System

Abstract

An object of the system according to the embodiment is to detect the dangerous behavior of the field operators in real time and to appropriately respond to the dangerous behavior.SOLUTION: A system according to an embodiment includes a dangerous behavior detection unit, an alert issuing unit, and an evidence recording unit. The dangerous action detector detects a dangerous action using the worker's voice or image. The alert issuing unit issues an alert in response to the dangerous behavior detected by the dangerous behavior detecting unit. The evidence recording unit records data on the dangerous behavior detected by the dangerous behavior detection unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem of making it difficult to detect dangerous worker behavior in real time and respond appropriately.

[0005] The system according to the embodiment aims to detect dangerous behavior of workers in real time and respond appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a risky behavior detection unit, an alert issuing unit, and an evidence recording unit. The risky behavior detection unit detects risky behavior using the voice and image of the worker. The alert issuing unit issues an alert in response to risky behavior detected by the risky behavior detection unit. The evidence recording unit records data on risky behavior detected by the risky behavior detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect dangerous behavior of workers in real time and respond appropriately. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

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

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

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

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

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

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The risky behavior detection system according to the embodiment of the present invention is a system that detects risky behavior using the voices and images of workers, issues an alert, and records evidence, thereby ensuring the safety of workers and enabling the company to fulfill its supervisory responsibilities.

[0029] A risky behavior detection system according to an embodiment includes a risky behavior detection unit, an alert issuing unit, and an evidence recording unit. The risky behavior detection unit detects risky behavior using the voice and image of a worker. For example, the risky behavior detection unit detects when a worker is working without a safety device. The risky behavior detection unit also detects when a worker is entering a dangerous location. The risky behavior detection unit also detects when a worker is performing inappropriate behavior. The alert issuing unit issues an alert in response to risky behavior detected by the risky behavior detection unit. For example, the alert issuing unit issues a voice alert such as "Risky behavior has been detected. Please take safe action immediately." The alert issuing unit also turns on a warning lamp. The alert issuing unit also issues a vibration alert. The evidence recording unit records data on risky behavior detected by the risky behavior detection unit. For example, the evidence recording unit records the date, time, and location at which the risky behavior was detected. The evidence recording unit also records specific details of the risky behavior. Furthermore, the evidence recording unit records audio data and video data when risky behavior occurs. As a result, the risky behavior detection system according to the embodiment can ensure the safety of workers and fulfill the supervisory responsibilities of the company. For example, the company can provide appropriate guidance to workers based on the evidence when risky behavior is detected. Furthermore, the company can identify areas for improvement in the work environment based on the evidence, and improve the working environment. Furthermore, the company can reduce insurance premiums based on the evidence.

[0030] The risky behavior detection unit can learn worker behavior patterns over a long period of time and construct a generative AI model for detecting abnormal behavior. The risky behavior detection unit, for example, collects worker behavior patterns over a long period of time and trains the generative AI model. For example, to detect behavior that differs from normal work behavior, data is collected over several months and abnormal behavior is identified. The risky behavior detection unit also uses the generative AI model to analyze worker behavior patterns in real time and detect abnormal behavior. For example, if the generative AI model detects behavior that differs from normal behavior, it issues an alert. The risky behavior detection unit also uses the generative AI model to analyze worker behavior patterns and detect signs of abnormal behavior early. For example, if the generative AI model detects signs of behavior that differs from normal behavior, it issues an alert. In this way, by learning worker behavior patterns and detecting abnormal behavior, it is possible to detect dangerous behavior early.

[0031] The risky behavior detection unit can analyze changes in the tone and tempo of the worker's voice to detect signs of stress or fatigue. The risky behavior detection unit, for example, analyzes the tone and tempo of the worker's voice in real time to detect signs of stress or fatigue. For example, stress is detected when the tone of the voice is higher than usual. The risky behavior detection unit also detects stress when the tempo of the voice is faster than usual. The risky behavior detection unit also detects fatigue when the tone of the voice is lower than usual. In this way, the health condition of the worker can be grasped by analyzing changes in the tone and tempo of the worker's voice to detect signs of stress or fatigue.

[0032] The risky behavior detection unit can monitor the worker's vital data in real time and detect signs of risky behavior. The risky behavior detection unit, for example, monitors the worker's heart rate and body temperature in real time and detects signs of risky behavior when abnormal values ​​are detected. For example, the risky behavior detection unit detects stress when the heart rate rises sharply. The risky behavior detection unit also detects the risk of heatstroke when the body temperature rises sharply. The risky behavior detection unit also analyzes the vital data and issues an alert when an abnormal value is detected. In this way, by monitoring the worker's vital data and detecting signs of risky behavior, the worker's health condition can be understood and accidents can be prevented.

[0033] The risky behavior detection unit can monitor changes in the work environment and evaluate the risk of risky behavior due to environmental factors. The risky behavior detection unit, for example, monitors the temperature, humidity, and noise level of the work environment in real time, and evaluates the risk of risky behavior when an abnormal value is detected. For example, the risk of heat stroke is evaluated when the temperature is too high. The risky behavior detection unit also evaluates the risk of dehydration when the humidity is too high. The risky behavior detection unit also evaluates the risk of hearing impairment when the noise level is too high. In this way, the safety of workers can be ensured by monitoring changes in the work environment and evaluating the risk of risky behavior due to environmental factors.

[0034] The alert issuing unit can generate a customized alert message according to the individual characteristics of each worker. The alert issuing unit generates a customized alert message according to, for example, the individual characteristics of each worker (such as age, experience, and health condition). For example, an alert including detailed instructions is issued to an inexperienced worker. The alert issuing unit also generates an alert message according to the health condition of the worker. For example, an alert urging a worker in poor health to take a break. The alert issuing unit also generates an alert message according to the age of the worker. For example, an alert urging an elderly worker to be careful. In this way, by generating an alert message customized according to the individual characteristics of each worker, more effective warnings can be issued.

[0035] The alert issuing unit can optimize the timing of issuing an alert and identify the moment when a worker can respond most effectively. In order to optimize the timing of issuing an alert, the alert issuing unit, for example, analyzes the behavioral patterns of workers and identifies the moment when a worker can respond most effectively. For example, it identifies a time when workers are concentrating. The alert issuing unit also analyzes the health status of workers and identifies the moment when a worker can respond most effectively. For example, it identifies a time when the worker's health is good. The alert issuing unit also analyzes the work environment of the worker and identifies the moment when a worker can respond most effectively. For example, it identifies a time when the work environment is quiet. In this way, by optimizing the timing of issuing an alert, it is possible to identify the moment when a worker can respond most effectively and prevent risky behavior.

[0036] The alert issuing unit can utilize a wearable device such as a smartwatch or smart glasses of the worker when issuing an alert. The alert issuing unit, for example, utilizes the worker's smartwatch or smart glasses to issue an alert. For example, the alert is transmitted using the vibration of the smartwatch or the display on the smartglasses. The alert issuing unit also uses the wearable device to acquire the worker's location information and issue an alert. For example, an alert is issued when the worker enters a dangerous area. The alert issuing unit also uses the wearable device to monitor the worker's health condition and issue an alert when an abnormality is detected. In this way, by utilizing the wearable device when issuing an alert, warnings can be more effectively communicated to the worker.

[0037] The alert issuing unit can make the content of the alert multilingual so that it can be used in international work sites. The alert issuing unit, for example, makes the content of the alert multilingual so that it can be used in international work sites. For example, the alert issuing unit issues an alert in multiple languages, such as English, Spanish, and Chinese. The alert issuing unit also generates an alert message according to the worker's native language. For example, if the worker's native language is Spanish, the alert is issued in Spanish. The alert issuing unit also generates an alert message according to the worker's language setting. For example, if the worker's language setting is English, the alert is issued in English. By making the content of the alert multilingual, it can be used in international work sites, ensuring the safety of workers.

[0038] The evidence recording unit can record related sensor data simultaneously with the detection of risky behavior. For example, when risky behavior is detected, the evidence recording unit simultaneously records sensor data such as the temperature, humidity, and noise level of the work environment. For example, it stores environmental data at the moment the risky behavior occurred. The evidence recording unit also simultaneously records the worker's vital signs data. For example, it stores data on heart rate and body temperature. The evidence recording unit also simultaneously records the worker's location information. For example, it stores data on the location where the risky behavior occurred. In this way, by recording related sensor data simultaneously with the detection of risky behavior, more detailed evidence can be provided.

[0039] The evidence recording unit can store evidence data in a tamper-proof form using blockchain technology. The evidence recording unit, for example, stores risky behavior detection data in a tamper-proof form using blockchain technology. For example, the hash value of the data is recorded in the blockchain. The evidence recording unit also stores the evidence data in a distributed ledger. For example, the data is distributed and stored across multiple nodes. The evidence recording unit also uses a digital signature to prevent tampering with the evidence data. For example, a digital signature is assigned to the data. In this way, the reliability of the data can be ensured by storing the evidence data in a tamper-proof form using blockchain technology.

[0040] The evidence recording unit can store evidence data on the cloud and make it accessible from a remote location. The evidence recording unit, for example, stores detection data of risky behavior on the cloud and makes it accessible from a remote location. For example, the evidence recording unit stores data using cloud storage. The evidence recording unit also encrypts the data stored on the cloud. For example, the data is encrypted and stored. The evidence recording unit also introduces an authentication system for accessing the data stored on the cloud. For example, two-factor authentication is used. This allows the evidence data to be stored on the cloud and accessible from a remote location, thereby improving the convenience of the data.

[0041] The evidence recording unit can automatically analyze the evidence data and generate a report of patterns and trends of risky behavior. The evidence recording unit, for example, automatically analyzes the evidence data and generates a report of patterns and trends of risky behavior. For example, it extracts patterns using data mining technology. The evidence recording unit also analyzes the frequency and time periods of occurrence of risky behavior. For example, it generates a report if risky behavior occurs frequently during a specific time period. The evidence recording unit also analyzes the location where risky behavior occurs. For example, it generates a report if risky behavior occurs frequently in a specific location. In this way, automatically analyzing the evidence data and generating a report of patterns and trends of risky behavior can be useful in improving the work environment.

[0042] The risky behavior detection unit can automatically activate an emergency stop device upon detecting a risky behavior. The risky behavior detection unit, for example, automatically activates the emergency stop device when risky behavior is detected. For example, it immediately stops the operation of a machine. The risky behavior detection unit also uses the emergency stop device to ensure the safety of workers. For example, it activates the emergency stop device when a worker enters a dangerous location. The risky behavior detection unit also uses the emergency stop device to ensure the safety of the work environment. For example, it activates the emergency stop device when abnormal operation of a machine is detected. In this way, the safety of workers can be ensured by automatically activating the emergency stop device upon detecting risky behavior.

[0043] The risky behavior detection unit can track the location information of workers in real time and prevent them from entering dangerous areas. The risky behavior detection unit, for example, tracks the location information of workers in real time and prevents them from entering dangerous areas. For example, it acquires location information using GPS technology. The risky behavior detection unit also analyzes the location information of workers and detects entry into dangerous areas. For example, it issues an alert if a worker enters a dangerous area. The risky behavior detection unit also takes measures to prevent entry into dangerous areas based on the location information of workers. For example, it issues a warning if the worker approaches a dangerous area. In this way, the safety of workers can be ensured by tracking the location information of workers in real time and preventing them from entering dangerous areas.

[0044] The risky behavior detection unit can constantly monitor the status of the worker's safety devices and issue an alert if an abnormality is detected. The risky behavior detection unit, for example, constantly monitors the status of the worker's safety devices and issues an alert if an abnormality is detected. For example, an alert is issued if the safety device is disengaged. The risky behavior detection unit also monitors the status of the safety devices in real time and issues an alert if an abnormality is detected. For example, an alert is issued if the safety device breaks down. The risky behavior detection unit also builds a system for monitoring the status of the safety devices and issuing an alert if an abnormality is detected. This allows the status of the worker's safety devices to be constantly monitored and an alert is issued if an abnormality is detected, thereby ensuring the safety of the worker.

[0045] The risky behavior detection unit can periodically check the health status of workers and issue a warning when a health risk increases. The risky behavior detection unit, for example, periodically checks the health status of workers and issues a warning when a health risk increases. For example, the warning is issued based on regular health check data. The risky behavior detection unit also periodically checks the vital signs data of workers and issues a warning when a health risk increases. For example, the warning is issued based on heart rate or body temperature data. The risky behavior detection unit also builds a system for checking the health status of workers and issuing a warning when a health risk increases. In this way, by periodically checking the health status of workers and issuing a warning when a health risk increases, it is possible to maintain the health of workers and ensure their safety.

[0046] The evidence recording unit can identify areas for improvement in the work environment based on the detection data of dangerous behavior and work to improve the working environment. The evidence recording unit, for example, identifies areas for improvement in the work environment based on the detection data of dangerous behavior and work to improve the working environment. For example, it identifies places where dangerous behavior occurs frequently and proposes improvement measures. The evidence recording unit also analyzes the temperature, humidity, and noise level of the work environment and identifies areas for improvement. For example, it suggests installing air conditioning equipment if the temperature is too high. The evidence recording unit also analyzes the vital signs data of workers and identifies areas for improvement. For example, it recommends taking a break if the heart rate is high. In this way, it is possible to identify areas for improvement in the work environment based on the detection data of dangerous behavior and work to improve the working environment, thereby ensuring the safety and health of workers.

[0047] The evidence recording unit can utilize evidence data to assess the risk of work-related accidents and reduce insurance premiums. The evidence recording unit, for example, utilizes evidence data to assess the risk of work-related accidents and reduce insurance premiums. For example, it assesses risk based on the frequency and patterns of dangerous behavior. The evidence recording unit also builds a system to assess the risk of work-related accidents and reduce insurance premiums. For example, it sets insurance premiums based on risk assessment. The evidence recording unit also proposes discounts on insurance premiums for implementing safety measures. In this way, by utilizing evidence data to assess the risk of work-related accidents and reduce insurance premiums, it is possible to reduce costs for companies and contribute to improving the working environment.

[0048] The evidence recording unit can apply the risky behavior detection system to other industries and applications, thereby developing new markets. For example, the evidence recording unit applies the risky behavior detection system to other industries and applications, thereby developing new markets. For example, it can be expanded to other industries such as the construction industry and manufacturing industry. The evidence recording unit can also apply the risky behavior detection system to applications other than safety management. For example, it can be used for quality control and efficiency improvement. The evidence recording unit can also formulate strategies for expanding the risky behavior detection system into new markets. In this way, applying the risky behavior detection system to other industries and applications can develop new markets and contribute to the growth of the company.

[0049] The evidence recording department can utilize evidence data to promote a company's safety management system and improve the company's brand value. The evidence recording department, for example, utilizes evidence data to promote a company's safety management system and improve the company's brand value. For example, it publishes safety management results. The evidence recording department also creates materials to promote the company's safety management system. For example, it creates materials summarizing the implementation status of safety manuals and safety training. The evidence recording department also formulates strategies to improve the company's brand value. In this way, the company can increase its credibility by utilizing evidence data to promote its safety management system and improve its brand value.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The risky behavior detection unit can learn worker behavior patterns over a long period of time and build a generative AI model to detect abnormal behavior. For example, worker behavior patterns are collected over a long period of time and trained into a generative AI model. Data is collected over several months to detect behavior that differs from normal work behavior and identify abnormal behavior. The generative AI model is also used to analyze worker behavior patterns in real time and detect abnormal behavior. An alert is issued if the generative AI model detects behavior that differs from normal behavior. The generative AI model is also used to analyze worker behavior patterns and detect signs of abnormal behavior early. An alert is issued if the generative AI model detects signs of behavior that differs from normal behavior. In this way, by learning worker behavior patterns and detecting abnormal behavior, risky behavior can be detected early.

[0052] The risky behavior detection unit can monitor workers' vital data in real time and detect signs of risky behavior. For example, it can monitor a worker's heart rate and body temperature in real time, and if abnormal values ​​are detected, it can detect signs of risky behavior. If the heart rate rises sharply, it can detect stress. Also, if the body temperature rises sharply, it can detect the risk of heatstroke. It analyzes the vital data and issues an alert if an abnormal value is detected. In this way, by monitoring workers' vital data and detecting signs of risky behavior, it is possible to understand the worker's health condition and prevent accidents from occurring.

[0053] The risky behavior detection unit can monitor changes in the work environment and assess the risk of risky behavior due to environmental factors. For example, it can monitor the temperature, humidity, and noise level of the work environment in real time and assess the risk of risky behavior if abnormal values ​​are detected. It can assess the risk of heatstroke if the temperature is too high, the risk of dehydration if the humidity is too high, and the risk of hearing loss if the noise level is too high. In this way, by monitoring changes in the work environment and assessing the risk of risky behavior due to environmental factors, the safety of workers can be ensured.

[0054] The alert issuing unit can generate a customized alert message according to the individual characteristics of each worker. For example, a customized alert message is generated according to the individual characteristics of each worker (such as age, experience, and health condition). An alert including detailed instructions is issued to an inexperienced worker. An alert message is also generated according to the worker's health condition. An alert urging a worker in poor health to take a break. An alert message is also generated according to the worker's age. An alert urging caution is issued to an elderly worker. In this way, by generating an alert message customized according to the individual characteristics of each worker, more effective warnings can be issued.

[0055] The alert issuing unit can optimize the timing of issuing an alert and identify the moment when a worker can respond most effectively. For example, to optimize the timing of issuing an alert, the behavioral patterns of workers are analyzed to identify the moment when they can respond most effectively. The timing when workers are concentrating is identified. The health status of workers is also analyzed to identify the moment when they can respond most effectively. The timing when their health is good is identified. The working environment of the worker is also analyzed to identify the moment when they can respond most effectively. The timing when the working environment is quiet is identified. In this way, by optimizing the timing of issuing an alert, the moment when workers can respond most effectively can be identified and dangerous behavior can be prevented.

[0056] The alert issuing unit can utilize a wearable device such as a worker's smartwatch or smart glasses when issuing an alert. For example, the alert is issued using the worker's smartwatch or smart glasses. The alert is communicated using the vibration of the smartwatch or the display on the smartglasses. The wearable device can also be used to obtain the worker's location information and issue an alert. An alert is issued when the worker enters a dangerous area. The wearable device can also be used to monitor the worker's health condition and issue an alert when an abnormality is detected. By utilizing a wearable device when issuing an alert, warnings can be more effectively communicated to workers.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The risky behavior detection unit detects risky behavior using the worker's voice and images, such as when a worker is working without safety equipment, entering a dangerous area, or performing inappropriate actions. Step 2: The alert issuing unit issues an alert for the risky behavior detected by the risky behavior detection unit. For example, it may issue a voice alert such as "Dangerous behavior has been detected. Take safe action immediately," or it may turn on a warning lamp or vibrate. Step 3: The evidence recording unit records data on the risky behavior detected by the risky behavior detection unit, such as the date and time when the risky behavior was detected, the location, the specific details of the behavior, and audio and video data at the time of the occurrence.

[0059] (Example 2) The risky behavior detection system according to the embodiment of the present invention is a system that detects risky behavior using the voices and images of workers, issues an alert, and records evidence, thereby ensuring the safety of workers and enabling the company to fulfill its supervisory responsibilities.

[0060] A risky behavior detection system according to an embodiment includes a risky behavior detection unit, an alert issuing unit, and an evidence recording unit. The risky behavior detection unit detects risky behavior using the voice and image of a worker. For example, the risky behavior detection unit detects when a worker is working without a safety device. The risky behavior detection unit also detects when a worker is entering a dangerous location. The risky behavior detection unit also detects when a worker is performing inappropriate behavior. The alert issuing unit issues an alert in response to risky behavior detected by the risky behavior detection unit. For example, the alert issuing unit issues a voice alert such as "Risky behavior has been detected. Please take safe action immediately." The alert issuing unit also turns on a warning lamp. The alert issuing unit also issues a vibration alert. The evidence recording unit records data on risky behavior detected by the risky behavior detection unit. For example, the evidence recording unit records the date, time, and location at which the risky behavior was detected. The evidence recording unit also records specific details of the risky behavior. Furthermore, the evidence recording unit records audio data and video data when risky behavior occurs. As a result, the risky behavior detection system according to the embodiment can ensure the safety of workers and fulfill the supervisory responsibilities of the company. For example, the company can provide appropriate guidance to workers based on the evidence when risky behavior is detected. Furthermore, the company can identify areas for improvement in the work environment based on the evidence, and improve the working environment. Furthermore, the company can reduce insurance premiums based on the evidence.

[0061] The risky behavior detection unit can learn worker behavior patterns over a long period of time and construct a generative AI model for detecting abnormal behavior. The risky behavior detection unit, for example, collects worker behavior patterns over a long period of time and trains the generative AI model. For example, to detect behavior that differs from normal work behavior, data is collected over several months and abnormal behavior is identified. The risky behavior detection unit also uses the generative AI model to analyze worker behavior patterns in real time and detect abnormal behavior. For example, if the generative AI model detects behavior that differs from normal behavior, it issues an alert. The risky behavior detection unit also uses the generative AI model to analyze worker behavior patterns and detect signs of abnormal behavior early. For example, if the generative AI model detects signs of behavior that differs from normal behavior, it issues an alert. In this way, by learning worker behavior patterns and detecting abnormal behavior, it is possible to detect dangerous behavior early.

[0062] The risky behavior detection unit can analyze changes in the tone and tempo of the worker's voice to detect signs of stress or fatigue. The risky behavior detection unit, for example, analyzes the tone and tempo of the worker's voice in real time to detect signs of stress or fatigue. For example, stress is detected when the tone of the voice is higher than usual. The risky behavior detection unit also detects stress when the tempo of the voice is faster than usual. The risky behavior detection unit also detects fatigue when the tone of the voice is lower than usual. In this way, the health condition of the worker can be grasped by analyzing changes in the tone and tempo of the worker's voice to detect signs of stress or fatigue.

[0063] The risky behavior detection unit uses the emotion estimation function to estimate emotions from the worker's voice and facial expression, thereby enabling early detection of signs of risky behavior. The risky behavior detection unit, for example, analyzes the worker's voice and facial expression in real time to estimate emotions. For example, if emotions such as anger or anxiety are detected, early detection of signs of risky behavior is possible. The risky behavior detection unit also uses the emotion estimation function to analyze the tone and tempo of the worker's voice to estimate emotions. For example, anger is detected if the voice tone is high. The risky behavior detection unit also uses the emotion estimation function to analyze the worker's facial expression to estimate emotions. For example, anxiety is detected if the brow is furrowed. In this way, accidents can be prevented by estimating emotions from the worker's voice and facial expression and detecting signs of risky behavior early.

[0064] The risky behavior detection unit can monitor the worker's vital data in real time and detect signs of risky behavior. The risky behavior detection unit, for example, monitors the worker's heart rate and body temperature in real time and detects signs of risky behavior when abnormal values ​​are detected. For example, the risky behavior detection unit detects stress when the heart rate rises sharply. The risky behavior detection unit also detects the risk of heatstroke when the body temperature rises sharply. The risky behavior detection unit also analyzes the vital data and issues an alert when an abnormal value is detected. In this way, by monitoring the worker's vital data and detecting signs of risky behavior, the worker's health condition can be understood and accidents can be prevented.

[0065] The risky behavior detection unit can monitor changes in the work environment and evaluate the risk of risky behavior due to environmental factors. The risky behavior detection unit, for example, monitors the temperature, humidity, and noise level of the work environment in real time, and evaluates the risk of risky behavior when an abnormal value is detected. For example, the risk of heat stroke is evaluated when the temperature is too high. The risky behavior detection unit also evaluates the risk of dehydration when the humidity is too high. The risky behavior detection unit also evaluates the risk of hearing impairment when the noise level is too high. In this way, the safety of workers can be ensured by monitoring changes in the work environment and evaluating the risk of risky behavior due to environmental factors.

[0066] The risky behavior detection unit can use the emotion estimation function to monitor the emotional state of a worker in real time and issue a warning when emotional stress increases. The risky behavior detection unit, for example, monitors the emotional state of a worker in real time and issues a warning when emotional stress increases. For example, it issues a warning when emotions such as anger or anxiety are detected. The risky behavior detection unit also uses the emotion estimation function to analyze the tone and tempo of the worker's voice to estimate the emotion. For example, anger is detected when the voice tone is high. The risky behavior detection unit also uses the emotion estimation function to analyze the worker's facial expression to estimate the emotion. For example, anxiety is detected when the brow is furrowed. In this way, the worker's emotional state can be monitored and a warning is issued when emotional stress increases, thereby ensuring the safety of the worker.

[0067] The alert issuing unit can generate a customized alert message according to the individual characteristics of each worker. The alert issuing unit generates a customized alert message according to, for example, the individual characteristics of each worker (such as age, experience, and health condition). For example, an alert including detailed instructions is issued to an inexperienced worker. The alert issuing unit also generates an alert message according to the health condition of the worker. For example, an alert urging a worker in poor health to take a break. The alert issuing unit also generates an alert message according to the age of the worker. For example, an alert urging an elderly worker to be careful. In this way, by generating an alert message customized according to the individual characteristics of each worker, more effective warnings can be issued.

[0068] The alert issuing unit can optimize the timing of issuing an alert and identify the moment when a worker can respond most effectively. In order to optimize the timing of issuing an alert, the alert issuing unit, for example, analyzes the behavioral patterns of workers and identifies the moment when a worker can respond most effectively. For example, it identifies a time when workers are concentrating. The alert issuing unit also analyzes the health status of workers and identifies the moment when a worker can respond most effectively. For example, it identifies a time when the worker's health is good. The alert issuing unit also analyzes the work environment of the worker and identifies the moment when a worker can respond most effectively. For example, it identifies a time when the work environment is quiet. In this way, by optimizing the timing of issuing an alert, it is possible to identify the moment when a worker can respond most effectively and prevent risky behavior.

[0069] The alert issuing unit can use the emotion estimation function to adjust the tone and content of the alert according to the emotional state of the worker. The alert issuing unit, for example, analyzes the emotional state of the worker in real time and adjusts the tone and content of the alert according to the emotion. For example, if the emotion of anger is strong, the alert issuing unit issues an alert in a calm tone. The alert issuing unit also uses the emotion estimation function to analyze the tone and tempo of the worker's voice and estimate the emotion. For example, if the voice tone is high, anger is detected. The alert issuing unit also uses the emotion estimation function to analyze the worker's facial expression and estimate the emotion. For example, if the brow is furrowed, anxiety is detected. In this way, by adjusting the tone and content of the alert according to the emotional state of the worker, more effective warnings can be issued.

[0070] The alert issuing unit can utilize a wearable device such as a smartwatch or smart glasses of the worker when issuing an alert. The alert issuing unit, for example, utilizes the worker's smartwatch or smart glasses to issue an alert. For example, the alert is transmitted using the vibration of the smartwatch or the display on the smartglasses. The alert issuing unit also uses the wearable device to acquire the worker's location information and issue an alert. For example, an alert is issued when the worker enters a dangerous area. The alert issuing unit also uses the wearable device to monitor the worker's health condition and issue an alert when an abnormality is detected. In this way, by utilizing the wearable device when issuing an alert, warnings can be more effectively communicated to the worker.

[0071] The alert issuing unit can make the content of the alert multilingual so that it can be used in international work sites. The alert issuing unit, for example, makes the content of the alert multilingual so that it can be used in international work sites. For example, the alert issuing unit issues an alert in multiple languages, such as English, Spanish, and Chinese. The alert issuing unit also generates an alert message according to the worker's native language. For example, if the worker's native language is Spanish, the alert is issued in Spanish. The alert issuing unit also generates an alert message according to the worker's language setting. For example, if the worker's language setting is English, the alert is issued in English. By making the content of the alert multilingual, it can be used in international work sites, ensuring the safety of workers.

[0072] The alert issuing unit can use the emotion estimation function to adjust the frequency and intensity of alerts according to the emotional state of the worker. The alert issuing unit, for example, analyzes the emotional state of the worker in real time and adjusts the frequency and intensity of alerts according to the emotion. For example, if the worker is under high stress, the alert issuing unit reduces the frequency of alerts. The alert issuing unit also uses the emotion estimation function to analyze the tone and tempo of the worker's voice to estimate the emotion. For example, if the voice tone is high, anger is detected. The alert issuing unit also uses the emotion estimation function to analyze the worker's facial expression to estimate the emotion. For example, if the brow is furrowed, anxiety is detected. In this way, by adjusting the frequency and intensity of alerts according to the emotional state of the worker, more effective warnings can be issued.

[0073] The evidence recording unit can record related sensor data simultaneously with the detection of risky behavior. For example, when risky behavior is detected, the evidence recording unit simultaneously records sensor data such as the temperature, humidity, and noise level of the work environment. For example, it stores environmental data at the moment the risky behavior occurred. The evidence recording unit also simultaneously records the worker's vital signs data. For example, it stores data on heart rate and body temperature. The evidence recording unit also simultaneously records the worker's location information. For example, it stores data on the location where the risky behavior occurred. In this way, by recording related sensor data simultaneously with the detection of risky behavior, more detailed evidence can be provided.

[0074] The evidence recording unit can store evidence data in a tamper-proof form using blockchain technology. The evidence recording unit, for example, stores risky behavior detection data in a tamper-proof form using blockchain technology. For example, the hash value of the data is recorded in the blockchain. The evidence recording unit also stores the evidence data in a distributed ledger. For example, the data is distributed and stored across multiple nodes. The evidence recording unit also uses a digital signature to prevent tampering with the evidence data. For example, a digital signature is assigned to the data. In this way, the reliability of the data can be ensured by storing the evidence data in a tamper-proof form using blockchain technology.

[0075] The evidence recording unit can use the emotion estimation function to record the emotional state of a worker when risky behavior occurs. The evidence recording unit records the emotional state of a worker in real time when risky behavior occurs, for example. For example, when emotions such as anger or anxiety are detected, the data is saved. The evidence recording unit also uses the emotion estimation function to analyze the tone and tempo of the worker's voice to estimate the emotion. For example, anger is detected when the voice tone is high. The evidence recording unit also uses the emotion estimation function to analyze the worker's facial expression to estimate the emotion. For example, anxiety is detected when the brow is furrowed. This allows for more detailed evidence to be provided by recording the emotional state of a worker when risky behavior occurs.

[0076] The evidence recording unit can store evidence data on the cloud and make it accessible from a remote location. The evidence recording unit, for example, stores detection data of risky behavior on the cloud and makes it accessible from a remote location. For example, the evidence recording unit stores data using cloud storage. The evidence recording unit also encrypts the data stored on the cloud. For example, the data is encrypted and stored. The evidence recording unit also introduces an authentication system for accessing the data stored on the cloud. For example, two-factor authentication is used. This allows the evidence data to be stored on the cloud and accessible from a remote location, thereby improving the convenience of the data.

[0077] The evidence recording unit can automatically analyze the evidence data and generate a report of patterns and trends of risky behavior. The evidence recording unit, for example, automatically analyzes the evidence data and generates a report of patterns and trends of risky behavior. For example, it extracts patterns using data mining technology. The evidence recording unit also analyzes the frequency and time periods of occurrence of risky behavior. For example, it generates a report if risky behavior occurs frequently during a specific time period. The evidence recording unit also analyzes the location where risky behavior occurs. For example, it generates a report if risky behavior occurs frequently in a specific location. In this way, automatically analyzing the evidence data and generating a report of patterns and trends of risky behavior can be useful in improving the work environment.

[0078] The evidence recording unit can use the emotion estimation function to identify emotional stress factors of workers based on evidence data and propose improvement measures. The evidence recording unit, for example, identifies emotional stress factors of workers based on evidence data and proposes improvement measures. For example, it identifies a high-stress work environment and proposes improvement measures. The evidence recording unit also uses the emotion estimation function to analyze the tone and tempo of a worker's voice and estimate their emotion. For example, anger is detected when the voice tone is high. The evidence recording unit also uses the emotion estimation function to analyze the worker's facial expression and estimate their emotion. For example, anxiety is detected when the brow is furrowed. This makes it possible to identify emotional stress factors of workers based on evidence data and propose improvement measures, which can be useful in improving the work environment.

[0079] The risky behavior detection unit can automatically activate an emergency stop device upon detecting a risky behavior. The risky behavior detection unit, for example, automatically activates the emergency stop device when risky behavior is detected. For example, it immediately stops the operation of a machine. The risky behavior detection unit also uses the emergency stop device to ensure the safety of workers. For example, it activates the emergency stop device when a worker enters a dangerous location. The risky behavior detection unit also uses the emergency stop device to ensure the safety of the work environment. For example, it activates the emergency stop device when abnormal operation of a machine is detected. In this way, the safety of workers can be ensured by automatically activating the emergency stop device upon detecting risky behavior.

[0080] The risky behavior detection unit can track the location information of workers in real time and prevent them from entering dangerous areas. The risky behavior detection unit, for example, tracks the location information of workers in real time and prevents them from entering dangerous areas. For example, it acquires location information using GPS technology. The risky behavior detection unit also analyzes the location information of workers and detects entry into dangerous areas. For example, it issues an alert if a worker enters a dangerous area. The risky behavior detection unit also takes measures to prevent entry into dangerous areas based on the location information of workers. For example, it issues a warning if the worker approaches a dangerous area. In this way, the safety of workers can be ensured by tracking the location information of workers in real time and preventing them from entering dangerous areas.

[0081] The risky behavior detection unit can use the emotion estimation function to monitor the emotional state of a worker and encourage the worker to take a break when stress increases. The risky behavior detection unit, for example, monitors the emotional state of a worker in real time and encourages the worker to take a break when stress increases. For example, an alert encouraging the worker to take a break is issued when stress is high. The risky behavior detection unit also uses the emotion estimation function to analyze the tone and tempo of the worker's voice and estimate the worker's emotion. For example, anger is detected when the voice tone is high. The risky behavior detection unit also uses the emotion estimation function to analyze the worker's facial expression and estimate the worker's emotion. For example, anxiety is detected when the brow is furrowed. In this way, the worker's emotional state can be monitored and the worker's health can be maintained and safety can be ensured by encouraging the worker to take a break when stress increases.

[0082] The risky behavior detection unit can constantly monitor the status of the worker's safety devices and issue an alert if an abnormality is detected. The risky behavior detection unit, for example, constantly monitors the status of the worker's safety devices and issues an alert if an abnormality is detected. For example, an alert is issued if the safety device is disengaged. The risky behavior detection unit also monitors the status of the safety devices in real time and issues an alert if an abnormality is detected. For example, an alert is issued if the safety device breaks down. The risky behavior detection unit also builds a system for monitoring the status of the safety devices and issuing an alert if an abnormality is detected. This allows the status of the worker's safety devices to be constantly monitored and an alert is issued if an abnormality is detected, thereby ensuring the safety of the worker.

[0083] The risky behavior detection unit can periodically check the health status of workers and issue a warning when a health risk increases. The risky behavior detection unit, for example, periodically checks the health status of workers and issues a warning when a health risk increases. For example, the warning is issued based on regular health check data. The risky behavior detection unit also periodically checks the vital signs data of workers and issues a warning when a health risk increases. For example, the warning is issued based on heart rate or body temperature data. The risky behavior detection unit also builds a system for checking the health status of workers and issuing a warning when a health risk increases. In this way, by periodically checking the health status of workers and issuing a warning when a health risk increases, it is possible to maintain the health of workers and ensure their safety.

[0084] The risky behavior detection unit can use the emotion estimation function to provide a safety education program that corresponds to the emotional state of the worker. The risky behavior detection unit, for example, analyzes the emotional state of the worker in real time and provides a safety education program that corresponds to the emotion. For example, a program that encourages relaxation is provided to a worker who is highly stressed. The risky behavior detection unit also uses the emotion estimation function to analyze the tone and tempo of the worker's voice and estimate the emotion. For example, anger is detected when the voice tone is high. The risky behavior detection unit also uses the emotion estimation function to analyze the worker's facial expression and estimate the emotion. For example, anxiety is detected when the brow is furrowed. In this way, by providing a safety education program that corresponds to the worker's emotional state, it is possible to increase the safety awareness of workers and prevent accidents from occurring.

[0085] The evidence recording unit can identify areas for improvement in the work environment based on the detection data of dangerous behavior and work to improve the working environment. The evidence recording unit, for example, identifies areas for improvement in the work environment based on the detection data of dangerous behavior and work to improve the working environment. For example, it identifies places where dangerous behavior occurs frequently and proposes improvement measures. The evidence recording unit also analyzes the temperature, humidity, and noise level of the work environment and identifies areas for improvement. For example, it suggests installing air conditioning equipment if the temperature is too high. The evidence recording unit also analyzes the vital signs data of workers and identifies areas for improvement. For example, it recommends taking a break if the heart rate is high. In this way, it is possible to identify areas for improvement in the work environment based on the detection data of dangerous behavior and work to improve the working environment, thereby ensuring the safety and health of workers.

[0086] The evidence recording unit can utilize evidence data to assess the risk of work-related accidents and reduce insurance premiums. The evidence recording unit, for example, utilizes evidence data to assess the risk of work-related accidents and reduce insurance premiums. For example, it assesses risk based on the frequency and patterns of dangerous behavior. The evidence recording unit also builds a system to assess the risk of work-related accidents and reduce insurance premiums. For example, it sets insurance premiums based on risk assessment. The evidence recording unit also proposes discounts on insurance premiums for implementing safety measures. In this way, by utilizing evidence data to assess the risk of work-related accidents and reduce insurance premiums, it is possible to reduce costs for companies and contribute to improving the working environment.

[0087] The evidence recording unit can use the emotion estimation function to monitor the emotional state of employees and strengthen mental healthcare measures. The evidence recording unit, for example, uses the emotion estimation function to monitor the emotional state of employees in real time and strengthen mental healthcare measures. For example, it provides counseling to employees who are highly stressed. The evidence recording unit also analyzes the tone and tempo of an employee's voice to estimate their emotion. For example, a high-pitched voice can detect anger. The evidence recording unit also analyzes an employee's facial expression to estimate their emotion. For example, a furrowed brow can detect anxiety. In this way, by monitoring the emotional state of employees and strengthening mental healthcare measures, it is possible to maintain employee health and contribute to improving the working environment.

[0088] The evidence recording unit can apply the risky behavior detection system to other industries and applications, thereby developing new markets. For example, the evidence recording unit applies the risky behavior detection system to other industries and applications, thereby developing new markets. For example, it can be expanded to other industries such as the construction industry and manufacturing industry. The evidence recording unit can also apply the risky behavior detection system to applications other than safety management. For example, it can be used for quality control and efficiency improvement. The evidence recording unit can also formulate strategies for expanding the risky behavior detection system into new markets. In this way, applying the risky behavior detection system to other industries and applications can develop new markets and contribute to the growth of the company.

[0089] The evidence recording department can utilize evidence data to promote a company's safety management system and improve the company's brand value. The evidence recording department, for example, utilizes evidence data to promote a company's safety management system and improve the company's brand value. For example, it publishes safety management results. The evidence recording department also creates materials to promote the company's safety management system. For example, it creates materials summarizing the implementation status of safety manuals and safety training. The evidence recording department also formulates strategies to improve the company's brand value. In this way, the company can increase its credibility by utilizing evidence data to promote its safety management system and improve its brand value.

[0090] The evidence recording unit can use the emotion estimation function to introduce an incentive program based on the emotional state of employees, thereby improving motivation. The evidence recording unit, for example, uses the emotion estimation function to introduce an incentive program based on the emotional state of employees, thereby improving motivation. For example, rewarding employees with strong positive emotions. The evidence recording unit also analyzes the tone and tempo of an employee's voice to estimate their emotion. For example, detecting happiness when the voice tone is high. The evidence recording unit also analyzes the employee's facial expression to estimate their emotion. For example, detecting happiness when there are many smiles. In this way, by introducing an incentive program based on the emotional state of employees, employee motivation can be improved and corporate productivity can be increased.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The risky behavior detection unit can learn worker behavior patterns over a long period of time and build a generative AI model to detect abnormal behavior. For example, worker behavior patterns are collected over a long period of time and trained into a generative AI model. Data is collected over several months to detect behavior that differs from normal work behavior and identify abnormal behavior. The generative AI model is also used to analyze worker behavior patterns in real time and detect abnormal behavior. An alert is issued if the generative AI model detects behavior that differs from normal behavior. The generative AI model is also used to analyze worker behavior patterns and detect signs of abnormal behavior early. An alert is issued if the generative AI model detects signs of behavior that differs from normal behavior. In this way, by learning worker behavior patterns and detecting abnormal behavior, risky behavior can be detected early.

[0093] The risky behavior detection unit can analyze changes in the tone and tempo of a worker's voice to detect signs of stress or fatigue. For example, it can analyze the tone and tempo of a worker's voice in real time to detect signs of stress or fatigue. Stress is detected when the voice tone is higher than usual. Stress is also detected when the voice tempo is faster than usual. Fatigue is detected when the voice tone is lower than usual. In this way, by analyzing changes in the tone and tempo of a worker's voice and detecting signs of stress or fatigue, the worker's health condition can be understood.

[0094] The risky behavior detection unit can monitor workers' vital data in real time and detect signs of risky behavior. For example, it can monitor a worker's heart rate and body temperature in real time, and if abnormal values ​​are detected, it can detect signs of risky behavior. If the heart rate rises sharply, it can detect stress. Also, if the body temperature rises sharply, it can detect the risk of heatstroke. It analyzes the vital data and issues an alert if an abnormal value is detected. In this way, by monitoring workers' vital data and detecting signs of risky behavior, it is possible to understand the worker's health condition and prevent accidents from occurring.

[0095] The risky behavior detection unit can monitor changes in the work environment and assess the risk of risky behavior due to environmental factors. For example, it can monitor the temperature, humidity, and noise level of the work environment in real time and assess the risk of risky behavior if abnormal values ​​are detected. It can assess the risk of heatstroke if the temperature is too high, the risk of dehydration if the humidity is too high, and the risk of hearing loss if the noise level is too high. In this way, by monitoring changes in the work environment and assessing the risk of risky behavior due to environmental factors, the safety of workers can be ensured.

[0096] The risky behavior detection unit can use the emotion estimation function to monitor the emotional state of workers in real time and issue a warning when emotional stress increases. For example, the unit monitors the emotional state of workers in real time and issues a warning when emotional stress increases. A warning is issued when emotions such as anger or anxiety are detected. The emotion estimation function also analyzes the tone and tempo of the worker's voice to estimate their emotion. Anger is detected when the voice tone is high. The emotion estimation function also analyzes the worker's facial expression to estimate their emotion. Anxiety is detected when the brow is furrowed. In this way, the safety of workers can be ensured by monitoring the emotional state of workers and issuing a warning when emotional stress increases.

[0097] The alert issuing unit can generate a customized alert message according to the individual characteristics of each worker. For example, a customized alert message is generated according to the individual characteristics of each worker (such as age, experience, and health condition). An alert including detailed instructions is issued to an inexperienced worker. An alert message is also generated according to the worker's health condition. An alert urging a worker in poor health to take a break. An alert message is also generated according to the worker's age. An alert urging caution is issued to an elderly worker. In this way, by generating an alert message customized according to the individual characteristics of each worker, more effective warnings can be issued.

[0098] The alert issuing unit can optimize the timing of issuing an alert and identify the moment when a worker can respond most effectively. For example, to optimize the timing of issuing an alert, the behavioral patterns of workers are analyzed to identify the moment when they can respond most effectively. The timing when workers are concentrating is identified. The health status of workers is also analyzed to identify the moment when they can respond most effectively. The timing when their health is good is identified. The working environment of the worker is also analyzed to identify the moment when they can respond most effectively. The timing when the working environment is quiet is identified. In this way, by optimizing the timing of issuing an alert, the moment when workers can respond most effectively can be identified and dangerous behavior can be prevented.

[0099] The alert issuing unit can use the emotion estimation function to adjust the tone and content of the alert according to the emotional state of the worker. For example, the emotional state of the worker can be analyzed in real time, and the tone and content of the alert can be adjusted according to the emotion. If the emotion is strong, an alert can be issued in a calm tone. The emotion estimation function can also be used to analyze the tone and tempo of the worker's voice to estimate the emotion. If the voice tone is high, anger can be detected. The emotion estimation function can also be used to analyze the worker's facial expression to estimate the emotion. If the brow is furrowed, anxiety can be detected. In this way, by adjusting the tone and content of the alert according to the emotional state of the worker, more effective warnings can be issued.

[0100] The alert issuing unit can utilize a wearable device such as a worker's smartwatch or smart glasses when issuing an alert. For example, the alert is issued using the worker's smartwatch or smart glasses. The alert is communicated using the vibration of the smartwatch or the display on the smartglasses. The wearable device can also be used to obtain the worker's location information and issue an alert. An alert is issued when the worker enters a dangerous area. The wearable device can also be used to monitor the worker's health condition and issue an alert when an abnormality is detected. By utilizing a wearable device when issuing an alert, warnings can be more effectively communicated to workers.

[0101] The alert issuing unit can use the emotion estimation function to adjust the frequency and intensity of alerts according to the emotional state of the worker. For example, the emotional state of the worker can be analyzed in real time, and the frequency and intensity of alerts can be adjusted according to the emotion. If stress is high, the frequency of alerts can be reduced. The emotion estimation function can also be used to analyze the tone and tempo of the worker's voice to estimate their emotion. If the voice tone is high, anger can be detected. The emotion estimation function can also be used to analyze the worker's facial expression to estimate their emotion. If the brow is furrowed, anxiety can be detected. This allows the frequency and intensity of alerts to be adjusted according to the worker's emotional state, making it possible to issue more effective warnings.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The risky behavior detection unit detects risky behavior using the worker's voice and images, such as when a worker is working without safety equipment, entering a dangerous area, or performing inappropriate actions. Step 2: The alert issuing unit issues an alert for the risky behavior detected by the risky behavior detection unit. For example, it may issue a voice alert such as "Dangerous behavior has been detected. Take safe action immediately," or it may turn on a warning lamp or vibrate. Step 3: The evidence recording unit records data on the risky behavior detected by the risky behavior detection unit, such as the date and time when the risky behavior was detected, the location, the specific details of the behavior, and audio and video data at the time of the occurrence.

[0104] 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.

[0105] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0110] 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.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] 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.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 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.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0125] 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.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] 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.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0130] 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.

[0131] 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. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0132] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] 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.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0140] 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.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] 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.

[0144] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0145] 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.

[0146] 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.

[0147] 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. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0148] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] 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.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] 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.

[0154] FIG. 9 illustrates 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 behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0155] 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.

[0156] 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).

[0157] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] 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."

[0159] 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.

[0160] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process 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 process may be a single processor.

[0166] 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.

[0167] 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.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] 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.

[0170] 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. [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a dangerous behavior detection unit that detects dangerous behavior using the voices and images of workers; an alert issuing unit that issues an alert in response to the risky behavior detected by the risky behavior detection unit; an evidence recording unit that records data on the risky behavior detected by the risky behavior detection unit; A system characterized by:

2. The risky behavior detection unit Using an emotion estimation function, emotions of workers are estimated from their voices and facial expressions, and early signs of dangerous behavior are detected.

2. The system of claim 1.

3. The risky behavior detection unit Monitor workers' vital signs in real time to detect signs of dangerous behavior.

2. The system of claim 1.

4. The alert issuing unit Generate customized alert messages based on the individual characteristics of the worker.

2. The system of claim 1.

5. The evidence recording unit Upon detecting the risky behavior, related sensor data is recorded.

2. The system of claim 1.

6. The risky behavior detection unit Upon detecting the dangerous behavior, the emergency stop device is automatically activated.

2. The system of claim 1.

7. The evidence recording unit Based on the data detected from the risky behavior, we will identify areas for improvement in the work environment and work to improve the working environment.

2. The system of claim 1.

8. The evidence recording unit Use emotion estimation to monitor employees' emotional states and strengthen mental health care initiatives 2. The system of claim 1.

Images