterns from the preprocessed data using natural language processing. This makes it possible to evaluate the risks of a new project based on information on past accidents and near misses, adjust the feedback provided to the user according to the user's emotional state, and automatically generate a detailed risk report.

[0997] "Accident information" is a detailed record of past accidents that have occurred on production lines or projects.

[0998] "Near miss information" refers to information about close calls or startling experiences or moments when people felt danger, even though they did not result in an accident.

[0999] "Emotion data" is data that represents the user's emotional state and is acquired through voice recognition, face recognition, or the like.

[1000] "Risk patterns" are data that are analyzed based on past accident and near-miss information and show trends in risks that occur repeatedly under specific conditions or situations.

[1001] "Requirements definition information" is information that describes the functions and specifications required for a new project, as well as their details.

[1002] "Clustering" is a data analysis technique for grouping data with similar characteristics and identifying common risk patterns.

[1003] "Feedback" refers to information about the results of risk assessment, points to note, and improvement suggestions that the system provides to the user.

[1004] The "report" is a summary of detailed information such as risk assessment results, past accident examples, and recommended countermeasures.

[1005] This invention is a system for preventing risks on production lines and providing appropriate feedback according to the emotional state of workers. The system consists of three main components: a server, a terminal, and a user.

[1006] System Overview

[1007] The system has the following main functions:

[1008] 1. Collecting information on past accidents and near misses

[1009] 2. Analysis of preprocessed data using natural language processing

[1010] 3. Receive requirements for a new project

[1011] 4. Risk assessment and feedback of risk assessment results

[1012] 5. Acquisition and Analysis of Emotion Data

[1013] 6. Adjust feedback based on emotional data

[1014] 7. Generate detailed reports

[1015] server

[1016] The server is responsible for the core processing of the system. Specifically, it is responsible for the following:

[1017] 1. Collecting information on past accidents and near misses:

[1018] The server collects information on past accidents and near misses from the company's database and various files. For example, it collects reports on "malfunctions of function A" related to "production line A."

[1019] 2. Data Preprocessing:

[1020] The server preprocesses the collected data and converts it into an analyzable format, specifically by performing text cleansing to remove unnecessary spaces and special characters, and then performing morphological analysis to extract important keywords and phrases.

[1021] 3. Data analysis using natural language processing:

[1022] Natural language processing is performed on the preprocessed data, and risk patterns are extracted by analyzing frequently occurring words and co-occurrence networks. This allows risk patterns such as "insufficient code reviews" and "insufficient testing" to be identified.

[1023] 4. Risk Assessment:

[1024] Based on the requirements definition information of a new project, risk assessment is performed by comparing it with past risk patterns. For example, a requirement to "introduce a new safety system" is received as project information, and a risk score is calculated by comparing it with past risk information.

[1025] 5. Acquiring and analyzing emotion data:

[1026] The system acquires user emotion data from the device and analyzes it using emotion recognition technology. For example, if a worker is feeling stressed, this can be detected using voice and facial recognition technology.

[1027] 6. Feedback adjustment:

[1028] Tailor feedback based on risk assessment and emotional data, for example, softening the tone of feedback if the user is stressed.

[1029] 7. Report Generation:

[1030] Generate detailed reports containing risk findings and provide them to users. For example, create a report containing "Past incidents and recommended countermeasures for new safety systems."

[1031] Terminal

[1032] The terminal acts as an interface for users to input requirements for new projects and receive feedback and reports from the server, and also collects emotion data using voice and facial recognition technology.

[1033] User

[1034] Users input requirements definition information for new projects and improve the project design based on risk findings and reports provided by the server. Users also have the role of providing their own emotional data.

[1035] Examples of specific examples and prompts

[1036] For example, a user inputs a project requirement, such as "introduce a safety system to a new manufacturing line," into a terminal and provides a facial image (worker_image.jpg) through the terminal. The server uses this information to perform risk assessment and analyze the user's emotional state.

[1037] Prompt Sentence Examples

[1038] New project description:

[1039] Introducing safety systems to new production lines

[1040] Path to worker's face image:

[1041] worker_image.jpg

[1042] Based on this information, the system performs risk assessment, provides appropriate feedback, and generates detailed reports, allowing users to effectively prevent project risks before they occur.

[1043] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1044] Step 1:

[1045] The server collects past accident and near-miss information from the company's database and various files. The input is past accident reports and near-miss information, and the output is the collected raw data. Specifically, it uses SQL queries and file access to collect reports related to "Production Line A."

[1046] Step 2:

[1047] The server preprocesses the collected data. The input is the raw data collected in step 1, and the output is cleansed text data. Specifically, it removes unnecessary spaces and special characters and performs morphological analysis to extract important keywords and phrases.

[1048] Step 3:

[1049] The server extracts risk patterns from the preprocessed data using natural language processing. The input is the text data preprocessed in step 2, and the output is the extracted risk patterns. Specifically, it analyzes frequently occurring words and co-occurrence networks to identify risk trends.

[1050] Step 4:

[1051] The user inputs the requirements definition information for a new project into a terminal. The input is the project requirements information entered by the user, and the output is the requirements information for the new project received by the terminal. For example, the user inputs information such as "Introduce a safety system to a new manufacturing line."

[1052] Step 5:

[1053] The terminal transmits the requirement definition information received from the user to the server. The input is the project requirement information entered by the user, and the output is the requirement information of the new project transmitted to the server.

[1054] Step 6:

[1055] The server compares the received requirements definition information of the new project with past risk patterns to evaluate the risk. The input is the requirements definition information and risk patterns of the new project, and the output is the risk evaluation results. Specifically, it calculates a risk score using similarity calculations and identifies potential problems.

[1056] Step 7:

[1057] The device acquires the user's emotional data using voice and facial recognition technology. The input is the user's voice data and facial image, and the output is analyzed emotional data. Specifically, the device uses voice recognition technology to determine whether the user is feeling stressed.

[1058] Step 8:

[1059] The server adjusts the feedback based on the risk assessment result and emotional data. The input is the risk assessment result and emotional data, and the output is the adjusted feedback content. Specifically, it provides gentle feedback to a user who is feeling stressed.

[1060] Step 9:

[1061] The server generates a detailed report including risk findings and provides it to the user via a terminal. The input is the risk assessment results and past accident report data, and the output is a detailed risk report. Specifically, a report is created that includes "past accident examples and recommended countermeasures for the new safety system" and is provided to the user in a downloadable format.

[1062] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1063] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1064] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1065] [Fourth embodiment]

[1066] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1067] 7, a 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.

[1068] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[1069] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1070] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1071] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1072] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1073] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1074] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1075] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[1076] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1077] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1078] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1079] System Configuration

[1080] This invention relates to a system that collects and analyzes information on past accidents and fire ant incidents, with the aim of preventing risks in new projects. The system is mainly composed of three elements: a server, a terminal, and a user.

[1081] 1. Server: Responsible for the main processing of data collection, pre-processing, analysis using natural language processing, risk assessment, risk feedback and report generation.

[1082] 2. Terminal: Serves as an interface for users to enter requirements for new projects and receive feedback and reports from the server.

[1083] 3. User: The entity that inputs the requirements definition for a new project and improves the project design based on the risk findings and reports provided by the server.

[1084] Program processing (overview)

[1085] The system's program is configured to achieve the following main functions:

[1086] Data collection

[1087] The server collects information on past accident reports and fire ant hats within the company. This collection is done via database queries and file system access. For example, it retrieves a report on a "fault in function A" that occurred in "project A."

[1088] Data Preprocessing

[1089] The server converts the collected data into an analyzable format, specifically by performing text cleansing to remove unnecessary white space and special characters, and using morphological analysis to extract important keywords and phrases.

[1090] Data analysis using natural language processing

[1091] The server performs natural language processing on the preprocessed data, extracting important keywords and risk patterns and clustering information on similar accidents and fire ant incidents. For example, if a "fault with user authentication" appears in multiple reports, it will be identified as a single risk pattern.

[1092] risk assessment

[1093] When a user inputs a requirement definition for a new project into a terminal, the terminal sends this information to the server, which analyzes the information and compares it with past risk patterns, thereby evaluating the potential risks in the new project.

[1094] Risk Feedback

[1095] The server provides real-time feedback to the user on risk issues based on the evaluation results, such as "There have been many problems with password encryption in the past, so you should recheck the encryption specifications for the user authentication function."

[1096] Report Generation

[1097] The server generates a report summarizing the risk assessment and feedback and provides it to the user. The report includes past cases, recommended countermeasures, details of the risk assessment, etc. For example, it generates a detailed report on "Past cases of accidents related to user authentication functions and recommended countermeasures."

[1098] Specific examples

[1099] Scenario 1: Data collection and preprocessing

[1100] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[1101] Scenario 2: Data Analysis with Natural Language Processing

[1102] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[1103] Scenario 3: Risk Assessment and Feedback

[1104] When a user inputs a requirement such as "Implementing user authentication functionality in the development of a new web application" from a terminal, the server compares this information with past risk patterns and proactively identifies the risk of "frequent password encryption errors."

[1105] Scenario 4: Report Generation

[1106] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[1107] In this way, the present invention provides an effective system for effectively utilizing information on past accidents and fire ant hats to prevent risks in new projects.

[1108] The processing flow will be explained below.

[1109] Step 1: Data collection

[1110] The server connects to the company's internal database to retrieve past accident reports and fire ant hat information. It uses a database query to extract the required records and downloads the data in a format such as JSON or CSV. For example, it executes the query "SELECT FROM incidents WHERE date > '2020-01-01'" on the database.

[1111] Step 2: Data Preprocessing

[1112] The server preprocesses the collected data. Specifically, it performs text cleansing to remove unnecessary white space and special characters. It then performs morphological analysis to break down sentences into tokens and extract important keywords and phrases. This converts the data into a format that is easy to analyze.

[1113] Step 3: Data analysis using natural language processing

[1114] The server performs natural language processing on the preprocessed data, analyzing frequently occurring words and co-occurrence networks to extract risk patterns. For example, risk patterns such as "insufficient code review" and "insufficient testing" are extracted. The server then clusters the data using similarity calculations to identify related risk factors.

[1115] Step 4: Risk Assessment

[1116] A user inputs requirements definition information for a new project into a terminal. For example, a requirement might be "Implement user authentication functionality in a new web application." The terminal then sends this information to the server. The server compares the received requirements definition information with past risk patterns and performs a risk assessment. A risk score is calculated based on the comparison results, and potential problems are identified.

[1117] Step 5: Risk feedback

[1118] The server provides the results of the risk assessment to the user in real time. For example, it may provide specific feedback via the terminal, such as, "There have been many instances of password encryption errors in the past in the user authentication function, so the encryption specifications should be rechecked." Based on this feedback, the user can revise the project requirements definition and design.

[1119] Step 6: Generate reports

[1120] The server generates a detailed report containing risk findings. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a specific report such as "Past incidents related to user authentication functions and recommended countermeasures" is created. The report is provided to the user via their device in a downloadable format.

[1121] In this way, by executing each step sequentially, the system can efficiently identify risks in new projects in advance and provide users with the necessary guidance and countermeasures.

[1122] Example 1

[1123] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1124] Conventional project management systems have difficulty effectively utilizing information on past accidents and fire ant hats to prevent risks in new projects. Furthermore, they lack the means to convert collected information into an analyzable format and extract risk patterns using natural language processing, resulting in issues with the accuracy and speed of risk assessment. Furthermore, they lack the means to provide specific feedback to users based on risk assessment results, or to provide detailed reports of that information.

[1125] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1126] In this invention, the server includes means for collecting information on past accidents and fire ant hats, means for preprocessing the collected information and converting it into an analyzable format, means for extracting risk patterns from the preprocessed information using natural language processing, means for receiving requirements definition information for a new project, means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns, means for providing feedback on risk items to a user based on the evaluation results, and means for generating a report summarizing the risk evaluation results and the feedback content and providing it to the user. This makes it possible to effectively utilize past information, identify risks in new projects in advance, and take measures.

[1127] "Past accident and fire ant information" refers to reports of troubles that have occurred within companies and organizations and information on hazard predictions.

[1128] "Means of collection" refers to the method of obtaining information via database queries or file system access.

[1129] "Means for preprocessing and converting into an analyzable format" refers to methods for formatting data using text cleansing and morphological analysis and converting it into a format suitable for analysis.

[1130] "Natural language processing" refers to the technology of analyzing text data using a computer and extracting meaning and patterns.

[1131] "Means for extracting risk patterns" refers to methods for identifying and extracting common risk elements from pre-processed data.

[1132] "Requirements definition information for a new project" refers to information about the functions, specifications, and requirements of a newly started project.

[1133] "Means for receiving" refers to the method by which the server receives information input by the user.

[1134] "Means for cross-checking and assessing risks" refers to a method for comparing the requirements definition information of a new project with existing risk patterns to identify potential risks.

[1135] "Means for providing feedback on risk items to users" refers to a method for providing information on identified risks to users in real time.

[1136] "Means for generating a report and providing it to the user" refers to a method for creating a report summarizing the evaluation results and feedback content and delivering it to the user.

[1137] "Clustering" refers to a machine learning technique that groups similar data.

[1138] "Risk findings" refer to potential risks identified for a new project based on past examples.

[1139] "Text cleansing" refers to the process of cleaning and removing unnecessary white space and special characters from text data.

[1140] "Methods for extracting important keywords and phrases" refers to methods for selecting particularly meaningful words and phrases from text data.

[1141] The present invention relates to a system that collects and analyzes information on past accidents and fire ant incidents, and aims to prevent risks in new projects. Specific embodiments of the present invention will be described in detail below.

[1142] System Configuration

[1143] The system of the present invention is mainly composed of three elements: a server, a terminal, and a user.

[1144] 1. Server: Responsible for the main processing of data collection, pre-processing, analysis using natural language processing, risk assessment, risk feedback and report generation.

[1145] 2. Terminal: Serves as an interface for users to enter requirements for new projects and receive feedback and reports from the server.

[1146] 3. User: The entity that inputs the requirements definition for a new project and improves the project design based on the risk findings and reports provided by the server.

[1147] Hardware and software used

[1148] The server uses Python's psycopg2 library to retrieve information from a PostgreSQL database to collect past accident reports and fire ant hat information from within the company. This allows for efficient collection of past accident and fire ant hat information. Python's NLTK library is used for data preprocessing, which performs text cleansing and morphological analysis to convert the data into an analyzable format.

[1149] Next, we use the Python sklearn library for natural language processing. Specifically, we use TF-IDF vectorization and K-means clustering to extract important keywords and risk patterns. This allows us to identify common risk elements from past accident reports and extract them as risk patterns.

[1150] The user inputs the requirements definition for a new project into the terminal, and the information is sent to the server. The server compares the information with risk patterns collected and processed in the past and evaluates potential risks. Based on the evaluation results, specific risk indications are fed back to the user in real time.

[1151] The risk assessment and feedback are then compiled into a detailed report that includes the assessment results, feedback, past similar incidents, and countermeasures. The report is generated using the Python FPDF library.

[1152] Specific examples

[1153] Specific examples of data collection and preprocessing

[1154] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[1155] Specific examples of data analysis using natural language processing

[1156] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[1157] Examples of risk assessment and feedback

[1158] When a user enters the requirements definition for a new project, such as "Implementing user authentication functionality in the development of a new web application," into a terminal, the server compares this information with past risk patterns and identifies the risk of "frequent password encryption errors" in advance.

[1159] Example of report generation

[1160] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[1161] Prompt Sentence Examples

[1162] "We are developing a new web app and are planning to implement user authentication. However, we have seen many issues with user authentication in past projects. Please use this information to identify potential risks and provide specific feedback."

[1163] As described above, the present invention provides an effective system for preventing risks in new projects by effectively utilizing information on past accidents and fire ant sightings.

[1164] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1165] Step 1: Data collection

[1166] The server retrieves past accident reports and fire ant information from the database. Specifically, it uses Python's psycopg2 library to send queries to the PostgreSQL database and collect information for the target period (for example, from 2020 onwards). The input is an SQL query, and the output is a dataset of accident reports and fire ant information. For example, it retrieves a report about a "fault in function A" related to "project A."

[1167] Step 2: Data Preprocessing

[1168] The server performs preprocessing to convert the collected data into an analyzable format. Specifically, it uses Python's NLTK library to perform text cleansing (removing unnecessary white space and special characters) and morphological analysis. This allows important keywords and phrases to be extracted. The input is the collected data, and the output is cleansed text data. For example, keywords such as "code review," "bug," and "deficiency" are extracted.

[1169] Step 3: Data analysis using natural language processing

[1170] The server performs natural language processing on the preprocessed data. Specifically, it performs TF-IDF vectorization using Python's sklearn library and extracts risk patterns using K-means clustering. The input is cleansed text data, and the output is a cluster of risk patterns. For example, it identifies patterns such as "insufficient code reviews" and "insufficient testing."

[1171] Step 4: Risk Assessment

[1172] When a user inputs the requirements definition for a new project into a terminal, it is sent to the server. The server preprocesses this information and compares it with previously extracted risk patterns. The input is the requirements definition information for the new project, and the output is a potential risk assessment based on the comparison. For example, if a requirement such as "Implement user authentication functionality in new web application development" is input, the server will evaluate the risk of "frequent password encryption errors."

[1173] Step 5: Risk feedback

[1174] The server provides the user with specific feedback based on the risk assessment results in real time. The input is the risk assessment results, and the output is a specific feedback message to the user. For example, it generates a message saying, "There have been many problems with password encryption in the past, so you should recheck the encryption specifications of the user authentication function."

[1175] Step 6: Generate reports

[1176] The server generates a report summarizing the risk assessment and feedback and provides it to the user. Specifically, it creates a PDF report using Python's FPDF library. The input is the risk assessment results and feedback, and the output is a PDF report. For example, it generates a detailed report on "Past accidents related to user authentication functions and recommended countermeasures."

[1177] By following the above processing steps, this system effectively utilizes information on past accidents and fire ant hats, and provides specific actions to prevent risks in new projects.

[1178] (Application example 1)

[1179] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1180] At work sites such as factories, it is difficult to assess risks in real time based on information on past accidents and fire ant incidents, leaving many workers exposed to potential danger. Rather than simply using past accident data as a record, it is necessary to effectively utilize this data to immediately warn workers and assess risks while they are working on-site, thereby preventing accidents and fire ant incidents from occurring.

[1181] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1182] In this invention, the server includes means for collecting information on past accidents and fire ant hats, means for preprocessing the collected data and converting it into an analyzable format, means for extracting risk patterns from the preprocessed data using natural language processing, means for receiving requirements definition information for a new project, means for evaluating risks by comparing the requirements definition information for the new project with the risk patterns, means for providing feedback on risk items to the user based on the evaluation results, means for recognizing the actions of workers and comparing them with a past accident database in real time, and means for providing feedback on warnings to the user when danger is detected. This enables real-time risk evaluation and warnings based on past accident data during work.

[1183] An "accident" refers to an unexpected problem or trouble that occurs at a work site or project.

[1184] "Fire ant hat information" refers to events or experiences that did not result in an accident but were close calls or startling events that almost led to danger.

[1185] "Collection means" refers to methods and systems for collecting information on past accidents and fire ant incidents from databases and documents.

[1186] "Preprocessing means" refers to data cleansing and formatting work to convert collected data into an analyzable format.

[1187] "Natural language processing methods" is a general term for machine learning and statistical methods used to analyze text data and extract meaning and patterns.

[1188] "Risk patterns" refer to common risk elements and models extracted from past accidents and fire ant hat information.

[1189] "Requirements definition information" refers to the conditions and specifications required when starting a new project.

[1190] An "assessment means" is a method or system for assessing risks by comparing the requirements definition information of a new project with risk patterns.

[1191] "Feedback means" refers to a method or system for notifying users of risk items based on the evaluation results and providing them with points for improvement or caution.

[1192] "Movement recognition means" refers to the technology or means for detecting and analyzing the actions and movements of workers using sensors, etc.

[1193] A "real-time comparison means" is a system that instantly compares the recognized actions of workers with a database of past accidents to assess risk.

[1194] "Warning feedback means" refers to a method or system for issuing a warning to a worker when a hazard is detected.

[1195] The system for implementing this invention consists of three main elements: a server, a terminal, and a user.

[1196] Server Configuration

[1197] The server is a combination of the following:

[1198] 1. Data collection method: Collect information on past accidents and fire ant incidents from the company's database or file system. For example, retrieve accident reports using a database query.

[1199] 2. Preprocessing: Convert the collected data into an analyzable format, using text cleansing to remove unnecessary whitespace and special characters, and morphological analysis to extract keywords and phrases.

[1200] 3. Natural language processing: Natural language processing is performed on the preprocessed data to extract important keywords and risk patterns. Clustering is performed to identify common risk factors.

[1201] 4. Evaluation method: Receives new project requirements definition information and evaluates the risks by comparing them with past risk patterns, thereby revealing potential risks in the project.

[1202] 5. Feedback method: Based on the evaluation results, risk items are fed back to the user. In addition, the system recognizes the worker's actions and compares them with a database of past accidents in real time.

[1203] 6. Warning feedback means: If a danger is detected, a warning is sent to the user and specific countermeasures are presented.

[1204] Device configuration

[1205] The terminal acts as an interface for users to input requirements for new projects and receive feedback and warnings from the server, and also functions as a display for workers wearing smart glasses to receive real-time risk assessments and warnings.

[1206] Hardware and Software Use

[1207] Hardware: smart glasses (e.g. Google Glass), servers, PCs

[1208] Software: SQLite (database management system), Janome (Python morphological analysis library), scikit-learn (machine learning library)

[1209] Data processing and calculation

[1210] The server collects accident information from the database and performs preprocessing using text cleansing and morphological analysis. It then uses natural language processing technology to extract risk patterns and perform clustering. When it receives requirement definition information for a new project, it compares it with past risk patterns and evaluates and provides feedback on the risks. When it recognizes worker movements, it analyzes data from sensors in real time and immediately issues an alert if a danger is detected.

[1211] Specific examples

[1212] For example, consider a case where a worker is wearing smart glasses while handling materials at height in a factory. If the camera detects that the worker is not wearing a safety belt, the system will display a warning based on past accident data, such as:

[1213] "In the past, similar accidents have occurred due to failure to fasten seat belts. Please fasten your seat belt."

[1214] Prompt Sentence Examples

[1215] "New tasks in factory work: material handling when working at height"

[1216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1217] Step 1:

[1218] The server collects past accident and fire ant information from a database. The input is a database of accident reports, and the output is a list of collected accident reports. Specifically, it executes a database query to retrieve accident reports.

[1219] Step 2:

[1220] The server preprocesses the collected data and converts it into an analyzable format. The input is a list of collected accident reports, and the output is preprocessed text data. Specifically, it performs text cleansing to remove unnecessary white space and special characters, and uses morphological analysis to extract important keywords and phrases.

[1221] Step 3:

[1222] The server performs natural language processing on the preprocessed data. The input is preprocessed text data, and the output is extracted risk patterns. Specifically, natural language processing technology is used to analyze the data, extract important keywords and phrases, and perform clustering to identify risk patterns.

[1223] Step 4:

[1224] The server receives the requirements definition information of the new project and compares it with past risk patterns. The input is the requirements definition information of the new project, and the output is the risk assessment results. Specifically, the information of the new project is input into a clustering model, and potential risks are evaluated by comparing it with past risk patterns.

[1225] Step 5:

[1226] The server provides feedback to the user on risk items based on the evaluation results. The input is the risk evaluation results, and the output is a feedback message to the user. Specifically, the server generates risk items based on the evaluation results and notifies the user.

[1227] Step 6:

[1228] The terminal recognizes the worker's movements and sends them to the server. The input is the worker's movement data, and the output is the movement recognition results. Specifically, the terminal analyzes data acquired from the camera in the smart glasses and recognizes the worker's movements.

[1229] Step 7:

[1230] The server compares the action recognition results with a past accident database in real time. The inputs are the action recognition results and the accident database, and the output is risk warning information. Specifically, the action recognition results are compared with past accident data, and a risk warning is generated if a risk is detected.

[1231] Step 8:

[1232] If a risk is detected, the device provides a warning to the user. The input is risk warning information, and the output is a warning message displayed to the user. Specifically, the warning message is displayed on the smart glasses display to alert the user.

[1233] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1234] System Configuration

[1235] This invention relates to a system that collects and analyzes information on past accidents and fire ant incidents to prevent risks in new projects. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide appropriate feedback based on the user's emotional state. This system consists of three main components: a server, a terminal, and a user.

[1236] 1. Server: Responsible for the core processing of data collection, pre-processing, analysis using natural language processing, risk assessment, emotion recognition, risk feedback and report generation.

[1237] 2. Terminal: This serves as an interface for users to input requirements for new projects and receive feedback and reports from the server. It also collects user sentiment data.

[1238] 3. User: Enters requirements for a new project and improves the project design based on risk findings and reports provided by the server. Sentiment data is also provided.

[1239] Program processing (overview)

[1240] The system's program is configured to achieve the following main functions:

[1241] Data collection

[1242] The server retrieves past accident reports and fire ant information from the company's database. This collection is done via database queries and file system access. For example, it retrieves a report on a "fault in function A" related to "project A."

[1243] Data Preprocessing

[1244] The server preprocesses the collected data, specifically by performing text cleansing to remove unnecessary white space and special characters, and then performs morphological analysis to break down the sentences into tokens and extract important keywords and phrases.

[1245] Data analysis using natural language processing

[1246] The server performs natural language processing on the preprocessed data, analyzing frequently occurring words and co-occurrence networks to extract risk patterns. For example, risk patterns such as "insufficient code review" and "insufficient testing" are extracted. The server then clusters the data using similarity calculations to identify related risk factors.

[1247] risk assessment

[1248] A user inputs requirements definition information for a new project into a terminal. For example, a requirement might be "Implement user authentication functionality in a new web application." The terminal then sends this information to the server. The server compares the received requirements definition information with past risk patterns and performs a risk assessment. A risk score is calculated based on the comparison results, and potential problems are identified.

[1249] emotion recognition

[1250] The server acquires the user's emotional data through the device. To do this, it uses voice and facial recognition technology to analyze the user's emotional state. For example, if the user is feeling stressed, the emotion engine will detect this.

[1251] Risk Feedback

[1252] The server adjusts the feedback based on the results of the risk assessment and the user's emotional state. For example, if the user is feeling stressed, the server will point out the risks in a gentle tone. Specific feedback may include the following: "There have been many instances of password encryption errors in the past with the user authentication function, so you should recheck the encryption specifications."

[1253] Report Generation

[1254] The server generates a detailed report containing risk findings. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a specific report such as "Past incidents related to user authentication functions and recommended countermeasures" is created. The report is provided to the user via their device in a downloadable format.

[1255] Specific examples

[1256] Scenario 1: Data collection and preprocessing

[1257] The server retrieves past accident reports from the database going back to 2020 and performs text cleansing. For example, it collects reports titled "Bugs caused by insufficient code reviews" and extracts keywords such as "code review," "bug," and "insufficient."

[1258] Scenario 2: Data Analysis with Natural Language Processing

[1259] The server analyzes the collected reports and extracts risk patterns such as "insufficient code reviews" and "insufficient testing," thereby identifying risk elements common to multiple projects.

[1260] Scenario 3: Risk Assessment and Feedback

[1261] When a user inputs a requirement such as "Implementing user authentication functionality in the development of a new web application" from a terminal, the server compares this information with past risk patterns and proactively identifies the risk of "frequent password encryption errors."

[1262] Scenario 4: Emotion recognition and feedback regulation

[1263] The server obtains the user's emotional data from the device, detects when the user is feeling stressed, and provides feedback in a gentle tone, saying, "There have been many instances of password encryption errors in the past with the user authentication function, so please carefully recheck the encryption specifications."

[1264] Scenario 5: Report Generation

[1265] The server generates a report containing "Past incidents in user authentication functions and recommended countermeasures" and provides it to the user via the terminal, allowing the user to review the project requirements definition and take concrete actions to improve safety.

[1266] In this way, the present invention provides an effective system for efficiently preventing risks in new projects by utilizing information on past accidents and fire ant incidents as well as the user's emotional state.

[1267] The processing flow will be explained below.

[1268] Step 1: Data collection

[1269] The server connects to the company's database and retrieves past accident reports and fire alarm information. For example, it executes a query such as "SELECT FROM incident_reports WHERE date > '2020-01-01'" and downloads the corresponding records in JSON format. Alternatively, it can read past CSV files from the file system.

[1270] Step 2: Data Preprocessing

[1271] The server preprocesses the collected data. Specifically, it cleanses the data and removes unnecessary white space and special characters. Next, it performs morphological analysis, breaking down sentences into tokens and extracting important keywords and phrases. For example, it extracts words such as "insufficient code review" and "insufficient testing."

[1272] Step 3: Data analysis using natural language processing

[1273] The server performs natural language processing on the preprocessed data, extracting risk patterns from accident and fire ant reports. It analyzes frequently occurring words and co-occurrence networks, and then clusters the data using similarity calculations to identify related risk elements. For example, it identifies a risk pattern related to "insufficient code reviews" that is common to multiple reports.

[1274] Step 4: Receive requirements for the new project

[1275] The user inputs the requirements definition for a new project into the terminal. For example, the user inputs the requirement information "Implement user authentication function in a new web application." The terminal then sends this information to the server.

[1276] Step 5: Risk Assessment

[1277] The server analyzes the received requirements definition information for the new project. It then compares it with existing past risk patterns and performs a risk assessment. This identifies potential risks in the new project and calculates a risk score. For example, it assesses the risk of user authentication functions based on past "password encryption errors."

[1278] Step 6: Obtaining emotion data

[1279] The server acquires the user's emotional data from the device. For example, it analyzes the user's tone of voice and facial expressions when inputting information, and uses an emotion engine to determine the user's emotional state (e.g., stress, relaxation).

[1280] Step 7: Emotion-Based Risk Feedback

[1281] The server combines the risk assessment results with the user's emotional state to generate appropriate feedback. For example, if the user is feeling stressed, the server may notify the user in a gentle tone, saying, "There have been many instances of password encryption errors in the past in the user authentication function, so please recheck the encryption specifications." The server then sends the risk feedback to the user via their device.

[1282] Step 8: Generate reports

[1283] The server generates a detailed report summarizing the identified risks. The report includes past incidents, detailed risk assessments, and recommended countermeasures. For example, a report on "Past incidents and recommended countermeasures for user authentication functions" is created. The report is provided to the user via their device, along with a downloadable link.

[1284] In this way, by executing each step sequentially, a system including an emotion engine can efficiently identify risks in new projects in advance and provide users with necessary guidance and countermeasures. Furthermore, by providing feedback that takes into account the user's emotional state, it reduces the burden on the user and achieves effective risk management.

[1285] Example 2

[1286] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1287] Conventional risk management systems are unable to fully utilize accident reports and fire ant information, and are unable to provide feedback that takes into account the user's emotional state, making it difficult to prevent risks in new projects.Furthermore, there is also the problem that providing specific risk feedback can easily cause stress to users.

[1288] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1289] In this invention, the server includes a means for collecting information on past accidents and fire ant incidents, a means for preprocessing the collected data and converting it into an analyzable format, and a means for extracting risk patterns from the preprocessed data using natural language processing, thereby enabling the collected information to be effectively analyzed and risks associated with new projects to be identified.

[1290] The server further includes means for receiving requirements definition information for a new project, means for comparing the requirements definition information for the new project with the risk pattern to evaluate risks, means for providing risk items as feedback to the user based on the evaluation results, means for acquiring emotional data of the user using voice recognition and face recognition technology to recognize emotions, and means for adjusting the content of the risk feedback based on the emotional data. This makes it possible to provide appropriate risk feedback according to the user's emotional state and reduce stress.

[1291] "Past accident and fire ant information" refers to records of accidents and incidents that have occurred within a company or organization, and is data collected to prevent risks before they occur.

[1292] A "means of collection" is a method for gathering the required information, such as using a database query or file system access.

[1293] "Means of preprocessing and converting into an analyzable format" refers to methods of removing noise from raw data, performing morphological analysis and tokenization, and preparing the data in an appropriate format for analysis.

[1294] "Natural language processing" is a technology that processes text data so that it can be analyzed by machines, and analyzes frequently occurring words and co-occurrence networks to extract important keywords and risk patterns.

[1295] "Risk patterns" are risk factors discovered through data analysis and the characteristics of associated error patterns.

[1296] "Requirements definition information for a new project" is information that describes the technical and functional requirements needed for a new project.

[1297] "Means for assessing risk" is a method for comparing past risk patterns with the requirements of a new project to measure potential danger.

[1298] "Feedback methods" are methods for notifying users of the results of risk assessment and providing specific improvements and points of caution for the project.

[1299] "Speech recognition technology" is a technology that analyzes voice data collected by microphones and other devices to understand the speaker's emotions and content.

[1300] "Facial recognition technology" is a technology that analyzes facial expressions captured by a camera or other device to determine the emotional state of the subject.

[1301] "Emotion data" is information about the user's emotional state obtained using voice recognition or face recognition technology.

[1302] The "means for emotion recognition" is a method for analyzing collected emotion data and determining the user's emotional state.

[1303] The "means for adjusting the content of feedback" refers to a method for appropriately changing the content of notifications and the tone of feedback to the user based on the results of emotion recognition.

[1304] This invention is a system that collects and analyzes information on past accidents and fire ant hats to prevent risks in new projects. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide appropriate feedback based on the user's emotional state. This system consists of three main components: a server, a terminal, and a user.

[1305] server

[1306] The server is responsible for data collection, pre-processing, natural language processing, risk assessment, emotion recognition, risk feedback and report generation.

[1307] 1. The server retrieves past accident reports and fire alarm information from within the company using database queries and file system access. For example, it executes an SQL query such as "SELECT FROM accident_reports WHERE project_id = 'A';".

[1308] 2. The server performs text cleansing on the collected data. This process uses a text analysis library (e.g., Python's regular expression library) and a morphological analysis tool (e.g., MeCab) to extract important keywords. For example, from the sentence "This bug occurred due to a lack of code review," keywords such as "bug," "code review," and "lack" are extracted.

[1309] 3. The server performs natural language processing on the preprocessed data using an NLP library (e.g., spaCy, NLTK). For example, it uses TF-IDF to analyze and extract risk patterns such as "insufficient testing" and "lack of code reviews."

[1310] 4. The server receives the requirements definition information of the new project and performs risk assessment by comparing it with past risk patterns. In this process, a risk score is calculated based on the requirements information of the new project and potential problems are identified.

[1311] 5. The server acquires the user's emotional data using voice recognition and facial recognition technology (e.g., OpenCV, Affectiva) and performs emotion recognition. For example, it captures the user's facial expressions with a camera and analyzes their emotional state.

[1312] 6. The server adjusts the content of the risk feedback based on the results of the risk assessment and the user's emotional state. For example, if the user is feeling stressed, the server provides feedback in a gentle tone. It also provides specific instructions such as, "There have been many instances of password encryption errors in the past with the user authentication function, so please carefully recheck the encryption specifications."

[1313] 7. The server generates a PDF report containing past incidents, detailed risk assessments, and recommended countermeasures. For example, a report titled "Past incidents related to user authentication functions and recommended countermeasures" is created and notified to the user via their device.

[1314] Terminal

[1315] The terminal functions as an interface for users to input requirements for new projects and receive feedback and reports from the server, and also collects user emotional data and sends it to the server.

[1316] User

[1317] Users input requirements for new projects and improve the project design based on risk findings and reports provided by the server. They also provide sentiment data, which contributes to the system's feedback adjustments.

[1318] Prompt Sentence Examples

[1319] "Write a program that analyzes past accident reports and generates risk findings for new projects."

[1320] "Please explain the algorithms used by the system to analyze user emotional data and adjust feedback."

[1321] In this way, the system can prevent risks in the next new project, and by providing feedback according to the user's emotional state, risk management can be more effective.

[1322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1323] Step 1: Data collection

[1324] The server uses database queries and file system access to retrieve past accident reports and fire ant information stored within the company. As input, it uses a query statement or file path to execute an SQL query. As a specific example, it executes the SQL query "SELECT FROM accident_reports WHERE project_id = 'A';". As output, it obtains a dataset of collected accident reports and fire ant information.

[1325] Step 2: Data Preprocessing

[1326] The server performs text cleansing on the collected data. It uses the collected accident report dataset as input. Specifically, it uses Python's regular expression library to remove unnecessary whitespace and special characters. It then uses a morphological analysis tool (e.g., MeCab) to break it down into tokens and extract important keywords and phrases. The cleansed and analyzed dataset is obtained as output.

[1327] Step 3: Data analysis using natural language processing

[1328] The server performs natural language processing on the preprocessed data using an NLP library (e.g., spaCy, NLTK). The preprocessed dataset is used as input. Specifically, it extracts frequently occurring words using TF-IDF and analyzes co-occurrence networks. Clustering techniques are used to extract risk patterns. The output is risk patterns such as "insufficient testing" and "lack of code review" and related risk factors.

[1329] Step 4: Receive requirements for your new project

[1330] The user inputs the requirements definition information for the new project through the terminal. As input, the project requirements manually entered by the user (e.g., "Implement user authentication functionality in a new web application") are used. The terminal sends the input information to the server. As output, the requirements definition information for the new project is obtained and sent to the server.

[1331] Step 5: Risk Assessment

[1332] The server receives the requirements definition information for a new project and compares it with past risk patterns to perform a risk assessment. The received project requirements definition information and past risk patterns are used as input. Specifically, a similarity calculation algorithm is used to compare the information and calculate a risk score. The output is the results of the risk assessment and potential problems.

[1333] Step 6: Emotion Recognition

[1334] The device collects the user's emotional data using a camera and microphone. The input is the user's audio and video data. The server analyzes this data to determine the user's emotional state. Specific operations include using voice recognition and facial recognition technology (e.g., OpenCV, Affectiva). The output is data related to the user's emotional state.

[1335] Step 7: Risk Feedback

[1336] The server adjusts the content of risk feedback taking into account the results of risk assessment and the user's emotional state. It uses the risk assessment results and emotion recognition data as input. Specific behavior involves generating a feedback message, providing it in a gentle tone if the user is feeling stressed. Specific feedback messages (e.g., "There have been many instances of password encryption errors in the past in the user authentication function, so please carefully recheck the encryption specifications") are obtained as output.

[1337] Step 8: Generate reports

[1338] The server generates a detailed report containing risk findings. It uses the collected and analyzed data, risk assessment results, and feedback as input. Specific operations include creating a report in PDF format and notifying the user via their terminal. The output is a detailed report (e.g., "Past incidents related to user authentication functions and recommended countermeasures").

[1339] The above are the specific processing steps of the program of this system.

[1340] (Application example 2)

[1341] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1342] In conventional manufacturing lines, there is a need for a system that can efficiently collect and analyze information on past accidents and near misses to prevent potential risks in new projects. However, current systems have the problem of providing uniform feedback without taking the user's emotional state into consideration, which often leads to stress for workers and results in workers not receiving appropriate feedback. Furthermore, they lack the functionality to automatically generate detailed risk reports, making it difficult for users to take adequate measures. These issues need to be resolved.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1344] In this invention, the server includes means for collecting information on past accidents and near misses, means for preprocessing the collected data and converting it into an analyzable format, and means for extracting risk patterns from the preprocessed data using natural language processing. This makes it possible to evaluate the risks of a new project based on information on past accidents and near misses, adjust the feedback provided to the user according to the user's emotional state, and automatically generate a detailed risk report.

[1345] "Accident information" is a detailed record of past accidents that have occurred on production lines or projects.

[1346] "Near miss information" refers to information about close calls or startling experiences or moments when people felt danger, even though they did not result in an accident.

[1347] "Emotion data" is data that represents the user's emotional state and is acquired through voice recognition, face recognition, or the like.

[1348] "Risk patterns" are data that are analyzed based on past accident and near-miss information and show trends in risks that occur repeatedly under specific conditions or situations.

[1349] "Requirements definition information" is information that describes the functions and specifications required for a new project, as well as their details.

[1350] "Clustering" is a data analysis technique for grouping data with similar characteristics and identifying common risk patterns.

[1351] "Feedback" refers to information about the results of risk assessment, points to note, and improvement suggestions that the system provides to the user.

[1352] The "report" is a summary of detailed information such as risk assessment results, past accident examples, and recommended countermeasures.

[1353] This invention is a system for preventing risks on production lines and providing appropriate feedback according to the emotional state of workers. The system consists of three main components: a server, a terminal, and a user.

[1354] System Overview

[1355] The system has the following main functions:

[1356] 1. Collecting information on past accidents and near misses

[1357] 2. Analysis of preprocessed data using natural language processing

[1358] 3. Receive requirements for a new project

[1359] 4. Risk assessment and feedback of risk assessment results

[1360] 5. Acquisition and Analysis of Emotion Data

[1361] 6. Adjust feedback based on emotional data

[1362] 7. Generate detailed reports

[1363] server

[1364] The server is responsible for the core processing of the system. Specifically, it is responsible for the following:

[1365] 1. Collecting information on past accidents and near misses:

[1366] The server collects information on past accidents and near misses from the company's database and various files. For example, it collects reports on "malfunctions of function A" related to "production line A."

[1367] 2. Data Preprocessing:

[1368] The server preprocesses the collected data and converts it into an analyzable format, specifically by performing text cleansing to remove unnecessary spaces and special characters, and then performing morphological analysis to extract important keywords and phrases.

[1369] 3. Data analysis using natural language processing:

[1370] Natural language processing is performed on the preprocessed data, and risk patterns are extracted by analyzing frequently occurring words and co-occurrence networks. This allows risk patterns such as "insufficient code reviews" and "insufficient testing" to be identified.

[1371] 4. Risk Assessment:

[1372] Based on the requirements definition information of a new project, risk assessment is performed by comparing it with past risk patterns. For example, a requirement to "introduce a new safety system" is received as project information, and a risk score is calculated by comparing it with past risk information.

[1373] 5. Acquiring and analyzing emotion data:

[1374] The system acquires user emotion data from the device and analyzes it using emotion recognition technology. For example, if a worker is feeling stressed, this can be detected using voice and facial recognition technology.

[1375] 6. Feedback adjustment:

[1376] Tailor feedback based on risk assessment and emotional data, for example, softening the tone of feedback if the user is stressed.

[1377] 7. Report Generation:

[1378] Generate detailed reports containing risk findings and provide them to users. For example, create a report containing "Past incidents and recommended countermeasures for new safety systems."

[1379] Terminal

[1380] The terminal acts as an interface for users to input requirements for new projects and receive feedback and reports from the server, and also collects emotion data using voice and facial recognition technology.

[1381] User

[1382] Users input requirements definition information for new projects and improve the project design based on risk findings and reports provided by the server. Users also have the role of providing their own emotional data.

[1383] Examples of specific examples and prompts

[1384] For example, a user inputs a project requirement, such as "introduce a safety system to a new manufacturing line," into a terminal and provides a facial image (worker_image.jpg) through the terminal. The server uses this information to perform risk assessment and analyze the user's emotional state.

[1385] Prompt Sentence Examples

[1386] New project description:

[1387] Introducing safety systems to new production lines

[1388] Path to worker's face image:

[1389] worker_image.jpg

[1390] Based on this information, the system performs risk assessment, provides appropriate feedback, and generates detailed reports, allowing users to effectively prevent project risks before they occur.

[1391] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1392] Step 1:

[1393] The server collects past accident and near-miss information from the company's database and various files. The input is past accident reports and near-miss information, and the output is the collected raw data. Specifically, it uses SQL queries and file access to collect reports related to "Production Line A."

[1394] Step 2:

[1395] The server preprocesses the collected data. The input is the raw data collected in step 1, and the output is cleansed text data. Specifically, it removes unnecessary spaces and special characters and performs morphological analysis to extract important keywords and phrases.

[1396] Step 3:

[1397] The server extracts risk patterns from the preprocessed data using natural language processing. The input is the text data preprocessed in step 2, and the output is the extracted risk patterns. Specifically, it analyzes frequently occurring words and co-occurrence networks to identify risk trends.

[1398] Step 4:

[1399] The user inputs the requirements definition information for a new project into a terminal. The input is the project requirements information entered by the user, and the output is the requirements information for the new project received by the terminal. For example, the user inputs information such as "Introduce a safety system to a new manufacturing line."

[1400] Step 5:

[1401] The terminal transmits the requirement definition information received from the user to the server. The input is the project requirement information entered by the user, and the output is the requirement information of the new project transmitted to the server.

[1402] Step 6:

[1403] The server compares the received requirements definition information of the new project with past risk patterns to evaluate the risk. The input is the requirements definition information and risk patterns of the new project, and the output is the risk evaluation results. Specifically, it calculates a risk score using similarity calculations and identifies potential problems.

[1404] Step 7:

[1405] The device acquires the user's emotional data using voice and facial recognition technology. The input is the user's voice data and facial image, and the output is analyzed emotional data. Specifically, the device uses voice recognition technology to determine whether the user is feeling stressed.

[1406] Step 8:

[1407] The server adjusts the feedback based on the risk assessment result and emotional data. The input is the risk assessment result and emotional data, and the output is the adjusted feedback content. Specifically, it provides gentle feedback to a user who is feeling stressed.

[1408] Step 9:

[1409] The server generates a detailed report including risk findings and provides it to the user via a terminal. The input is the risk assessment results and past accident report data, and the output is a detailed risk report. Specifically, a report is created that includes "past accident examples and recommended countermeasures for the new safety system" and is provided to the user in a downloadable format.

[1410] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1411] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1412] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1413] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1414] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1415] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1416] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1417] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1418] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1419] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1420] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1421] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1422] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1423] 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.

[1424] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1425] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1426] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1427] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1428] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1429] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1430] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1431] The following is further disclosed regarding the above embodiment.

[1432] (Claim 1)

[1433] A means of collecting information on past accidents and fire ant hats,

[1434] a means of preprocessing the collected data and converting it into an analyzable format;

[1435] means for extracting risk patterns from the preprocessed data using natural language processing;

[1436] a means for receiving requirements definition information for a new project;

[1437] a means for comparing requirements definition information of the new project with the risk pattern to evaluate risks;

[1438] a means for providing feedback of risk items to a user based on the evaluation results;

[1439] A system including:

[1440] (Claim 2)

[1441] The system according to claim 1, further comprising means for clustering past accident and fire ant information to generate associated risk patterns.

[1442] (Claim 3)

[1443] 10. The system of claim 1, further comprising means for generating and providing to the user a report including risk findings based on the collected data.

[1444] "Example 1"

[1445] (Claim 1)

[1446] A means of collecting information on past accidents and fire ant hats,

[1447] a means of preprocessing the collected information and converting it into an analyzable format;

[1448] means for extracting risk patterns from the preprocessed information using natural language processing;

[1449] a means for receiving requirements definition information for a new project;

[1450] a means for comparing requirements definition information of the new project with the risk pattern to evaluate risks;

[1451] a means for providing feedback of risk items to a user based on the evaluation results;

[1452] A means for generating a report summarizing the risk assessment results and feedback contents and providing the report to the user;

[1453] A system including:

[1454] (Claim 2)

[1455] The system according to claim 1, further comprising means for clustering past accident and fire ant information to generate associated risk patterns.

[1456] (Claim 3)

[1457] 10. The system of claim 1, further comprising means for text cleansing and extracting significant keywords and phrases based on natural language analysis.

[1458] "Application Example 1"

[1459] (Claim 1)

[1460] A means of collecting information on past accidents and fire ant hats,

[1461] a means of preprocessing the collected data and converting it into an analyzable format;

[1462] means for extracting risk patterns from the preprocessed data using natural language processing;

[1463] a means for receiving requirements definition information for a new project;

[1464] a means for comparing requirements definition information of the new project with the risk pattern to evaluate risks;

[1465] a means for providing feedback of risk items to a user based on the evaluation results;

[1466] A means of recognizing worker movements and comparing them with a database of past accidents in real time;

[1467] means for providing warning feedback to the user if a danger is detected;

[1468] A system including:

[1469] (Claim 2)

[1470] The system according to claim 1, further comprising means for clustering past accident and fire ant information to generate associated risk patterns.

[1471] (Claim 3)

[1472] 10. The system of claim 1, further comprising means for generating and providing to the user a report including risk findings based on the collected data.

[1473] "Example 2: Combining Emotion Engines"

[1474] (Claim 1)

[1475] A means of collecting information on past accidents and fire ant hats,

[1476] a means of preprocessing the collected data and converting it into an analyzable format;

[1477] means for extracting risk patterns from the preprocessed data using natural language processing;

[1478] a means for receiving requirements definition information for a new project;

[1479] a means for comparing requirements definition information of the new project with the risk pattern to evaluate risks;

[1480] a means for providing feedback of risk items to a user based on the evaluation results;

[1481] A means for acquiring user emotion data and performing emotion recognition using voice recognition and face recognition technology;

[1482] means for adjusting the content of risk feedback based on the emotion data;

[1483] A system including:

[1484] (Claim 2)

[1485] The system according to claim 1, further comprising means for clustering past accident and fire ant information to generate associated risk patterns.

[1486] (Claim 3)

[1487] 10. The system of claim 1, further comprising means for generating and providing to the user a report including risk findings based on the collected data.

[1488] "Application example 2 when combining emotion engines"

[1489] (Claim 1)

[1490] A means of collecting information on past accidents and near misses,

[1491] a means of preprocessing the collected data and converting it into an analyzable format;

[1492] means for extracting risk patterns from the preprocessed data using natural language processing;

[1493] a means for receiving requirements definition information for a new project;

[1494] a means for comparing requirements definition information of the new project with the risk pattern to evaluate risks;

[1495] a means for providing feedback of risk items to a user based on the evaluation results;

[1496] means for acquiring user emotion data for performing emotion analysis;

[1497] a means for adjusting the content of the feedback based on the risk assessment results and the sentiment data;

[1498] a means of generating detailed reports and providing them to the user;

[1499] A system including:

[1500] (Claim 2)

[1501] 2. The system according to claim 1, further comprising means for clustering past accident and near miss information to generate associated risk patterns.

[1502] (Claim 3)

[1503] 10. The system of claim 1, further comprising means for generating and providing to said user a report including risk findings based on the collected data. [Explanation of symbols]

[1504] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting information on past accidents and fire ant hats, a means of preprocessing the collected data and converting it into an analyzable format; means for extracting risk patterns from the preprocessed data using natural language processing; a means for receiving requirements definition information for a new project; a means for comparing requirements definition information of the new project with the risk pattern to evaluate risks; a means for providing feedback of risk items to a user based on the evaluation results; A system including:

2. The system according to claim 1 , further comprising means for clustering past accident and fire ant information to generate associated risk patterns.

3. 10. The system of claim 1, further comprising means for generating and providing to said user a report including risk findings based on said collected data.

Images