system

Abstract

To provide a system that improves the safety of work at a site. [Solution] A system including an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to a server, a validation means on the server for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating the prediction results, a formatting means for converting the generated prediction results into a format that is easy for the user to understand, a transmission means for transmitting the prediction results converted by the formatting means to a user terminal, and a display means for displaying the prediction results transmitted from the transmission means on the user terminal.

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] Despite the increasing importance of safe work at construction sites, there is a problem of inconsistency in the quality of hazard prediction activities due to differences in worker skills and experience. This situation increases the risk of accidents and disasters. In particular, at construction sites with many newly hired workers, the lack of experienced workers leads to insufficient hazard prediction, limiting the effectiveness of safety measures. There is a need for a system that can solve this problem and improve work safety. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system including an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating the prediction results, a formatting means for converting the generated prediction results into a format easy for users to understand, a transmission means for transmitting the prediction results converted by the formatting means to a user terminal, and a display means for displaying the prediction results transmitted from the transmission means on the user terminal. In particular, by using an AI model to calculate a risk score based on past accident data and providing the prediction results to the user, variation in hazard prediction due to differences in skill is reduced and work safety is improved.

[0006] The "work plan" refers to all of the specific planning information for carrying out the work, such as the work content, work location, work time, and necessary equipment.

[0007] "Input means" refers to a device or interface that allows a user to input a work plan into the system.

[0008] The "transmission means" refers to the entire communication means for transmitting the work plan data acquired from the input means to the server.

[0009] "Validation means" refers to a means for confirming the consistency and completeness of the work plan data transmitted from the transmission means to the server.

[0010] "Risk analysis means" refers to the means by which an AI model performs risk analysis using work plan data confirmed by validation means.

[0011] "AI model" refers to an algorithm or machine learning model that calculates and analyzes work-related risks based on historical data and statistics.

[0012] The "prediction means" refers to a means for predicting potential danger based on the risk score obtained by the risk analysis means and generating the prediction result.

[0013] The "formatting means" refers to a means for converting the generated prediction results into a user-friendly format, such as text, graphics, or list format.

[0014] The "display means" refers to a means for displaying the prediction results converted by the format means on a user terminal. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system for inputting a work plan, performing risk analysis, and providing hazard prediction results. This system includes an input means for inputting a work plan, a transmission means for transmitting work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for users to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal.

[0037] The user inputs a work plan using a terminal, including detailed information such as the work content, work location, work time, and required equipment. The terminal then sends this information to a server. The server validates the sent data to ensure that all necessary information is included. Data that passes validation is then used for risk analysis. The server uses an AI model to perform risk analysis based on past data and statistical information, and calculates a risk score. Potential dangers are predicted based on this risk score.

[0038] The prediction tool organizes the prediction results generated from the risk scores and converts them into a format that is easy for users to understand. For example, if past data indicates a high probability of a fall accident for a specific task, the prediction is displayed visually in text and graphics. The formatted prediction results are sent from the server to the user's device, where the user can view them.

[0039] As a concrete example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The terminal sends this information to the server, which validates it. The confirmed data is input into the AI ​​model, which calculates a risk score based on past accident data from similar work. For example, if there have been many cases of machine entrapment accidents in the same location in the past, the risk is determined to be high. Based on this risk, the prediction means generates a prediction result that reads, "There is a high possibility of an entrapment accident occurring during machine maintenance. Ensure that the machine is stopped thoroughly." The formatting means converts this prediction into a format that is easy for the user to understand and sends it to the terminal. The user can check this prediction result through the terminal and take the necessary safety measures.

[0040] The processing flow will be explained below.

[0041] Step 1:

[0042] The user inputs the work plan into the terminal.

[0043] The user enters detailed information such as the work content, work location, work time, and necessary equipment into the work plan input form on the terminal.

[0044] Step 2:

[0045] The terminal transmits the input work plan data to the server.

[0046] The terminal converts the input work plan information into JSON format and sends it to the server using an HTTP POST request to the specified API endpoint.

[0047] Step 3:

[0048] The server validates the received work plan data.

[0049] The server validates the incoming data using a JSON schema to ensure it is in the correct format and contains all required information.

[0050] Step 4:

[0051] The server inputs the validated data into the AI ​​model and performs risk analysis.

[0052] The server feeds the data that passes validation into the AI ​​model, which calculates a risk score based on past accident data and statistical information that is updated regularly.

[0053] Step 5:

[0054] The server predicts potential danger based on the risk score and generates the predicted result.

[0055] The server analyzes the risk scores returned by the AI ​​model and extracts potential risk factors, such as the risk of falling while working at height.

[0056] Step 6:

[0057] The server converts the prediction results into a user-friendly format.

[0058] The server converts the prediction results into text, graphic, list, or other formats, organizing them in a way that is easy for users to understand.

[0059] Step 7:

[0060] The server sends the formatted prediction results to the terminal.

[0061] The server returns the formatted prediction results to the device via an HTTP POST request.

[0062] Step 8:

[0063] The terminal displays the prediction results received from the server to the user.

[0064] The device renders the received information in the display area and displays specific risks and countermeasures to the user.

[0065] Step 9:

[0066] The user implements necessary safety measures based on the displayed prediction results.

[0067] Based on the prediction results provided, users can take specific safety measures, such as rechecking safety equipment and using an anemometer when working at height.

[0068] Example 1

[0069] 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."

[0070] Conventional risk management systems based on work plans were unable to fully utilize past accident data and statistical information, making it difficult to predict potential hazards. Furthermore, the predicted risks were not adequately presented, making it difficult for users to take appropriate measures. Therefore, there was a need for the development of a system that could accurately and effectively predict risks for work plans set by users and present the prediction results in a format that was easy for users to understand.

[0071] 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.

[0072] In this invention, the server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for the user to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, a display means for displaying the prediction result transmitted from the transmission means on the user terminal, and specific operation steps in which a user inputs detailed work information using the terminal and then the terminal transmits the data to the server. This enables accurate and effective risk prediction based on the work plan input by the user, and further enables the prediction result to be provided to the user in a format easy for the user to understand.

[0073] A "work plan" is a plan that shows detailed information such as the type of work, location, time, and necessary equipment.

[0074] The "input means" is a means for a user to input a work plan into the system via a terminal.

[0075] The "transmission means" is a means for transmitting the work plan data obtained from the input means to the server.

[0076] "Validation measures" are measures for verifying the submitted work plan data and confirming that all necessary information is present.

[0077] The "risk analysis means" is a means of inputting work plan data confirmed by the validation means into an AI model and performing risk analysis.

[0078] An "AI model" is an artificial intelligence model that performs risk analysis based on vast amounts of past data and statistical information.

[0079] "Risk Score" is a numerical indicator of the potential risk associated with a particular task, calculated by a risk analysis tool.

[0080] A "prediction means" is a means for predicting potential danger based on a risk score and generating a prediction result.

[0081] The "formatting means" is a means for converting the generated prediction results into a format that is easy for the user to understand.

[0082] A "user terminal" is a device that a user uses to input work plans and check prediction results.

[0083] The "display means" is a means for displaying the prediction results transmitted from the transmission means at the user terminal.

[0084] The present invention is a system that inputs a work plan, performs risk analysis, and provides the results of risk prediction. This system includes a series of processes from an input means for inputting a work plan to providing the user with the results of risk prediction.

[0085] First, the user logs in to the system using a terminal and inputs a work plan. The input screen provides fields for entering detailed information such as the work content, work location, work time, and required equipment. For example, a work plan such as "Machine maintenance at Factory B" may be entered. Once the input is complete, the user clicks the "Submit" button.

[0086] The device then uses an HTTP POST request to send the input work plan data to the server, including information such as the work content, work location, work time, and required equipment.

[0087] The server uses validation methods to check the received data. Specifically, it checks whether all required fields have been entered and whether there are any abnormalities in the data format. For example, it checks whether the work content is blank. Data that has been successfully validated is sent to the next risk analysis step.

[0088] The server inputs the validated data into a generative AI model (e.g., OpenAI's GPT-4) to perform risk analysis. The AI ​​model analyzes risk by referencing past data and statistical information, and calculates a risk score. Examples of prompts used in this process include:

[0089] "Conduct a risk analysis of machine maintenance at Factory B and predict possible hazards based on past data."

[0090] The server obtains the risk score and uses it to predict potential dangers and generate a prediction result. For example, if the risk score is high, the server generates a text message with the prediction result, such as, "This work has a high risk of being pinched. Wear appropriate safety equipment and make sure the machine is stopped."

[0091] Next, the server converts the generated prediction results into a user-friendly format using a formatting method, such as text, graphics, heat maps, etc. The formatted prediction results are constructed in a format such as HTML or JSON.

[0092] The formatted prediction results are sent from the server to the user's device. The server returns the prediction results as an HTTP response, and the device displays the received data. For example, the risk score and its explanation are displayed in text and graphic format on the device screen, allowing the user to check the prediction results.

[0093] Through this series of processes, accurate and effective risk predictions can be made based on the work plan entered by the user, and the prediction results can be provided to the user in an easy-to-understand format. This system allows users to take appropriate measures for their work plans, thereby improving work safety.

[0094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0095] Step 1:

[0096] The user logs in to the system using a terminal and inputs a work plan. The input screen displays fields for entering detailed information such as the work content (e.g., machine maintenance), work location (e.g., Factory B), work time (e.g., 2 hours), and required equipment (e.g., helmet, gloves). The user enters this information and clicks the "Submit" button.

[0097] Input: Details of the work, location, duration, and required equipment

[0098] Output: Workplan data (e.g., in JSON format)

[0099] Step 2:

[0100] The device collects the work plan data entered by the user and sends it to the server using an HTTP POST request, which includes information such as the work content, work location, work time, and required equipment.

[0101] Input: Work plan data entered by the user

[0102] Output: Work plan data sent to the server (HTTP request)

[0103] Step 3:

[0104] The server receives the submitted work plan data and validates it using validation measures. Specifically, it checks whether all required fields are entered and whether the data format is correct. For example, it checks whether the work content is blank and whether the location and time are in the correct format. If the data passes validation, it is sent to the next risk analysis step; if it fails, a general error message is generated.

[0105] Input: Work plan data sent to the server

[0106] Output: Validation result (pass / fail), validated data if successful, error message if failed

[0107] Step 4:

[0108] The server inputs the validated data into a generative AI model (e.g., OpenAI's GPT-4) to perform risk analysis. The AI ​​model analyzes the input data by referring to past data and statistical information, and calculates a risk score. Examples of prompts used in this process include:

[0109] "Conduct a risk analysis of machine maintenance at Factory B and predict possible hazards based on past data."

[0110] Input: Validated data, prompt statement

[0111] Output: Risk score (numeric)

[0112] Step 5:

[0113] The server generates specific hazard prediction results based on the risk score obtained from the AI ​​model. For example, if the risk score is high, it generates a text message such as, "This work has a high risk of being pinched. Please wear appropriate safety equipment and make sure the machine is stopped."

[0114] Input: Risk Score

[0115] Output: Prediction result (text message)

[0116] Step 6:

[0117] The server formats the generated prediction results into a user-friendly format, such as text, graphics, heat maps, etc. The formatted results are constructed in HTML, JSON, etc.

[0118] Input: Prediction result

[0119] Output: Formatted prediction results (HTML / JSON format)

[0120] Step 7:

[0121] The server sends the formatted prediction results to the user's device. The prediction results are returned using an HTTP response, and the device displays the received data. The user can check the prediction results by viewing the risk score and its explanation in text and graphic format on the device screen.

[0122] Input: Formatted prediction results

[0123] Output: Prediction results (text / graphics) displayed on the user's terminal

[0124] (Application example 1)

[0125] 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."

[0126] In modern factories, many tasks are planned, many of which involve risks. However, it is difficult to properly predict work risks and take prompt and appropriate countermeasures, making it necessary to ensure the safety of workers. Furthermore, conventional systems make it cumbersome to input work plans and display risk prediction results, and lack a user-friendly interface. Therefore, there is a need for a method that allows easy input of work plans using voice input or QR codes (registered trademark), and displays risk prediction results in an easy-to-understand manner.

[0127] 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.

[0128] In this invention, the server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means in the server for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for the user to understand, a means for the user to input the work plan using voice input or a QR code on a terminal, a transmission means for transmitting the prediction result converted by the formatting means to the user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal. This makes it possible to centrally manage everything from inputting the work plan to displaying the risk prediction result and provide a user-friendly interface.

[0129] "Work plan" means a detailed plan of work, including specific locations, times, contents, and equipment required.

[0130] "Input means" refers to a device or interface that allows a user to input a work plan.

[0131] The "transmission means" refers to a mechanism for transmitting the work plan data acquired from the input means to the server.

[0132] "Validation Measures" means a mechanism that verifies that submitted work plan data is accurate and complete.

[0133] The "risk analysis means" is a mechanism for inputting work plan data confirmed by the validation means into an AI model and analyzing the risk.

[0134] A "risk score" is a numerical representation of potential danger obtained through risk analysis.

[0135] "Prediction means" refers to a mechanism that predicts potential danger based on a risk score and generates the prediction results.

[0136] The "formatting means" is a mechanism for converting the generated prediction results into a format that is easy for the user to understand.

[0137] "Voice input" refers to a method in which a user inputs a work plan using voice.

[0138] A "QR code" is a type of two-dimensional barcode and is a means of efficiently reading information.

[0139] "Display means" refers to a mechanism for displaying prediction results on a user terminal.

[0140] A specific system configuration for implementing the present invention is shown below: The system inputs a factory work plan, performs risk analysis and danger prediction, and proposes appropriate countermeasures.

[0141] The system begins with the user inputting a work plan using a device such as a smartphone. The user can input specific details about the work, location, time, and necessary equipment, and can also use voice input or QR code reading. The input work plan is sent to the server by a transmission means. The server then performs the following specific processes:

[0142] The server uses a validation means to check the received work plan data to ensure that the information is accurate and complete. If this validation is successful, the risk analysis means is activated and the validated data is input into the AI ​​model. The AI ​​model used here is configured using machine learning libraries such as TENSORFLOW (registered trademark) and Keras. The AI ​​model calculates a risk score based on past accident data and statistical information.

[0143] Once the risk score is obtained, the prediction means uses the score to predict potential dangers and generate prediction results. These prediction results are created by referring to past accident data for specific tasks. For example, they may include specific countermeasures such as "There is a high possibility of a pinch accident occurring during machine maintenance. Ensure that the machine is thoroughly stopped."

[0144] The generated prediction results are converted by the formatting means into a format that is easy for the user to understand. This conversion can be in a text format, a graphic format, a list format, etc. The formatted prediction results are again sent from the server to the user terminal via the transmission means, and are visually presented to the user by the display means.

[0145] As a specific example, if a user inputs a plan for "machine maintenance work at Factory B," the plan is sent to the server and the data is validated. Risk analysis is then performed using an AI model, and potential hazards are predicted based on past accident data and a risk score. The prediction results are displayed on the user's device along with a clear instruction to "thoroughly check that the machine is stopped."

[0146] An example prompt is:

[0147] Please enter your work:

[0148] Content: "Machine Maintenance"

[0149] Location: "Factory B"

[0150] Time: "2023-10-20 13:00"

[0151] Required Equipment: ["Gloves", "Safety Glasses"]

[0152] Send the submitted data to the server and validate it...

[0153] Predictive results based on risk analysis:

[0154] Risk Score: 8.5 / 10

[0155] Prediction result: "There is a high possibility of an accident occurring during machine maintenance. Make sure to check that the machine is stopped."

[0156] The prediction results are displayed.

[0157] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0158] Step 1:

[0159] The user inputs a work plan using a smartphone or other device. The input includes detailed information such as the work content, location, time, and required equipment. The user can also input information using voice input or a QR code. The input data obtained at this stage is sent to the server.

[0160] Step 2:

[0161] The terminal transmits the acquired work plan data to the server. Once the transmitted data arrives at the server, a validation procedure checks that the information is accurate and complete. The input of this validation procedure is the transmitted work plan data, and the output is the complete data that has passed validation.

[0162] Step 3:

[0163] The validated data is input into the risk analysis tool. The AI ​​model on the server performs a risk analysis based on this data and calculates a risk score based on past accident data and statistical information. This risk score is obtained as the output.

[0164] Step 4:

[0165] The prediction means predicts potential dangers based on the risk score obtained by the risk analysis means. The server compares the risk of a specific task with past data and generates a prediction result. This prediction result is output.

[0166] Step 5:

[0167] The generated prediction results are converted into a user-friendly format by a formatting means. Specifically, they are formatted so that they can be displayed in text format, graphic format, or list format. The input of this conversion procedure is the prediction results, and the output is the formatted prediction results.

[0168] Step 6:

[0169] The server sends the formatted prediction results to the terminal. The terminal receives this data and visually presents it to the user using a display means. The user can check the prediction results and take necessary measures.

[0170] As a specific example of how it works, when a user inputs a plan for "machine maintenance work at Factory B," this plan is sent to the server and validated. As a result of the risk analysis, a risk prediction is generated, such as "Thoroughly confirm that the machine is stopped," and this is displayed on the user's device.

[0171] An example prompt is:

[0172] Please enter your work:

[0173] Content: "Machine Maintenance"

[0174] Location: "Factory B"

[0175] Time: "2023-10-20 13:00"

[0176] Required Equipment: ["Gloves", "Safety Glasses"]

[0177] Send the submitted data to the server and validate it...

[0178] Predictive results based on risk analysis:

[0179] Risk Score: 8.5 / 10

[0180] Prediction result: "There is a high possibility of an accident occurring during machine maintenance. Make sure to check that the machine is stopped."

[0181] The prediction results are displayed.

[0182] 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.

[0183] The present invention combines an emotion engine with a system that inputs a work plan, performs risk analysis, and provides hazard prediction results. The system includes an input means for inputting a work plan, a transmission means for transmitting work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format that is easy for users to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal.

[0184] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions, adjusting the display of prediction results according to the user's emotional state. The emotion engine includes means for recognizing the user's emotional state based on facial expression analysis, voice analysis, data from biosensors, etc. The device also has a function that highlights the prediction results and calls for appropriate attention when it is determined that the user is under stress or has lost concentration.

[0185] The user inputs a work plan using a terminal, including detailed information such as the work content, work location, work time, and necessary equipment. The terminal then sends this information to a server. The server validates the received data and confirms that all necessary information is present. Data that passes validation is used for risk analysis. An AI model is used to perform risk analysis based on past accident data and statistical information, and a risk score is calculated. Potential dangers are predicted based on this risk score, and a predictive method generates the results.

[0186] The prediction results are converted into a user-friendly format by a formatting means. For example, if a specific task is predicted to have a high risk of a fall accident based on past data, the prediction is visually displayed in text and graphics. The formatted prediction results are sent from the server to the user's terminal, where they are displayed.

[0187] The emotion engine analyzes the user's emotional state when viewing the prediction results, and if the user is in an unstable state, it highlights the risk and warns them. For example, when a user is entering a work plan for machine maintenance, if facial expression analysis and voice analysis determine that the user's emotional state is anxious, the emotion engine sends that information to the server. Based on that information, the server highlights the prediction results and displays specific warnings such as, "There is a high possibility of a pinch accident occurring during machine maintenance. Make sure the machine is stopped and warn those around you to be careful."

[0188] As a concrete example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The device sends the input information to the server, which validates the data. The verified data is then input into the AI ​​model, which calculates a risk score based on past accident data. The prediction results are formatted and sent from the server to the user's device. The emotion engine analyzes the user's emotional state, and if the user is feeling anxious, the prediction results are highlighted and necessary precautions are presented to the user. The user can then take the necessary safety measures based on the results.

[0189] This improves work safety and reduces the influence of skill differences and emotions.

[0190] The processing flow will be explained below.

[0191] Step 1:

[0192] The user inputs the work plan into the terminal.

[0193] The user enters detailed information such as the work content, work location, work time, and necessary equipment into the work plan input form on the terminal.

[0194] Step 2:

[0195] The terminal transmits the input work plan data to the server.

[0196] The terminal converts the input work plan information into JSON format and sends it to the server using an HTTP POST request to the specified API endpoint.

[0197] Step 3:

[0198] The server validates the received work plan data.

[0199] The server validates the incoming data using a JSON schema to ensure it is in the correct format and contains all required information.

[0200] Step 4:

[0201] The server inputs the validated data into the AI ​​model and performs risk analysis.

[0202] The server feeds the data that passes validation into the AI ​​model, which calculates a risk score based on past accident data and statistical information that is updated regularly.

[0203] Step 5:

[0204] The server predicts potential danger based on the risk score and generates the predicted result.

[0205] The server analyzes the risk scores returned by the AI ​​model and extracts potential risk factors, such as the risk of falling while working at height.

[0206] Step 6:

[0207] The server converts the prediction results into a user-friendly format.

[0208] The server converts the prediction results into text, graphic, list, or other formats, organizing them in a way that is easy for users to understand.

[0209] Step 7:

[0210] The server sends the formatted prediction results to the terminal.

[0211] The server returns the formatted prediction results to the device via an HTTP POST request.

[0212] Step 8:

[0213] The emotion engine recognizes the user's emotions.

[0214] The emotion engine uses data from the user's facial expressions, voice, and biometric sensors to analyze their emotional state.

[0215] Step 9:

[0216] The emotional state recognized by the emotion engine is sent to the server.

[0217] The emotion engine sends the user's emotion data to the server and reports whether the user is feeling anxious or stressed.

[0218] Step 10:

[0219] The server receives the emotion data and adjusts how the prediction results are displayed.

[0220] The server uses the emotion data to decide whether to highlight the risk prediction results or include additional warnings.

[0221] Step 11:

[0222] The terminal presents the prediction result received from the server and the adjusted display method to the user.

[0223] The device renders the prediction results in the display area, highlighting them or displaying additional notes depending on the user's emotional state.

[0224] Step 12:

[0225] The user implements necessary safety measures based on the displayed prediction results.

[0226] Based on the prediction results provided, users can take specific safety measures, such as rechecking safety equipment and using an anemometer when working at height.

[0227] Example 2

[0228] 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."

[0229] Ensuring safety is an important issue in on-site work planning. However, conventional risk analysis systems do not provide appropriate warnings that take into account the user's emotional state, which can lead to accidents due to decreased attention or emotional instability. Therefore, it is necessary to further improve work safety by providing risk prediction results that take into account the user's emotional state.

[0230] 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.

[0231] In this invention, the server includes an input means, a transmission means, a validation means, a risk analysis means, a prediction means, a formatting means, and an emotion recognition means. This not only enables the server to perform a series of processes from inputting work plan data to risk analysis and displaying prediction results, but also enables the server to recognize the user's emotional state and adjust the risk prediction results.

[0232] "Input means" refers to the devices and software that allow users to input work plans.

[0233] "Transmission means" refers to the functions and technologies for transmitting work plan data obtained from the input means to the server.

[0234] "Validation means" refers to the processes or functions used to verify whether the work plan data sent from the transmission means is correct.

[0235] The "risk analysis means" is a function that uses an AI model to evaluate risk based on work plan data confirmed by the validation means and calculate a risk score.

[0236] A "prediction method" is a process or device that predicts potential dangers based on the risk score obtained by the risk analysis method and generates the results.

[0237] "Formatting means" refers to the functions and technologies used to convert prediction results into a format that is easy for users to understand.

[0238] "Display means" refers to a device or software for displaying the prediction results converted by the formatting means on a user terminal.

[0239] "Emotion recognition means" refers to the functions and processes that recognize the user's emotional state based on data from facial expression analysis, voice analysis, biometric sensors, etc., and adjust the display of prediction results accordingly.

[0240] This invention is a system that combines the input of work plans, risk analysis, prediction of potential dangers, and user emotion recognition. A specific embodiment of this system is described below.

[0241] Hardware and Software

[0242] The system includes hardware such as a terminal for inputting work plans, a server for processing data, and an emotion recognition device for analyzing the user's emotional state, as well as software such as a communication program for sending and receiving data, a program for validating data, a program for analyzing risks using AI models, a program for generating and formatting prediction results, and an emotion recognition engine.

[0243] Data processing and calculation

[0244] The user uses a terminal to input work plan data. This work plan data is sent to the server. The server validates the received data and checks whether all necessary information is included. Next, data that passes validation is input into the AI ​​model, which calculates a risk score based on past accident data and statistical information. The AI ​​model uses generative AI models such as TensorFlow and PyTorch.

[0245] Based on the risk score, a prediction result of potential danger is generated. This prediction result is formatted in a user-friendly format. For example, if a high risk of a fall is predicted, the information is displayed in text and graphic format.

[0246] Additionally, an emotion recognition engine is used to analyze the user's emotional state. If the server determines that the user is feeling anxious or stressed based on facial expression analysis, voice analysis, and biometric sensor data, it will highlight the prediction result based on that information and urge the user to take appropriate precautions.

[0247] Specific examples

[0248] For example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The user inputs the work content, work location, work time, and necessary equipment into the terminal. The terminal sends the input information to the server, which validates the data. The verified data is input into the AI ​​model, and a risk score is calculated. The generated prediction results are formatted and sent from the server to the user's terminal.

[0249] Furthermore, the emotion recognition engine analyzes the user's emotional state, and if the user is feeling anxious, the prediction result is highlighted. For example, specific precautions such as "There is a high possibility of a pinch accident occurring during machine maintenance. Make sure the machine is stopped and alert those around you" are highlighted. This allows the user to take the necessary safety measures.

[0250] Prompt Sentence Examples

[0251] By inputting prompt statements such as the following into the generative AI model, appropriate risk analysis and prediction results can be obtained.

[0252] Work plan: Machine maintenance at B factory

[0253] Work: Machine inspection and repair

[0254] Work location: B Factory, Line 2

[0255] Working hours: October 15, 2023 08:00-12:00

[0256] Required equipment: helmet, safety shoes, gloves

[0257] Emotional data to be analyzed: user facial expression analysis, voice analysis, biometric sensors

[0258] Please provide potential risks and precautions for this work.

[0259] As a result, this system improves work safety and can provide optimal warnings according to the user's emotional state.

[0260] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0261] Step 1:

[0262] The user inputs a work plan using a terminal. The input items include the work content, work location, work time, required equipment, etc. This input data is saved as work plan data.

[0263] Input: Work content, work location, work time, required equipment

[0264] Output: Work plan data

[0265] Step 2:

[0266] The terminal transmits the work plan data to the server using a secure communication protocol (e.g., HTTPS).

[0267] Input: Workplan data

[0268] Output: Data sent to the server

[0269] Step 3:

[0270] The server validates the received work plan data, checking whether required items are included, whether the work time is appropriate, and whether the work location is valid.

[0271] Input: Data sent to the server

[0272] Output: Validated data

[0273] Step 4:

[0274] The server inputs the validated data into an AI model to perform risk analysis. Specifically, a generative AI model (e.g., TensorFlow, PyTorch) is used to calculate a risk score based on past accident data and statistical information.

[0275] Input: Validated data

[0276] Output: Risk score

[0277] Step 5:

[0278] The server generates a prediction result of potential danger based on the risk score. For example, if the risk score is high, the server outputs a prediction result such as "high risk of falling accidents."

[0279] Input: Risk Score

[0280] Output: Prediction result

[0281] Step 6:

[0282] The server formats the prediction results in a user-friendly format, such as text, graphics, or a list.

[0283] Input: Prediction result

[0284] Output: Formatted prediction results

[0285] Step 7:

[0286] The server transmits the formatted prediction results to the user terminal.

[0287] Input: Formatted prediction results

[0288] Output: Prediction results sent to the user's terminal

[0289] Step 8:

[0290] The device displays the received prediction results, allowing the user to check the risks and countermeasures for their work.

[0291] Input: Prediction results sent to the user's terminal

[0292] Output: Prediction results displayed on the terminal

[0293] Step 9:

[0294] The server receives and analyzes the user's emotional data, determining the user's emotional state based on facial expression analysis, voice analysis, biometric sensor data, etc.

[0295] Input: Emotion data (facial expression analysis data, voice analysis data, biosensor data)

[0296] Output: Parsed emotional state

[0297] Step 10:

[0298] The server adjusts the prediction results based on the analyzed emotional state and highlights them as necessary. For example, if the user is feeling anxious, the prediction results will be highlighted in red to urge caution.

[0299] Input: Analyzed emotional state, prediction result

[0300] Output: Adjusted prediction results

[0301] (Application example 2)

[0302] 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."

[0303] In recent years, there has been a demand for risk analysis and hazard prediction for work plans in work environments such as factories. However, conventional systems provide prediction results without taking the user's emotional state into consideration, making it difficult to provide appropriate warnings when the user is under stress or has low concentration. In addition, risk prediction results are sometimes presented in a format that is difficult for users to understand, making it difficult to implement effective risk avoidance measures.

[0304] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: an input means for inputting a work plan; a transmission means for transmitting the work plan data acquired from the input means to the server; a validation means in the server for validating the work plan data transmitted from the transmission means; a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis; a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result; a formatting means for converting the generated prediction result into a format easy for the user to understand; a transmission means for transmitting the prediction result converted by the formatting means to a user terminal; a display means for displaying the prediction result transmitted from the transmission means on the user terminal; an emotion engine for analyzing the user's emotional state when viewing the prediction result; and a display adjustment means for adjusting and displaying the prediction result based on the result of the emotion engine's analysis of the user's emotional state. This makes it possible to provide risk prediction results in an easy-to-understand format while taking the user's emotional state into consideration and to encourage appropriate caution.

[0305] A "work plan" is a set of work instructions that includes detailed information such as the specific work to be done, the location of the work, the time required to do the work, and the equipment required.

[0306] "Input means" refers to a device or interface for inputting a work plan into the system by a user.

[0307] The "transmission means" is a device or function for transmitting the work plan data acquired from the input means to the server.

[0308] "Validation means" refers to a device or function that checks the completeness and consistency of the work plan data sent to the server and verifies that all necessary information is present.

[0309] "Risk analysis means" refers to a device or function that inputs work plan data confirmed by validation means into an AI model to perform risk analysis.

[0310] The "prediction means" is a device or function for predicting potential danger based on the risk score obtained by the risk analysis means and generating the prediction results.

[0311] "Formatting means" refers to a device or function for converting the generated prediction results into a user-friendly format.

[0312] "Display means" refers to a device or function for displaying the prediction results sent to the user terminal.

[0313] An "emotion engine" is a device or function that includes an AI model that analyzes the emotional state of the user when viewing the prediction results and provides appropriate output.

[0314] The "display adjustment means" is a device or function for adjusting the display of prediction results based on the user's emotional state analyzed by the emotion engine.

[0315] A "smartphone" is a type of mobile phone, a mobile device with advanced information processing capabilities and internet connectivity.

[0316] "Smart glasses" are wearable devices that use special lenses and displays to overlay additional information on top of real-world information.

[0317] A "head-mounted display" is a display device worn on the head, and is used to display virtual reality and augmented reality.

[0318] A "robot" is a mechanical device that operates autonomously or semi-autonomously and is programmed to perform specific tasks.

[0319] This invention is a system that inputs a work plan, performs risk analysis, and provides the results of risk prediction. Specifically, it includes the following means:

[0320] The server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model to perform a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating the prediction results, a formatting means for converting the generated prediction results into a format that is easy for the user to understand, a transmission means for transmitting the prediction results converted by the formatting means to a user terminal, a display means for displaying the prediction results transmitted from the transmission means on the user terminal, an emotion engine for analyzing the emotional state of the user when viewing the prediction results, and a display adjustment means for adjusting and displaying the prediction results based on the results of the analysis of the user's emotional state by the emotion engine.

[0321] This allows risk prediction results to be displayed more accurately, making it easier for users to understand the risks.

[0322] The input means is an interface for the user to input a work plan (e.g., "machine maintenance at factory A"). The work plan includes detailed information such as the work content, location, time, and required equipment. This data is sent to the server via the transmission means.

[0323] The server validates the received data using validation methods, such as a validation model using Keras, to ensure data integrity and consistency. Data that passes validation is then input into the AI ​​model.

[0324] The risk analysis method uses an AI model to analyze risk based on past accident data and statistical information. This AI model is built on Keras. A risk score is calculated, and the prediction method predicts potential dangers based on this risk score.

[0325] The generated prediction results are converted into a user-friendly format by the formatting means. For example, the risks and countermeasures are displayed in text or graphic format. The formatted prediction results are sent to the user terminal via the transmission means and displayed by the display means.

[0326] The emotion engine analyzes the user's emotional state based on data obtained from facial expression analysis, voice analysis, and biometric sensors. This analysis is performed using libraries such as OpenCV. The results are sent to the server, and the display adjustment means highlights the prediction results according to the user's emotional state. For example, if the user is in a state of high stress, a warning message is highlighted to draw attention.

[0327] A specific example is the procedure when a user inputs a work plan for "machine maintenance at factory A," and the system predicts and displays the associated risks. If the user is in a stressful state, the system highlights the risk and provides a warning such as, "High risk! There is a high possibility of being pinched during machine maintenance. Please make sure the machine is stopped."

[0328] Example prompt sentence:

[0329] "After entering a machine maintenance work plan and using the emotion engine to analyze facial expressions, it was determined that the user's emotional state was high in stress. Please display the results of a risk analysis for performing the work in this state and provide necessary precautions."

[0330] This makes it possible to provide risk prediction results in an easy-to-understand format while taking into account the user's emotional state, and to encourage appropriate caution.

[0331] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0332] Step 1:

[0333] The user inputs the work plan. Using the input means, the user inputs detailed information such as the work content, location, time, required equipment, etc. into the interface. The input data is provided to the system and sent to the server.

[0334] Step 2:

[0335] The server validates the submitted work plan data using a validation method. A validation model (e.g., a model based on Keras) is used to check the completeness and consistency of the input data. Data that passes validation is sent to the risk analysis method.

[0336] Step 3:

[0337] The server performs risk analysis using an AI model. The risk analysis means calculates a risk score based on past accident data and statistical information. The risk score for the input data (work plan) is calculated and sent to the prediction means.

[0338] Step 4:

[0339] The server predicts potential danger based on the risk score. The prediction means generates a prediction result based on the risk score. The generated prediction result is sent to the formatting means.

[0340] Step 5:

[0341] The server converts the generated prediction results into a format that is easy for users to understand. The formatting means converts the risks and their countermeasures into a display format such as text, graphics, or a list. The formatted prediction results are sent to the user terminal.

[0342] Step 6:

[0343] The server analyzes the user's emotional state. The emotion engine analyzes data from the camera, microphone, and biometric sensors installed on the user's device. The emotion engine evaluates the user's emotional state using facial expression analysis, voice analysis, and biometric data.

[0344] Step 7:

[0345] The emotion engine sends the analysis results (e.g., whether the user is in a high-stress state) to the server, which then adjusts the prediction results based on that information.

[0346] Step 8:

[0347] The server displays the adjusted prediction results on the user terminal using a display means. For example, if the user is in a high stress state, a warning message is highlighted. The user can check the displayed prediction results and adjustment display and take appropriate measures.

[0348] 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.

[0349] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0350] 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.

[0351] [Second embodiment]

[0352] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0353] 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.

[0354] 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).

[0355] 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.

[0356] 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.

[0357] 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).

[0358] 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.

[0359] 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.

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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."

[0364] The present invention is a system for inputting a work plan, performing risk analysis, and providing hazard prediction results. This system includes an input means for inputting a work plan, a transmission means for transmitting work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for users to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal.

[0365] The user inputs a work plan using a terminal, including detailed information such as the work content, work location, work time, and required equipment. The terminal then sends this information to a server. The server validates the sent data to ensure that all necessary information is included. Data that passes validation is then used for risk analysis. The server uses an AI model to perform risk analysis based on past data and statistical information, and calculates a risk score. Potential dangers are predicted based on this risk score.

[0366] The prediction tool organizes the prediction results generated from the risk scores and converts them into a format that is easy for users to understand. For example, if past data indicates a high probability of a fall accident for a specific task, the prediction is displayed visually in text and graphics. The formatted prediction results are sent from the server to the user's device, where the user can view them.

[0367] As a concrete example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The terminal sends this information to the server, which validates it. The confirmed data is input into the AI ​​model, which calculates a risk score based on past accident data from similar work. For example, if there have been many cases of machine entrapment accidents in the same location in the past, the risk is determined to be high. Based on this risk, the prediction means generates a prediction result that reads, "There is a high possibility of an entrapment accident occurring during machine maintenance. Ensure that the machine is stopped thoroughly." The formatting means converts this prediction into a format that is easy for the user to understand and sends it to the terminal. The user can check this prediction result through the terminal and take the necessary safety measures.

[0368] The processing flow will be explained below.

[0369] Step 1:

[0370] The user inputs the work plan into the terminal.

[0371] The user enters detailed information such as the work content, work location, work time, and necessary equipment into the work plan input form on the terminal.

[0372] Step 2:

[0373] The terminal transmits the input work plan data to the server.

[0374] The terminal converts the input work plan information into JSON format and sends it to the server using an HTTP POST request to the specified API endpoint.

[0375] Step 3:

[0376] The server validates the received work plan data.

[0377] The server validates the incoming data using a JSON schema to ensure it is in the correct format and contains all required information.

[0378] Step 4:

[0379] The server inputs the validated data into the AI ​​model and performs risk analysis.

[0380] The server feeds the data that passes validation into the AI ​​model, which calculates a risk score based on past accident data and statistical information that is updated regularly.

[0381] Step 5:

[0382] The server predicts potential danger based on the risk score and generates the predicted result.

[0383] The server analyzes the risk scores returned by the AI ​​model and extracts potential risk factors, such as the risk of falling while working at height.

[0384] Step 6:

[0385] The server converts the prediction results into a user-friendly format.

[0386] The server converts the prediction results into text, graphic, list, or other formats, organizing them in a way that is easy for users to understand.

[0387] Step 7:

[0388] The server sends the formatted prediction results to the terminal.

[0389] The server returns the formatted prediction results to the device via an HTTP POST request.

[0390] Step 8:

[0391] The terminal displays the prediction results received from the server to the user.

[0392] The device renders the received information in the display area and displays specific risks and countermeasures to the user.

[0393] Step 9:

[0394] The user implements necessary safety measures based on the displayed prediction results.

[0395] Based on the prediction results provided, users can take specific safety measures, such as rechecking safety equipment and using an anemometer when working at height.

[0396] Example 1

[0397] 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."

[0398] Conventional risk management systems based on work plans were unable to fully utilize past accident data and statistical information, making it difficult to predict potential hazards. Furthermore, the predicted risks were not adequately presented, making it difficult for users to take appropriate measures. Therefore, there was a need for the development of a system that could accurately and effectively predict risks for work plans set by users and present the prediction results in a format that was easy for users to understand.

[0399] 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.

[0400] In this invention, the server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for the user to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, a display means for displaying the prediction result transmitted from the transmission means on the user terminal, and specific operation steps in which a user inputs detailed work information using the terminal and then the terminal transmits the data to the server. This enables accurate and effective risk prediction based on the work plan input by the user, and further enables the prediction result to be provided to the user in a format easy for the user to understand.

[0401] A "work plan" is a plan that shows detailed information such as the type of work, location, time, and necessary equipment.

[0402] The "input means" is a means for a user to input a work plan into the system via a terminal.

[0403] The "transmission means" is a means for transmitting the work plan data obtained from the input means to the server.

[0404] "Validation measures" are measures for verifying the submitted work plan data and confirming that all necessary information is present.

[0405] The "risk analysis means" is a means of inputting work plan data confirmed by the validation means into an AI model and performing risk analysis.

[0406] An "AI model" is an artificial intelligence model that performs risk analysis based on vast amounts of past data and statistical information.

[0407] "Risk Score" is a numerical indicator of the potential risk associated with a particular task, calculated by a risk analysis tool.

[0408] A "prediction means" is a means for predicting potential danger based on a risk score and generating a prediction result.

[0409] The "formatting means" is a means for converting the generated prediction results into a format that is easy for the user to understand.

[0410] A "user terminal" is a device that a user uses to input work plans and check prediction results.

[0411] The "display means" is a means for displaying the prediction results transmitted from the transmission means at the user terminal.

[0412] The present invention is a system that inputs a work plan, performs risk analysis, and provides the results of risk prediction. This system includes a series of processes from an input means for inputting a work plan to providing the user with the results of risk prediction.

[0413] First, the user logs in to the system using a terminal and inputs a work plan. The input screen provides fields for entering detailed information such as the work content, work location, work time, and required equipment. For example, a work plan such as "Machine maintenance at Factory B" may be entered. Once the input is complete, the user clicks the "Submit" button.

[0414] The device then uses an HTTP POST request to send the input work plan data to the server, including information such as the work content, work location, work time, and required equipment.

[0415] The server uses validation methods to check the received data. Specifically, it checks whether all required fields have been entered and whether there are any abnormalities in the data format. For example, it checks whether the work content is blank. Data that has been successfully validated is sent to the next risk analysis step.

[0416] The server inputs the validated data into a generative AI model (e.g., OpenAI's GPT-4) to perform risk analysis. The AI ​​model analyzes risk by referring to past data and statistical information, and calculates a risk score. Examples of prompts used in this process include:

[0417] "Conduct a risk analysis of machine maintenance at Factory B and predict possible hazards based on past data."

[0418] The server obtains the risk score and uses it to predict potential dangers and generate a prediction result. For example, if the risk score is high, the server generates a text message with the prediction result, such as, "This work has a high risk of being pinched. Wear appropriate safety equipment and make sure the machine is stopped."

[0419] Next, the server converts the generated prediction results into a user-friendly format using a formatting method, such as text, graphics, heat maps, etc. The formatted prediction results are constructed in a format such as HTML or JSON.

[0420] The formatted prediction results are sent from the server to the user's device. The server returns the prediction results as an HTTP response, and the device displays the received data. For example, the risk score and its explanation are displayed in text and graphic format on the device screen, allowing the user to check the prediction results.

[0421] Through this series of processes, accurate and effective risk predictions can be made based on the work plan entered by the user, and the prediction results can be provided to the user in an easy-to-understand format. This system allows users to take appropriate measures for their work plans, thereby improving work safety.

[0422] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0423] Step 1:

[0424] The user logs in to the system using a terminal and inputs a work plan. The input screen displays fields for entering detailed information such as the work content (e.g., machine maintenance), work location (e.g., Factory B), work time (e.g., 2 hours), and required equipment (e.g., helmet, gloves). The user enters this information and clicks the "Submit" button.

[0425] Input: Details of the work, location, duration, and required equipment

[0426] Output: Workplan data (e.g., in JSON format)

[0427] Step 2:

[0428] The device collects the work plan data entered by the user and sends it to the server using an HTTP POST request, which includes information such as the work content, work location, work time, and required equipment.

[0429] Input: Work plan data entered by the user

[0430] Output: Work plan data sent to the server (HTTP request)

[0431] Step 3:

[0432] The server receives the submitted work plan data and validates it using validation measures. Specifically, it checks whether all required fields are entered and whether the data format is correct. For example, it checks whether the work content is blank and whether the location and time are in the correct format. If the data passes validation, it is sent to the next risk analysis step; if it fails, a general error message is generated.

[0433] Input: Work plan data sent to the server

[0434] Output: Validation result (pass / fail), validated data if successful, error message if failed

[0435] Step 4:

[0436] The server inputs the validated data into a generative AI model (e.g., OpenAI's GPT-4) to perform risk analysis. The AI ​​model analyzes the input data by referring to past data and statistical information, and calculates a risk score. Examples of prompts used in this process include:

[0437] "Conduct a risk analysis of machine maintenance at Factory B and predict possible hazards based on past data."

[0438] Input: Validated data, prompt statement

[0439] Output: Risk score (numeric)

[0440] Step 5:

[0441] The server generates specific hazard prediction results based on the risk score obtained from the AI ​​model. For example, if the risk score is high, it generates a text message such as, "This work has a high risk of being pinched. Please wear appropriate safety equipment and make sure the machine is stopped."

[0442] Input: Risk Score

[0443] Output: Prediction result (text message)

[0444] Step 6:

[0445] The server formats the generated prediction results into a user-friendly format, such as text, graphics, heat maps, etc. The formatted results are constructed in HTML, JSON, etc.

[0446] Input: Prediction result

[0447] Output: Formatted prediction results (HTML / JSON format)

[0448] Step 7:

[0449] The server sends the formatted prediction results to the user's device. The prediction results are returned using an HTTP response, and the device displays the received data. The user can check the prediction results by viewing the risk score and its explanation in text and graphic format on the device screen.

[0450] Input: Formatted prediction results

[0451] Output: Prediction results (text / graphics) displayed on the user's terminal

[0452] (Application example 1)

[0453] 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."

[0454] In modern factories, many tasks are planned, many of which involve risks. However, it is difficult to properly predict work risks and take prompt and appropriate countermeasures, making it necessary to ensure the safety of workers. Furthermore, conventional systems make it cumbersome to input work plans and display risk prediction results, and lack a user-friendly interface. Therefore, a means is needed to easily input work plans using voice input or QR codes and display risk prediction results in an easy-to-understand manner.

[0455] 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.

[0456] In this invention, the server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means in the server for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for the user to understand, a means for the user to input the work plan using voice input or a QR code on a terminal, a transmission means for transmitting the prediction result converted by the formatting means to the user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal. This makes it possible to centrally manage everything from inputting the work plan to displaying the risk prediction result and provide a user-friendly interface.

[0457] "Work plan" means a detailed plan of work, including specific locations, times, contents, and equipment required.

[0458] "Input means" refers to a device or interface that allows a user to input a work plan.

[0459] The "transmission means" refers to a mechanism for transmitting the work plan data acquired from the input means to the server.

[0460] "Validation Measures" means a mechanism that verifies that submitted work plan data is accurate and complete.

[0461] The "risk analysis means" is a mechanism for inputting work plan data confirmed by the validation means into an AI model and analyzing the risk.

[0462] A "risk score" is a numerical representation of potential danger obtained through risk analysis.

[0463] "Prediction means" refers to a mechanism that predicts potential danger based on a risk score and generates the prediction results.

[0464] The "formatting means" is a mechanism for converting the generated prediction results into a format that is easy for the user to understand.

[0465] "Voice input" refers to a method in which a user inputs a work plan using voice.

[0466] A "QR code" is a type of two-dimensional barcode and is a means of efficiently reading information.

[0467] "Display means" refers to a mechanism for displaying prediction results on a user terminal.

[0468] A specific system configuration for implementing the present invention is shown below: The system inputs a factory work plan, performs risk analysis and danger prediction, and proposes appropriate countermeasures.

[0469] The system begins with the user inputting a work plan using a device such as a smartphone. The user can input specific details about the work, location, time, and necessary equipment, and can also use voice input or QR code reading. The input work plan is sent to the server by a transmission means. The server then performs the following specific processes:

[0470] The server uses a validation method to check the received work plan data and ensure that the information is accurate and complete. If this validation is successful, the risk analysis method is activated and the validated data is input into the AI ​​model. The AI ​​model used here is configured using machine learning libraries such as TensorFlow and Keras. The AI ​​model calculates a risk score based on past accident data and statistical information.

[0471] Once the risk score is obtained, the prediction means uses the score to predict potential dangers and generate prediction results. These prediction results are created by referring to past accident data for specific tasks. For example, they may include specific countermeasures such as "There is a high possibility of a pinch accident occurring during machine maintenance. Ensure that the machine is thoroughly stopped."

[0472] The generated prediction results are converted by the formatting means into a format that is easy for the user to understand. This conversion can be in a text format, a graphic format, a list format, etc. The formatted prediction results are again sent from the server to the user terminal via the transmission means, and are visually presented to the user by the display means.

[0473] As a specific example, if a user inputs a plan for "machine maintenance work at Factory B," the plan is sent to the server and the data is validated. Risk analysis is then performed using an AI model, and potential hazards are predicted based on past accident data and a risk score. The prediction results are displayed on the user's device along with a clear instruction to "thoroughly check that the machine is stopped."

[0474] An example prompt is:

[0475] Please enter your work:

[0476] Content: "Machine Maintenance"

[0477] Location: "Factory B"

[0478] Time: "2023-10-20 13:00"

[0479] Required Equipment: ["Gloves", "Safety Glasses"]

[0480] Send the submitted data to the server and validate it...

[0481] Predictive results based on risk analysis:

[0482] Risk Score: 8.5 / 10

[0483] Prediction result: "There is a high possibility of an accident occurring during machine maintenance. Make sure to check that the machine is stopped."

[0484] The prediction results are displayed.

[0485] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0486] Step 1:

[0487] The user inputs a work plan using a smartphone or other device. The input includes detailed information such as the work content, location, time, and required equipment. The user can also input information using voice input or a QR code. The input data obtained at this stage is sent to the server.

[0488] Step 2:

[0489] The terminal transmits the acquired work plan data to the server. Once the transmitted data arrives at the server, a validation procedure checks that the information is accurate and complete. The input of this validation procedure is the transmitted work plan data, and the output is the complete data that has passed validation.

[0490] Step 3:

[0491] The validated data is input into the risk analysis tool. The AI ​​model on the server performs a risk analysis based on this data and calculates a risk score based on past accident data and statistical information. This risk score is obtained as the output.

[0492] Step 4:

[0493] The prediction means predicts potential dangers based on the risk score obtained by the risk analysis means. The server compares the risk of a specific task with past data and generates a prediction result. This prediction result is output.

[0494] Step 5:

[0495] The generated prediction results are converted into a user-friendly format by a formatting means. Specifically, they are formatted so that they can be displayed in text format, graphic format, or list format. The input of this conversion procedure is the prediction results, and the output is the formatted prediction results.

[0496] Step 6:

[0497] The server sends the formatted prediction results to the terminal. The terminal receives this data and visually presents it to the user using a display means. The user can check the prediction results and take necessary measures.

[0498] As a specific example of how it works, when a user inputs a plan for "machine maintenance work at Factory B," this plan is sent to the server and validated. As a result of the risk analysis, a risk prediction is generated, such as "Thoroughly confirm that the machine is stopped," and this is displayed on the user's device.

[0499] An example prompt is:

[0500] Please enter your work:

[0501] Content: "Machine Maintenance"

[0502] Location: "Factory B"

[0503] Time: "2023-10-20 13:00"

[0504] Required Equipment: ["Gloves", "Safety Glasses"]

[0505] Send the submitted data to the server and validate it...

[0506] Predictive results based on risk analysis:

[0507] Risk Score: 8.5 / 10

[0508] Prediction result: "There is a high possibility of an accident occurring during machine maintenance. Make sure to check that the machine is stopped."

[0509] The prediction results are displayed.

[0510] 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.

[0511] The present invention combines an emotion engine with a system that inputs a work plan, performs risk analysis, and provides hazard prediction results. The system includes an input means for inputting a work plan, a transmission means for transmitting work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format that is easy for users to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal.

[0512] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions, adjusting the display of prediction results according to the user's emotional state. The emotion engine includes means for recognizing the user's emotional state based on facial expression analysis, voice analysis, data from biosensors, etc. The device also has a function that highlights the prediction results and calls for appropriate attention when it is determined that the user is under stress or has lost concentration.

[0513] The user inputs a work plan using a terminal, including detailed information such as the work content, work location, work time, and necessary equipment. The terminal then sends this information to a server. The server validates the received data and confirms that all necessary information is present. Data that passes validation is used for risk analysis. An AI model is used to perform risk analysis based on past accident data and statistical information, and a risk score is calculated. Potential dangers are predicted based on this risk score, and a predictive method generates the results.

[0514] The prediction results are converted into a user-friendly format by a formatting means. For example, if a specific task is predicted to have a high risk of a fall accident based on past data, the prediction is visually displayed in text and graphics. The formatted prediction results are sent from the server to the user's terminal, where they are displayed.

[0515] The emotion engine analyzes the user's emotional state when viewing the prediction results, and if the user is in an unstable state, it highlights the risk and warns them. For example, when a user is entering a work plan for machine maintenance, if facial expression analysis and voice analysis determine that the user's emotional state is anxious, the emotion engine sends that information to the server. Based on that information, the server highlights the prediction results and displays specific warnings such as, "There is a high possibility of a pinch accident occurring during machine maintenance. Make sure the machine is stopped and warn those around you to be careful."

[0516] As a concrete example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The device sends the input information to the server, which validates the data. The verified data is then input into the AI ​​model, which calculates a risk score based on past accident data. The prediction results are formatted and sent from the server to the user's device. The emotion engine analyzes the user's emotional state, and if the user is feeling anxious, the prediction results are highlighted and necessary precautions are presented to the user. The user can then take the necessary safety measures based on the results.

[0517] This improves work safety and reduces the influence of skill differences and emotions.

[0518] The processing flow will be explained below.

[0519] Step 1:

[0520] The user inputs the work plan into the terminal.

[0521] The user enters detailed information such as the work content, work location, work time, and necessary equipment into the work plan input form on the terminal.

[0522] Step 2:

[0523] The terminal transmits the input work plan data to the server.

[0524] The terminal converts the input work plan information into JSON format and sends it to the server using an HTTP POST request to the specified API endpoint.

[0525] Step 3:

[0526] The server validates the received work plan data.

[0527] The server validates the incoming data using a JSON schema to ensure it is in the correct format and contains all required information.

[0528] Step 4:

[0529] The server inputs the validated data into the AI ​​model and performs risk analysis.

[0530] The server feeds the data that passes validation into the AI ​​model, which calculates a risk score based on past accident data and statistical information that is updated regularly.

[0531] Step 5:

[0532] The server predicts potential danger based on the risk score and generates the predicted result.

[0533] The server analyzes the risk scores returned by the AI ​​model and extracts potential risk factors, such as the risk of falling while working at height.

[0534] Step 6:

[0535] The server converts the prediction results into a user-friendly format.

[0536] The server converts the prediction results into text, graphic, list, or other formats, organizing them in a way that is easy for users to understand.

[0537] Step 7:

[0538] The server sends the formatted prediction results to the terminal.

[0539] The server returns the formatted prediction results to the device via an HTTP POST request.

[0540] Step 8:

[0541] The emotion engine recognizes the user's emotions.

[0542] The emotion engine uses data from the user's facial expressions, voice, and biometric sensors to analyze their emotional state.

[0543] Step 9:

[0544] The emotional state recognized by the emotion engine is sent to the server.

[0545] The emotion engine sends the user's emotion data to the server and reports whether the user is feeling anxious or stressed.

[0546] Step 10:

[0547] The server receives the emotion data and adjusts how the prediction results are displayed.

[0548] The server uses the emotion data to decide whether to highlight the risk prediction results or include additional warnings.

[0549] Step 11:

[0550] The terminal presents the prediction result received from the server and the adjusted display method to the user.

[0551] The device renders the prediction results in the display area, highlighting them or displaying additional notes depending on the user's emotional state.

[0552] Step 12:

[0553] The user implements necessary safety measures based on the displayed prediction results.

[0554] Based on the prediction results provided, users can take specific safety measures, such as rechecking safety equipment and using an anemometer when working at height.

[0555] Example 2

[0556] 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."

[0557] Ensuring safety is an important issue in on-site work planning. However, conventional risk analysis systems do not provide appropriate warnings that take into account the user's emotional state, which can lead to accidents due to decreased attention or emotional instability. Therefore, it is necessary to further improve work safety by providing risk prediction results that take into account the user's emotional state.

[0558] 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.

[0559] In this invention, the server includes an input means, a transmission means, a validation means, a risk analysis means, a prediction means, a formatting means, and an emotion recognition means. This not only enables the server to perform a series of processes from inputting work plan data to risk analysis and displaying prediction results, but also enables the server to recognize the user's emotional state and adjust the risk prediction results.

[0560] "Input means" refers to the devices and software that allow users to input work plans.

[0561] "Transmission means" refers to the functions and technologies for transmitting work plan data obtained from the input means to the server.

[0562] "Validation means" refers to the processes or functions used to verify whether the work plan data sent from the transmission means is correct.

[0563] The "risk analysis means" is a function that uses an AI model to evaluate risk based on work plan data confirmed by the validation means and calculate a risk score.

[0564] A "prediction method" is a process or device that predicts potential dangers based on the risk score obtained by the risk analysis method and generates the results.

[0565] "Formatting means" refers to the functions and technologies used to convert prediction results into a format that is easy for users to understand.

[0566] "Display means" refers to a device or software for displaying the prediction results converted by the formatting means on a user terminal.

[0567] "Emotion recognition means" refers to the functions and processes that recognize the user's emotional state based on data from facial expression analysis, voice analysis, biometric sensors, etc., and adjust the display of prediction results accordingly.

[0568] This invention is a system that combines the input of work plans, risk analysis, prediction of potential dangers, and user emotion recognition. A specific embodiment of this system is described below.

[0569] Hardware and Software

[0570] The system includes hardware such as a terminal for inputting work plans, a server for processing data, and an emotion recognition device for analyzing the user's emotional state, as well as software such as a communication program for sending and receiving data, a program for validating data, a program for analyzing risks using AI models, a program for generating and formatting prediction results, and an emotion recognition engine.

[0571] Data processing and calculation

[0572] The user uses a terminal to input work plan data. This work plan data is sent to the server. The server validates the received data and checks whether all necessary information is included. Next, data that passes validation is input into the AI ​​model, which calculates a risk score based on past accident data and statistical information. The AI ​​model uses generative AI models such as TensorFlow and PyTorch.

[0573] Based on the risk score, a prediction result of potential danger is generated. This prediction result is formatted in a user-friendly format. For example, if a high risk of a fall is predicted, the information is displayed in text and graphic format.

[0574] Additionally, an emotion recognition engine is used to analyze the user's emotional state. If the server determines that the user is feeling anxious or stressed based on facial expression analysis, voice analysis, and biometric sensor data, it will highlight the prediction result based on that information and urge the user to take appropriate precautions.

[0575] Specific examples

[0576] For example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The user inputs the work content, work location, work time, and necessary equipment into the terminal. The terminal sends the input information to the server, which validates the data. The verified data is input into the AI ​​model, and a risk score is calculated. The generated prediction results are formatted and sent from the server to the user's terminal.

[0577] Furthermore, the emotion recognition engine analyzes the user's emotional state, and if the user is feeling anxious, the prediction result is highlighted. For example, specific precautions such as "There is a high possibility of a pinch accident occurring during machine maintenance. Make sure the machine is stopped and alert those around you" are highlighted. This allows the user to take the necessary safety measures.

[0578] Prompt Sentence Examples

[0579] By inputting prompt statements such as the following into the generative AI model, appropriate risk analysis and prediction results can be obtained.

[0580] Work plan: Machine maintenance at B factory

[0581] Work: Machine inspection and repair

[0582] Work location: B Factory, Line 2

[0583] Working hours: October 15, 2023 08:00-12:00

[0584] Required equipment: helmet, safety shoes, gloves

[0585] Emotional data to be analyzed: user facial expression analysis, voice analysis, biometric sensors

[0586] Please provide potential risks and precautions for this work.

[0587] As a result, this system improves work safety and can provide optimal warnings according to the user's emotional state.

[0588] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0589] Step 1:

[0590] The user inputs a work plan using a terminal. The input items include the work content, work location, work time, required equipment, etc. This input data is saved as work plan data.

[0591] Input: Work content, work location, work time, required equipment

[0592] Output: Work plan data

[0593] Step 2:

[0594] The terminal transmits the work plan data to the server using a secure communication protocol (e.g., HTTPS).

[0595] Input: Workplan data

[0596] Output: Data sent to the server

[0597] Step 3:

[0598] The server validates the received work plan data, checking whether required items are included, whether the work time is appropriate, and whether the work location is valid.

[0599] Input: Data sent to the server

[0600] Output: Validated data

[0601] Step 4:

[0602] The server inputs the validated data into an AI model to perform risk analysis. Specifically, a generative AI model (e.g., TensorFlow, PyTorch) is used to calculate a risk score based on past accident data and statistical information.

[0603] Input: Validated data

[0604] Output: Risk score

[0605] Step 5:

[0606] The server generates a prediction result of potential danger based on the risk score. For example, if the risk score is high, the server outputs a prediction result such as "high risk of falling accidents."

[0607] Input: Risk Score

[0608] Output: Prediction result

[0609] Step 6:

[0610] The server formats the prediction results in a user-friendly format, such as text, graphics, or a list.

[0611] Input: Prediction result

[0612] Output: Formatted prediction results

[0613] Step 7:

[0614] The server transmits the formatted prediction results to the user terminal.

[0615] Input: Formatted prediction results

[0616] Output: Prediction results sent to the user's terminal

[0617] Step 8:

[0618] The device displays the received prediction results, allowing the user to check the risks and countermeasures for their work.

[0619] Input: Prediction results sent to the user's terminal

[0620] Output: Prediction results displayed on the terminal

[0621] Step 9:

[0622] The server receives and analyzes the user's emotional data, determining the user's emotional state based on facial expression analysis, voice analysis, biometric sensor data, etc.

[0623] Input: Emotion data (facial expression analysis data, voice analysis data, biosensor data)

[0624] Output: Parsed emotional state

[0625] Step 10:

[0626] The server adjusts the prediction results based on the analyzed emotional state and highlights them as necessary. For example, if the user is feeling anxious, the prediction results will be highlighted in red to urge caution.

[0627] Input: Analyzed emotional state, prediction result

[0628] Output: Adjusted prediction results

[0629] (Application example 2)

[0630] 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."

[0631] In recent years, there has been a demand for risk analysis and hazard prediction for work plans in work environments such as factories. However, conventional systems provide prediction results without taking the user's emotional state into consideration, making it difficult to provide appropriate warnings when the user is under stress or has low concentration. In addition, risk prediction results are sometimes presented in a format that is difficult for users to understand, making it difficult to implement effective risk avoidance measures.

[0632] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: an input means for inputting a work plan; a transmission means for transmitting the work plan data acquired from the input means to the server; a validation means in the server for validating the work plan data transmitted from the transmission means; a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis; a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result; a formatting means for converting the generated prediction result into a format easy for the user to understand; a transmission means for transmitting the prediction result converted by the formatting means to a user terminal; a display means for displaying the prediction result transmitted from the transmission means on the user terminal; an emotion engine for analyzing the user's emotional state when viewing the prediction result; and a display adjustment means for adjusting and displaying the prediction result based on the result of the emotion engine's analysis of the user's emotional state. This makes it possible to provide risk prediction results in an easy-to-understand format while taking the user's emotional state into consideration and to encourage appropriate caution.

[0633] A "work plan" is a set of work instructions that includes detailed information such as the specific work to be done, the location of the work, the time required to do the work, and the equipment required.

[0634] "Input means" refers to a device or interface for inputting a work plan into the system by a user.

[0635] The "transmission means" is a device or function for transmitting the work plan data acquired from the input means to the server.

[0636] "Validation means" refers to a device or function that checks the completeness and consistency of the work plan data sent to the server and verifies that all necessary information is present.

[0637] "Risk analysis means" refers to a device or function that inputs work plan data confirmed by validation means into an AI model to perform risk analysis.

[0638] The "prediction means" is a device or function for predicting potential danger based on the risk score obtained by the risk analysis means and generating the prediction results.

[0639] "Formatting means" refers to a device or function for converting the generated prediction results into a user-friendly format.

[0640] "Display means" refers to a device or function for displaying the prediction results sent to the user terminal.

[0641] An "emotion engine" is a device or function that includes an AI model that analyzes the emotional state of the user when viewing the prediction results and provides appropriate output.

[0642] The "display adjustment means" is a device or function for adjusting the display of prediction results based on the user's emotional state analyzed by the emotion engine.

[0643] A "smartphone" is a type of mobile phone, a mobile device with advanced information processing capabilities and internet connectivity.

[0644] "Smart glasses" are wearable devices that use special lenses and displays to overlay additional information on top of real-world information.

[0645] A "head-mounted display" is a display device worn on the head, and is used to display virtual reality and augmented reality.

[0646] A "robot" is a mechanical device that operates autonomously or semi-autonomously and is programmed to perform specific tasks.

[0647] This invention is a system that inputs a work plan, performs risk analysis, and provides the results of risk prediction. Specifically, it includes the following means:

[0648] The server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model to perform a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating the prediction results, a formatting means for converting the generated prediction results into a format that is easy for the user to understand, a transmission means for transmitting the prediction results converted by the formatting means to a user terminal, a display means for displaying the prediction results transmitted from the transmission means on the user terminal, an emotion engine for analyzing the emotional state of the user when viewing the prediction results, and a display adjustment means for adjusting and displaying the prediction results based on the results of the analysis of the user's emotional state by the emotion engine.

[0649] This allows risk prediction results to be displayed more accurately, making it easier for users to understand the risks.

[0650] The input means is an interface for the user to input a work plan (e.g., "machine maintenance at factory A"). The work plan includes detailed information such as the work content, location, time, and required equipment. This data is sent to the server via the transmission means.

[0651] The server validates the received data using validation methods, such as a validation model using Keras, to ensure data integrity and consistency. Data that passes validation is then input into the AI ​​model.

[0652] The risk analysis method uses an AI model to analyze risk based on past accident data and statistical information. This AI model is built on Keras. A risk score is calculated, and the prediction method predicts potential dangers based on this risk score.

[0653] The generated prediction results are converted into a user-friendly format by the formatting means. For example, the risks and countermeasures are displayed in text or graphic format. The formatted prediction results are sent to the user terminal via the transmission means and displayed by the display means.

[0654] The emotion engine analyzes the user's emotional state based on data obtained from facial expression analysis, voice analysis, and biometric sensors. This analysis is performed using libraries such as OpenCV. The results are sent to the server, and the display adjustment means highlights the prediction results according to the user's emotional state. For example, if the user is in a state of high stress, a warning message is highlighted to draw attention.

[0655] A specific example is the procedure when a user inputs a work plan for "machine maintenance at factory A," and the system predicts and displays the associated risks. If the user is in a stressful state, the system highlights the risk and provides a warning such as, "High risk! There is a high possibility of being pinched during machine maintenance. Please make sure the machine is stopped."

[0656] Example prompt sentence:

[0657] "After entering a machine maintenance work plan and using the emotion engine to analyze facial expressions, it was determined that the user's emotional state was high in stress. Please display the results of a risk analysis for performing the work in this state and provide necessary precautions."

[0658] This makes it possible to provide risk prediction results in an easy-to-understand format while taking into account the user's emotional state, and to encourage appropriate caution.

[0659] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0660] Step 1:

[0661] The user inputs the work plan. Using the input means, the user inputs detailed information such as the work content, location, time, required equipment, etc. into the interface. The input data is provided to the system and sent to the server.

[0662] Step 2:

[0663] The server validates the submitted work plan data using a validation method. A validation model (e.g., a model based on Keras) is used to check the completeness and consistency of the input data. Data that passes validation is sent to the risk analysis method.

[0664] Step 3:

[0665] The server performs risk analysis using an AI model. The risk analysis means calculates a risk score based on past accident data and statistical information. The risk score for the input data (work plan) is calculated and sent to the prediction means.

[0666] Step 4:

[0667] The server predicts potential danger based on the risk score. The prediction means generates a prediction result based on the risk score. The generated prediction result is sent to the formatting means.

[0668] Step 5:

[0669] The server converts the generated prediction results into a format that is easy for users to understand. The formatting means converts the risks and their countermeasures into a display format such as text, graphics, or a list. The formatted prediction results are sent to the user terminal.

[0670] Step 6:

[0671] The server analyzes the user's emotional state. The emotion engine analyzes data from the camera, microphone, and biometric sensors installed on the user's device. The emotion engine evaluates the user's emotional state using facial expression analysis, voice analysis, and biometric data.

[0672] Step 7:

[0673] The emotion engine sends the analysis results (e.g., whether the user is in a high-stress state) to the server, which then adjusts the prediction results based on that information.

[0674] Step 8:

[0675] The server displays the adjusted prediction results on the user terminal using a display means. For example, if the user is in a high stress state, a warning message is highlighted. The user can check the displayed prediction results and adjustment display and take appropriate measures.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] [Third embodiment]

[0680] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0681] 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.

[0682] 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).

[0683] 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.

[0684] 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.

[0685] 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).

[0686] 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.

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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."

[0692] The present invention is a system for inputting a work plan, performing risk analysis, and providing hazard prediction results. This system includes an input means for inputting a work plan, a transmission means for transmitting work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for users to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal.

[0693] The user inputs a work plan using a terminal, including detailed information such as the work content, work location, work time, and required equipment. The terminal then sends this information to a server. The server validates the sent data to ensure that all necessary information is included. Data that passes validation is then used for risk analysis. The server uses an AI model to perform risk analysis based on past data and statistical information, and calculates a risk score. Potential dangers are predicted based on this risk score.

[0694] The prediction tool organizes the prediction results generated from the risk scores and converts them into a format that is easy for users to understand. For example, if past data indicates a high probability of a fall accident for a specific task, the prediction is displayed visually in text and graphics. The formatted prediction results are sent from the server to the user's device, where the user can view them.

[0695] As a concrete example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The terminal sends this information to the server, which validates it. The confirmed data is input into the AI ​​model, which calculates a risk score based on past accident data from similar work. For example, if there have been many cases of machine entrapment accidents in the same location in the past, the risk is determined to be high. Based on this risk, the prediction means generates a prediction result that reads, "There is a high possibility of an entrapment accident occurring during machine maintenance. Ensure that the machine is stopped thoroughly." The formatting means converts this prediction into a format that is easy for the user to understand and sends it to the terminal. The user can check this prediction result through the terminal and take the necessary safety measures.

[0696] The processing flow will be explained below.

[0697] Step 1:

[0698] The user inputs the work plan into the terminal.

[0699] The user enters detailed information such as the work content, work location, work time, and necessary equipment into the work plan input form on the terminal.

[0700] Step 2:

[0701] The terminal transmits the input work plan data to the server.

[0702] The terminal converts the input work plan information into JSON format and sends it to the server using an HTTP POST request to the specified API endpoint.

[0703] Step 3:

[0704] The server validates the received work plan data.

[0705] The server validates the incoming data using a JSON schema to ensure it is in the correct format and contains all required information.

[0706] Step 4:

[0707] The server inputs the validated data into the AI ​​model and performs risk analysis.

[0708] The server feeds the data that passes validation into the AI ​​model, which calculates a risk score based on past accident data and statistical information that is updated regularly.

[0709] Step 5:

[0710] The server predicts potential danger based on the risk score and generates the predicted result.

[0711] The server analyzes the risk scores returned by the AI ​​model and extracts potential risk factors, such as the risk of falling while working at height.

[0712] Step 6:

[0713] The server converts the prediction results into a user-friendly format.

[0714] The server converts the prediction results into text, graphic, list, or other formats, organizing them in a way that is easy for users to understand.

[0715] Step 7:

[0716] The server sends the formatted prediction results to the terminal.

[0717] The server returns the formatted prediction results to the device via an HTTP POST request.

[0718] Step 8:

[0719] The terminal displays the prediction results received from the server to the user.

[0720] The device renders the received information in the display area and displays specific risks and countermeasures to the user.

[0721] Step 9:

[0722] The user implements necessary safety measures based on the displayed prediction results.

[0723] Based on the prediction results provided, users can take specific safety measures, such as rechecking safety equipment and using an anemometer when working at height.

[0724] Example 1

[0725] 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."

[0726] Conventional risk management systems based on work plans were unable to fully utilize past accident data and statistical information, making it difficult to predict potential hazards. Furthermore, the predicted risks were not adequately presented, making it difficult for users to take appropriate measures. Therefore, there was a need for the development of a system that could accurately and effectively predict risks for work plans set by users and present the prediction results in a format that was easy for users to understand.

[0727] 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.

[0728] In this invention, the server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for the user to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, a display means for displaying the prediction result transmitted from the transmission means on the user terminal, and specific operation steps in which a user inputs detailed work information using the terminal and then the terminal transmits the data to the server. This enables accurate and effective risk prediction based on the work plan input by the user, and further enables the prediction result to be provided to the user in a format easy for the user to understand.

[0729] A "work plan" is a plan that shows detailed information such as the type of work, location, time, and necessary equipment.

[0730] The "input means" is a means for a user to input a work plan into the system via a terminal.

[0731] The "transmission means" is a means for transmitting the work plan data obtained from the input means to the server.

[0732] "Validation measures" are measures for verifying the submitted work plan data and confirming that all necessary information is present.

[0733] The "risk analysis means" is a means of inputting work plan data confirmed by the validation means into an AI model and performing risk analysis.

[0734] An "AI model" is an artificial intelligence model that performs risk analysis based on vast amounts of past data and statistical information.

[0735] "Risk Score" is a numerical indicator of the potential risk associated with a particular task, calculated by a risk analysis tool.

[0736] A "prediction means" is a means for predicting potential danger based on a risk score and generating a prediction result.

[0737] The "formatting means" is a means for converting the generated prediction results into a format that is easy for the user to understand.

[0738] A "user terminal" is a device that a user uses to input work plans and check prediction results.

[0739] The "display means" is a means for displaying the prediction results transmitted from the transmission means at the user terminal.

[0740] The present invention is a system that inputs a work plan, performs risk analysis, and provides the results of risk prediction. This system includes a series of processes from an input means for inputting a work plan to providing the user with the results of risk prediction.

[0741] First, the user logs in to the system using a terminal and inputs a work plan. The input screen provides fields for entering detailed information such as the work content, work location, work time, and required equipment. For example, a work plan such as "Machine maintenance at Factory B" may be entered. Once the input is complete, the user clicks the "Submit" button.

[0742] The device then uses an HTTP POST request to send the input work plan data to the server, including information such as the work content, work location, work time, and required equipment.

[0743] The server uses validation methods to check the received data. Specifically, it checks whether all required fields have been entered and whether there are any abnormalities in the data format. For example, it checks whether the work content is blank. Data that has been successfully validated is sent to the next risk analysis step.

[0744] The server inputs the validated data into a generative AI model (e.g., OpenAI's GPT-4) to perform risk analysis. The AI ​​model analyzes risk by referring to past data and statistical information, and calculates a risk score. Examples of prompts used in this process include:

[0745] "Conduct a risk analysis of machine maintenance at Factory B and predict possible hazards based on past data."

[0746] The server obtains the risk score and uses it to predict potential dangers and generate a prediction result. For example, if the risk score is high, the server generates a text message with the prediction result, such as, "This work has a high risk of being pinched. Wear appropriate safety equipment and make sure the machine is stopped."

[0747] Next, the server converts the generated prediction results into a user-friendly format using a formatting method, such as text, graphics, heat maps, etc. The formatted prediction results are constructed in a format such as HTML or JSON.

[0748] The formatted prediction results are sent from the server to the user's device. The server returns the prediction results as an HTTP response, and the device displays the received data. For example, the risk score and its explanation are displayed in text and graphic format on the device screen, allowing the user to check the prediction results.

[0749] Through this series of processes, accurate and effective risk predictions can be made based on the work plan entered by the user, and the prediction results can be provided to the user in an easy-to-understand format. This system allows users to take appropriate measures for their work plans, thereby improving work safety.

[0750] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0751] Step 1:

[0752] The user logs in to the system using a terminal and inputs a work plan. The input screen displays fields for entering detailed information such as the work content (e.g., machine maintenance), work location (e.g., Factory B), work time (e.g., 2 hours), and required equipment (e.g., helmet, gloves). The user enters this information and clicks the "Submit" button.

[0753] Input: Details of the work, location, duration, and required equipment

[0754] Output: Workplan data (e.g., in JSON format)

[0755] Step 2:

[0756] The device collects the work plan data entered by the user and sends it to the server using an HTTP POST request, which includes information such as the work content, work location, work time, and required equipment.

[0757] Input: Work plan data entered by the user

[0758] Output: Work plan data sent to the server (HTTP request)

[0759] Step 3:

[0760] The server receives the submitted work plan data and validates it using validation measures. Specifically, it checks whether all required fields are entered and whether the data format is correct. For example, it checks whether the work content is blank and whether the location and time are in the correct format. If the data passes validation, it is sent to the next risk analysis step; if it fails, a general error message is generated.

[0761] Input: Work plan data sent to the server

[0762] Output: Validation result (pass / fail), validated data if successful, error message if failed

[0763] Step 4:

[0764] The server inputs the validated data into a generative AI model (e.g., OpenAI's GPT-4) to perform risk analysis. The AI ​​model analyzes the input data by referring to past data and statistical information, and calculates a risk score. Examples of prompts used in this process include:

[0765] "Conduct a risk analysis of machine maintenance at Factory B and predict possible hazards based on past data."

[0766] Input: Validated data, prompt statement

[0767] Output: Risk score (numeric)

[0768] Step 5:

[0769] The server generates specific hazard prediction results based on the risk score obtained from the AI ​​model. For example, if the risk score is high, it generates a text message such as, "This work has a high risk of being pinched. Please wear appropriate safety equipment and make sure the machine is stopped."

[0770] Input: Risk Score

[0771] Output: Prediction result (text message)

[0772] Step 6:

[0773] The server formats the generated prediction results into a user-friendly format, such as text, graphics, heat maps, etc. The formatted results are constructed in HTML, JSON, etc.

[0774] Input: Prediction result

[0775] Output: Formatted prediction results (HTML / JSON format)

[0776] Step 7:

[0777] The server sends the formatted prediction results to the user's device. The prediction results are returned using an HTTP response, and the device displays the received data. The user can check the prediction results by viewing the risk score and its explanation in text and graphic format on the device screen.

[0778] Input: Formatted prediction results

[0779] Output: Prediction results (text / graphics) displayed on the user's terminal

[0780] (Application example 1)

[0781] 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."

[0782] In modern factories, many tasks are planned, many of which involve risks. However, it is difficult to properly predict work risks and take prompt and appropriate countermeasures, making it necessary to ensure the safety of workers. Furthermore, conventional systems make it cumbersome to input work plans and display risk prediction results, and lack a user-friendly interface. Therefore, a means is needed to easily input work plans using voice input or QR codes and display risk prediction results in an easy-to-understand manner.

[0783] 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.

[0784] In this invention, the server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means in the server for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for the user to understand, a means for the user to input the work plan using voice input or a QR code on a terminal, a transmission means for transmitting the prediction result converted by the formatting means to the user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal. This makes it possible to centrally manage everything from inputting the work plan to displaying the risk prediction result and provide a user-friendly interface.

[0785] "Work plan" means a detailed plan of work, including specific locations, times, contents, and equipment required.

[0786] "Input means" refers to a device or interface that allows a user to input a work plan.

[0787] The "transmission means" refers to a mechanism for transmitting the work plan data acquired from the input means to the server.

[0788] "Validation Measures" means a mechanism that verifies that submitted work plan data is accurate and complete.

[0789] The "risk analysis means" is a mechanism for inputting work plan data confirmed by the validation means into an AI model and analyzing the risk.

[0790] A "risk score" is a numerical representation of potential danger obtained through risk analysis.

[0791] "Prediction means" refers to a mechanism that predicts potential danger based on a risk score and generates the prediction results.

[0792] The "formatting means" is a mechanism for converting the generated prediction results into a format that is easy for the user to understand.

[0793] "Voice input" refers to a method in which a user inputs a work plan using voice.

[0794] A "QR code" is a type of two-dimensional barcode and is a means of efficiently reading information.

[0795] "Display means" refers to a mechanism for displaying prediction results on a user terminal.

[0796] A specific system configuration for implementing the present invention is shown below: The system inputs a factory work plan, performs risk analysis and danger prediction, and proposes appropriate countermeasures.

[0797] The system begins with the user inputting a work plan using a device such as a smartphone. The user can input specific details about the work, location, time, and necessary equipment, and can also use voice input or QR code reading. The input work plan is sent to the server by a transmission means. The server then performs the following specific processes:

[0798] The server uses a validation method to check the received work plan data and ensure that the information is accurate and complete. If this validation is successful, the risk analysis method is activated and the validated data is input into the AI ​​model. The AI ​​model used here is configured using machine learning libraries such as TensorFlow and Keras. The AI ​​model calculates a risk score based on past accident data and statistical information.

[0799] Once the risk score is obtained, the prediction means uses the score to predict potential dangers and generate prediction results. These prediction results are created by referring to past accident data for specific tasks. For example, they may include specific countermeasures such as "There is a high possibility of a pinch accident occurring during machine maintenance. Ensure that the machine is thoroughly stopped."

[0800] The generated prediction results are converted by the formatting means into a format that is easy for the user to understand. This conversion can be in a text format, a graphic format, a list format, etc. The formatted prediction results are again sent from the server to the user terminal via the transmission means, and are visually presented to the user by the display means.

[0801] As a specific example, if a user inputs a plan for "machine maintenance work at Factory B," the plan is sent to the server and the data is validated. Risk analysis is then performed using an AI model, and potential hazards are predicted based on past accident data and a risk score. The prediction results are displayed on the user's device along with a clear instruction to "thoroughly check that the machine is stopped."

[0802] An example prompt is:

[0803] Please enter your work:

[0804] Content: "Machine Maintenance"

[0805] Location: "Factory B"

[0806] Time: "2023-10-20 13:00"

[0807] Required Equipment: ["Gloves", "Safety Glasses"]

[0808] Send the submitted data to the server and validate it...

[0809] Predictive results based on risk analysis:

[0810] Risk Score: 8.5 / 10

[0811] Prediction result: "There is a high possibility of an accident occurring during machine maintenance. Make sure to check that the machine is stopped."

[0812] The prediction results are displayed.

[0813] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0814] Step 1:

[0815] The user inputs a work plan using a smartphone or other device. The input includes detailed information such as the work content, location, time, and required equipment. The user can also input information using voice input or a QR code. The input data obtained at this stage is sent to the server.

[0816] Step 2:

[0817] The terminal transmits the acquired work plan data to the server. Once the transmitted data arrives at the server, a validation procedure checks that the information is accurate and complete. The input of this validation procedure is the transmitted work plan data, and the output is the complete data that has passed validation.

[0818] Step 3:

[0819] The validated data is input into the risk analysis tool. The AI ​​model on the server performs a risk analysis based on this data and calculates a risk score based on past accident data and statistical information. This risk score is obtained as the output.

[0820] Step 4:

[0821] The prediction means predicts potential dangers based on the risk score obtained by the risk analysis means. The server compares the risk of a specific task with past data and generates a prediction result. This prediction result is output.

[0822] Step 5:

[0823] The generated prediction results are converted into a user-friendly format by a formatting means. Specifically, they are formatted so that they can be displayed in text format, graphic format, or list format. The input of this conversion procedure is the prediction results, and the output is the formatted prediction results.

[0824] Step 6:

[0825] The server sends the formatted prediction results to the terminal. The terminal receives this data and visually presents it to the user using a display means. The user can check the prediction results and take necessary measures.

[0826] As a specific example of how it works, when a user inputs a plan for "machine maintenance work at Factory B," this plan is sent to the server and validated. As a result of the risk analysis, a risk prediction is generated, such as "Thoroughly confirm that the machine is stopped," and this is displayed on the user's device.

[0827] An example prompt is:

[0828] Please enter your work:

[0829] Content: "Machine Maintenance"

[0830] Location: "Factory B"

[0831] Time: "2023-10-20 13:00"

[0832] Required Equipment: ["Gloves", "Safety Glasses"]

[0833] Send the submitted data to the server and validate it...

[0834] Predictive results based on risk analysis:

[0835] Risk Score: 8.5 / 10

[0836] Prediction result: "There is a high possibility of an accident occurring during machine maintenance. Make sure to check that the machine is stopped."

[0837] The prediction results are displayed.

[0838] 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.

[0839] The present invention combines an emotion engine with a system that inputs a work plan, performs risk analysis, and provides hazard prediction results. The system includes an input means for inputting a work plan, a transmission means for transmitting work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format that is easy for users to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal.

[0840] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions, adjusting the display of prediction results according to the user's emotional state. The emotion engine includes means for recognizing the user's emotional state based on facial expression analysis, voice analysis, data from biosensors, etc. The device also has a function that highlights the prediction results and calls for appropriate attention when it is determined that the user is under stress or has lost concentration.

[0841] The user inputs a work plan using a terminal, including detailed information such as the work content, work location, work time, and necessary equipment. The terminal then sends this information to a server. The server validates the received data and confirms that all necessary information is present. Data that passes validation is used for risk analysis. An AI model is used to perform risk analysis based on past accident data and statistical information, and a risk score is calculated. Potential dangers are predicted based on this risk score, and a predictive method generates the results.

[0842] The prediction results are converted into a user-friendly format by a formatting means. For example, if a specific task is predicted to have a high risk of a fall accident based on past data, the prediction is visually displayed in text and graphics. The formatted prediction results are sent from the server to the user's terminal, where they are displayed.

[0843] The emotion engine analyzes the user's emotional state when viewing the prediction results, and if the user is in an unstable state, it highlights the risk and warns them. For example, when a user is entering a work plan for machine maintenance, if facial expression analysis and voice analysis determine that the user's emotional state is anxious, the emotion engine sends that information to the server. Based on that information, the server highlights the prediction results and displays specific warnings such as, "There is a high possibility of a pinch accident occurring during machine maintenance. Make sure the machine is stopped and warn those around you to be careful."

[0844] As a concrete example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The device sends the input information to the server, which validates the data. The verified data is then input into the AI ​​model, which calculates a risk score based on past accident data. The prediction results are formatted and sent from the server to the user's device. The emotion engine analyzes the user's emotional state, and if the user is feeling anxious, the prediction results are highlighted and necessary precautions are presented to the user. The user can then take the necessary safety measures based on the results.

[0845] This improves work safety and reduces the influence of skill differences and emotions.

[0846] The processing flow will be explained below.

[0847] Step 1:

[0848] The user inputs the work plan into the terminal.

[0849] The user enters detailed information such as the work content, work location, work time, and necessary equipment into the work plan input form on the terminal.

[0850] Step 2:

[0851] The terminal transmits the input work plan data to the server.

[0852] The terminal converts the input work plan information into JSON format and sends it to the server using an HTTP POST request to the specified API endpoint.

[0853] Step 3:

[0854] The server validates the received work plan data.

[0855] The server validates the incoming data using a JSON schema to ensure it is in the correct format and contains all required information.

[0856] Step 4:

[0857] The server inputs the validated data into the AI ​​model and performs risk analysis.

[0858] The server feeds the data that passes validation into the AI ​​model, which calculates a risk score based on past accident data and statistical information that is updated regularly.

[0859] Step 5:

[0860] The server predicts potential danger based on the risk score and generates the predicted result.

[0861] The server analyzes the risk scores returned by the AI ​​model and extracts potential risk factors, such as the risk of falling while working at height.

[0862] Step 6:

[0863] The server converts the prediction results into a user-friendly format.

[0864] The server converts the prediction results into text, graphic, list, or other formats, organizing them in a way that is easy for users to understand.

[0865] Step 7:

[0866] The server sends the formatted prediction results to the terminal.

[0867] The server returns the formatted prediction results to the device via an HTTP POST request.

[0868] Step 8:

[0869] The emotion engine recognizes the user's emotions.

[0870] The emotion engine uses data from the user's facial expressions, voice, and biometric sensors to analyze their emotional state.

[0871] Step 9:

[0872] The emotional state recognized by the emotion engine is sent to the server.

[0873] The emotion engine sends the user's emotion data to the server and reports whether the user is feeling anxious or stressed.

[0874] Step 10:

[0875] The server receives the emotion data and adjusts how the prediction results are displayed.

[0876] The server uses the emotion data to decide whether to highlight the risk prediction results or include additional warnings.

[0877] Step 11:

[0878] The terminal presents the prediction result received from the server and the adjusted display method to the user.

[0879] The device renders the prediction results in the display area, highlighting them or displaying additional notes depending on the user's emotional state.

[0880] Step 12:

[0881] The user implements necessary safety measures based on the displayed prediction results.

[0882] Based on the prediction results provided, users can take specific safety measures, such as rechecking safety equipment and using an anemometer when working at height.

[0883] Example 2

[0884] 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."

[0885] Ensuring safety is an important issue in on-site work planning. However, conventional risk analysis systems do not provide appropriate warnings that take into account the user's emotional state, which can lead to accidents due to decreased attention or emotional instability. Therefore, it is necessary to further improve work safety by providing risk prediction results that take into account the user's emotional state.

[0886] 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.

[0887] In this invention, the server includes an input means, a transmission means, a validation means, a risk analysis means, a prediction means, a formatting means, and an emotion recognition means. This not only enables the server to perform a series of processes from inputting work plan data to risk analysis and displaying prediction results, but also enables the server to recognize the user's emotional state and adjust the risk prediction results.

[0888] "Input means" refers to the devices and software that allow users to input work plans.

[0889] "Transmission means" refers to the functions and technologies for transmitting work plan data obtained from the input means to the server.

[0890] "Validation means" refers to the processes or functions used to verify whether the work plan data sent from the transmission means is correct.

[0891] The "risk analysis means" is a function that uses an AI model to evaluate risk based on work plan data confirmed by the validation means and calculate a risk score.

[0892] A "prediction method" is a process or device that predicts potential dangers based on the risk score obtained by the risk analysis method and generates the results.

[0893] "Formatting means" refers to the functions and technologies used to convert prediction results into a format that is easy for users to understand.

[0894] "Display means" refers to a device or software for displaying the prediction results converted by the formatting means on a user terminal.

[0895] "Emotion recognition means" refers to the functions and processes that recognize the user's emotional state based on data from facial expression analysis, voice analysis, biometric sensors, etc., and adjust the display of prediction results accordingly.

[0896] This invention is a system that combines the input of work plans, risk analysis, prediction of potential dangers, and user emotion recognition. A specific embodiment of this system is described below.

[0897] Hardware and Software

[0898] The system includes hardware such as a terminal for inputting work plans, a server for processing data, and an emotion recognition device for analyzing the user's emotional state, as well as software such as a communication program for sending and receiving data, a program for validating data, a program for analyzing risks using AI models, a program for generating and formatting prediction results, and an emotion recognition engine.

[0899] Data processing and calculation

[0900] The user uses a terminal to input work plan data. This work plan data is sent to the server. The server validates the received data and checks whether all necessary information is included. Next, data that passes validation is input into the AI ​​model, which calculates a risk score based on past accident data and statistical information. The AI ​​model uses generative AI models such as TensorFlow and PyTorch.

[0901] Based on the risk score, a prediction result of potential danger is generated. This prediction result is formatted in a user-friendly format. For example, if a high risk of a fall is predicted, the information is displayed in text and graphic format.

[0902] Additionally, an emotion recognition engine is used to analyze the user's emotional state. If the server determines that the user is feeling anxious or stressed based on facial expression analysis, voice analysis, and biometric sensor data, it will highlight the prediction result based on that information and urge the user to take appropriate precautions.

[0903] Specific examples

[0904] For example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The user inputs the work content, work location, work time, and necessary equipment into the terminal. The terminal sends the input information to the server, which validates the data. The verified data is input into the AI ​​model, and a risk score is calculated. The generated prediction results are formatted and sent from the server to the user's terminal.

[0905] Furthermore, the emotion recognition engine analyzes the user's emotional state, and if the user is feeling anxious, the prediction result is highlighted. For example, specific precautions such as "There is a high possibility of a pinch accident occurring during machine maintenance. Make sure the machine is stopped and alert those around you" are highlighted. This allows the user to take the necessary safety measures.

[0906] Prompt Sentence Examples

[0907] By inputting prompt statements such as the following into the generative AI model, appropriate risk analysis and prediction results can be obtained.

[0908] Work plan: Machine maintenance at B factory

[0909] Work: Machine inspection and repair

[0910] Work location: B Factory, Line 2

[0911] Working hours: October 15, 2023 08:00-12:00

[0912] Required equipment: helmet, safety shoes, gloves

[0913] Emotional data to be analyzed: user facial expression analysis, voice analysis, biometric sensors

[0914] Please provide potential risks and precautions for this work.

[0915] As a result, this system improves work safety and can provide optimal warnings according to the user's emotional state.

[0916] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0917] Step 1:

[0918] The user inputs a work plan using a terminal. The input items include the work content, work location, work time, required equipment, etc. This input data is saved as work plan data.

[0919] Input: Work content, work location, work time, required equipment

[0920] Output: Work plan data

[0921] Step 2:

[0922] The terminal transmits the work plan data to the server using a secure communication protocol (e.g., HTTPS).

[0923] Input: Workplan data

[0924] Output: Data sent to the server

[0925] Step 3:

[0926] The server validates the received work plan data, checking whether required items are included, whether the work time is appropriate, and whether the work location is valid.

[0927] Input: Data sent to the server

[0928] Output: Validated data

[0929] Step 4:

[0930] The server inputs the validated data into an AI model to perform risk analysis. Specifically, a generative AI model (e.g., TensorFlow, PyTorch) is used to calculate a risk score based on past accident data and statistical information.

[0931] Input: Validated data

[0932] Output: Risk score

[0933] Step 5:

[0934] The server generates a prediction result of potential danger based on the risk score. For example, if the risk score is high, the server outputs a prediction result such as "high risk of falling accidents."

[0935] Input: Risk Score

[0936] Output: Prediction result

[0937] Step 6:

[0938] The server formats the prediction results in a user-friendly format, such as text, graphics, or a list.

[0939] Input: Prediction result

[0940] Output: Formatted prediction results

[0941] Step 7:

[0942] The server transmits the formatted prediction results to the user terminal.

[0943] Input: Formatted prediction results

[0944] Output: Prediction results sent to the user's terminal

[0945] Step 8:

[0946] The device displays the received prediction results, allowing the user to check the risks and countermeasures for their work.

[0947] Input: Prediction results sent to the user's terminal

[0948] Output: Prediction results displayed on the terminal

[0949] Step 9:

[0950] The server receives and analyzes the user's emotional data, determining the user's emotional state based on facial expression analysis, voice analysis, biometric sensor data, etc.

[0951] Input: Emotion data (facial expression analysis data, voice analysis data, biosensor data)

[0952] Output: Parsed emotional state

[0953] Step 10:

[0954] The server adjusts the prediction results based on the analyzed emotional state and highlights them as necessary. For example, if the user is feeling anxious, the prediction results will be highlighted in red to urge caution.

[0955] Input: Analyzed emotional state, prediction result

[0956] Output: Adjusted prediction results

[0957] (Application example 2)

[0958] 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."

[0959] In recent years, there has been a demand for risk analysis and hazard prediction for work plans in work environments such as factories. However, conventional systems provide prediction results without taking the user's emotional state into consideration, making it difficult to provide appropriate warnings when the user is under stress or has low concentration. In addition, risk prediction results are sometimes presented in a format that is difficult for users to understand, making it difficult to implement effective risk avoidance measures.

[0960] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: an input means for inputting a work plan; a transmission means for transmitting the work plan data acquired from the input means to the server; a validation means in the server for validating the work plan data transmitted from the transmission means; a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis; a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result; a formatting means for converting the generated prediction result into a format easy for the user to understand; a transmission means for transmitting the prediction result converted by the formatting means to a user terminal; a display means for displaying the prediction result transmitted from the transmission means on the user terminal; an emotion engine for analyzing the user's emotional state when viewing the prediction result; and a display adjustment means for adjusting and displaying the prediction result based on the result of the emotion engine's analysis of the user's emotional state. This makes it possible to provide risk prediction results in an easy-to-understand format while taking the user's emotional state into consideration and to encourage appropriate caution.

[0961] A "work plan" is a set of work instructions that includes detailed information such as the specific work to be done, the location of the work, the time required to do the work, and the equipment required.

[0962] "Input means" refers to a device or interface for inputting a work plan into the system by a user.

[0963] The "transmission means" is a device or function for transmitting the work plan data acquired from the input means to the server.

[0964] "Validation means" refers to a device or function that checks the completeness and consistency of the work plan data sent to the server and verifies that all necessary information is present.

[0965] "Risk analysis means" refers to a device or function that inputs work plan data confirmed by validation means into an AI model to perform risk analysis.

[0966] The "prediction means" is a device or function for predicting potential danger based on the risk score obtained by the risk analysis means and generating the prediction results.

[0967] "Formatting means" refers to a device or function for converting the generated prediction results into a user-friendly format.

[0968] "Display means" refers to a device or function for displaying the prediction results sent to the user terminal.

[0969] An "emotion engine" is a device or function that includes an AI model that analyzes the emotional state of the user when viewing the prediction results and provides appropriate output.

[0970] The "display adjustment means" is a device or function for adjusting the display of prediction results based on the user's emotional state analyzed by the emotion engine.

[0971] A "smartphone" is a type of mobile phone, a mobile device with advanced information processing capabilities and internet connectivity.

[0972] "Smart glasses" are wearable devices that use special lenses and displays to overlay additional information on top of real-world information.

[0973] A "head-mounted display" is a display device worn on the head, and is used to display virtual reality and augmented reality.

[0974] A "robot" is a mechanical device that operates autonomously or semi-autonomously and is programmed to perform specific tasks.

[0975] This invention is a system that inputs a work plan, performs risk analysis, and provides the results of risk prediction. Specifically, it includes the following means:

[0976] The server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model to perform a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating the prediction results, a formatting means for converting the generated prediction results into a format that is easy for the user to understand, a transmission means for transmitting the prediction results converted by the formatting means to a user terminal, a display means for displaying the prediction results transmitted from the transmission means on the user terminal, an emotion engine for analyzing the emotional state of the user when viewing the prediction results, and a display adjustment means for adjusting and displaying the prediction results based on the results of the analysis of the user's emotional state by the emotion engine.

[0977] This allows risk prediction results to be displayed more accurately, making it easier for users to understand the risks.

[0978] The input means is an interface for the user to input a work plan (e.g., "machine maintenance at factory A"). The work plan includes detailed information such as the work content, location, time, and required equipment. This data is sent to the server via the transmission means.

[0979] The server validates the received data using validation methods, such as a validation model using Keras, to ensure data integrity and consistency. Data that passes validation is then input into the AI ​​model.

[0980] The risk analysis method uses an AI model to analyze risk based on past accident data and statistical information. This AI model is built on Keras. A risk score is calculated, and the prediction method predicts potential dangers based on this risk score.

[0981] The generated prediction results are converted into a user-friendly format by the formatting means. For example, the risks and countermeasures are displayed in text or graphic format. The formatted prediction results are sent to the user terminal via the transmission means and displayed by the display means.

[0982] The emotion engine analyzes the user's emotional state based on data obtained from facial expression analysis, voice analysis, and biometric sensors. This analysis is performed using libraries such as OpenCV. The results are sent to the server, and the display adjustment means highlights the prediction results according to the user's emotional state. For example, if the user is in a state of high stress, a warning message is highlighted to draw attention.

[0983] A specific example is the procedure when a user inputs a work plan for "machine maintenance at factory A," and the system predicts and displays the associated risks. If the user is in a stressful state, the system highlights the risk and provides a warning such as, "High risk! There is a high possibility of being pinched during machine maintenance. Please make sure the machine is stopped."

[0984] Example prompt sentence:

[0985] "After entering a machine maintenance work plan and using the emotion engine to analyze facial expressions, it was determined that the user's emotional state was high in stress. Please display the results of a risk analysis for performing the work in this state and provide necessary precautions."

[0986] This makes it possible to provide risk prediction results in an easy-to-understand format while taking into account the user's emotional state, and to encourage appropriate caution.

[0987] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0988] Step 1:

[0989] The user inputs the work plan. Using the input means, the user inputs detailed information such as the work content, location, time, required equipment, etc. into the interface. The input data is provided to the system and sent to the server.

[0990] Step 2:

[0991] The server validates the submitted work plan data using a validation method. A validation model (e.g., a model based on Keras) is used to check the completeness and consistency of the input data. Data that passes validation is sent to the risk analysis method.

[0992] Step 3:

[0993] The server performs risk analysis using an AI model. The risk analysis means calculates a risk score based on past accident data and statistical information. The risk score for the input data (work plan) is calculated and sent to the prediction means.

[0994] Step 4:

[0995] The server predicts potential danger based on the risk score. The prediction means generates a prediction result based on the risk score. The generated prediction result is sent to the formatting means.

[0996] Step 5:

[0997] The server converts the generated prediction results into a format that is easy for users to understand. The formatting means converts the risks and their countermeasures into a display format such as text, graphics, or a list. The formatted prediction results are sent to the user terminal.

[0998] Step 6:

[0999] The server analyzes the user's emotional state. The emotion engine analyzes data from the camera, microphone, and biometric sensors installed on the user's device. The emotion engine evaluates the user's emotional state using facial expression analysis, voice analysis, and biometric data.

[1000] Step 7:

[1001] The emotion engine sends the analysis results (e.g., whether the user is in a high-stress state) to the server, which then adjusts the prediction results based on that information.

[1002] Step 8:

[1003] The server displays the adjusted prediction results on the user terminal using a display means. For example, if the user is in a high stress state, a warning message is highlighted. The user can check the displayed prediction results and adjustment display and take appropriate measures.

[1004] 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.

[1005] 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.

[1006] 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.

[1007] [Fourth embodiment]

[1008] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1009] 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.

[1010] 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).

[1011] 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.

[1012] 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.

[1013] 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).

[1014] 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.

[1015] 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.

[1016] 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.

[1017] 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.

[1018] 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.

[1019] 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.

[1020] 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."

[1021] The present invention is a system for inputting a work plan, performing risk analysis, and providing hazard prediction results. This system includes an input means for inputting a work plan, a transmission means for transmitting work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for users to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal.

[1022] The user inputs a work plan using a terminal, including detailed information such as the work content, work location, work time, and required equipment. The terminal then sends this information to a server. The server validates the sent data to ensure that all necessary information is included. Data that passes validation is then used for risk analysis. The server uses an AI model to perform risk analysis based on past data and statistical information, and calculates a risk score. Potential dangers are predicted based on this risk score.

[1023] The prediction tool organizes the prediction results generated from the risk scores and converts them into a format that is easy for users to understand. For example, if past data indicates a high probability of a fall accident for a specific task, the prediction is displayed visually in text and graphics. The formatted prediction results are sent from the server to the user's device, where the user can view them.

[1024] As a concrete example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The terminal sends this information to the server, which validates it. The confirmed data is input into the AI ​​model, which calculates a risk score based on past accident data from similar work. For example, if there have been many cases of machine entrapment accidents in the same location in the past, the risk is determined to be high. Based on this risk, the prediction means generates a prediction result that reads, "There is a high possibility of an entrapment accident occurring during machine maintenance. Ensure that the machine is stopped thoroughly." The formatting means converts this prediction into a format that is easy for the user to understand and sends it to the terminal. The user can check this prediction result through the terminal and take the necessary safety measures.

[1025] The processing flow will be explained below.

[1026] Step 1:

[1027] The user inputs the work plan into the terminal.

[1028] The user enters detailed information such as the work content, work location, work time, and necessary equipment into the work plan input form on the terminal.

[1029] Step 2:

[1030] The terminal transmits the input work plan data to the server.

[1031] The terminal converts the input work plan information into JSON format and sends it to the server using an HTTP POST request to the specified API endpoint.

[1032] Step 3:

[1033] The server validates the received work plan data.

[1034] The server validates the incoming data using a JSON schema to ensure it is in the correct format and contains all required information.

[1035] Step 4:

[1036] The server inputs the validated data into the AI ​​model and performs risk analysis.

[1037] The server feeds the data that passes validation into the AI ​​model, which calculates a risk score based on past accident data and statistical information that is updated regularly.

[1038] Step 5:

[1039] The server predicts potential danger based on the risk score and generates the predicted result.

[1040] The server analyzes the risk scores returned by the AI ​​model and extracts potential risk factors, such as the risk of falling while working at height.

[1041] Step 6:

[1042] The server converts the prediction results into a user-friendly format.

[1043] The server converts the prediction results into text, graphic, list, or other formats, organizing them in a way that is easy for users to understand.

[1044] Step 7:

[1045] The server sends the formatted prediction results to the terminal.

[1046] The server returns the formatted prediction results to the device via an HTTP POST request.

[1047] Step 8:

[1048] The terminal displays the prediction results received from the server to the user.

[1049] The device renders the received information in the display area and displays specific risks and countermeasures to the user.

[1050] Step 9:

[1051] The user implements necessary safety measures based on the displayed prediction results.

[1052] Based on the prediction results provided, users can take specific safety measures, such as rechecking safety equipment and using an anemometer when working at height.

[1053] Example 1

[1054] 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."

[1055] Conventional risk management systems based on work plans were unable to fully utilize past accident data and statistical information, making it difficult to predict potential hazards. Furthermore, the predicted risks were not adequately presented, making it difficult for users to take appropriate measures. Therefore, there was a need for the development of a system that could accurately and effectively predict risks for work plans set by users and present the prediction results in a format that was easy for users to understand.

[1056] 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.

[1057] In this invention, the server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for the user to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, a display means for displaying the prediction result transmitted from the transmission means on the user terminal, and specific operation steps in which a user inputs detailed work information using the terminal and then the terminal transmits the data to the server. This enables accurate and effective risk prediction based on the work plan input by the user, and further enables the prediction result to be provided to the user in a format easy for the user to understand.

[1058] A "work plan" is a plan that shows detailed information such as the type of work, location, time, and necessary equipment.

[1059] The "input means" is a means for a user to input a work plan into the system via a terminal.

[1060] The "transmission means" is a means for transmitting the work plan data obtained from the input means to the server.

[1061] "Validation measures" are measures for verifying the submitted work plan data and confirming that all necessary information is present.

[1062] The "risk analysis means" is a means of inputting work plan data confirmed by the validation means into an AI model and performing risk analysis.

[1063] An "AI model" is an artificial intelligence model that performs risk analysis based on vast amounts of past data and statistical information.

[1064] "Risk Score" is a numerical indicator of the potential risk associated with a particular task, calculated by a risk analysis tool.

[1065] A "prediction means" is a means for predicting potential danger based on a risk score and generating a prediction result.

[1066] The "formatting means" is a means for converting the generated prediction results into a format that is easy for the user to understand.

[1067] A "user terminal" is a device that a user uses to input work plans and check prediction results.

[1068] The "display means" is a means for displaying the prediction results transmitted from the transmission means at the user terminal.

[1069] The present invention is a system that inputs a work plan, performs risk analysis, and provides the results of risk prediction. This system includes a series of processes from an input means for inputting a work plan to providing the user with the results of risk prediction.

[1070] First, the user logs in to the system using a terminal and inputs a work plan. The input screen provides fields for entering detailed information such as the work content, work location, work time, and required equipment. For example, a work plan such as "Machine maintenance at Factory B" may be entered. Once the input is complete, the user clicks the "Submit" button.

[1071] The device then uses an HTTP POST request to send the input work plan data to the server, including information such as the work content, work location, work time, and required equipment.

[1072] The server uses validation methods to check the received data. Specifically, it checks whether all required fields have been entered and whether there are any abnormalities in the data format. For example, it checks whether the work content is blank. Data that has been successfully validated is sent to the next risk analysis step.

[1073] The server inputs the validated data into a generative AI model (e.g., OpenAI's GPT-4) to perform risk analysis. The AI ​​model analyzes risk by referring to past data and statistical information, and calculates a risk score. Examples of prompts used in this process include:

[1074] "Conduct a risk analysis of machine maintenance at Factory B and predict possible hazards based on past data."

[1075] The server obtains the risk score and uses it to predict potential dangers and generate a prediction result. For example, if the risk score is high, the server generates a text message with the prediction result, such as, "This work has a high risk of being pinched. Wear appropriate safety equipment and make sure the machine is stopped."

[1076] Next, the server converts the generated prediction results into a user-friendly format using a formatting method, such as text, graphics, heat maps, etc. The formatted prediction results are constructed in a format such as HTML or JSON.

[1077] The formatted prediction results are sent from the server to the user's device. The server returns the prediction results as an HTTP response, and the device displays the received data. For example, the risk score and its explanation are displayed in text and graphic format on the device screen, allowing the user to check the prediction results.

[1078] Through this series of processes, accurate and effective risk predictions can be made based on the work plan entered by the user, and the prediction results can be provided to the user in an easy-to-understand format. This system allows users to take appropriate measures for their work plans, thereby improving work safety.

[1079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1080] Step 1:

[1081] The user logs in to the system using a terminal and inputs a work plan. The input screen displays fields for entering detailed information such as the work content (e.g., machine maintenance), work location (e.g., Factory B), work time (e.g., 2 hours), and required equipment (e.g., helmet, gloves). The user enters this information and clicks the "Submit" button.

[1082] Input: Details of the work, location, duration, and required equipment

[1083] Output: Workplan data (e.g., in JSON format)

[1084] Step 2:

[1085] The device collects the work plan data entered by the user and sends it to the server using an HTTP POST request, which includes information such as the work content, work location, work time, and required equipment.

[1086] Input: Work plan data entered by the user

[1087] Output: Work plan data sent to the server (HTTP request)

[1088] Step 3:

[1089] The server receives the submitted work plan data and validates it using validation measures. Specifically, it checks whether all required fields are entered and whether the data format is correct. For example, it checks whether the work content is blank and whether the location and time are in the correct format. If the data passes validation, it is sent to the next risk analysis step; if it fails, a general error message is generated.

[1090] Input: Work plan data sent to the server

[1091] Output: Validation result (pass / fail), validated data if successful, error message if failed

[1092] Step 4:

[1093] The server inputs the validated data into a generative AI model (e.g., OpenAI's GPT-4) to perform risk analysis. The AI ​​model analyzes the input data by referring to past data and statistical information, and calculates a risk score. Examples of prompts used in this process include:

[1094] "Conduct a risk analysis of machine maintenance at Factory B and predict possible hazards based on past data."

[1095] Input: Validated data, prompt statement

[1096] Output: Risk score (numeric)

[1097] Step 5:

[1098] The server generates specific hazard prediction results based on the risk score obtained from the AI ​​model. For example, if the risk score is high, it generates a text message such as, "This work has a high risk of being pinched. Please wear appropriate safety equipment and make sure the machine is stopped."

[1099] Input: Risk Score

[1100] Output: Prediction result (text message)

[1101] Step 6:

[1102] The server formats the generated prediction results into a user-friendly format, such as text, graphics, heat maps, etc. The formatted results are constructed in HTML, JSON, etc.

[1103] Input: Prediction result

[1104] Output: Formatted prediction results (HTML / JSON format)

[1105] Step 7:

[1106] The server sends the formatted prediction results to the user's device. The prediction results are returned using an HTTP response, and the device displays the received data. The user can check the prediction results by viewing the risk score and its explanation in text and graphic format on the device screen.

[1107] Input: Formatted prediction results

[1108] Output: Prediction results (text / graphics) displayed on the user's terminal

[1109] (Application example 1)

[1110] 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."

[1111] In modern factories, many tasks are planned, many of which involve risks. However, it is difficult to properly predict work risks and take prompt and appropriate countermeasures, making it necessary to ensure the safety of workers. Furthermore, conventional systems make it cumbersome to input work plans and display risk prediction results, and lack a user-friendly interface. Therefore, a means is needed to easily input work plans using voice input or QR codes and display risk prediction results in an easy-to-understand manner.

[1112] 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.

[1113] In this invention, the server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means in the server for validating the work plan data transmitted from the transmission means, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format easy for the user to understand, a means for the user to input the work plan using voice input or a QR code on a terminal, a transmission means for transmitting the prediction result converted by the formatting means to the user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal. This makes it possible to centrally manage everything from inputting the work plan to displaying the risk prediction result and provide a user-friendly interface.

[1114] "Work plan" means a detailed plan of work, including specific locations, times, contents, and equipment required.

[1115] "Input means" refers to a device or interface that allows a user to input a work plan.

[1116] The "transmission means" refers to a mechanism for transmitting the work plan data acquired from the input means to the server.

[1117] "Validation Measures" means a mechanism that verifies that submitted work plan data is accurate and complete.

[1118] The "risk analysis means" is a mechanism for inputting work plan data confirmed by the validation means into an AI model and analyzing the risk.

[1119] A "risk score" is a numerical representation of potential danger obtained through risk analysis.

[1120] "Prediction means" refers to a mechanism that predicts potential danger based on a risk score and generates the prediction results.

[1121] The "formatting means" is a mechanism for converting the generated prediction results into a format that is easy for the user to understand.

[1122] "Voice input" refers to a method in which a user inputs a work plan using voice.

[1123] A "QR code" is a type of two-dimensional barcode and is a means of efficiently reading information.

[1124] "Display means" refers to a mechanism for displaying prediction results on a user terminal.

[1125] A specific system configuration for implementing the present invention is shown below: The system inputs a factory work plan, performs risk analysis and danger prediction, and proposes appropriate countermeasures.

[1126] The system begins with the user inputting a work plan using a device such as a smartphone. The user can input specific details about the work, location, time, and necessary equipment, and can also use voice input or QR code reading. The input work plan is sent to the server by a transmission means. The server then performs the following specific processes:

[1127] The server uses a validation method to check the received work plan data and ensure that the information is accurate and complete. If this validation is successful, the risk analysis method is activated and the validated data is input into the AI ​​model. The AI ​​model used here is configured using machine learning libraries such as TensorFlow and Keras. The AI ​​model calculates a risk score based on past accident data and statistical information.

[1128] Once the risk score is obtained, the prediction means uses the score to predict potential dangers and generate prediction results. These prediction results are created by referring to past accident data for specific tasks. For example, they may include specific countermeasures such as "There is a high possibility of a pinch accident occurring during machine maintenance. Ensure that the machine is thoroughly stopped."

[1129] The generated prediction results are converted by the formatting means into a format that is easy for the user to understand. This conversion can be in a text format, a graphic format, a list format, etc. The formatted prediction results are again sent from the server to the user terminal via the transmission means, and are visually presented to the user by the display means.

[1130] As a specific example, if a user inputs a plan for "machine maintenance work at Factory B," the plan is sent to the server and the data is validated. Risk analysis is then performed using an AI model, and potential hazards are predicted based on past accident data and a risk score. The prediction results are displayed on the user's device along with a clear instruction to "thoroughly check that the machine is stopped."

[1131] An example prompt is:

[1132] Please enter your work:

[1133] Content: "Machine Maintenance"

[1134] Location: "Factory B"

[1135] Time: "2023-10-20 13:00"

[1136] Required Equipment: ["Gloves", "Safety Glasses"]

[1137] Send the submitted data to the server and validate it...

[1138] Predictive results based on risk analysis:

[1139] Risk Score: 8.5 / 10

[1140] Prediction result: "There is a high possibility of an accident occurring during machine maintenance. Make sure to check that the machine is stopped."

[1141] The prediction results are displayed.

[1142] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1143] Step 1:

[1144] The user inputs a work plan using a smartphone or other device. The input includes detailed information such as the work content, location, time, and required equipment. The user can also input information using voice input or a QR code. The input data obtained at this stage is sent to the server.

[1145] Step 2:

[1146] The terminal transmits the acquired work plan data to the server. Once the transmitted data arrives at the server, a validation procedure checks that the information is accurate and complete. The input of this validation procedure is the transmitted work plan data, and the output is the complete data that has passed validation.

[1147] Step 3:

[1148] The validated data is input into the risk analysis tool. The AI ​​model on the server performs a risk analysis based on this data and calculates a risk score based on past accident data and statistical information. This risk score is obtained as the output.

[1149] Step 4:

[1150] The prediction means predicts potential dangers based on the risk score obtained by the risk analysis means. The server compares the risk of a specific task with past data and generates a prediction result. This prediction result is output.

[1151] Step 5:

[1152] The generated prediction results are converted into a user-friendly format by a formatting means. Specifically, they are formatted so that they can be displayed in text format, graphic format, or list format. The input of this conversion procedure is the prediction results, and the output is the formatted prediction results.

[1153] Step 6:

[1154] The server sends the formatted prediction results to the terminal. The terminal receives this data and visually presents it to the user using a display means. The user can check the prediction results and take necessary measures.

[1155] As a specific example of how it works, when a user inputs a plan for "machine maintenance work at Factory B," this plan is sent to the server and validated. As a result of the risk analysis, a risk prediction is generated, such as "Thoroughly confirm that the machine is stopped," and this is displayed on the user's device.

[1156] An example prompt is:

[1157] Please enter your work:

[1158] Content: "Machine Maintenance"

[1159] Location: "Factory B"

[1160] Time: "2023-10-20 13:00"

[1161] Required Equipment: ["Gloves", "Safety Glasses"]

[1162] Send the submitted data to the server and validate it...

[1163] Predictive results based on risk analysis:

[1164] Risk Score: 8.5 / 10

[1165] Prediction result: "There is a high possibility of an accident occurring during machine maintenance. Make sure to check that the machine is stopped."

[1166] The prediction results are displayed.

[1167] 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.

[1168] The present invention combines an emotion engine with a system that inputs a work plan, performs risk analysis, and provides hazard prediction results. The system includes an input means for inputting a work plan, a transmission means for transmitting work plan data acquired from the input means to a server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis, a prediction means for predicting potential hazards based on a risk score obtained by the risk analysis means and generating a prediction result, a formatting means for converting the generated prediction result into a format that is easy for users to understand, a transmission means for transmitting the prediction result converted by the formatting means to a user terminal, and a display means for displaying the prediction result transmitted from the transmission means on the user terminal.

[1169] Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions, adjusting the display of prediction results according to the user's emotional state. The emotion engine includes means for recognizing the user's emotional state based on facial expression analysis, voice analysis, data from biosensors, etc. The device also has a function that highlights the prediction results and calls for appropriate attention when it is determined that the user is under stress or has lost concentration.

[1170] The user inputs a work plan using a terminal, including detailed information such as the work content, work location, work time, and necessary equipment. The terminal then sends this information to a server. The server validates the received data and confirms that all necessary information is present. Data that passes validation is used for risk analysis. An AI model is used to perform risk analysis based on past accident data and statistical information, and a risk score is calculated. Potential dangers are predicted based on this risk score, and a predictive method generates the results.

[1171] The prediction results are converted into a user-friendly format by a formatting means. For example, if a specific task is predicted to have a high risk of a fall accident based on past data, the prediction is visually displayed in text and graphics. The formatted prediction results are sent from the server to the user's terminal, where they are displayed.

[1172] The emotion engine analyzes the user's emotional state when viewing the prediction results, and if the user is in an unstable state, it highlights the risk and warns them. For example, when a user is entering a work plan for machine maintenance, if facial expression analysis and voice analysis determine that the user's emotional state is anxious, the emotion engine sends that information to the server. Based on that information, the server highlights the prediction results and displays specific warnings such as, "There is a high possibility of a pinch accident occurring during machine maintenance. Make sure the machine is stopped and warn those around you to be careful."

[1173] As a concrete example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The device sends the input information to the server, which validates the data. The verified data is then input into the AI ​​model, which calculates a risk score based on past accident data. The prediction results are formatted and sent from the server to the user's device. The emotion engine analyzes the user's emotional state, and if the user is feeling anxious, the prediction results are highlighted and necessary precautions are presented to the user. The user can then take the necessary safety measures based on the results.

[1174] This improves work safety and reduces the influence of skill differences and emotions.

[1175] The processing flow will be explained below.

[1176] Step 1:

[1177] The user inputs the work plan into the terminal.

[1178] The user enters detailed information such as the work content, work location, work time, and necessary equipment into the work plan input form on the terminal.

[1179] Step 2:

[1180] The terminal transmits the input work plan data to the server.

[1181] The terminal converts the input work plan information into JSON format and sends it to the server using an HTTP POST request to the specified API endpoint.

[1182] Step 3:

[1183] The server validates the received work plan data.

[1184] The server validates the incoming data using a JSON schema to ensure it is in the correct format and contains all required information.

[1185] Step 4:

[1186] The server inputs the validated data into the AI ​​model and performs risk analysis.

[1187] The server feeds the data that passes validation into the AI ​​model, which calculates a risk score based on past accident data and statistical information that is updated regularly.

[1188] Step 5:

[1189] The server predicts potential danger based on the risk score and generates the predicted result.

[1190] The server analyzes the risk scores returned by the AI ​​model and extracts potential risk factors, such as the risk of falling while working at height.

[1191] Step 6:

[1192] The server converts the prediction results into a user-friendly format.

[1193] The server converts the prediction results into text, graphic, list, or other formats, organizing them in a way that is easy for users to understand.

[1194] Step 7:

[1195] The server sends the formatted prediction results to the terminal.

[1196] The server returns the formatted prediction results to the device via an HTTP POST request.

[1197] Step 8:

[1198] The emotion engine recognizes the user's emotions.

[1199] The emotion engine uses data from the user's facial expressions, voice, and biometric sensors to analyze their emotional state.

[1200] Step 9:

[1201] The emotional state recognized by the emotion engine is sent to the server.

[1202] The emotion engine sends the user's emotion data to the server and reports whether the user is feeling anxious or stressed.

[1203] Step 10:

[1204] The server receives the emotion data and adjusts how the prediction results are displayed.

[1205] The server uses the emotion data to decide whether to highlight the risk prediction results or include additional warnings.

[1206] Step 11:

[1207] The terminal presents the prediction result received from the server and the adjusted display method to the user.

[1208] The device renders the prediction results in the display area, highlighting them or displaying additional notes depending on the user's emotional state.

[1209] Step 12:

[1210] The user implements necessary safety measures based on the displayed prediction results.

[1211] Based on the prediction results provided, users can take specific safety measures, such as rechecking safety equipment and using an anemometer when working at height.

[1212] Example 2

[1213] 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."

[1214] Ensuring safety is an important issue in on-site work planning. However, conventional risk analysis systems do not provide appropriate warnings that take into account the user's emotional state, which can lead to accidents due to decreased attention or emotional instability. Therefore, it is necessary to further improve work safety by providing risk prediction results that take into account the user's emotional state.

[1215] 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.

[1216] In this invention, the server includes an input means, a transmission means, a validation means, a risk analysis means, a prediction means, a formatting means, and an emotion recognition means. This not only enables the server to perform a series of processes from inputting work plan data to risk analysis and displaying prediction results, but also enables the server to recognize the user's emotional state and adjust the risk prediction results.

[1217] "Input means" refers to the devices and software that allow users to input work plans.

[1218] "Transmission means" refers to the functions and technologies for transmitting work plan data obtained from the input means to the server.

[1219] "Validation means" refers to the processes or functions used to verify whether the work plan data sent from the transmission means is correct.

[1220] The "risk analysis means" is a function that uses an AI model to evaluate risk based on work plan data confirmed by the validation means and calculate a risk score.

[1221] A "prediction method" is a process or device that predicts potential dangers based on the risk score obtained by the risk analysis method and generates the results.

[1222] "Formatting means" refers to the functions and technologies used to convert prediction results into a format that is easy for users to understand.

[1223] "Display means" refers to a device or software for displaying the prediction results converted by the formatting means on a user terminal.

[1224] "Emotion recognition means" refers to the functions and processes that recognize the user's emotional state based on data from facial expression analysis, voice analysis, biometric sensors, etc., and adjust the display of prediction results accordingly.

[1225] This invention is a system that combines the input of work plans, risk analysis, prediction of potential dangers, and user emotion recognition. A specific embodiment of this system is described below.

[1226] Hardware and Software

[1227] The system includes hardware such as a terminal for inputting work plans, a server for processing data, and an emotion recognition device for analyzing the user's emotional state, as well as software such as a communication program for sending and receiving data, a program for validating data, a program for analyzing risks using AI models, a program for generating and formatting prediction results, and an emotion recognition engine.

[1228] Data processing and calculation

[1229] The user uses a terminal to input work plan data. This work plan data is sent to the server. The server validates the received data and checks whether all necessary information is included. Next, data that passes validation is input into the AI ​​model, which calculates a risk score based on past accident data and statistical information. The AI ​​model uses generative AI models such as TensorFlow and PyTorch.

[1230] Based on the risk score, a prediction result of potential danger is generated. This prediction result is formatted in a user-friendly format. For example, if a high risk of a fall is predicted, the information is displayed in text and graphic format.

[1231] Additionally, an emotion recognition engine is used to analyze the user's emotional state. If the server determines that the user is feeling anxious or stressed based on facial expression analysis, voice analysis, and biometric sensor data, it will highlight the prediction result based on that information and urge the user to take appropriate precautions.

[1232] Specific examples

[1233] For example, consider the case where a user inputs a work plan for "machine maintenance at Factory B." The user inputs the work content, work location, work time, and necessary equipment into the terminal. The terminal sends the input information to the server, which validates the data. The verified data is input into the AI ​​model, and a risk score is calculated. The generated prediction results are formatted and sent from the server to the user's terminal.

[1234] Furthermore, the emotion recognition engine analyzes the user's emotional state, and if the user is feeling anxious, the prediction result is highlighted. For example, specific precautions such as "There is a high possibility of a pinch accident occurring during machine maintenance. Make sure the machine is stopped and alert those around you" are highlighted. This allows the user to take the necessary safety measures.

[1235] Prompt Sentence Examples

[1236] By inputting prompt statements such as the following into the generative AI model, appropriate risk analysis and prediction results can be obtained.

[1237] Work plan: Machine maintenance at B factory

[1238] Work: Machine inspection and repair

[1239] Work location: B Factory, Line 2

[1240] Working hours: October 15, 2023 08:00-12:00

[1241] Required equipment: helmet, safety shoes, gloves

[1242] Emotional data to be analyzed: user facial expression analysis, voice analysis, biometric sensors

[1243] Please provide potential risks and precautions for this work.

[1244] As a result, this system improves work safety and can provide optimal warnings according to the user's emotional state.

[1245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1246] Step 1:

[1247] The user inputs a work plan using a terminal. The input items include the work content, work location, work time, required equipment, etc. This input data is saved as work plan data.

[1248] Input: Work content, work location, work time, required equipment

[1249] Output: Work plan data

[1250] Step 2:

[1251] The terminal transmits the work plan data to the server using a secure communication protocol (e.g., HTTPS).

[1252] Input: Workplan data

[1253] Output: Data sent to the server

[1254] Step 3:

[1255] The server validates the received work plan data, checking whether required items are included, whether the work time is appropriate, and whether the work location is valid.

[1256] Input: Data sent to the server

[1257] Output: Validated data

[1258] Step 4:

[1259] The server inputs the validated data into an AI model to perform risk analysis. Specifically, a generative AI model (e.g., TensorFlow, PyTorch) is used to calculate a risk score based on past accident data and statistical information.

[1260] Input: Validated data

[1261] Output: Risk score

[1262] Step 5:

[1263] The server generates a prediction result of potential danger based on the risk score. For example, if the risk score is high, the server outputs a prediction result such as "high risk of falling accidents."

[1264] Input: Risk Score

[1265] Output: Prediction result

[1266] Step 6:

[1267] The server formats the prediction results in a user-friendly format, such as text, graphics, or a list.

[1268] Input: Prediction result

[1269] Output: Formatted prediction results

[1270] Step 7:

[1271] The server transmits the formatted prediction results to the user terminal.

[1272] Input: Formatted prediction results

[1273] Output: Prediction results sent to the user's terminal

[1274] Step 8:

[1275] The device displays the received prediction results, allowing the user to check the risks and countermeasures for their work.

[1276] Input: Prediction results sent to the user's terminal

[1277] Output: Prediction results displayed on the terminal

[1278] Step 9:

[1279] The server receives and analyzes the user's emotional data, determining the user's emotional state based on facial expression analysis, voice analysis, biometric sensor data, etc.

[1280] Input: Emotion data (facial expression analysis data, voice analysis data, biosensor data)

[1281] Output: Parsed emotional state

[1282] Step 10:

[1283] The server adjusts the prediction results based on the analyzed emotional state and highlights them as necessary. For example, if the user is feeling anxious, the prediction results will be highlighted in red to urge caution.

[1284] Input: Analyzed emotional state, prediction result

[1285] Output: Adjusted prediction results

[1286] (Application example 2)

[1287] 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."

[1288] In recent years, there has been a demand for risk analysis and hazard prediction for work plans in work environments such as factories. However, conventional systems provide prediction results without taking the user's emotional state into consideration, making it difficult to provide appropriate warnings when the user is under stress or has low concentration. In addition, risk prediction results are sometimes presented in a format that is difficult for users to understand, making it difficult to implement effective risk avoidance measures.

[1289] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: an input means for inputting a work plan; a transmission means for transmitting the work plan data acquired from the input means to the server; a validation means in the server for validating the work plan data transmitted from the transmission means; a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis; a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result; a formatting means for converting the generated prediction result into a format easy for the user to understand; a transmission means for transmitting the prediction result converted by the formatting means to a user terminal; a display means for displaying the prediction result transmitted from the transmission means on the user terminal; an emotion engine for analyzing the user's emotional state when viewing the prediction result; and a display adjustment means for adjusting and displaying the prediction result based on the result of the emotion engine's analysis of the user's emotional state. This makes it possible to provide risk prediction results in an easy-to-understand format while taking the user's emotional state into consideration and to encourage appropriate caution.

[1290] A "work plan" is a set of work instructions that includes detailed information such as the specific work to be done, the location of the work, the time required to do the work, and the equipment required.

[1291] "Input means" refers to a device or interface for inputting a work plan into the system by a user.

[1292] The "transmission means" is a device or function for transmitting the work plan data acquired from the input means to the server.

[1293] "Validation means" refers to a device or function that checks the completeness and consistency of the work plan data sent to the server and verifies that all necessary information is present.

[1294] "Risk analysis means" refers to a device or function that inputs work plan data confirmed by validation means into an AI model to perform risk analysis.

[1295] The "prediction means" is a device or function for predicting potential danger based on the risk score obtained by the risk analysis means and generating the prediction results.

[1296] "Formatting means" refers to a device or function for converting the generated prediction results into a user-friendly format.

[1297] "Display means" refers to a device or function for displaying the prediction results sent to the user terminal.

[1298] An "emotion engine" is a device or function that includes an AI model that analyzes the emotional state of the user when viewing the prediction results and provides appropriate output.

[1299] The "display adjustment means" is a device or function for adjusting the display of prediction results based on the user's emotional state analyzed by the emotion engine.

[1300] A "smartphone" is a type of mobile phone, a mobile device with advanced information processing capabilities and internet connectivity.

[1301] "Smart glasses" are wearable devices that use special lenses and displays to overlay additional information on top of real-world information.

[1302] A "head-mounted display" is a display device worn on the head, and is used to display virtual reality and augmented reality.

[1303] A "robot" is a mechanical device that operates autonomously or semi-autonomously and is programmed to perform specific tasks.

[1304] This invention is a system that inputs a work plan, performs risk analysis, and provides the results of risk prediction. Specifically, it includes the following means:

[1305] The server includes an input means for inputting a work plan, a transmission means for transmitting the work plan data acquired from the input means to the server, a validation means for validating the work plan data transmitted from the transmission means in the server, a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model to perform a risk analysis, a prediction means for predicting potential dangers based on the risk score obtained by the risk analysis means and generating the prediction results, a formatting means for converting the generated prediction results into a format that is easy for the user to understand, a transmission means for transmitting the prediction results converted by the formatting means to a user terminal, a display means for displaying the prediction results transmitted from the transmission means on the user terminal, an emotion engine for analyzing the emotional state of the user when viewing the prediction results, and a display adjustment means for adjusting and displaying the prediction results based on the results of the analysis of the user's emotional state by the emotion engine.

[1306] This allows risk prediction results to be displayed more accurately, making it easier for users to understand the risks.

[1307] The input means is an interface for the user to input a work plan (e.g., "machine maintenance at factory A"). The work plan includes detailed information such as the work content, location, time, and required equipment. This data is sent to the server via the transmission means.

[1308] The server validates the received data using validation methods, such as a validation model using Keras, to ensure data integrity and consistency. Data that passes validation is then input into the AI ​​model.

[1309] The risk analysis method uses an AI model to analyze risk based on past accident data and statistical information. This AI model is built on Keras. A risk score is calculated, and the prediction method predicts potential dangers based on this risk score.

[1310] The generated prediction results are converted into a user-friendly format by the formatting means. For example, the risks and countermeasures are displayed in text or graphic format. The formatted prediction results are sent to the user terminal via the transmission means and displayed by the display means.

[1311] The emotion engine analyzes the user's emotional state based on data obtained from facial expression analysis, voice analysis, and biometric sensors. This analysis is performed using libraries such as OpenCV. The results are sent to the server, and the display adjustment means highlights the prediction results according to the user's emotional state. For example, if the user is in a state of high stress, a warning message is highlighted to draw attention.

[1312] A specific example is the procedure when a user inputs a work plan for "machine maintenance at factory A," and the system predicts and displays the associated risks. If the user is in a stressful state, the system highlights the risk and provides a warning such as, "High risk! There is a high possibility of being pinched during machine maintenance. Please make sure the machine is stopped."

[1313] Example prompt sentence:

[1314] "After entering a machine maintenance work plan and using the emotion engine to analyze facial expressions, it was determined that the user's emotional state was high in stress. Please display the results of a risk analysis for performing the work in this state and provide necessary precautions."

[1315] This makes it possible to provide risk prediction results in an easy-to-understand format while taking into account the user's emotional state, and to encourage appropriate caution.

[1316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1317] Step 1:

[1318] The user inputs the work plan. Using the input means, the user inputs detailed information such as the work content, location, time, required equipment, etc. into the interface. The input data is provided to the system and sent to the server.

[1319] Step 2:

[1320] The server validates the submitted work plan data using a validation method. A validation model (e.g., a model based on Keras) is used to check the completeness and consistency of the input data. Data that passes validation is sent to the risk analysis method.

[1321] Step 3:

[1322] The server performs risk analysis using an AI model. The risk analysis means calculates a risk score based on past accident data and statistical information. The risk score for the input data (work plan) is calculated and sent to the prediction means.

[1323] Step 4:

[1324] The server predicts potential danger based on the risk score. The prediction means generates a prediction result based on the risk score. The generated prediction result is sent to the formatting means.

[1325] Step 5:

[1326] The server converts the generated prediction results into a format that is easy for users to understand. The formatting means converts the risks and their countermeasures into a display format such as text, graphics, or a list. The formatted prediction results are sent to the user terminal.

[1327] Step 6:

[1328] The server analyzes the user's emotional state. The emotion engine analyzes data from the camera, microphone, and biometric sensors installed on the user's device. The emotion engine evaluates the user's emotional state using facial expression analysis, voice analysis, and biometric data.

[1329] Step 7:

[1330] The emotion engine sends the analysis results (e.g., whether the user is in a high-stress state) to the server, which then adjusts the prediction results based on that information.

[1331] Step 8:

[1332] The server displays the adjusted prediction results on the user terminal using a display means. For example, if the user is in a high stress state, a warning message is highlighted. The user can check the displayed prediction results and adjustment display and take appropriate measures.

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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).

[1340] 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.

[1341] 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."

[1342] 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.

[1343] 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).

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] The following is further disclosed regarding the above embodiment.

[1355] (Claim 1)

[1356] an input means for inputting a work plan;

[1357] a transmission means for transmitting the work plan data acquired from the input means to a server;

[1358] a validation means in the server for validating the work plan data transmitted from the transmission means;

[1359] a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis;

[1360] a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result;

[1361] a formatting means for converting the generated prediction results into a user-friendly format;

[1362] a transmitting means for transmitting the prediction result converted by the formatting means to a user terminal;

[1363] A display means for displaying the prediction result transmitted from the transmission means in the user terminal;

[1364] A system including:

[1365] (Claim 2)

[1366] 2. The system of claim 1, wherein the prediction means includes means for calculating a risk score based on past accident data related to a specific work content.

[1367] (Claim 3)

[1368] 2. The system of claim 1, wherein the formatting means includes means for converting the risks and their countermeasures into a display format such as text, graphics, or a list.

[1369] "Example 1"

[1370] (Claim 1)

[1371] an input means for inputting a work plan;

[1372] a transmission means for transmitting the work plan data acquired from the input means to a server;

[1373] a validation means in the server for validating the work plan data transmitted from the transmission means;

[1374] a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis;

[1375] a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result;

[1376] a formatting means for converting the generated prediction results into a user-friendly format;

[1377] a transmitting means for transmitting the prediction result converted by the formatting means to a user terminal;

[1378] A display means for displaying the prediction result transmitted from the transmission means in the user terminal;

[1379] A system that includes specific operational steps in which a user inputs detailed work information using a terminal, and then the terminal transmits the data to a server.

[1380] (Claim 2)

[1381] The system of claim 1, wherein the prediction means calculates a risk score based on past accident data related to a specific work content and uses the risk score obtained from the generative AI model.

[1382] (Claim 3)

[1383] 2. The system of claim 1, wherein the formatting means includes means for converting the risks and their countermeasures into a display format such as text, graphics, heat maps, etc., for a user.

[1384] "Application Example 1"

[1385] (Claim 1)

[1386] an input means for inputting a work plan;

[1387] a transmission means for transmitting the work plan data acquired from the input means to a server;

[1388] a validation means in the server for validating the work plan data transmitted from the transmission means;

[1389] a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis;

[1390] a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result;

[1391] a formatting means for converting the generated prediction results into a user-friendly format;

[1392] A means for a user to input a work plan using a terminal by voice input or QR code;

[1393] a transmitting means for transmitting the prediction result converted by the formatting means to a user terminal;

[1394] A display means for displaying the prediction result transmitted from the transmission means in the user terminal;

[1395] A system including:

[1396] (Claim 2)

[1397] 2. The system of claim 1, wherein the prediction means includes means for calculating a risk score based on past accident data related to a specific work content.

[1398] (Claim 3)

[1399] 2. The system of claim 1, wherein the formatting means includes means for converting the risks and their countermeasures into a display format such as text, graphics, or a list.

[1400] "Example 2: Combining Emotion Engines"

[1401] (Claim 1)

[1402] an input means for inputting a work plan;

[1403] a transmission means for transmitting the work plan data acquired from the input means to a server;

[1404] a validation means in the server for validating the work plan data transmitted from the transmission means;

[1405] a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis;

[1406] a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result;

[1407] a formatting means for converting the generated prediction results into a user-friendly format;

[1408] a transmitting means for transmitting the prediction result converted by the formatting means to a user terminal;

[1409] A display means for displaying the prediction result transmitted from the transmission means in the user terminal;

[1410] an emotion recognition means incorporating an emotion engine that recognizes the emotion of a user and adjusts the display of the prediction result;

[1411] A system including:

[1412] (Claim 2)

[1413] 2. The system of claim 1, wherein the prediction means includes means for calculating a risk score based on past accident data related to a specific work content.

[1414] (Claim 3)

[1415] 2. The system of claim 1, wherein the formatting means includes means for converting the risks and their countermeasures into a display format such as text, graphics, or a list.

[1416] "Application example 2 when combining emotion engines"

[1417] (Claim 1)

[1418] an input means for inputting a work plan;

[1419] a transmission means for transmitting the work plan data acquired from the input means to a server;

[1420] a validation means in the server for validating the work plan data transmitted from the transmission means;

[1421] a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis;

[1422] a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result;

[1423] a formatting means for converting the generated prediction results into a user-friendly format;

[1424] a transmitting means for transmitting the prediction result converted by the formatting means to a user terminal;

[1425] A display means for displaying the prediction result transmitted from the transmission means in the user terminal;

[1426] an emotion engine that analyzes the user's emotional state when viewing the prediction results;

[1427] a display adjustment means for adjusting and displaying the prediction result based on the result of the analysis of the user's emotional state by the emotion engine;

[1428] A system including:

[1429] (Claim 2)

[1430] 2. The system of claim 1, wherein the prediction means includes means for calculating a risk score based on past accident data related to a specific work content.

[1431] (Claim 3)

[1432] 2. The system of claim 1, wherein the formatting means includes means for converting the risks and their countermeasures into a display format such as text, graphics, or a list.

[1433] (Claim 4)

[1434] 10. The system of claim 1, wherein the emotion engine includes means for analyzing the emotional state using facial expression analysis, voice analysis, and data from biometric sensors.

[1435] (Claim 5)

[1436] 2. The system of claim 1, wherein the display adjusting means includes means for highlighting the prediction result based on the emotional state of the user.

[1437] (Claim 6)

[1438] The system of claim 1, further comprising means for executing a series of processes related to input of work plans, transmission and validation of data, risk analysis, generation of prediction results and display adjustment by an application installed on a smartphone, smart glasses, a head-mounted display or a robot. [Explanation of symbols]

[1439] 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. an input means for inputting a work plan; a transmission means for transmitting the work plan data acquired from the input means to a server; a validation means in the server for validating the work plan data transmitted from the transmission means; a risk analysis means for inputting the work plan data confirmed by the validation means into an AI model and performing a risk analysis; a prediction means for predicting potential danger based on the risk score obtained by the risk analysis means and generating a prediction result; a formatting means for converting the generated prediction results into a user-friendly format; a transmitting means for transmitting the prediction result converted by the formatting means to a user terminal; A display means for displaying the prediction result transmitted from the transmission means in the user terminal; A system including:

2. The system of claim 1 , wherein the predictive means includes means for calculating a risk score based on past accident data related to a specific work content.

3. 2. The system of claim 1, wherein the formatting means includes means for converting the risks and their countermeasures into a display format such as text, graphics, or a list.

Images