system

Abstract

The system according to this embodiment aims to efficiently detect and prevent fraudulent billing in nursing care facilities and hospitals. [Solution] The system according to the embodiment comprises an acquisition unit, an analysis unit, a detection unit, and a notification unit. The acquisition unit acquires video. The analysis unit analyzes the video acquired by the acquisition unit. The detection unit detects fraud based on the results of the analysis performed by the analysis unit. The notification unit notifies the system of the fraud detected by the detection unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to efficiently detect and prevent fraudulent claims in nursing facilities and hospital facilities, and there is a risk of reducing the reliability of the long-term care insurance system.

[0005] The system according to the embodiment aims to efficiently detect and prevent fraudulent claims in nursing facilities and hospital facilities.

Means for Solving the Problems

[0006] The system according to the embodiment includes an acquisition unit, an analysis unit, a detection unit, and a notification unit. The acquisition unit acquires videos. The analysis unit analyzes the videos acquired by the acquisition unit. The detection unit detects fraud based on the results analyzed by the analysis unit. The notification unit notifies the fraud detected by the detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently detect and prevent fraudulent billing in nursing care facilities and hospitals. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The fraudulent billing prevention system according to an embodiment of the present invention is a solution using an AI agent to prevent fraudulent billing in nursing care facilities and hospitals. This fraudulent billing prevention system incorporates an AI agent into cameras in nursing care facilities and hospitals and analyzes the video in real time. This AI agent automatically detects fraudulent billing, such as specific business establishment allowances and care worker treatment improvement allowances, and immediately notifies administrators and auditing bodies. It also improves accuracy by learning patterns of fraud in conjunction with past data. For example, the fraudulent billing prevention system incorporates an AI agent into cameras in nursing care facilities and hospitals and acquires video in real time. For example, cameras are installed in various locations within the facility to monitor how care workers are performing specific tasks and the situation within the facility. Next, the fraudulent billing prevention system analyzes the video acquired by the AI ​​agent. The AI ​​agent analyzes the movements and actions in the video and detects fraudulent billing, such as specific business establishment allowances and care worker treatment improvement allowances. For example, it can detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations. Furthermore, if fraudulent activity is detected, the fraudulent billing prevention system immediately notifies administrators and auditing bodies. This enables a swift response and helps prevent fraudulent claims. For example, administrators can identify fraudulent activity and take appropriate measures. Furthermore, the fraud prevention system learns patterns of fraud by linking with past data. This improves the accuracy of the AI ​​agent, enabling more effective fraud detection. For example, it can detect similar patterns based on past fraudulent claim data. This enables the detection and prevention of fraudulent claims, improving the reliability of the long-term care insurance system. This ensures that truly necessary funds are allocated appropriately, improving the quality of care services. It also creates an environment where the elderly and their families can receive care with peace of mind, leading to the sustainable operation of the entire long-term care industry. For example, in care facilities, the AI ​​agent monitors the work of care staff and detects fraudulent claims, ensuring appropriate fund allocation. This improves the quality of care services and creates an environment where the elderly and their families can receive care with peace of mind. It also improves the reliability of the long-term care insurance system, leading to the sustainable operation of the entire long-term care industry.This means that the fraudulent billing prevention system can prevent fraudulent billing in nursing care facilities and hospitals, and improve the reliability of the long-term care insurance system.

[0029] The fraudulent billing prevention system according to this embodiment comprises an acquisition unit, an analysis unit, a detection unit, and a notification unit. The acquisition unit acquires video. The acquisition unit acquires video using, for example, cameras in nursing homes or hospitals. The acquisition unit can acquire, for example, real-time footage of care workers performing specific tasks or the situation within the facility using cameras installed in various locations within the facility. The acquisition unit can monitor the movements and actions of care workers using, for example, cameras within the facility. The acquisition unit can verify the tasks actually being performed by care workers using, for example, cameras within the facility. The analysis unit analyzes the video acquired by the acquisition unit. The analysis unit analyzes the movements and actions in the video using, for example, AI. The analysis unit can analyze the movements and actions in the video and detect fraudulent billing, such as specific business establishment allowances or care worker treatment improvement allowances. The analysis unit can analyze the movements and actions in the video and detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations. The analysis unit can, for example, analyze movements and actions in video and detect patterns of fraudulent billing. The detection unit detects fraud based on the results of the analysis by the analysis unit. The detection unit can, for example, use AI to detect fraud based on the analysis results. The detection unit can, for example, detect fraudulent billing of specific business establishment allowances and care worker treatment improvement allowances based on the analysis results. The detection unit can, for example, detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations, based on the analysis results. The detection unit can, for example, detect patterns of fraudulent billing based on the analysis results. The notification unit notifies of fraud detected by the detection unit. The notification unit notifies administrators and auditing bodies of fraud detected using AI, for example. The notification unit can, for example, immediately notify administrators and auditing bodies when fraudulent activity is detected. The notification unit can, for example, notify administrators and auditing bodies of the details of fraudulent activity. The notification unit can, for example, notify administrators and auditing bodies of the location and time of the fraudulent activity. As a result, the fraud prevention system according to this embodiment can consistently perform tasks from video acquisition and analysis to fraud detection and notification.

[0030] The acquisition unit acquires video footage. For example, it uses cameras in nursing homes and hospitals to acquire video footage. Specifically, it can use high-resolution cameras installed throughout the facility to capture real-time footage of care staff performing specific tasks and the overall situation within the facility. These cameras are equipped with wide-angle lenses and zoom capabilities, allowing them to capture detailed images over a wide area. Furthermore, infrared cameras and high-sensitivity sensors may be used to acquire clear images even at night or in low-light environments. The acquisition unit can, for example, use cameras within the facility to monitor the movements and actions of care staff. This allows for verification of the tasks actually performed by care staff and evaluation of their accuracy and efficiency. The acquired video footage is transmitted in real-time to a central database and later analyzed by the analysis unit. The acquisition unit can, for example, use cameras within the facility to verify the actual tasks performed by care staff. This allows for verification of the consistency between the tasks reported by care staff and the actual tasks performed, helping to prevent fraudulent billing. Furthermore, the acquisition unit is equipped with a storage system for saving and managing video data, enabling long-term data storage and backup. This makes it possible to analyze long-term business trends and patterns by referring to past video data.

[0031] The analysis unit analyzes the video footage acquired by the acquisition unit. For example, the analysis unit uses AI to analyze movements and actions within the video. Specifically, it utilizes image recognition algorithms based on deep learning technology to analyze the movements of people and objects within the video with high accuracy. For instance, it can analyze movements and actions within the video to determine whether a caregiver is performing a specific task, thereby detecting fraudulent claims for specific service provider allowances and caregiver treatment improvement allowances. The analysis unit can also analyze movements and actions within the video to detect cases where caregivers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations. This allows for early detection of discrepancies between caregiver work content and reported content, reducing the risk of fraudulent claims. Furthermore, the analysis unit can analyze movements and actions within the video to detect patterns of fraudulent claims. For example, if fraudulent activity frequently occurs during specific time periods or with specific staff members, the pattern can be analyzed, and preventative measures can be taken. The analysis unit can also utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, based on past fraudulent billing data, the system can predict risk fluctuations in specific regions and time periods and formulate future countermeasures. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the overall reliability and security of the system.

[0032] The detection unit detects fraud based on the results analyzed by the analysis unit. For example, the detection unit uses AI to detect fraud based on the analysis results. Specifically, it identifies specific patterns and abnormal behaviors based on data provided by the analysis unit and evaluates the possibility of fraudulent activity. For example, it can detect fraudulent claims for specific business establishment allowances and care worker treatment improvement allowances. For example, the detection unit can detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations, based on the analysis results. This allows for the early detection of discrepancies between the care worker's work content and reported content, reducing the risk of fraudulent claims. Furthermore, the detection unit can detect patterns of fraudulent claims based on the analysis results. For example, if fraudulent activity frequently occurs during specific time periods or with specific staff members, the pattern can be analyzed, and preventive measures can be taken. The detection unit can also utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, based on past fraudulent claim data, it can predict fluctuations in risk in specific regions or time periods and formulate future countermeasures. Furthermore, the detection unit can use an anomaly detection algorithm to detect unusual patterns or abnormal data, and issue warnings early. This allows the detection unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the entire system.

[0033] The notification unit notifies administrators and auditing bodies of fraud detected by the detection unit. For example, the notification unit notifies administrators and auditing bodies of fraud detected using AI. Specifically, it can immediately notify administrators and auditing bodies when fraudulent activity is detected. The notification unit can notify administrators and auditing bodies of details of the fraudulent activity, such as the location and time of the fraud, information on the employees involved, and the specific nature of the fraudulent activity. The notification unit can notify administrators and auditing bodies of the location and time of the fraudulent activity, for example. This allows administrators and auditing bodies to respond quickly and take appropriate measures. Furthermore, the notification unit can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using a combination of email, SMS, voice calls, and dedicated notification applications. This allows the notification unit to provide users with quick and reliable instructions and minimize the risk of damage. Furthermore, the notification unit can collect user feedback and continuously improve the accuracy and effectiveness of the notification content. For example, it can review and improve the notification content based on feedback from users who have received notifications. Furthermore, the notification unit can automatically and reliably transmit information using multiple notification methods in emergencies. This allows the notification unit to provide users with prompt and reliable instructions, minimizing the risk of disaster.

[0034] The analysis unit includes a learning unit that learns fraud patterns in conjunction with past data. The analysis unit can learn fraud patterns using, for example, past video data or fraud detection data. The analysis unit can detect similar patterns based on, for example, past fraudulent billing data. The analysis unit can improve detection accuracy by learning fraud patterns using, for example, past data. As a result, the accuracy of fraud detection is improved by learning from past data.

[0035] The detection unit includes a specific detection unit for detecting fraudulent claims for specific business establishment allowances. The detection unit can effectively detect fraudulent claims for specific business establishment allowances by, for example, using the specific detection unit for detecting fraudulent claims for specific business establishment allowances. The detection unit can detect patterns of fraudulent claims for specific business establishment allowances by, for example, using the specific detection unit for detecting fraudulent claims for specific business establishment allowances. The detection unit can detect details of fraudulent claims for specific business establishment allowances by, for example, using the specific detection unit for detecting fraudulent claims for specific business establishment allowances. This allows for the effective detection of fraudulent claims for specific business establishment allowances.

[0036] The detection unit includes a treatment detection unit that detects fraudulent claims for the care worker treatment improvement allowance. The detection unit can effectively detect fraudulent claims for the care worker treatment improvement allowance by, for example, using the treatment detection unit for detecting fraudulent claims for the care worker treatment improvement allowance. The detection unit can detect patterns of fraudulent claims for the care worker treatment improvement allowance by, for example, using the treatment detection unit for detecting fraudulent claims for the care worker treatment improvement allowance. The detection unit can detect details of fraudulent claims for the care worker treatment improvement allowance by, for example, using the treatment detection unit for detecting fraudulent claims for the care worker treatment improvement allowance. This makes it possible to effectively detect fraudulent claims for the care worker treatment improvement allowance.

[0037] The notification unit will immediately notify administrators and auditing bodies if fraudulent activity is detected. For example, the notification unit can immediately notify administrators and auditing bodies if fraudulent activity is detected. For example, the notification unit can notify administrators and auditing bodies within seconds if fraudulent activity is detected. For example, the notification unit can notify administrators and auditing bodies within minutes if fraudulent activity is detected. This allows for a swift response when fraudulent activity is detected.

[0038] The acquisition unit prioritizes acquiring activity in specific areas within the facility. For example, it can prioritize monitoring and acquiring video footage of areas frequently used by care staff. For example, it can prioritize monitoring and acquiring video footage of areas where important medical equipment is installed. For example, it can prioritize monitoring and acquiring video footage of areas where many elderly people gather. This allows for the efficient collection of important information by prioritizing the acquisition of activity in specific areas.

[0039] The acquisition unit filters video footage based on specific time periods or events. For example, it can prioritize acquiring video footage from nighttime hours to monitor for misconduct during those hours. It can also acquire video footage based on important events (e.g., medication distribution times) to verify that proper procedures are being followed. Furthermore, it can acquire video footage during shift changes among care staff to monitor for misconduct during these changes. By filtering video footage based on specific time periods or events, important information can be acquired efficiently.

[0040] The acquisition unit acquires optimal video footage by considering the temperature and lighting conditions within the facility. For example, if the temperature inside the facility is high, the acquisition unit can prioritize acquiring video footage from areas with air conditioning. For example, if the lighting inside the facility is dim, the acquisition unit can prioritize acquiring video footage from brightly lit areas. For example, the acquisition unit can automatically adjust the video acquisition settings according to the temperature and lighting conditions inside the facility. This improves video quality by acquiring optimal video footage according to the temperature and lighting conditions inside the facility.

[0041] The acquisition unit selects the video to acquire in conjunction with audio data from within the facility when acquiring video. For example, if an abnormal sound is detected within the facility, the acquisition unit can prioritize acquiring video from that area. For example, if a specific sound (e.g., a cry for help) is detected within the facility, the acquisition unit can prioritize acquiring video from that area. For example, the acquisition unit can automatically acquire video from the area where the abnormal sound occurred in conjunction with audio data from within the facility. This allows for the efficient acquisition of important information by selecting video in conjunction with audio data.

[0042] The analysis unit prioritizes analyzing specific movements and actions within the video during the analysis process. For example, the analysis unit can prioritize analyzing specific movements of care staff (e.g., distributing medication). For example, the analysis unit can prioritize analyzing specific actions of elderly individuals (e.g., falls). For example, the analysis unit can prioritize analyzing movements and actions in specific areas within a facility. By prioritizing the analysis of specific movements and actions, important information can be analyzed efficiently.

[0043] The analysis unit applies different analysis algorithms depending on the video resolution and frame rate during analysis. For example, the analysis unit can apply a detailed analysis algorithm to high-resolution video. For example, the analysis unit can apply a simplified analysis algorithm to low-resolution video. For example, the analysis unit can apply a motion analysis algorithm to high-frame-rate video. By applying analysis algorithms according to the video resolution and frame rate, the accuracy of the analysis is improved.

[0044] The analysis unit determines the priority of analysis based on when the video footage was acquired. For example, the analysis unit can prioritize the analysis of daytime footage to detect daytime misconduct. For example, the analysis unit can prioritize the analysis of nighttime footage to detect nighttime misconduct. For example, the analysis unit can prioritize the analysis of footage from specific events (e.g., drug distribution times). By determining the priority of analysis based on when the video footage was acquired, important information can be analyzed efficiently.

[0045] The analysis unit improves the accuracy of the analysis by referring to related video data (e.g., audio data and sensor data) during the analysis. For example, the analysis unit can combine video and audio data to prioritize the analysis of video when an abnormal sound occurs. For example, the analysis unit can combine video and sensor data to prioritize the analysis of video when an abnormal operation is detected. For example, the analysis unit can combine video and related data to provide more accurate analysis results. In this way, the accuracy of the analysis is improved by referring to related data during the analysis.

[0046] The detection unit improves detection accuracy by referring to past fraud patterns during detection. For example, the detection unit can detect similar fraudulent activities based on past fraud patterns. For example, the detection unit can optimize its detection algorithm by referring to past fraud patterns. For example, the detection unit can learn from past fraud patterns and detect new fraudulent activities. As a result, detection accuracy is improved by referring to past fraud patterns.

[0047] The detection unit prioritizes detecting fraud based on specific actions or behaviors during detection. For example, the detection unit can detect fraud based on specific actions of care staff (e.g., distributing medication). For example, the detection unit can detect fraud based on specific actions of elderly individuals (e.g., falling). For example, the detection unit can detect fraud based on actions or behaviors in specific areas within a facility. This allows for the efficient detection of significant fraudulent activities by prioritizing the detection of fraud based on specific actions or behaviors.

[0048] The detection unit detects fraud based on specific areas and time periods within the facility. For example, the detection unit can prioritize the detection of fraud in specific areas within the facility (e.g., drug storage rooms). For example, the detection unit can prioritize the detection of fraud during specific time periods (e.g., nighttime). For example, the detection unit can adjust the fraud detection criteria based on specific areas and time periods within the facility. This allows for the efficient detection of significant fraudulent activity by detecting fraud based on specific areas and time periods within the facility.

[0049] The detection unit improves detection accuracy by referring to relevant documents and databases during detection. For example, the detection unit can detect fraud by referring to relevant documents (e.g., business reports). For example, the detection unit can detect fraud by referring to databases and comparing them with past fraudulent activities. For example, the detection unit can perform more accurate fraud detection by combining relevant documents and databases. In this way, the accuracy of detection is improved by referring to relevant documents and databases.

[0050] The notification unit prioritizes notifications based on the severity of the detected misconduct. For example, if significant misconduct is detected, the notification unit can issue an immediate notification. For example, if minor misconduct is detected, the notification unit can include it in a regular report. For example, the notification unit can adjust the frequency and method of notifications according to the severity of the misconduct. This allows for a swift response to significant misconduct by prioritizing notifications based on the severity of the detected misconduct.

[0051] The notification unit provides customized notifications to specific administrators or auditing bodies. For example, the notification unit can provide administrators with notifications containing detailed reports, while it can provide auditing bodies with notifications containing concise reports. The notification unit can also customize the content of notifications according to the recipient. This allows for appropriate responses by providing customized notifications to specific administrators or auditing bodies.

[0052] The notification unit selects the notification method based on specific areas and time zones within the facility. For example, the notification unit can send notifications to specific areas within the facility (e.g., the administrator's office). It can also send notifications during specific time zones (e.g., during business hours). Furthermore, the notification unit can adjust the notification method based on specific areas and time zones within the facility. This allows for appropriate notifications by selecting the notification method based on specific areas and time zones within the facility.

[0053] The notification unit improves the accuracy of notifications by attaching relevant data and documents when sending notifications. For example, the notification unit can attach a detailed report of the misconduct when sending a notification. For example, the notification unit can attach relevant video data when sending a notification. For example, the notification unit can send more accurate notifications by attaching relevant documents and data. In this way, the accuracy of notifications is improved by attaching relevant data and documents.

[0054] The learning unit optimizes the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. For example, the learning unit can adjust the learning algorithm by referring to past learning data. For example, the learning unit can improve the accuracy of learning by utilizing past learning data. Thus, the accuracy of the learning algorithm is improved by referring to past learning data.

[0055] The learning unit weights the training data based on when the video was acquired during training. For example, the learning unit can prioritize training on daytime video data to detect daytime fraudulent activity. For example, the learning unit can prioritize training on nighttime video data to detect nighttime fraudulent activity. For example, the learning unit can prioritize training on video data of specific events (e.g., drug distribution times). By weighting the training data based on when the video was acquired, the accuracy of the training is improved.

[0056] The specific detection unit improves detection accuracy by referring to past fraud patterns when detecting fraud in specific business establishment additions. For example, the specific detection unit can detect similar fraudulent activities based on past fraud patterns. For example, the specific detection unit can optimize the detection algorithm by referring to past fraud patterns. For example, the specific detection unit can learn past fraud patterns and detect new fraudulent activities. As a result, the accuracy of detecting fraud in specific business establishment additions is improved by referring to past fraud patterns.

[0057] The specific detection unit improves the accuracy of detection when detecting fraud in specific business establishment allowances by referring to relevant documents and databases. For example, the specific detection unit can detect fraud by referring to relevant documents (e.g., business reports). For example, the specific detection unit can detect fraud by referring to databases and comparing them with past fraudulent activities. For example, the specific detection unit can perform more accurate fraud detection by combining relevant documents and databases. As a result, the accuracy of detecting fraud in specific business establishment allowances is improved by referring to relevant documents and databases.

[0058] The treatment detection unit improves the accuracy of detection when detecting fraud in the care worker treatment improvement allowance by referring to past fraud patterns. For example, the treatment detection unit can detect similar fraudulent activities based on past fraud patterns. For example, the treatment detection unit can optimize the detection algorithm by referring to past fraud patterns. For example, the treatment detection unit can learn from past fraud patterns and detect new fraudulent activities. As a result, the accuracy of detecting fraud in the care worker treatment improvement allowance is improved by referring to past fraud patterns.

[0059] The treatment detection unit improves the accuracy of detection when detecting fraudulent claims for the care worker treatment improvement allowance by referring to relevant documents and databases. For example, the treatment detection unit can detect fraud by referring to relevant documents (e.g., work reports). For example, the treatment detection unit can detect fraud by referring to databases and comparing them with past fraudulent activities. For example, the treatment detection unit can perform more accurate fraud detection by combining relevant documents and databases. As a result, the accuracy of detecting fraudulent claims for the care worker treatment improvement allowance is improved by referring to relevant documents and databases.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The acquisition unit can also acquire optimal video by considering the temperature and lighting conditions within the facility. For example, if the temperature inside the facility is high, it can prioritize acquiring video from areas with air conditioning. If the lighting inside the facility is dim, for example, the acquisition unit can prioritize acquiring video from brightly lit areas. The acquisition unit can also automatically adjust the video acquisition settings according to the temperature and lighting conditions inside the facility. This improves video quality by acquiring optimal video according to the temperature and lighting conditions inside the facility.

[0062] The detection unit can also prioritize the detection of fraud based on specific actions or behaviors. For example, it can detect fraud based on specific actions of caregivers (e.g., distributing medication). The detection unit can detect fraud based on specific actions of elderly individuals (e.g., falling). The detection unit can detect fraud based on actions or behaviors in specific areas within a facility. This allows for the efficient detection of significant fraudulent activities by prioritizing the detection of fraud based on specific actions or behaviors.

[0063] The acquisition unit can also prioritize acquiring activity in specific areas within a facility. For example, it can prioritize monitoring and acquiring video footage of areas where care staff frequently enter and exit. The acquisition unit can prioritize monitoring and acquiring video footage of areas where important medical equipment is installed. The acquisition unit can prioritize monitoring and acquiring video footage of areas where many elderly people gather. By prioritizing the acquisition of activity in specific areas, important information can be collected efficiently.

[0064] The analysis unit can apply different analysis algorithms depending on the video resolution and frame rate during analysis. For example, a detailed analysis algorithm can be applied to high-resolution video. The analysis unit can apply a simplified analysis algorithm to low-resolution video, for example. The analysis unit can apply a motion analysis algorithm to high-frame-rate video, for example. By applying the analysis algorithm according to the video resolution and frame rate, the accuracy of the analysis is improved.

[0065] The acquisition unit can also filter video footage based on specific time periods or events. For example, it can prioritize acquiring video footage from nighttime hours to monitor for misconduct during those hours. The acquisition unit can also acquire video footage based on important events (e.g., medication distribution times) to verify that operations are being carried out correctly. For example, the acquisition unit can acquire video footage during shift changes of care staff to monitor for misconduct during shift changes. This allows for the efficient acquisition of important information by filtering video footage based on specific time periods or events.

[0066] The analysis unit can also improve the accuracy of its analysis by referring to related video data (e.g., audio data and sensor data) during the analysis. For example, it can combine video and audio data for analysis and prioritize the analysis of video when an abnormal sound occurs. The analysis unit can combine video and sensor data for analysis and prioritize the analysis of video when an abnormal operation is detected. The analysis unit can combine video and related data for analysis and provide more accurate analysis results. In this way, the accuracy of the analysis is improved by referring to related data during the analysis.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The acquisition unit acquires video. The acquisition unit acquires video using, for example, cameras in nursing homes or hospitals. The acquisition unit can acquire real-time footage of care staff performing specific tasks and the overall situation within the facility using cameras installed throughout the facility. The acquisition unit can monitor the movements and actions of care staff using cameras within the facility. The acquisition unit can verify the tasks that care staff are actually performing using cameras within the facility. Step 2: The analysis unit analyzes the video acquired by the acquisition unit. The analysis unit analyzes actions and behaviors in the video, for example, using AI. The analysis unit can analyze actions and behaviors in the video and detect fraudulent claims such as specific business establishment allowances and care worker treatment improvement allowances. The analysis unit can analyze actions and behaviors in the video and detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations. The analysis unit can analyze actions and behaviors in the video and detect patterns of fraudulent claims. Step 3: The detection unit detects fraud based on the results analyzed by the analysis unit. The detection unit can, for example, use AI to detect fraud based on the analysis results. The detection unit can detect fraudulent claims for specific business establishment allowances and care worker treatment improvement allowances based on the analysis results. The detection unit can detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations, based on the analysis results. The detection unit can detect patterns of fraudulent claims based on the analysis results. Step 4: The notification unit notifies the detection unit of any fraudulent activity detected. For example, the notification unit notifies administrators or auditing bodies of fraudulent activity detected using AI. The notification unit can immediately notify administrators or auditing bodies when fraudulent activity is detected. The notification unit can notify administrators or auditing bodies of the details of the fraudulent activity. The notification unit can notify administrators or auditing bodies of the location and time the fraudulent activity occurred.

[0069] (Example of form 2) The fraudulent billing prevention system according to an embodiment of the present invention is a solution using an AI agent to prevent fraudulent billing in nursing care facilities and hospitals. This fraudulent billing prevention system incorporates an AI agent into cameras in nursing care facilities and hospitals and analyzes the video in real time. This AI agent automatically detects fraudulent billing, such as specific business establishment allowances and care worker treatment improvement allowances, and immediately notifies administrators and auditing bodies. It also improves accuracy by learning patterns of fraud in conjunction with past data. For example, the fraudulent billing prevention system incorporates an AI agent into cameras in nursing care facilities and hospitals and acquires video in real time. For example, cameras are installed in various locations within the facility to monitor how care workers are performing specific tasks and the situation within the facility. Next, the fraudulent billing prevention system analyzes the video acquired by the AI ​​agent. The AI ​​agent analyzes the movements and actions in the video and detects fraudulent billing, such as specific business establishment allowances and care worker treatment improvement allowances. For example, it can detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations. Furthermore, if fraudulent activity is detected, the fraudulent billing prevention system immediately notifies administrators and auditing bodies. This enables a swift response and helps prevent fraudulent claims. For example, administrators can identify fraudulent activity and take appropriate measures. Furthermore, the fraud prevention system learns patterns of fraud by linking with past data. This improves the accuracy of the AI ​​agent, enabling more effective fraud detection. For example, it can detect similar patterns based on past fraudulent claim data. This enables the detection and prevention of fraudulent claims, improving the reliability of the long-term care insurance system. This ensures that truly necessary funds are allocated appropriately, improving the quality of care services. It also creates an environment where the elderly and their families can receive care with peace of mind, leading to the sustainable operation of the entire long-term care industry. For example, in care facilities, the AI ​​agent monitors the work of care staff and detects fraudulent claims, ensuring appropriate fund allocation. This improves the quality of care services and creates an environment where the elderly and their families can receive care with peace of mind. It also improves the reliability of the long-term care insurance system, leading to the sustainable operation of the entire long-term care industry.This means that the fraudulent billing prevention system can prevent fraudulent billing in nursing care facilities and hospitals, and improve the reliability of the long-term care insurance system.

[0070] The fraudulent billing prevention system according to this embodiment comprises an acquisition unit, an analysis unit, a detection unit, and a notification unit. The acquisition unit acquires video. The acquisition unit acquires video using, for example, cameras in nursing homes or hospitals. The acquisition unit can acquire, for example, real-time footage of care workers performing specific tasks or the situation within the facility using cameras installed in various locations within the facility. The acquisition unit can monitor the movements and actions of care workers using, for example, cameras within the facility. The acquisition unit can verify the tasks actually being performed by care workers using, for example, cameras within the facility. The analysis unit analyzes the video acquired by the acquisition unit. The analysis unit analyzes the movements and actions in the video using, for example, AI. The analysis unit can analyze the movements and actions in the video and detect fraudulent billing, such as specific business establishment allowances or care worker treatment improvement allowances. The analysis unit can analyze the movements and actions in the video and detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations. The analysis unit can, for example, analyze movements and actions in video and detect patterns of fraudulent billing. The detection unit detects fraud based on the results of the analysis by the analysis unit. The detection unit can, for example, use AI to detect fraud based on the analysis results. The detection unit can, for example, detect fraudulent billing of specific business establishment allowances and care worker treatment improvement allowances based on the analysis results. The detection unit can, for example, detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations, based on the analysis results. The detection unit can, for example, detect patterns of fraudulent billing based on the analysis results. The notification unit notifies of fraud detected by the detection unit. The notification unit notifies administrators and auditing bodies of fraud detected using AI, for example. The notification unit can, for example, immediately notify administrators and auditing bodies when fraudulent activity is detected. The notification unit can, for example, notify administrators and auditing bodies of the details of fraudulent activity. The notification unit can, for example, notify administrators and auditing bodies of the location and time of the fraudulent activity. As a result, the fraud prevention system according to this embodiment can consistently perform tasks from video acquisition and analysis to fraud detection and notification.

[0071] The acquisition unit acquires video footage. For example, it uses cameras in nursing homes and hospitals to acquire video footage. Specifically, it can use high-resolution cameras installed throughout the facility to capture real-time footage of care staff performing specific tasks and the overall situation within the facility. These cameras are equipped with wide-angle lenses and zoom capabilities, allowing them to capture detailed images over a wide area. Furthermore, infrared cameras and high-sensitivity sensors may be used to acquire clear images even at night or in low-light environments. The acquisition unit can, for example, use cameras within the facility to monitor the movements and actions of care staff. This allows for verification of the tasks actually performed by care staff and evaluation of their accuracy and efficiency. The acquired video footage is transmitted in real-time to a central database and later analyzed by the analysis unit. The acquisition unit can, for example, use cameras within the facility to verify the actual tasks performed by care staff. This allows for verification of the consistency between the tasks reported by care staff and the actual tasks performed, helping to prevent fraudulent billing. Furthermore, the acquisition unit is equipped with a storage system for saving and managing video data, enabling long-term data storage and backup. This makes it possible to analyze long-term business trends and patterns by referring to past video data.

[0072] The analysis unit analyzes the video footage acquired by the acquisition unit. For example, the analysis unit uses AI to analyze movements and actions within the video. Specifically, it utilizes image recognition algorithms based on deep learning technology to analyze the movements of people and objects within the video with high accuracy. For instance, it can analyze movements and actions within the video to determine whether a caregiver is performing a specific task, thereby detecting fraudulent claims for specific service provider allowances and caregiver treatment improvement allowances. The analysis unit can also analyze movements and actions within the video to detect cases where caregivers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations. This allows for early detection of discrepancies between caregiver work content and reported content, reducing the risk of fraudulent claims. Furthermore, the analysis unit can analyze movements and actions within the video to detect patterns of fraudulent claims. For example, if fraudulent activity frequently occurs during specific time periods or with specific staff members, the pattern can be analyzed, and preventative measures can be taken. The analysis unit can also utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, based on past fraudulent billing data, the system can predict risk fluctuations in specific regions and time periods and formulate future countermeasures. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the overall reliability and security of the system.

[0073] The detection unit detects fraud based on the results analyzed by the analysis unit. For example, the detection unit uses AI to detect fraud based on the analysis results. Specifically, it identifies specific patterns and abnormal behaviors based on data provided by the analysis unit and evaluates the possibility of fraudulent activity. For example, it can detect fraudulent claims for specific business establishment allowances and care worker treatment improvement allowances. For example, the detection unit can detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations, based on the analysis results. This allows for the early detection of discrepancies between the care worker's work content and reported content, reducing the risk of fraudulent claims. Furthermore, the detection unit can detect patterns of fraudulent claims based on the analysis results. For example, if fraudulent activity frequently occurs during specific time periods or with specific staff members, the pattern can be analyzed, and preventive measures can be taken. The detection unit can also utilize historical data and statistical information to conduct long-term risk assessments and trend analyses. For example, based on past fraudulent claim data, it can predict fluctuations in risk in specific regions or time periods and formulate future countermeasures. Furthermore, the detection unit can use an anomaly detection algorithm to detect unusual patterns or abnormal data, and issue warnings early. This allows the detection unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the entire system.

[0074] The notification unit notifies administrators and auditing bodies of fraud detected by the detection unit. For example, the notification unit notifies administrators and auditing bodies of fraud detected using AI. Specifically, it can immediately notify administrators and auditing bodies when fraudulent activity is detected. The notification unit can notify administrators and auditing bodies of details of the fraudulent activity, such as the location and time of the fraud, information on the employees involved, and the specific nature of the fraudulent activity. The notification unit can notify administrators and auditing bodies of the location and time of the fraudulent activity, for example. This allows administrators and auditing bodies to respond quickly and take appropriate measures. Furthermore, the notification unit can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using a combination of email, SMS, voice calls, and dedicated notification applications. This allows the notification unit to provide users with quick and reliable instructions and minimize the risk of damage. Furthermore, the notification unit can collect user feedback and continuously improve the accuracy and effectiveness of the notification content. For example, it can review and improve the notification content based on feedback from users who have received notifications. Furthermore, the notification unit can automatically and reliably transmit information using multiple notification methods in emergencies. This allows the notification unit to provide users with prompt and reliable instructions, minimizing the risk of disaster.

[0075] The analysis unit includes a learning unit that learns fraud patterns in conjunction with past data. The analysis unit can learn fraud patterns using, for example, past video data or fraud detection data. The analysis unit can detect similar patterns based on, for example, past fraudulent billing data. The analysis unit can improve detection accuracy by learning fraud patterns using, for example, past data. As a result, the accuracy of fraud detection is improved by learning from past data.

[0076] The detection unit includes a specific detection unit for detecting fraudulent claims for specific business establishment allowances. The detection unit can effectively detect fraudulent claims for specific business establishment allowances by, for example, using the specific detection unit for detecting fraudulent claims for specific business establishment allowances. The detection unit can detect patterns of fraudulent claims for specific business establishment allowances by, for example, using the specific detection unit for detecting fraudulent claims for specific business establishment allowances. The detection unit can detect details of fraudulent claims for specific business establishment allowances by, for example, using the specific detection unit for detecting fraudulent claims for specific business establishment allowances. This allows for the effective detection of fraudulent claims for specific business establishment allowances.

[0077] The detection unit includes a treatment detection unit that detects fraudulent claims for the care worker treatment improvement allowance. The detection unit can effectively detect fraudulent claims for the care worker treatment improvement allowance by, for example, using the treatment detection unit for detecting fraudulent claims for the care worker treatment improvement allowance. The detection unit can detect patterns of fraudulent claims for the care worker treatment improvement allowance by, for example, using the treatment detection unit for detecting fraudulent claims for the care worker treatment improvement allowance. The detection unit can detect details of fraudulent claims for the care worker treatment improvement allowance by, for example, using the treatment detection unit for detecting fraudulent claims for the care worker treatment improvement allowance. This makes it possible to effectively detect fraudulent claims for the care worker treatment improvement allowance.

[0078] The notification unit will immediately notify administrators and auditing bodies if fraudulent activity is detected. For example, the notification unit can immediately notify administrators and auditing bodies if fraudulent activity is detected. For example, the notification unit can notify administrators and auditing bodies within seconds if fraudulent activity is detected. For example, the notification unit can notify administrators and auditing bodies within minutes if fraudulent activity is detected. This allows for a swift response when fraudulent activity is detected.

[0079] The acquisition unit estimates the user's emotions and adjusts the timing of video acquisition based on the estimated emotions. For example, if the user is stressed, the acquisition unit can reduce the frequency of video acquisition and capture only important moments. For example, if the user is relaxed, the acquisition unit can increase the frequency of video acquisition and record in detail. For example, if the user is in a hurry, the acquisition unit can adjust to acquire important information in a short amount of time. In this way, more appropriate video can be acquired by adjusting the timing of video acquisition according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0080] The acquisition unit prioritizes acquiring activity in specific areas within the facility. For example, it can prioritize monitoring and acquiring video footage of areas frequently used by care staff. For example, it can prioritize monitoring and acquiring video footage of areas where important medical equipment is installed. For example, it can prioritize monitoring and acquiring video footage of areas where many elderly people gather. This allows for the efficient collection of important information by prioritizing the acquisition of activity in specific areas.

[0081] The acquisition unit filters video footage based on specific time periods or events. For example, it can prioritize acquiring video footage from nighttime hours to monitor for misconduct during those hours. It can also acquire video footage based on important events (e.g., medication distribution times) to verify that proper procedures are being followed. Furthermore, it can acquire video footage during shift changes among care staff to monitor for misconduct during these changes. By filtering video footage based on specific time periods or events, important information can be acquired efficiently.

[0082] The acquisition unit estimates the user's emotions and determines the priority of the video to acquire based on the estimated user emotions. For example, if the user is feeling anxious, the acquisition unit can prioritize acquiring video of areas important to provide a sense of security. For example, if the user is relaxed, the acquisition unit can acquire wide-angle video for overall monitoring. For example, if the user is in a hurry, the acquisition unit can prioritize acquiring video of specific areas to obtain important information in a short amount of time. In this way, important information can be efficiently acquired by determining the priority of video according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The acquisition unit acquires optimal video footage by considering the temperature and lighting conditions within the facility. For example, if the temperature inside the facility is high, the acquisition unit can prioritize acquiring video footage from areas with air conditioning. For example, if the lighting inside the facility is dim, the acquisition unit can prioritize acquiring video footage from brightly lit areas. For example, the acquisition unit can automatically adjust the video acquisition settings according to the temperature and lighting conditions inside the facility. This improves video quality by acquiring optimal video footage according to the temperature and lighting conditions inside the facility.

[0084] The acquisition unit selects the video to acquire in conjunction with audio data from within the facility when acquiring video. For example, if an abnormal sound is detected within the facility, the acquisition unit can prioritize acquiring video from that area. For example, if a specific sound (e.g., a cry for help) is detected within the facility, the acquisition unit can prioritize acquiring video from that area. For example, the acquisition unit can automatically acquire video from the area where the abnormal sound occurred in conjunction with audio data from within the facility. This allows for the efficient acquisition of important information by selecting video in conjunction with audio data.

[0085] The analysis unit estimates the user's emotions and adjusts the presentation of the analysis based on the estimated emotions. For example, if the user is tense, the analysis unit can provide simple and easy-to-understand analysis results. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. For example, if the user is in a hurry, the analysis unit can provide concise analysis results. By adjusting the presentation of the analysis according to the user's emotions, the analysis results become easier to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The analysis unit prioritizes analyzing specific movements and actions within the video during the analysis process. For example, the analysis unit can prioritize analyzing specific movements of care staff (e.g., distributing medication). For example, the analysis unit can prioritize analyzing specific actions of elderly individuals (e.g., falls). For example, the analysis unit can prioritize analyzing movements and actions in specific areas within a facility. By prioritizing the analysis of specific movements and actions, important information can be analyzed efficiently.

[0087] The analysis unit applies different analysis algorithms depending on the video resolution and frame rate during analysis. For example, the analysis unit can apply a detailed analysis algorithm to high-resolution video. For example, the analysis unit can apply a simplified analysis algorithm to low-resolution video. For example, the analysis unit can apply a motion analysis algorithm to high-frame-rate video. By applying analysis algorithms according to the video resolution and frame rate, the accuracy of the analysis is improved.

[0088] The analysis unit estimates the user's emotions and adjusts the level of detail of the analysis based on the estimated emotions. For example, if the user is tense, the analysis unit can provide simple and easy-to-understand analysis results. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. For example, if the user is in a hurry, the analysis unit can provide concise analysis results. By adjusting the level of detail of the analysis according to the user's emotions, the analysis results become easier to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The analysis unit determines the priority of analysis based on when the video footage was acquired. For example, the analysis unit can prioritize the analysis of daytime footage to detect daytime misconduct. For example, the analysis unit can prioritize the analysis of nighttime footage to detect nighttime misconduct. For example, the analysis unit can prioritize the analysis of footage from specific events (e.g., drug distribution times). By determining the priority of analysis based on when the video footage was acquired, important information can be analyzed efficiently.

[0090] The analysis unit improves the accuracy of the analysis by referring to related video data (e.g., audio data and sensor data) during the analysis. For example, the analysis unit can combine video and audio data to prioritize the analysis of video when an abnormal sound occurs. For example, the analysis unit can combine video and sensor data to prioritize the analysis of video when an abnormal operation is detected. For example, the analysis unit can combine video and related data to provide more accurate analysis results. In this way, the accuracy of the analysis is improved by referring to related data during the analysis.

[0091] The detection unit estimates the user's emotions and adjusts the fraud detection criteria based on the estimated emotions. For example, if the user is tense, the detection unit can apply strict detection criteria. For example, if the user is relaxed, the detection unit can apply flexible detection criteria. For example, if the user is in a hurry, the detection unit can apply criteria for rapid fraud detection. This allows for more appropriate fraud detection by adjusting the fraud detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The detection unit improves detection accuracy by referring to past fraud patterns during detection. For example, the detection unit can detect similar fraudulent activities based on past fraud patterns. For example, the detection unit can optimize its detection algorithm by referring to past fraud patterns. For example, the detection unit can learn from past fraud patterns and detect new fraudulent activities. As a result, detection accuracy is improved by referring to past fraud patterns.

[0093] The detection unit prioritizes detecting fraud based on specific actions or behaviors during detection. For example, the detection unit can detect fraud based on specific actions of care staff (e.g., distributing medication). For example, the detection unit can detect fraud based on specific actions of elderly individuals (e.g., falling). For example, the detection unit can detect fraud based on actions or behaviors in specific areas within a facility. This allows for the efficient detection of significant fraudulent activities by prioritizing the detection of fraud based on specific actions or behaviors.

[0094] The detection unit estimates the user's emotions and adjusts the display method of the detection results based on the estimated emotions. For example, if the user is tense, the detection unit can provide a simple and highly visible display method. For example, if the user is relaxed, the detection unit can provide a display method that includes detailed information. For example, if the user is in a hurry, the detection unit can provide a display method that gets straight to the point. By adjusting the display method of the detection results according to the user's emotions, the understanding of the detection results becomes easier. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The detection unit detects fraud based on specific areas and time periods within the facility. For example, the detection unit can prioritize the detection of fraud in specific areas within the facility (e.g., drug storage rooms). For example, the detection unit can prioritize the detection of fraud during specific time periods (e.g., nighttime). For example, the detection unit can adjust the fraud detection criteria based on specific areas and time periods within the facility. This allows for the efficient detection of significant fraudulent activity by detecting fraud based on specific areas and time periods within the facility.

[0096] The detection unit improves detection accuracy by referring to relevant documents and databases during detection. For example, the detection unit can detect fraud by referring to relevant documents (e.g., business reports). For example, the detection unit can detect fraud by referring to databases and comparing them with past fraudulent activities. For example, the detection unit can perform more accurate fraud detection by combining relevant documents and databases. In this way, the accuracy of detection is improved by referring to relevant documents and databases.

[0097] The notification unit estimates the user's emotions and adjusts the notification method based on the estimated emotions. For example, if the user is tense, the notification unit can deliver a notification in a calm tone. If the user is relaxed, the notification unit can deliver a notification in a cheerful tone. If the user is in a hurry, the notification unit can deliver a quick and concise notification. By adjusting the notification method according to the user's emotions, the effectiveness of notifications is improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The notification unit prioritizes notifications based on the severity of the detected misconduct. For example, if significant misconduct is detected, the notification unit can issue an immediate notification. For example, if minor misconduct is detected, the notification unit can include it in a regular report. For example, the notification unit can adjust the frequency and method of notifications according to the severity of the misconduct. This allows for a swift response to significant misconduct by prioritizing notifications based on the severity of the detected misconduct.

[0099] The notification unit provides customized notifications to specific administrators or auditing bodies. For example, the notification unit can provide administrators with notifications containing detailed reports, while it can provide auditing bodies with notifications containing concise reports. The notification unit can also customize the content of notifications according to the recipient. This allows for appropriate responses by providing customized notifications to specific administrators or auditing bodies.

[0100] The notification unit estimates the user's emotions and adjusts the content of the notification based on the estimated emotions. For example, if the user is nervous, the notification unit can send a concise and reassuring notification. If the user is relaxed, the notification unit can send a notification containing detailed information. If the user is in a hurry, the notification unit can send a notification that gets straight to the point. By adjusting the content of the notification according to the user's emotions, the effectiveness of the notification is improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The notification unit selects the notification method based on specific areas and time zones within the facility. For example, the notification unit can send notifications to specific areas within the facility (e.g., the administrator's office). It can also send notifications during specific time zones (e.g., during business hours). Furthermore, the notification unit can adjust the notification method based on specific areas and time zones within the facility. This allows for appropriate notifications by selecting the notification method based on specific areas and time zones within the facility.

[0102] The notification unit improves the accuracy of notifications by attaching relevant data and documents when sending notifications. For example, the notification unit can attach a detailed report of the misconduct when sending a notification. For example, the notification unit can attach relevant video data when sending a notification. For example, the notification unit can send more accurate notifications by attaching relevant documents and data. In this way, the accuracy of notifications is improved by attaching relevant data and documents.

[0103] The learning unit estimates the user's emotions and selects training data based on the estimated emotions. For example, if the user is nervous, the learning unit can prioritize learning important data. For example, if the user is relaxed, the learning unit can learn a wide range of data. For example, if the user is in a hurry, the learning unit can select data that can be learned quickly. This improves the effectiveness of learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The learning unit optimizes the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. For example, the learning unit can adjust the learning algorithm by referring to past learning data. For example, the learning unit can improve the accuracy of learning by utilizing past learning data. Thus, the accuracy of the learning algorithm is improved by referring to past learning data.

[0105] The learning unit estimates the user's emotions and adjusts the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency and learn only important data. For example, if the user is relaxed, the learning unit can increase the learning frequency and learn a wide range of data. For example, if the user is in a hurry, the learning unit can adjust the learning frequency to allow for rapid learning. This improves the effectiveness of learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0106] The learning unit weights the training data based on when the video was acquired during training. For example, the learning unit can prioritize training on daytime video data to detect daytime fraudulent activity. For example, the learning unit can prioritize training on nighttime video data to detect nighttime fraudulent activity. For example, the learning unit can prioritize training on video data of specific events (e.g., drug distribution times). By weighting the training data based on when the video was acquired, the accuracy of the training is improved.

[0107] The specific detection unit estimates the user's emotions and adjusts the fraud detection criteria for specific business establishment additions based on the estimated user emotions. For example, if the user is tense, the specific detection unit can apply strict detection criteria. For example, if the user is relaxed, the specific detection unit can apply flexible detection criteria. For example, if the user is in a hurry, the specific detection unit can apply criteria for rapid fraud detection. This allows for more appropriate fraud detection by adjusting the fraud detection criteria for specific business establishment additions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The specific detection unit improves detection accuracy by referring to past fraud patterns when detecting fraud in specific business establishment additions. For example, the specific detection unit can detect similar fraudulent activities based on past fraud patterns. For example, the specific detection unit can optimize the detection algorithm by referring to past fraud patterns. For example, the specific detection unit can learn past fraud patterns and detect new fraudulent activities. As a result, the accuracy of detecting fraud in specific business establishment additions is improved by referring to past fraud patterns.

[0109] The specific detection unit estimates the user's emotions and adjusts the display method of the fraud detection results for specific business establishment additions based on the estimated user emotions. For example, if the user is tense, the specific detection unit can provide a simple and highly visible display method. For example, if the user is relaxed, the specific detection unit can provide a display method that includes detailed information. For example, if the user is in a hurry, the specific detection unit can provide a display method that gets straight to the point. By adjusting the display method of the fraud detection results for specific business establishment additions according to the user's emotions, the detection results become easier to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The specific detection unit improves the accuracy of detection when detecting fraud in specific business establishment allowances by referring to relevant documents and databases. For example, the specific detection unit can detect fraud by referring to relevant documents (e.g., business reports). For example, the specific detection unit can detect fraud by referring to databases and comparing them with past fraudulent activities. For example, the specific detection unit can perform more accurate fraud detection by combining relevant documents and databases. As a result, the accuracy of detecting fraud in specific business establishment allowances is improved by referring to relevant documents and databases.

[0111] The treatment detection unit estimates the user's emotions and adjusts the fraud detection criteria for the care worker treatment improvement allowance based on the estimated user emotions. For example, if the user is tense, the treatment detection unit can apply strict detection criteria. For example, if the user is relaxed, the treatment detection unit can apply flexible detection criteria. For example, if the user is in a hurry, the treatment detection unit can apply criteria for rapid fraud detection. This allows for more appropriate fraud detection by adjusting the fraud detection criteria for the care worker treatment improvement allowance according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0112] The treatment detection unit improves the accuracy of detection when detecting fraud in the care worker treatment improvement allowance by referring to past fraud patterns. For example, the treatment detection unit can detect similar fraudulent activities based on past fraud patterns. For example, the treatment detection unit can optimize the detection algorithm by referring to past fraud patterns. For example, the treatment detection unit can learn from past fraud patterns and detect new fraudulent activities. As a result, the accuracy of detecting fraud in the care worker treatment improvement allowance is improved by referring to past fraud patterns.

[0113] The treatment detection unit estimates the user's emotions and adjusts the display method of the fraud detection results for the care worker treatment improvement allowance based on the estimated user emotions. For example, if the user is tense, the treatment detection unit can provide a simple and highly visible display method. For example, if the user is relaxed, the treatment detection unit can provide a display method that includes detailed information. For example, if the user is in a hurry, the treatment detection unit can provide a display method that gets straight to the point. By adjusting the display method of the fraud detection results for the care worker treatment improvement allowance according to the user's emotions, the detection results become easier to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] The treatment detection unit improves the accuracy of detection when detecting fraudulent claims for the care worker treatment improvement allowance by referring to relevant documents and databases. For example, the treatment detection unit can detect fraud by referring to relevant documents (e.g., work reports). For example, the treatment detection unit can detect fraud by referring to databases and comparing them with past fraudulent activities. For example, the treatment detection unit can perform more accurate fraud detection by combining relevant documents and databases. As a result, the accuracy of detecting fraudulent claims for the care worker treatment improvement allowance is improved by referring to relevant documents and databases.

[0115] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0116] The acquisition unit can also acquire optimal video by considering the temperature and lighting conditions within the facility. For example, if the temperature inside the facility is high, it can prioritize acquiring video from areas with air conditioning. If the lighting inside the facility is dim, for example, the acquisition unit can prioritize acquiring video from brightly lit areas. The acquisition unit can also automatically adjust the video acquisition settings according to the temperature and lighting conditions inside the facility. This improves video quality by acquiring optimal video according to the temperature and lighting conditions inside the facility.

[0117] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is nervous, it can provide a simple and easy-to-understand analysis result. If the user is relaxed, for example, the analysis unit can provide a detailed analysis result. If the user is in a hurry, for example, the analysis unit can provide a concise analysis result. By adjusting the presentation of the analysis according to the user's emotions, the analysis results become easier to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0118] The detection unit can also prioritize the detection of fraud based on specific actions or behaviors. For example, it can detect fraud based on specific actions of caregivers (e.g., distributing medication). The detection unit can detect fraud based on specific actions of elderly individuals (e.g., falling). The detection unit can detect fraud based on actions or behaviors in specific areas within a facility. This allows for the efficient detection of significant fraudulent activities by prioritizing the detection of fraud based on specific actions or behaviors.

[0119] The notification unit can also estimate the user's emotions and adjust the notification method based on the estimated emotions. For example, if the user is tense, the notification can be delivered in a calm tone. If the user is relaxed, the notification can be delivered in a cheerful tone. If the user is in a hurry, the notification can be delivered quickly and concisely. This improves the effectiveness of notifications by adjusting the notification method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0120] The acquisition unit can also prioritize acquiring activity in specific areas within a facility. For example, it can prioritize monitoring and acquiring video footage of areas where care staff frequently enter and exit. The acquisition unit can prioritize monitoring and acquiring video footage of areas where important medical equipment is installed. The acquisition unit can prioritize monitoring and acquiring video footage of areas where many elderly people gather. By prioritizing the acquisition of activity in specific areas, important information can be collected efficiently.

[0121] The analysis unit can apply different analysis algorithms depending on the video resolution and frame rate during analysis. For example, a detailed analysis algorithm can be applied to high-resolution video. The analysis unit can apply a simplified analysis algorithm to low-resolution video, for example. The analysis unit can apply a motion analysis algorithm to high-frame-rate video, for example. By applying the analysis algorithm according to the video resolution and frame rate, the accuracy of the analysis is improved.

[0122] The detection unit can also estimate the user's emotions and adjust the fraud detection criteria based on the estimated emotions. For example, if the user is stressed, strict detection criteria can be applied. If the user is relaxed, for example, the detection unit can apply flexible detection criteria. If the user is in a hurry, for example, the detection unit can apply criteria for rapid fraud detection. This allows for more appropriate fraud detection by adjusting the fraud detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0123] The acquisition unit can also filter video footage based on specific time periods or events. For example, it can prioritize acquiring video footage from nighttime hours to monitor for misconduct during those hours. The acquisition unit can also acquire video footage based on important events (e.g., medication distribution times) to verify that operations are being carried out correctly. For example, the acquisition unit can acquire video footage during shift changes of care staff to monitor for misconduct during shift changes. This allows for the efficient acquisition of important information by filtering video footage based on specific time periods or events.

[0124] The analysis unit can also improve the accuracy of its analysis by referring to related video data (e.g., audio data and sensor data) during the analysis. For example, it can combine video and audio data for analysis and prioritize the analysis of video when an abnormal sound occurs. The analysis unit can combine video and sensor data for analysis and prioritize the analysis of video when an abnormal operation is detected. The analysis unit can combine video and related data for analysis and provide more accurate analysis results. In this way, the accuracy of the analysis is improved by referring to related data during the analysis.

[0125] The acquisition unit can also estimate the user's emotions and determine the priority of the video to acquire based on the estimated emotions. For example, if the user is feeling anxious, the acquisition unit can prioritize acquiring video of areas important to provide a sense of security. If the user is relaxed, the acquisition unit can acquire wide-angle video for overall monitoring. If the user is in a hurry, the acquisition unit can prioritize acquiring video of specific areas to obtain important information quickly. This allows for efficient acquisition of important information by prioritizing video according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0126] The following briefly describes the processing flow for example form 2.

[0127] Step 1: The acquisition unit acquires video. The acquisition unit acquires video using, for example, cameras in nursing homes or hospitals. The acquisition unit can acquire real-time footage of care staff performing specific tasks and the overall situation within the facility using cameras installed throughout the facility. The acquisition unit can monitor the movements and actions of care staff using cameras within the facility. The acquisition unit can verify the tasks that care staff are actually performing using cameras within the facility. Step 2: The analysis unit analyzes the video acquired by the acquisition unit. The analysis unit analyzes actions and behaviors in the video, for example, using AI. The analysis unit can analyze actions and behaviors in the video and detect fraudulent claims such as specific business establishment allowances and care worker treatment improvement allowances. The analysis unit can analyze actions and behaviors in the video and detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations. The analysis unit can analyze actions and behaviors in the video and detect patterns of fraudulent claims. Step 3: The detection unit detects fraud based on the results analyzed by the analysis unit. The detection unit can, for example, use AI to detect fraud based on the analysis results. The detection unit can detect fraudulent claims for specific business establishment allowances and care worker treatment improvement allowances based on the analysis results. The detection unit can detect cases where care workers report performing tasks they did not actually perform, or where they are engaging in activities that violate regulations, based on the analysis results. The detection unit can detect patterns of fraudulent claims based on the analysis results. Step 4: The notification unit notifies the detection unit of any fraudulent activity detected. For example, the notification unit notifies administrators or auditing bodies of fraudulent activity detected using AI. The notification unit can immediately notify administrators or auditing bodies when fraudulent activity is detected. The notification unit can notify administrators or auditing bodies of the details of the fraudulent activity. The notification unit can notify administrators or auditing bodies of the location and time the fraudulent activity occurred.

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0130] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements described above, including the acquisition unit, analysis unit, detection unit, and notification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the acquisition unit acquires video using the camera 42 of the smart device 14 and monitors the movements and actions of care workers with the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the acquired video to detect fraudulent claims. The detection unit is implemented in the specific processing unit 290 of the data processing unit 12 and detects fraud based on the analysis results. The notification unit is implemented in the specific processing unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12 and notifies the administrator or auditing body when fraudulent activity is detected. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0132] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0133] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0134] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0135] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0136] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0138] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0139] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0140] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0141] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements described above, including the acquisition unit, analysis unit, detection unit, and notification unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit acquires video using the camera 42 of the smart glasses 214 and monitors the movements and actions of care workers with the control unit 46A. The analysis unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12 and analyzes the acquired video to detect fraudulent claims. The detection unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12 and detects fraud based on the analysis results. The notification unit is implemented, for example, in the control unit 46A of the smart glasses 214 or in the specific processing unit 290 of the data processing unit 12 and notifies the administrator or auditing body when fraudulent activity is detected. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0148] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0149] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0150] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0151] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0152] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0154] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0155] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the acquisition unit, analysis unit, detection unit, and notification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit acquires video using the camera 42 of the headset terminal 314 and monitors the movements and actions of care workers with the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the acquired video to detect fraudulent claims. The detection unit is implemented in the specific processing unit 290 of the data processing unit 12 and detects fraud based on the analysis results. The notification unit is implemented in the specific processing unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12 and notifies the administrator or auditing body when fraudulent activity is detected. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0164] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0165] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0166] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0167] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0168] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0169] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0170] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0171] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0172] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0173] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0174] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0175] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0176] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0177] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0178] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0179] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0180] Each of the multiple elements described above, including the acquisition unit, analysis unit, detection unit, and notification unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit acquires video using the camera 42 of the robot 414 and monitors the movements and actions of care workers with the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the acquired video to detect fraudulent claims. The detection unit is implemented in the specific processing unit 290 of the data processing unit 12 and detects fraud based on the analysis results. The notification unit is implemented in the specific processing unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12 and notifies the administrator or auditing body when fraudulent activity is detected. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0181] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0182] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0183] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0184] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0185] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0186] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0187] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0188] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0189] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0190] 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.

[0191] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0192] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0193] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0194] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0195] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0196] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0197] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0198] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0199] (Note 1) The acquisition unit acquires video, An analysis unit analyzes the video acquired by the acquisition unit, A detection unit that detects fraud based on the results of analysis performed by the aforementioned analysis unit, The system includes a notification unit that notifies of the fraud detected by the detection unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, It includes a learning unit that learns patterns of fraud by linking with past data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The detection unit is It is equipped with a specific detection unit that detects fraudulent claims for the special business establishment allowance. The system described in Appendix 1, characterized by the features described herein. (Note 4) The detection unit is It is equipped with a treatment detection unit that detects fraudulent claims for the care worker treatment improvement allowance. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned notification unit, If fraudulent activity is detected, the administrator and auditing body will be notified immediately. The system described in Appendix 1, characterized by the features described herein. (Note 6) The acquisition unit is, The system estimates the user's emotions and adjusts the timing of video acquisition based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, Prioritize acquiring data on activities within specific areas of the facility. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, When acquiring video footage, filtering is performed based on specific time periods or events. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, It estimates the user's emotions and determines the priority of the videos to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, When acquiring video footage, the system takes into account the temperature and lighting conditions inside the facility to select the optimal image. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, When acquiring video footage, the system selects the video footage to be acquired in conjunction with audio data from within the facility. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, prioritize analyzing specific movements or actions within the video. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the video resolution and frame rate. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, It estimates the user's emotions and adjusts the level of detail in the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the video footage was acquired. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved by referring to related data in the video. The system described in Appendix 1, characterized by the features described herein. (Note 18) The detection unit is We estimate user sentiment and adjust fraud detection criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The detection unit is During detection, past fraud patterns are referenced to improve detection accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 20) The detection unit is During detection, fraud is prioritized based on specific actions or behaviors. The system described in Appendix 1, characterized by the features described herein. (Note 21) The detection unit is It estimates the user's emotions and adjusts how the detection results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The detection unit is When detection occurs, fraud is detected based on specific areas and time periods within the facility. The system described in Appendix 1, characterized by the features described herein. (Note 23) The detection unit is During detection, the system references relevant documents and databases to improve detection accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned notification unit, It estimates the user's emotions and adjusts the notification method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned notification unit, When a notification is sent, the priority of the notification is determined based on the severity of the detected fraud. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned notification unit, When a notification is sent, it can be customized for specific administrators or auditing bodies. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned notification unit, It estimates the user's emotions and adjusts the content of notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned notification unit, When sending a notification, the notification method will be selected based on specific areas and time periods within the facility. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned notification unit, Attach relevant data and documents to notifications to improve their accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned learning unit, During training, the training data is weighted based on when the video was acquired. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned specific detection unit is We will estimate user sentiment and adjust the fraud detection criteria for specific business establishment allowances based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned specific detection unit is When detecting fraudulent activity related to specific business establishment allowances, the accuracy of detection is improved by referring to past fraud patterns. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned specific detection unit is The system estimates the user's emotions and adjusts the display method of the fraud detection results for specific business establishment allowances based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned specific detection unit is When detecting fraudulent activity related to the special business establishment allowance, we improve the accuracy of detection by referring to relevant documents and databases. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned treatment detection unit, We will estimate the user's emotions and adjust the criteria for detecting fraud in the care worker treatment improvement allowance based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned treatment detection unit, When detecting fraudulent activities related to the care worker compensation improvement allowance, the accuracy of detection will be improved by referring to past fraud patterns. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned treatment detection unit, The system estimates the user's emotions and adjusts the display method of the results for detecting fraud in the care worker treatment improvement allowance based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned treatment detection unit, When detecting fraudulent activities related to the care worker compensation improvement allowance, we will improve the accuracy of the detection by referring to relevant documents and databases. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

[0200] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The acquisition unit acquires video, An analysis unit analyzes the video acquired by the acquisition unit, A detection unit that detects fraud based on the results of analysis performed by the aforementioned analysis unit, The system includes a notification unit that notifies of the fraud detected by the detection unit. A system characterized by the following features.

2. The aforementioned analysis unit, It includes a learning unit that learns patterns of fraud by linking with past data. The system according to feature 1.

3. The detection unit is It is equipped with a specific detection unit that detects fraudulent claims for the special business establishment allowance. The system according to feature 1.

4. The detection unit is It is equipped with a treatment detection unit that detects fraudulent claims for the care worker treatment improvement allowance. The system according to feature 1.

5. The aforementioned notification unit, If fraudulent activity is detected, the administrator and auditing body will be notified immediately. The system according to feature 1.

6. The acquisition unit is, The system estimates the user's emotions and adjusts the timing of video acquisition based on those emotions. The system according to feature 1.

7. The acquisition unit is, Prioritize acquiring data on activities within specific areas of the facility. The system according to feature 1.

8. The acquisition unit is, When acquiring video footage, filtering is performed based on specific time periods or events. The system according to feature 1.

Images