System

Abstract

An object of the system according to the embodiment is to effectively detect and prevent compliance violation behavior of a worker.SOLUTION: A system includes an action detection part, a voice detection part, an image detection part, and an alert output part. The behavior detector monitors the behavior of the field operators. The voice detector monitors the worker's voice. The image detection unit monitors an image of the work site. The alert output unit outputs an alert when an action violating compliance is detected by the action detection unit, the voice detection unit, and the image 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 technologies have had the problem of making it difficult to effectively detect and prevent non-compliance behavior in the manufacturing industry.

[0005] The system according to the embodiment aims to effectively detect and prevent non-compliance behavior by workers. [Means for solving the problem]

[0006] The system according to the embodiment includes a behavior detection unit, a voice detection unit, an image detection unit, and an alert output unit. The behavior detection unit monitors the behavior of workers. The voice detection unit monitors the voices of workers. The image detection unit monitors images of the work site. The alert output unit outputs an alert when the behavior detection unit, voice detection unit, and image detection unit detect non-compliance behavior. [Effects of the Invention]

[0007] The system according to the embodiment can effectively detect and prevent non-compliance behavior by workers. [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 non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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 compliance violation behavior detection system according to an embodiment of the present invention is a system in which a generation AI simultaneously monitors the behavior, voice, and image of workers and issues an alert if compliance violation behavior is detected. As a result, the compliance violation behavior detection system prevents workers from committing fraud and allows companies to maintain compliance.

[0029] A compliance violation behavior detection system according to an embodiment includes a behavior detection unit, a voice detection unit, an image detection unit, and an alert output unit. The behavior detection unit monitors worker behavior. For example, the behavior detection unit analyzes video data and sensor data recording the worker's actions to detect cases where the worker performs work while ignoring prescribed procedures or commits fraud by repeating specific actions. The behavior detection unit also uses a generation AI to monitor the worker's actions in real time and identify abnormal behavior. For example, the generation AI detects abnormal behavior based on the type of action and the type of sensor used for detection. The voice detection unit monitors the worker's voice. For example, the voice detection unit analyzes audio data recording the worker's voice to detect cases where the worker is discussing fraud with other workers or issuing instructions that ignore prescribed procedures. The voice detection unit also uses a generation AI to analyze the worker's voice using voice recognition technology to identify abnormal statements. For example, the generation AI detects abnormal statements based on voice recognition technology. The image detection unit monitors images of the work site. For example, the image detection unit analyzes image data from a work site to detect cases where work is being performed using improper procedures or tools other than those specified. Furthermore, the image detection unit uses image analysis technology to analyze images of the work site and identify abnormal behavior. For example, the generation AI detects abnormal behavior based on image analysis technology. The alert output unit outputs an alert when a compliance violation is detected by the behavior detection unit, voice detection unit, and image detection unit. For example, the alert output unit outputs an alert message or a warning sound, and also issues an alert to the worker himself / herself. The alert output unit also notifies the administrator of the alert, allowing for a prompt response. As a result, the compliance violation behavior detection system according to the embodiment can prevent fraudulent activities by detecting compliance violation behavior from multiple angles and quickly outputting an alert.

[0030] The behavior detection unit learns worker behavior patterns over a long period of time and can detect subtle behaviors that differ from normal behavior. For example, the behavior detection unit records worker behavior patterns over a long period of time, and the generation AI learns that data. For example, it identifies abnormal behavior based on normal work procedures and actions. The behavior detection unit also analyzes long-term behavior data and detects subtle changes in behavior. For example, it detects hand movements or body postures that differ from normal behavior. The behavior detection unit also learns worker behavior patterns and builds a system that detects abnormal behavior in real time. For example, it immediately identifies behaviors that deviate from normal work procedures. In this way, by learning long-term behavior data, it can detect subtle abnormal behavior.

[0031] The behavior detection unit can 3D model the worker's movements and analyze abnormal movements in three dimensions. For example, the behavior detection unit 3D models the worker's movements, and the generation AI analyzes the data. For example, it identifies three-dimensional movements that differ from normal movements. The behavior detection unit also uses 3D modeling technology to record the worker's movements in detail and detect abnormal movements. For example, it analyzes hand movements and body postures that differ from normal movements in three dimensions. The behavior detection unit also 3D models the worker's movements and builds a system that detects abnormal movements in real time. For example, it immediately identifies movements that deviate from normal work procedures. This makes it possible to detect abnormal movements in three dimensions through 3D modeling.

[0032] The behavior detection unit can compare worker behavior data with other production lines or different factories to identify common fraudulent patterns. For example, the behavior detection unit builds a system that compares worker behavior data with other production lines or different factories to identify common fraudulent patterns. For example, it integrates and analyzes data from different work sites. The behavior detection unit also collects behavioral data from other production lines or factories, and the generation AI analyzes that data to identify common fraudulent patterns. For example, it detects when the same fraudulent behavior is occurring at multiple work sites. The behavior detection unit also compares behavioral data from different production lines or factories to develop an algorithm that identifies common fraudulent patterns. For example, it analyzes trends in fraudulent behavior at different work sites. This makes it possible to identify common fraudulent patterns by comparing data from different work sites.

[0033] The behavior detection unit not only monitors worker behavior in real time, but also analyzes past behavioral history to predict future fraudulent behavior. The behavior detection unit, for example, builds a system that monitors worker behavior in real time and analyzes past behavioral history. For example, it predicts future fraudulent behavior based on past data. The behavior detection unit also analyzes past behavioral history and develops an algorithm that predicts the possibility of future fraudulent behavior. For example, it makes predictions based on patterns of past fraudulent behavior. The behavior detection unit also combines real-time behavior monitoring with analysis of past behavioral history to build a system that predicts future fraudulent behavior. For example, it issues an alert if abnormal behavior is repeated. This makes it possible to predict future fraudulent behavior by analyzing past behavioral history.

[0034] The voice detection unit can analyze the tone and rhythm of a worker's voice to detect abnormal statements that differ from normal conversation. The voice detection unit, for example, analyzes the tone and rhythm of a worker's voice to build a system that detects abnormal statements that differ from normal conversation. For example, it identifies abnormalities based on changes in voice pitch and speed. The voice detection unit also analyzes the tone and rhythm of the voice in real time to detect abnormal statements. For example, it identifies patterns that differ from normal conversation. The voice detection unit also analyzes the worker's voice data to develop an algorithm that detects abnormal statements. For example, it identifies abnormalities based on changes in voice tone and rhythm. In this way, abnormal statements can be detected by analyzing the tone and rhythm of the voice.

[0035] The voice detection unit can use data on the voices of workers to identify patterns in which specific keywords and phrases frequently appear. For example, the voice detection unit analyzes data on the voices of workers to build a system that identifies patterns in which specific keywords and phrases frequently appear. For example, it detects words related to fraudulent activities. The voice detection unit also uses the voice data to develop an algorithm that identifies patterns in which specific keywords and phrases frequently appear. For example, it detects abnormalities when specific words are repeated. The voice detection unit also analyzes data on the voices of workers to detect patterns in which specific keywords and phrases frequently appear in real time. For example, it issues an alert when words related to fraudulent activities frequently appear. In this way, fraudulent behavior can be detected by identifying patterns in which specific keywords and phrases frequently appear.

[0036] The voice detection unit can compare the worker's voice data with other voice data to identify abnormal speech patterns. The voice detection unit, for example, builds a system that compares the worker's voice data with other voice data to identify abnormal speech patterns. For example, it detects patterns that differ from normal conversation. The voice detection unit also analyzes the worker's voice data by comparing it with other voice data to identify abnormal speech patterns. For example, it detects abnormalities when specific keywords or phrases appear frequently. The voice detection unit also compares the worker's voice data with other voice data to detect abnormal speech patterns in real time. For example, it identifies tones and rhythms that differ from normal conversation. This makes it possible to identify abnormal speech patterns by comparing it with other voice data.

[0037] The voice detection unit can analyze the voice data of workers and identify trends in fraudulent behavior across different shifts and time periods. The voice detection unit, for example, analyzes the voice data of workers and builds a system that identifies trends in fraudulent behavior across different shifts and time periods. For example, it detects when there are many abnormal utterances during a specific time period. The voice detection unit also analyzes the voice data of workers across different shifts and time periods and develops an algorithm that identifies trends in fraudulent behavior. For example, it detects abnormal utterance patterns during a specific shift. The voice detection unit also analyzes the voice data of workers and detects trends in fraudulent behavior across different shifts and time periods in real time. For example, it issues an alert when there are many abnormal utterances during a specific time period. This makes it possible to identify trends in fraudulent behavior across different shifts and time periods.

[0038] The image detection unit can analyze images of the work site at high resolution and detect subtle abnormalities. The image detection unit, for example, analyzes images of the work site at high resolution and builds a system that detects subtle abnormalities. For example, it identifies subtle changes that differ from the normal work environment. The image detection unit also analyzes high-resolution image data and detects subtle abnormalities in real time. For example, it identifies subtle movements or changes in objects that deviate from normal work procedures. The image detection unit also analyzes high-resolution images of the work site and develops an algorithm that detects subtle abnormalities. For example, it identifies subtle changes that differ from the normal work environment. This makes it possible to detect subtle abnormalities through high-resolution image analysis.

[0039] The image detection unit can continuously capture the movements of a worker and identify abnormal movement sequences. The image detection unit, for example, builds a system that continuously captures the movements of a worker and identifies abnormal movement sequences. For example, it detects patterns that differ from normal movement sequences. The image detection unit also analyzes the continuous movement captures and detects abnormal movement sequences in real time. For example, it identifies movement sequences that deviate from normal work procedures. The image detection unit also continuously captures the movements of a worker and develops an algorithm that identifies abnormal movement sequences. For example, it identifies patterns that differ from normal movement sequences. In this way, abnormal movement sequences can be identified by continuous movement capture.

[0040] The image detection unit can compare image data from a work site with other sites and identify common fraudulent patterns. For example, the image detection unit builds a system that compares image data from a work site with other sites and identifies common fraudulent patterns. For example, it integrates and analyzes data from different sites. The image detection unit also collects image data from other sites, and the generation AI analyzes that data to identify common fraudulent patterns. For example, it detects when the same fraudulent behavior is occurring at multiple sites. The image detection unit also develops an algorithm that compares image data from different sites and identifies common fraudulent patterns. For example, it analyzes trends in fraudulent behavior at different sites. This makes it possible to identify common fraudulent patterns by comparing it with image data from other sites.

[0041] The image detection unit can analyze image data from the work site and identify trends in fraudulent behavior over different time periods or shifts. The image detection unit, for example, analyzes image data from the work site and builds a system that identifies trends in fraudulent behavior over different time periods or shifts. For example, it detects when there is a lot of abnormal behavior during a specific time period. The image detection unit also analyzes image data from different time periods or shifts and develops an algorithm that identifies trends in fraudulent behavior. For example, it detects abnormal behavior patterns during a specific shift. The image detection unit also analyzes image data from the work site and detects trends in fraudulent behavior over different time periods or shifts in real time. For example, it issues an alert when there is a lot of abnormal behavior during a specific time period. This makes it possible to identify trends in fraudulent behavior over different time periods or shifts.

[0042] The alert output unit customizes the alert output based on the individual behavioral patterns of the worker, thereby more effectively preventing fraudulent behavior. The alert output unit, for example, builds a system that customizes the alert output based on the individual behavioral patterns of the worker. For example, it issues an alert when there is a deviation from a normal behavioral pattern. The alert output unit also analyzes the individual behavioral patterns of the worker and customizes the alert output. For example, it issues an alert when a specific movement or behavior is detected. The alert output unit also develops a system that outputs alerts based on individual behavioral patterns, more effectively preventing fraudulent behavior. For example, it immediately issues an alert when there is a deviation from a normal behavioral pattern. In this way, by customizing alerts based on individual behavioral patterns, fraudulent behavior can be more effectively prevented.

[0043] The alert output unit not only outputs alerts in real time, but can also issue predictive alerts based on past data. The alert output unit, for example, builds a system that not only outputs alerts in real time, but also issues predictive alerts based on past data. For example, it issues predictive alerts based on past patterns of fraudulent behavior. The alert output unit also analyzes past data and develops an algorithm that predicts the possibility of future fraudulent behavior. For example, it issues predictive alerts based on past patterns of fraudulent behavior. The alert output unit also builds a system that issues predictive alerts by combining real-time alert output with past data analysis. For example, it predicts future fraudulent behavior based on past patterns of fraudulent behavior. In this way, future fraudulent behavior can be predicted by issuing predictive alerts based on past data.

[0044] The alert output unit can link the alert output with other systems to perform comprehensive compliance management. The alert output unit, for example, links the alert output with other systems to build a system that performs comprehensive compliance management. For example, it links with an ERP system or a quality control system to issue an alert. The alert output unit also links with other systems to manage the alert output in an integrated manner. For example, it links with an ERP system or a quality control system to issue an alert. The alert output unit also develops an algorithm that links the alert output with other systems to perform comprehensive compliance management. For example, it links with an ERP system or a quality control system to issue an alert. In this way, by linking with other systems, comprehensive compliance management is possible.

[0045] The alert output unit can adapt the alert output to different devices so that workers can immediately recognize it. The alert output unit, for example, builds a system that adapts the alert output to different devices. For example, it displays the alert on a smartwatch or AR glasses. The alert output unit also outputs the alert to different devices so that workers can immediately recognize it. For example, it displays the alert on a smartwatch or AR glasses. The alert output unit also develops an algorithm that adapts the alert output to different devices so that workers can immediately recognize it. For example, it displays the alert on a smartwatch or AR glasses. In this way, by adapting to different devices, workers can immediately recognize the alert.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The behavior detection unit not only monitors the behavior of workers, but can also detect changes in the work environment. For example, the behavior detection unit can monitor changes in the temperature, humidity, and lighting of the workplace in real time to detect abnormal environmental changes. The behavior detection unit can also analyze the impact of changes in the work environment on worker behavior and identify whether abnormal behavior is due to environmental changes. Furthermore, the behavior detection unit can also build a system that provides appropriate feedback to workers in response to changes in the work environment. For example, it can respond by issuing an instruction to activate a cooling device if the temperature is too high.

[0048] The behavior detection unit not only learns the behavioral patterns of workers, but can also monitor their health. For example, the behavior detection unit monitors vital data such as a worker's heart rate, body temperature, and blood pressure in real time to detect abnormal health conditions. The behavior detection unit can also analyze the impact of changes in health conditions on a worker's behavior and identify whether abnormal behavior is due to a health condition. Furthermore, the behavior detection unit can build a system that provides appropriate feedback to workers based on their health condition. For example, if a worker's heart rate is too high, it can issue an instruction to take a break.

[0049] The behavior detection unit can not only 3D model worker movements, but also simulate them. For example, the behavior detection unit can simulate movements under different scenarios based on worker movement data and propose optimal work procedures. The behavior detection unit can also provide training programs to improve worker movements based on the simulation results. Furthermore, the behavior detection unit can provide feedback on simulation results in real time, building a system that allows workers to immediately understand areas for improvement. For example, it is possible to visually display areas for improvement in work procedures based on the simulation results.

[0050] The behavioral detection unit can compare worker behavior data not only with data from other production lines or different factories, but also with data from different lines of business and industries. For example, the behavioral detection unit can collect behavioral data from different lines of business and industries and build a system to identify common fraudulent patterns. The behavioral detection unit can also analyze data from different lines of business and industries and incorporate best practices from other industries to improve work efficiency. Furthermore, the behavioral detection unit can develop algorithms that predict signs of new fraudulent behavior based on data from different lines of business and industries. For example, it can analyze trends in fraudulent behavior across different industries and identify common patterns.

[0051] The behavior detection unit not only monitors worker behavior in real time, but can also predict worker behavior. For example, the behavior detection unit can build a system that predicts future behavior based on past behavior data. The behavior detection unit can also provide feedback to optimize worker behavior based on the predicted data. Furthermore, the behavior detection unit can build a system that provides feedback on the predicted data in real time, allowing workers to immediately understand areas for improvement. For example, it is possible to visually display areas for improvement in work procedures based on the predicted data.

[0052] The voice detection unit not only analyzes the tone and rhythm of a worker's voice, but can also learn the characteristics of the worker's voice. For example, the voice detection unit records data on the worker's voice over a long period of time and learns the characteristics of a normal voice. The voice detection unit can also build a system that identifies abnormal utterances based on the learned voice characteristics. Furthermore, the voice detection unit can analyze the characteristics of a worker's voice in real time and immediately identify abnormal utterances. For example, it can respond by issuing an alert if the voice tone or rhythm differs from the normal voice tone or rhythm.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The behavior detection unit monitors the behavior of workers. For example, the behavior detection unit analyzes video data and sensor data that record the worker's actions, and detects cases where the worker ignores prescribed procedures or commits fraud by repeating specific actions. The behavior detection unit also uses the generation AI to monitor the worker's actions in real time and identify abnormal behavior. For example, the generation AI detects abnormal behavior based on the type of action and the type of sensor used for detection. Step 2: The voice detection unit monitors the voices of workers. For example, the voice detection unit analyzes audio data that records the worker's voice and detects when the worker is discussing misconduct with other workers or when the worker is giving instructions that ignore prescribed procedures. The voice detection unit also uses the generation AI to analyze the worker's voice using voice recognition technology and identify abnormal statements. For example, the generation AI detects abnormal statements based on voice recognition technology. Step 3: The image detection unit monitors images of the work site. For example, the image detection unit analyzes image data from the work site to detect cases where work is being done using improper procedures or unspecified tools. The image detection unit also uses image analysis technology to allow the generation AI to analyze images of the work site and identify abnormal behavior. For example, the generation AI detects abnormal behavior based on image analysis technology. Step 4: The alert output unit outputs an alert when the behavior detection unit, voice detection unit, and image detection unit detect non-compliance behavior. For example, the alert output unit outputs an alert message or a warning sound, and also issues an alert to the worker himself. The alert output unit also notifies the administrator of the alert, allowing for a prompt response.

[0055] (Example 2) The compliance violation behavior detection system according to an embodiment of the present invention is a system in which a generation AI simultaneously monitors the behavior, voice, and image of workers and issues an alert if compliance violation behavior is detected. As a result, the compliance violation behavior detection system prevents workers from committing fraud and allows companies to maintain compliance.

[0056] A compliance violation behavior detection system according to an embodiment includes a behavior detection unit, a voice detection unit, an image detection unit, and an alert output unit. The behavior detection unit monitors worker behavior. For example, the behavior detection unit analyzes video data and sensor data recording the worker's actions to detect cases where the worker performs work while ignoring prescribed procedures or commits fraud by repeating specific actions. The behavior detection unit also uses a generation AI to monitor the worker's actions in real time and identify abnormal behavior. For example, the generation AI detects abnormal behavior based on the type of action and the type of sensor used for detection. The voice detection unit monitors the worker's voice. For example, the voice detection unit analyzes audio data recording the worker's voice to detect cases where the worker is discussing fraud with other workers or issuing instructions that ignore prescribed procedures. The voice detection unit also uses a generation AI to analyze the worker's voice using voice recognition technology to identify abnormal statements. For example, the generation AI detects abnormal statements based on voice recognition technology. The image detection unit monitors images of the work site. For example, the image detection unit analyzes image data from a work site to detect cases where work is being performed using improper procedures or tools other than those specified. Furthermore, the image detection unit uses image analysis technology to analyze images of the work site and identify abnormal behavior. For example, the generation AI detects abnormal behavior based on image analysis technology. The alert output unit outputs an alert when a compliance violation is detected by the behavior detection unit, voice detection unit, and image detection unit. For example, the alert output unit outputs an alert message or a warning sound, and also issues an alert to the worker himself / herself. The alert output unit also notifies the administrator of the alert, allowing for a prompt response. As a result, the compliance violation behavior detection system according to the embodiment can prevent fraudulent activities by detecting compliance violation behavior from multiple angles and quickly outputting an alert.

[0057] The behavior detection unit learns worker behavior patterns over a long period of time and can detect subtle behaviors that differ from normal behavior. For example, the behavior detection unit records worker behavior patterns over a long period of time, and the generation AI learns that data. For example, it identifies abnormal behavior based on normal work procedures and actions. The behavior detection unit also analyzes long-term behavior data and detects subtle changes in behavior. For example, it detects hand movements or body postures that differ from normal behavior. The behavior detection unit also learns worker behavior patterns and builds a system that detects abnormal behavior in real time. For example, it immediately identifies behaviors that deviate from normal work procedures. In this way, by learning long-term behavior data, it can detect subtle abnormal behavior.

[0058] The behavior detection unit can 3D model the worker's movements and analyze abnormal movements in three dimensions. For example, the behavior detection unit 3D models the worker's movements, and the generation AI analyzes the data. For example, it identifies three-dimensional movements that differ from normal movements. The behavior detection unit also uses 3D modeling technology to record the worker's movements in detail and detect abnormal movements. For example, it analyzes hand movements and body postures that differ from normal movements in three dimensions. The behavior detection unit also 3D models the worker's movements and builds a system that detects abnormal movements in real time. For example, it immediately identifies movements that deviate from normal work procedures. This makes it possible to detect abnormal movements in three dimensions through 3D modeling.

[0059] The behavior detection unit uses the emotion estimation function to detect a worker's stress or tension and predict whether this will lead to fraudulent behavior. The behavior detection unit, for example, uses the emotion estimation function to analyze a worker's stress or tension in real time. For example, it calculates an emotion score based on facial expressions and voice tone. The behavior detection unit also analyzes a worker's emotional state and builds a system that predicts the possibility of fraudulent behavior when stress or tension increases. For example, it issues an alert when the emotion score is high. The behavior detection unit also monitors a worker's stress or tension based on the emotion estimation data and detects signs of fraudulent behavior. For example, it notifies a manager when the emotion score is high. This makes it possible to detect stress or tension and predict fraudulent behavior through emotion estimation.

[0060] The behavior detection unit can compare worker behavior data with other production lines or different factories to identify common fraudulent patterns. For example, the behavior detection unit builds a system that compares worker behavior data with other production lines or different factories to identify common fraudulent patterns. For example, it integrates and analyzes data from different work sites. The behavior detection unit also collects behavioral data from other production lines or factories, and the generation AI analyzes that data to identify common fraudulent patterns. For example, it detects when the same fraudulent behavior is occurring at multiple work sites. The behavior detection unit also compares behavioral data from different production lines or factories to develop an algorithm that identifies common fraudulent patterns. For example, it analyzes trends in fraudulent behavior at different work sites. This makes it possible to identify common fraudulent patterns by comparing data from different work sites.

[0061] The behavior detection unit not only monitors worker behavior in real time, but also analyzes past behavioral history to predict future fraudulent behavior. The behavior detection unit, for example, builds a system that monitors worker behavior in real time and analyzes past behavioral history. For example, it predicts future fraudulent behavior based on past data. The behavior detection unit also analyzes past behavioral history and develops an algorithm that predicts the possibility of future fraudulent behavior. For example, it makes predictions based on patterns of past fraudulent behavior. The behavior detection unit also combines real-time behavior monitoring with analysis of past behavioral history to build a system that predicts future fraudulent behavior. For example, it issues an alert if abnormal behavior is repeated. This makes it possible to predict future fraudulent behavior by analyzing past behavioral history.

[0062] The behavior detection unit uses the emotion estimation function to provide positive feedback to workers before they engage in fraudulent behavior, thereby preventing fraud before it occurs. For example, the behavior detection unit uses the emotion estimation function to build a system that provides positive feedback to workers before they engage in fraudulent behavior. For example, an encouraging message is displayed when the emotion score is low. The behavior detection unit also analyzes the emotional state of workers in real time and provides positive feedback. For example, advice is given to relax when stress or tension increases. The behavior detection unit also develops a system that provides positive feedback to workers before they engage in fraudulent behavior based on the emotion estimation data. For example, a positive message is sent when the emotion score is low. This positive feedback can prevent fraud before it occurs.

[0063] The voice detection unit can analyze the tone and rhythm of a worker's voice to detect abnormal statements that differ from normal conversation. The voice detection unit, for example, analyzes the tone and rhythm of a worker's voice to build a system that detects abnormal statements that differ from normal conversation. For example, it identifies abnormalities based on changes in voice pitch and speed. The voice detection unit also analyzes the tone and rhythm of the voice in real time to detect abnormal statements. For example, it identifies patterns that differ from normal conversation. The voice detection unit also analyzes the worker's voice data to develop an algorithm that detects abnormal statements. For example, it identifies abnormalities based on changes in voice tone and rhythm. In this way, abnormal statements can be detected by analyzing the tone and rhythm of the voice.

[0064] The voice detection unit can use data on the voices of workers to identify patterns in which specific keywords and phrases frequently appear. For example, the voice detection unit analyzes data on the voices of workers to build a system that identifies patterns in which specific keywords and phrases frequently appear. For example, it detects words related to fraudulent activities. The voice detection unit also uses the voice data to develop an algorithm that identifies patterns in which specific keywords and phrases frequently appear. For example, it detects abnormalities when specific words are repeated. The voice detection unit also analyzes data on the voices of workers to detect patterns in which specific keywords and phrases frequently appear in real time. For example, it issues an alert when words related to fraudulent activities frequently appear. In this way, fraudulent behavior can be detected by identifying patterns in which specific keywords and phrases frequently appear.

[0065] The voice detection unit uses the emotion estimation function to estimate the emotional state from the worker's voice and predict whether tension or impatience will lead to fraudulent behavior. The voice detection unit, for example, uses the emotion estimation function to analyze the emotional state from the worker's voice in real time. For example, it calculates an emotion score based on the tone and rhythm of the voice. The voice detection unit also analyzes the worker's voice data and builds a system that predicts the possibility of fraudulent behavior when tension or impatience increases. For example, it issues an alert when the emotion score is high. The voice detection unit also estimates the emotional state from the worker's voice based on the emotion estimation data and detects signs of fraudulent behavior. For example, it notifies a manager when tension or impatience increases. In this way, emotion estimation can predict the possibility that tension or impatience will lead to fraudulent behavior.

[0066] The voice detection unit can compare the worker's voice data with other voice data to identify abnormal speech patterns. The voice detection unit, for example, builds a system that compares the worker's voice data with other voice data to identify abnormal speech patterns. For example, it detects patterns that differ from normal conversation. The voice detection unit also analyzes the worker's voice data by comparing it with other voice data to identify abnormal speech patterns. For example, it detects abnormalities when specific keywords or phrases appear frequently. The voice detection unit also compares the worker's voice data with other voice data to detect abnormal speech patterns in real time. For example, it identifies tones and rhythms that differ from normal conversation. This makes it possible to identify abnormal speech patterns by comparing it with other voice data.

[0067] The voice detection unit can analyze the voice data of workers and identify trends in fraudulent behavior across different shifts and time periods. The voice detection unit, for example, analyzes the voice data of workers and builds a system that identifies trends in fraudulent behavior across different shifts and time periods. For example, it detects when there are many abnormal utterances during a specific time period. The voice detection unit also analyzes the voice data of workers across different shifts and time periods and develops an algorithm that identifies trends in fraudulent behavior. For example, it detects abnormal utterance patterns during a specific shift. The voice detection unit also analyzes the voice data of workers and detects trends in fraudulent behavior across different shifts and time periods in real time. For example, it issues an alert when there are many abnormal utterances during a specific time period. This makes it possible to identify trends in fraudulent behavior across different shifts and time periods.

[0068] The voice detection unit can use the emotion estimation function to provide voice guidance to help workers relax before committing fraudulent behavior. The voice detection unit, for example, uses the emotion estimation function to build a system that provides voice guidance to help workers relax before committing fraudulent behavior. For example, a voice message to help workers relax is played when the emotion score is high. The voice detection unit also analyzes the emotional state of the worker in real time and provides voice guidance to help workers relax. For example, voice advice to help workers relax is given when stress or tension increases. The voice detection unit also develops a system that provides voice guidance to help workers relax before committing fraudulent behavior based on the emotion estimation data. For example, a voice message to help workers relax is sent when the emotion score is high. This makes it possible to prevent fraudulent behavior before it occurs by providing voice guidance to help workers relax.

[0069] The image detection unit can analyze images of the work site at high resolution and detect subtle abnormalities. The image detection unit, for example, analyzes images of the work site at high resolution and builds a system that detects subtle abnormalities. For example, it identifies subtle changes that differ from the normal work environment. The image detection unit also analyzes high-resolution image data and detects subtle abnormalities in real time. For example, it identifies subtle movements or changes in objects that deviate from normal work procedures. The image detection unit also analyzes high-resolution images of the work site and develops an algorithm that detects subtle abnormalities. For example, it identifies subtle changes that differ from the normal work environment. This makes it possible to detect subtle abnormalities through high-resolution image analysis.

[0070] The image detection unit can continuously capture the movements of a worker and identify abnormal movement sequences. The image detection unit, for example, builds a system that continuously captures the movements of a worker and identifies abnormal movement sequences. For example, it detects patterns that differ from normal movement sequences. The image detection unit also analyzes the continuous movement captures and detects abnormal movement sequences in real time. For example, it identifies movement sequences that deviate from normal work procedures. The image detection unit also continuously captures the movements of a worker and develops an algorithm that identifies abnormal movement sequences. For example, it identifies patterns that differ from normal movement sequences. In this way, abnormal movement sequences can be identified by continuous movement capture.

[0071] The image detection unit uses the emotion estimation function to estimate the emotional state from the facial expressions of the worker and detect signs of fraudulent behavior. The image detection unit, for example, uses the emotion estimation function to analyze the emotional state from the facial expressions of the worker in real time. For example, it calculates an emotion score based on the facial expressions. The image detection unit also analyzes the facial expression data of the worker and builds a system that estimates the emotional state. For example, it detects signs of fraudulent behavior when stress or tension increases. The image detection unit also estimates the emotional state from the facial expressions of the worker based on the emotion estimation data and detects signs of fraudulent behavior in real time. For example, it issues an alert when the emotion score is high. In this way, emotion estimation can detect signs of fraudulent behavior from facial expressions.

[0072] The image detection unit can compare image data from a work site with other sites and identify common fraudulent patterns. For example, the image detection unit builds a system that compares image data from a work site with other sites and identifies common fraudulent patterns. For example, it integrates and analyzes data from different sites. The image detection unit also collects image data from other sites, and the generation AI analyzes that data to identify common fraudulent patterns. For example, it detects when the same fraudulent behavior is occurring at multiple sites. The image detection unit also develops an algorithm that compares image data from different sites and identifies common fraudulent patterns. For example, it analyzes trends in fraudulent behavior at different sites. This makes it possible to identify common fraudulent patterns by comparing it with image data from other sites.

[0073] The image detection unit can analyze image data from the work site and identify trends in fraudulent behavior over different time periods or shifts. The image detection unit, for example, analyzes image data from the work site and builds a system that identifies trends in fraudulent behavior over different time periods or shifts. For example, it detects when there is a lot of abnormal behavior during a specific time period. The image detection unit also analyzes image data from different time periods or shifts and develops an algorithm that identifies trends in fraudulent behavior. For example, it detects abnormal behavior patterns during a specific shift. The image detection unit also analyzes image data from the work site and detects trends in fraudulent behavior over different time periods or shifts in real time. For example, it issues an alert when there is a lot of abnormal behavior during a specific time period. This makes it possible to identify trends in fraudulent behavior over different time periods or shifts.

[0074] The image detection unit can use the emotion estimation function to provide positive visual feedback to a worker before he or she engages in fraudulent behavior. For example, the image detection unit uses the emotion estimation function to build a system that provides positive visual feedback to a worker before he or she engages in fraudulent behavior. For example, an encouraging visual message is displayed when the emotion score is low. The image detection unit also analyzes the emotional state of a worker in real time and provides positive visual feedback. For example, visual advice to help the worker relax when stress or tension increases. The image detection unit also develops a system that provides positive visual feedback to a worker before he or she engages in fraudulent behavior based on the emotion estimation data. For example, a positive visual message is sent when the emotion score is low. This positive visual feedback can prevent fraudulent behavior from occurring.

[0075] The alert output unit customizes the alert output based on the individual behavioral patterns of the worker, thereby more effectively preventing fraudulent behavior. The alert output unit, for example, builds a system that customizes the alert output based on the individual behavioral patterns of the worker. For example, it issues an alert when there is a deviation from a normal behavioral pattern. The alert output unit also analyzes the individual behavioral patterns of the worker and customizes the alert output. For example, it issues an alert when a specific movement or behavior is detected. The alert output unit also develops a system that outputs alerts based on individual behavioral patterns, more effectively preventing fraudulent behavior. For example, it immediately issues an alert when there is a deviation from a normal behavioral pattern. In this way, by customizing alerts based on individual behavioral patterns, fraudulent behavior can be more effectively prevented.

[0076] The alert output unit not only outputs alerts in real time, but can also issue predictive alerts based on past data. The alert output unit, for example, builds a system that not only outputs alerts in real time, but also issues predictive alerts based on past data. For example, it issues predictive alerts based on past patterns of fraudulent behavior. The alert output unit also analyzes past data and develops an algorithm that predicts the possibility of future fraudulent behavior. For example, it issues predictive alerts based on past patterns of fraudulent behavior. The alert output unit also builds a system that issues predictive alerts by combining real-time alert output with past data analysis. For example, it predicts future fraudulent behavior based on past patterns of fraudulent behavior. In this way, future fraudulent behavior can be predicted by issuing predictive alerts based on past data.

[0077] The alert output unit uses the emotion estimation function to generate an alert message according to the emotional state of the worker, thereby reducing stress. The alert output unit, for example, uses the emotion estimation function to build a system that generates an alert message according to the emotional state of the worker. For example, an alert message encouraging relaxation is displayed when the emotion score is high. The alert output unit also analyzes the emotional state of the worker in real time and generates an alert message according to the emotional state. For example, an alert message encouraging relaxation is displayed when stress or tension increases. The alert output unit also develops a system that generates an alert message according to the emotional state of the worker based on the emotion estimation data. For example, an alert message encouraging relaxation is sent when the emotion score is high. In this way, by generating an alert message according to the emotional state, stress of the worker can be reduced.

[0078] The alert output unit can link the alert output with other systems to perform comprehensive compliance management. The alert output unit, for example, links the alert output with other systems to build a system that performs comprehensive compliance management. For example, it links with an ERP system or a quality control system to issue an alert. The alert output unit also links with other systems to manage the alert output in an integrated manner. For example, it links with an ERP system or a quality control system to issue an alert. The alert output unit also develops an algorithm that links the alert output with other systems to perform comprehensive compliance management. For example, it links with an ERP system or a quality control system to issue an alert. In this way, by linking with other systems, comprehensive compliance management is possible.

[0079] The alert output unit can adapt the alert output to different devices so that workers can immediately recognize it. The alert output unit, for example, builds a system that adapts the alert output to different devices. For example, it displays the alert on a smartwatch or AR glasses. The alert output unit also outputs the alert to different devices so that workers can immediately recognize it. For example, it displays the alert on a smartwatch or AR glasses. The alert output unit also develops an algorithm that adapts the alert output to different devices so that workers can immediately recognize it. For example, it displays the alert on a smartwatch or AR glasses. In this way, by adapting to different devices, workers can immediately recognize the alert.

[0080] The alert output unit uses the emotion estimation function to monitor the emotional reactions of workers when they receive an alert, and can continuously improve the effectiveness of the alert. The alert output unit, for example, uses the emotion estimation function to build a system that monitors the emotional reactions of workers when they receive an alert in real time. For example, the effectiveness of the alert is evaluated based on an emotion score. The alert output unit also monitors the emotional reactions of workers and continuously improves the effectiveness of the alert. For example, the alert message is adjusted if the emotion score is low. The alert output unit also monitors the emotional reactions of workers when they receive an alert based on the emotion estimation data, and develops a system that continuously improves the effectiveness of the alert. For example, the alert message is adjusted based on the emotion score. In this way, the effectiveness of the alert can be continuously improved by monitoring the emotional reactions.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The behavior detection unit not only monitors the behavior of workers, but can also detect changes in the work environment. For example, the behavior detection unit can monitor changes in the temperature, humidity, and lighting of the workplace in real time to detect abnormal environmental changes. The behavior detection unit can also analyze the impact of changes in the work environment on worker behavior and identify whether abnormal behavior is due to environmental changes. Furthermore, the behavior detection unit can also build a system that provides appropriate feedback to workers in response to changes in the work environment. For example, it can respond by issuing an instruction to activate a cooling device if the temperature is too high.

[0083] The behavior detection unit not only learns the behavioral patterns of workers, but can also monitor their health. For example, the behavior detection unit monitors vital data such as a worker's heart rate, body temperature, and blood pressure in real time to detect abnormal health conditions. The behavior detection unit can also analyze the impact of changes in health conditions on a worker's behavior and identify whether abnormal behavior is due to a health condition. Furthermore, the behavior detection unit can build a system that provides appropriate feedback to workers based on their health condition. For example, if a worker's heart rate is too high, it can issue an instruction to take a break.

[0084] The behavior detection unit can not only 3D model worker movements, but also simulate them. For example, the behavior detection unit can simulate movements under different scenarios based on worker movement data and propose optimal work procedures. The behavior detection unit can also provide training programs to improve worker movements based on the simulation results. Furthermore, the behavior detection unit can provide feedback on simulation results in real time, building a system that allows workers to immediately understand areas for improvement. For example, it is possible to visually display areas for improvement in work procedures based on the simulation results.

[0085] The behavior detection unit can use the emotion estimation function to not only detect a worker's stress or tension, but also provide feedback to improve the worker's motivation. For example, the behavior detection unit can analyze the worker's emotional state and display an encouraging message if the worker's motivation is low. The behavior detection unit can also build a system that provides incentives to improve the worker's motivation based on the emotion estimation data. For example, it can provide a reward if the emotional score is high. Furthermore, the behavior detection unit can provide a training program to improve the worker's motivation depending on the worker's emotional state. For example, it can encourage the worker to take a break to refresh themselves if the emotional score is low.

[0086] The behavioral detection unit can compare worker behavior data not only with data from other production lines or different factories, but also with data from different lines of business and industries. For example, the behavioral detection unit can collect behavioral data from different lines of business and industries and build a system to identify common fraudulent patterns. The behavioral detection unit can also analyze data from different lines of business and industries and incorporate best practices from other industries to improve work efficiency. Furthermore, the behavioral detection unit can develop algorithms that predict signs of new fraudulent behavior based on data from different lines of business and industries. For example, it can analyze trends in fraudulent behavior across different industries and identify common patterns.

[0087] The behavior detection unit not only monitors worker behavior in real time, but can also predict worker behavior. For example, the behavior detection unit can build a system that predicts future behavior based on past behavior data. The behavior detection unit can also provide feedback to optimize worker behavior based on the predicted data. Furthermore, the behavior detection unit can build a system that provides feedback on the predicted data in real time, allowing workers to immediately understand areas for improvement. For example, it is possible to visually display areas for improvement in work procedures based on the predicted data.

[0088] The behavior detection unit can use its emotion estimation function to not only provide positive feedback to workers before they engage in misconduct, but also provide training programs tailored to the worker's emotional state. For example, the behavior detection unit can analyze a worker's emotional state and provide a training program to help them relax when stress or tension increases. The behavior detection unit can also build a system that customizes training programs based on the worker's emotional state based on the emotion estimation data. For example, it can encourage workers to take a break to refresh themselves when their emotional score is low. Furthermore, the behavior detection unit can build a system that provides real-time feedback on the effectiveness of training programs based on the worker's emotional state, allowing workers to immediately identify areas for improvement. For example, it can visually display areas for improvement in work procedures based on the effectiveness of the training program.

[0089] The voice detection unit not only analyzes the tone and rhythm of a worker's voice, but can also learn the characteristics of the worker's voice. For example, the voice detection unit records data on the worker's voice over a long period of time and learns the characteristics of a normal voice. The voice detection unit can also build a system that identifies abnormal utterances based on the learned voice characteristics. Furthermore, the voice detection unit can analyze the characteristics of a worker's voice in real time and immediately identify abnormal utterances. For example, it can respond by issuing an alert if the voice tone or rhythm differs from the normal voice tone or rhythm.

[0090] The voice detection unit uses data on the worker's voice to not only identify patterns in which specific keywords and phrases frequently appear, but also analyze the emotional state of the worker's voice. For example, the voice detection unit calculates an emotional score based on the tone and rhythm of the worker's voice and determines whether abnormal utterances are due to their emotional state. The voice detection unit can also build a system that provides feedback according to the worker's emotional state based on the emotional score. Furthermore, the voice detection unit can analyze the emotional state of the worker's voice in real time and immediately determine whether abnormal utterances are due to their emotional state. For example, it is possible to take action such as issuing an alert if the emotional score is high.

[0091] The voice detection unit uses its emotion estimation function to not only estimate the emotional state from the worker's voice, but also to learn the characteristics of the worker's voice. For example, the voice detection unit records the worker's voice data over a long period of time and learns the characteristics of a normal voice. The voice detection unit can also build a system that identifies abnormal utterances based on the learned voice characteristics. Furthermore, the voice detection unit can analyze the characteristics of the worker's voice in real time and immediately identify abnormal utterances. For example, it can respond by issuing an alert if the voice tone or rhythm differs from the normal voice.

[0092] The processing flow of the second embodiment will be briefly explained below.

[0093] Step 1: The behavior detection unit monitors the behavior of workers. For example, the behavior detection unit analyzes video data and sensor data that record the worker's actions, and detects cases where the worker ignores prescribed procedures or commits fraud by repeating specific actions. The behavior detection unit also uses the generation AI to monitor the worker's actions in real time and identify abnormal behavior. For example, the generation AI detects abnormal behavior based on the type of action and the type of sensor used for detection. Step 2: The voice detection unit monitors the voices of workers. For example, the voice detection unit analyzes audio data that records the worker's voice and detects when the worker is discussing misconduct with other workers or when the worker is giving instructions that ignore prescribed procedures. The voice detection unit also uses the generation AI to analyze the worker's voice using voice recognition technology and identify abnormal statements. For example, the generation AI detects abnormal statements based on voice recognition technology. Step 3: The image detection unit monitors images of the work site. For example, the image detection unit analyzes image data from the work site to detect cases where work is being done using improper procedures or unspecified tools. The image detection unit also uses image analysis technology to allow the generation AI to analyze images of the work site and identify abnormal behavior. For example, the generation AI detects abnormal behavior based on image analysis technology. Step 4: The alert output unit outputs an alert when the behavior detection unit, voice detection unit, and image detection unit detect non-compliance behavior. For example, the alert output unit outputs an alert message or a warning sound, and also issues an alert to the worker himself. The alert output unit also notifies the administrator of the alert, allowing for a prompt response.

[0094] 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.

[0095] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> 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.

[0096] 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.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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).

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0107] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0108] 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.

[0109] 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.

[0110] 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 AI 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.

[0111] 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.

[0112] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0122] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0123] 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.

[0124] 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.

[0125] 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 AI 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.

[0126] 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.

[0127] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0128] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0138] In the robot 414, 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. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] 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.

[0140] 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.

[0141] 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 AI 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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."

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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, in order to avoid confusion and to 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.

[0160] 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]

[0161] 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 behavior detection unit that monitors the behavior of workers; a voice detection unit that monitors the voices of workers; an image detection unit that monitors images of the work site; an alert output unit that outputs an alert when a compliance violation behavior is detected by the behavior detection unit, the voice detection unit, and the image detection unit. A system characterized by:

2. The behavior detection unit It learns worker behavior patterns over a long period of time and detects subtle movements that deviate from normal behavior.

2. The system of claim 1.

3. The behavior detection unit 3D modeling of worker movements and three-dimensional analysis of abnormal movements 2. The system of claim 1.

4. The behavior detection unit Detecting stress and tension among workers and predicting whether this will lead to fraudulent behavior 2. The system of claim 1.

5. The behavior detection unit Compare worker behavior data with other production lines or different factories to identify common fraud patterns 2. The system of claim 1.

6. The behavior detection unit Not only do we monitor the actions of workers in real time, but we also analyze their past behavioral history and predict future fraudulent behavior. The system of claim 1 .

Images