system

Abstract

The system according to this embodiment aims to enable early detection and prevention of fraud by utilizing records of fraud cases within a company. [Solution] The system according to the embodiment comprises an anonymization unit, a collection unit, an identification unit, and a provision unit. The anonymization unit anonymizes records of fraud cases within a company. The collection unit collects the records of fraud cases anonymized by the anonymization unit. The identification unit learns from the records of fraud cases collected by the collection unit and identifies and detects fraud patterns. The provision unit provides early detection and prevention measures for fraud based on the fraud patterns identified and detected by the identification unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including 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 prior art, there was a problem that the records of fraud incidents within a company were not fully utilized effectively for early detection and prevention of fraud.

[0005] The system according to the embodiment aims to utilize the records of fraud incidents within a company for early detection and prevention of fraud.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an anonymization unit, a collection unit, an identification unit, and a provision unit. The anonymization unit anonymizes records of fraud cases within a company. The collection unit collects the records of fraud cases anonymized by the anonymization unit. The identification unit learns from the records of fraud cases collected by the collection unit and identifies and detects fraud patterns. The provision unit provides early detection and prevention measures for fraud based on the fraud patterns identified and detected by the identification unit. [Effects of the Invention]

[0007] The system according to this embodiment can utilize records of fraud cases within a company to enable early detection and prevention of fraud. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also 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 fraud detection system according to an embodiment of the present invention is a system that anonymizes records of fraud incidents within a company and identifies and detects fraud patterns using LLM. The fraud detection system anonymizes records of fraud incidents that occur within a company, protecting personal and confidential information. Next, the anonymized records of fraud incidents are input into LLM to identify and detect fraud patterns. LLM can learn from past fraud data and grasp new fraud methods and trends. This system can also learn about frauds and troubles that are likely to occur in each industry, enabling efficient fraud prevention and compliance strengthening. For example, in a financial institution, if certain transaction patterns are often signs of fraud, LLM can identify those patterns and issue warnings early. Furthermore, this system can be used by the company's internal audit department, legal department, risk management department, etc. This minimizes the risk of fraud throughout the entire company. By introducing this system, companies can take measures for early detection and prevention of fraud, minimizing damages and risks caused by fraud. In addition, by learning the trends of fraud that should be watched out for in each industry, it becomes possible to efficiently prevent fraud and strengthen compliance. This allows fraud detection systems to anonymize records of fraud incidents within a company and identify and detect patterns of fraud, enabling early detection and prevention of fraud.

[0029] The fraud detection system according to the embodiment comprises an anonymization unit, a collection unit, an identification unit, and a provision unit. The anonymization unit anonymizes records of fraud cases within a company. The anonymization unit generalizes the data by, for example, removing personal and confidential information. The anonymization unit removes personal information such as names, addresses, and telephone numbers. The anonymization unit can also generalize confidential documents and specific transaction information. For example, the anonymization unit expresses a specific transaction amount as a range. The collection unit collects the records of fraud cases anonymized by the anonymization unit. The collection unit collects anonymized data from each department within a company, for example. The collection unit periodically collects data and stores it in a database, for example. The collection unit sets the scope of data collection and collects only the necessary data, for example. The identification unit learns from the records of fraud cases collected by the collection unit and identifies and detects fraud patterns. The identification unit learns from past fraud case data using, for example, LLM. The identification unit periodically updates the data to grasp new fraud methods and trends, for example. The identification unit, for example, detects abnormal transaction patterns and identifies signs of fraud. The provision unit provides early detection and prevention measures for fraud based on the fraud patterns identified and detected by the identification unit. For example, if a particular transaction pattern is a sign of fraud, the provision unit identifies that pattern and issues an early warning. For example, the provision unit learns fraud trends that should be watched out for in each industry and efficiently implements fraud prevention and compliance strengthening. For example, the provision unit provides preventive measures to minimize the risk of fraud to the internal audit department, legal department, risk management department, etc. of a company. As a result, the fraud detection system according to the embodiment enables early detection and prevention of fraud by anonymizing records of fraud cases within a company and identifying and detecting fraud patterns.

[0030] The anonymization unit anonymizes records of fraud cases within a company. Specifically, the anonymization unit removes personal and confidential information and generalizes the data. For example, when removing personal information such as names, addresses, and phone numbers, the unit either leaves the corresponding fields in the database blank or replaces them with a specific pattern. When generalizing confidential documents or specific transaction information, it expresses specific transaction amounts as a range. For example, if the transaction amount is in the range of 1 million to 2 million yen, it is expressed as "1 million to 2 million". Furthermore, the anonymization unit also has a checking function to verify that the data anonymization process has been performed appropriately. For example, it randomly extracts data after anonymization and compares it with the original data to check whether personal and confidential information has been properly removed. In this way, the anonymization unit can securely anonymize records of fraud cases within a company and protect data privacy.

[0031] The collection unit collects records of fraud cases that have been anonymized by the anonymization unit. Specifically, the collection unit collects anonymized data from various departments within a company. For example, it collects data periodically and stores it in a database. The collection unit has the ability to set the scope of data collection and collect only the necessary data. For example, it can be set to collect only data from a specific period or data from a specific department. Furthermore, the collection unit also has a filtering function to ensure data quality. For example, it can automatically detect and remove duplicate or incomplete data. The collection unit also has a scheduling function to automate the data collection process. For example, it can be set to collect data at a fixed time every day. This allows the collection unit to collect data efficiently and effectively, improving the overall system performance.

[0032] The identification unit learns from records of fraud cases collected by the collection unit and identifies and detects fraud patterns. Specifically, the identification unit learns from past fraud case data using an LLM (Large-Scale Language Model). The LLM has the ability to extract fraud patterns and trends based on a vast dataset. For example, the identification unit detects unusual transaction patterns and identifies signs of fraud. The LLM analyzes characteristics such as the content, timing, and amount of transactions to find patterns that are different from the norm. In addition, the identification unit regularly updates the data to grasp new fraud methods and trends. For example, by incorporating data from the latest fraud cases and retraining the model, it can always respond to the latest fraud methods. Furthermore, the identification unit can use anomaly detection algorithms to detect unusual patterns and abnormal data and issue warnings early. As a result, the identification unit can not only grasp the situation in real time but also handle long-term risk management and anomaly detection, improving the reliability and security of the entire system.

[0033] The Service Provider provides early detection and prevention measures for fraud based on fraud patterns identified and detected by the Specialized Services Department. Specifically, if a particular transaction pattern is a sign of fraud, the Service Provider identifies that pattern and issues an early warning. For example, if an unusual transaction is detected, an alert is issued in real time and relevant parties are notified. The Service Provider also learns the fraud trends that should be watched out for in each industry and efficiently implements fraud prevention and compliance enhancement. For example, in the financial industry, certain transaction patterns are often signs of fraud, but different patterns may be signs of fraud in the manufacturing industry. The Service Provider learns these industry-specific characteristics and provides appropriate preventive measures. Furthermore, the Service Provider provides preventive measures to minimize fraud risk to the company's internal audit department, legal department, risk management department, etc. For example, it proposes strengthening audits of specific transaction patterns to the internal audit department and assists the legal department in assessing legal risks related to fraud. It also assists the risk management department in assessing fraud risk and developing countermeasures. In this way, the Service Provider supports the management and prevention of fraud risk throughout the company, enabling early detection and prevention of fraud.

[0034] The anonymization unit can remove personal and confidential information and generalize the data. For example, the anonymization unit can remove personal and confidential information and generalize the data. For example, the anonymization unit can remove personal information such as names, addresses, and telephone numbers. The anonymization unit can also generalize confidential documents and specific transaction information. For example, the anonymization unit can represent specific transaction amounts as a range. This enhances privacy protection by removing personal and confidential information and generalizing the data. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can anonymize data using an AI model for removing personal and confidential information.

[0035] The collection unit can collect anonymized records of fraud cases. The collection unit can, for example, collect anonymized data from various departments within a company. The collection unit can, for example, periodically collect data and store it in a database. The collection unit can, for example, set the scope of data collection and collect only the necessary data. This enables centralized data management by collecting anonymized records of fraud cases. Some or all of the above processes in the collection unit may be performed using AI, for example, or not using AI. For example, the collection unit can collect data using an AI model to set the scope of data collection.

[0036] The identification unit can learn from data on past fraud cases to identify new fraud methods and trends. The identification unit can learn from data on past fraud cases using, for example, an LLM. The identification unit can periodically update data to identify new fraud methods and trends. The identification unit can detect unusual transaction patterns and identify signs of fraud. In this way, new fraud methods and trends can be identified by learning from data on past fraud cases. Some or all of the above processing in the identification unit may be performed using, for example, AI, or not using AI. For example, the identification unit can identify fraud patterns using an AI model for learning from data on past fraud cases.

[0037] The service provider can identify specific transaction patterns that are signs of fraud and issue early warnings. For example, the service provider can identify specific transaction patterns that are signs of fraud and issue early warnings. For example, the service provider can detect unusual transaction frequencies or a large number of small transactions and issue warnings. The service provider can also learn fraud trends that should be watched out for in each industry and efficiently implement fraud prevention and compliance strengthening. For example, the service provider can learn specific transaction patterns in financial institutions and detect signs of fraud early. This enables early detection of fraud by identifying specific transaction patterns that are signs of fraud and issuing early warnings. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can use an AI model to identify specific transaction patterns to detect signs of fraud.

[0038] The service provider can learn the trends of fraud that should be watched out for in each industry, enabling efficient fraud prevention and compliance strengthening. For example, the service provider can learn specific transaction patterns in financial institutions to detect signs of fraud early. Furthermore, the service provider can learn specific fraud patterns in manufacturing and provide fraud prevention measures. This allows for efficient fraud prevention and compliance strengthening by learning the trends of fraud that should be watched out for in each industry. Some or all of the above processes in the service provider may be performed using AI, for example, or not. For example, the service provider can use an AI model to learn the trends of fraud that should be watched out for in each industry to prevent fraud and strengthen compliance.

[0039] The anonymization unit can adjust the level of anonymization detail based on the importance of the data. For example, the anonymization unit applies a more rigorous anonymization algorithm to high-importance data. For example, the anonymization unit applies a simpler anonymization algorithm to low-importance data to improve processing speed. For example, the anonymization unit adjusts the level of anonymization detail in stages according to the importance of the data. This enables efficient anonymization by adjusting the level of anonymization detail based on the importance of the data. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can adjust the level of anonymization detail using an AI model to evaluate the importance of the data.

[0040] The anonymization unit can apply different anonymization algorithms depending on the data category. For example, the anonymization unit applies a specific anonymization algorithm to personal information to ensure confidentiality. For example, the anonymization unit applies a different anonymization algorithm to financial data to maintain data integrity. For example, the anonymization unit selects and applies the optimal anonymization algorithm for each data category. This ensures data confidentiality and integrity by applying the optimal anonymization algorithm according to the data category. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can use an AI model to classify data categories and apply the optimal anonymization algorithm.

[0041] The anonymization unit can determine the priority of anonymization based on the data submission date. For example, the anonymization unit prioritizes anonymizing the most recent data and processes it quickly. For example, the anonymization unit postpones anonymizing older data. For example, the anonymization unit dynamically adjusts the anonymization priority according to the submission date. This enables efficient data processing by determining the anonymization priority based on the data submission date. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can determine the anonymization priority using an AI model to evaluate the data submission date.

[0042] The anonymization unit can adjust the order of anonymization based on the relevance of the data. For example, the anonymization unit can anonymize highly relevant data preferentially to maintain data integrity. For example, the anonymization unit can anonymize less relevant data later. For example, the anonymization unit can dynamically adjust the order of anonymization according to the relevance of the data. This ensures data integrity by adjusting the order of anonymization based on the relevance of the data. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can adjust the order of anonymization using an AI model to evaluate the relevance of the data.

[0043] The data collection unit can adjust the level of detail of the data collection based on its importance. For example, the data collection unit collects highly important data in more detail. For example, it collects less important data simply to improve processing speed. For example, the data collection unit adjusts the level of detail of the data collection in stages according to its importance. This allows for efficient data collection by adjusting the level of detail of the data collection based on its importance. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can adjust the level of detail of the data collection using an AI model to evaluate the importance of the data.

[0044] The data collection unit can apply different collection algorithms depending on the data category. For example, the data collection unit can apply a specific collection algorithm to personal information to ensure confidentiality. For example, the data collection unit can apply a different collection algorithm to financial data to maintain data integrity. For example, the data collection unit can select and apply the most suitable collection algorithm for each data category. This ensures data confidentiality and integrity by applying the most suitable collection algorithm according to the data category. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can use an AI model to classify data categories and apply the most suitable collection algorithm.

[0045] The data collection unit can determine the priority of data collection based on the submission date. For example, the data collection unit may prioritize the collection of the most recent data and process it quickly. For example, the data collection unit may postpone the collection of older data. For example, the data collection unit may dynamically adjust the collection priority according to the submission date. This enables efficient data processing by determining the collection priority based on the data submission date. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit may use an AI model to evaluate the data submission date to determine the collection priority.

[0046] The data collection unit can adjust the order of collection based on the relevance of the data. For example, the data collection unit can prioritize the collection of highly relevant data to maintain data integrity. For example, the data collection unit can postpone the collection of less relevant data. For example, the data collection unit can dynamically adjust the order of collection according to the relevance of the data. This ensures data integrity by adjusting the order of collection based on the relevance of the data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can adjust the order of collection using an AI model to evaluate the relevance of the data.

[0047] The identification unit can adjust the level of detail based on the importance of the data. For example, the identification unit identifies highly important data in more detail. For example, the identification unit identifies less important data simply to improve processing speed. For example, the identification unit adjusts the level of detail in stages according to the importance of the data. This enables efficient data identification by adjusting the level of detail based on the importance of the data. Some or all of the above processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can adjust the level of detail using an AI model to evaluate the importance of the data.

[0048] The specific unit can apply different specific algorithms depending on the data category. For example, the specific unit applies a specific algorithm to personal information to ensure confidentiality. For example, the specific unit applies a different specific algorithm to financial data to maintain data integrity. The specific unit selects and applies the most suitable specific algorithm for each data category. This ensures data confidentiality and integrity by applying the most suitable specific algorithm according to the data category. Some or all of the above processing in the specific unit may be performed using AI, for example, or without AI. For example, the specific unit can use an AI model to classify data categories and apply the most suitable specific algorithm.

[0049] The identification unit can determine specific priorities based on the timing of data submission. For example, the identification unit prioritizes identifying the most recent data and processes it quickly. For example, it may postpone identifying older data. The identification unit can dynamically adjust specific priorities according to the submission timing. This enables efficient data processing by determining specific priorities based on the timing of data submission. Some or all of the above processing in the identification unit may be performed using AI, for example, or not using AI. For example, the identification unit can determine specific priorities using an AI model to evaluate the timing of data submission.

[0050] The identification unit can adjust a specific order based on the relevance of the data. For example, the identification unit can prioritize the identification of highly relevant data to maintain data integrity. For example, the identification unit can postpone the identification of less relevant data. For example, the identification unit can dynamically adjust the specific order according to the relevance of the data. This ensures data integrity by adjusting the specific order based on the relevance of the data. Some or all of the above processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can adjust the specific order using an AI model to evaluate the relevance of the data.

[0051] The service provider can adjust the level of detail provided based on the importance of the data. For example, the service provider might provide detailed explanations and specific steps for preventative measures based on high-importance data, or concise explanations and only an overview for preventative measures based on low-importance data. The service provider might adjust the level of detail of the preventative measures provided in stages, depending on the importance of the data. This allows for the efficient provision of preventative measures by adjusting the level of detail based on the importance of the data. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can adjust the level of detail using an AI model to evaluate the importance of the data.

[0052] The data delivery unit can apply different delivery algorithms depending on the data category. For example, the data delivery unit can apply a specific delivery algorithm to ensure confidentiality for personal information. For example, the data delivery unit can apply a different delivery algorithm to maintain data integrity for financial data. The data delivery unit can select and apply the optimal delivery algorithm for each data category. This ensures data confidentiality and integrity by applying the optimal delivery algorithm according to the data category. Some or all of the above processing in the data delivery unit may be performed using AI, for example, or without AI. For example, the data delivery unit can use an AI model to classify data categories and apply the optimal delivery algorithm.

[0053] The service provider can determine the priority of service provision based on the timing of data submission. For example, the service provider may prioritize and respond quickly to preventative measures based on the latest data. For example, the service provider may postpone the provision of preventative measures based on older data. The service provider may dynamically adjust the priority of service provision according to the submission timing. This enables efficient data processing by determining the priority of service provision based on the timing of data submission. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider may use an AI model to evaluate the timing of data submission to determine the priority of service provision.

[0054] The delivery unit can adjust the order of delivery based on the relevance of the data. For example, the delivery unit can prioritize the delivery of preventive measures based on highly relevant data to maintain data integrity. For example, the delivery unit can postpone the delivery of preventive measures based on less relevant data. The delivery unit can dynamically adjust the order of delivery according to the relevance of the data. This ensures data integrity by adjusting the order of delivery based on the relevance of the data. Some or all of the above processing in the delivery unit may be performed using AI, for example, or not using AI. For example, the delivery unit can adjust the order of delivery using an AI model to evaluate the relevance of the data.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The fraud detection system can also be equipped with a real-time monitoring unit. This unit monitors internal company transactions and communications in real time, instantly detecting any unusual patterns. For example, it can detect and warn of large-scale fund transfers occurring outside of normal business hours. It can also monitor suspicious access from specific IP addresses and issue immediate alerts. Furthermore, it can learn employee behavior patterns and warn of any unusual behavior. This enables early detection and rapid response to fraud.

[0057] The fraud detection system may also include a user feedback unit. This unit collects user feedback on the system's detection results to improve the system's accuracy. For example, it collects user ratings of false positive fraud alerts and adjusts the system's algorithms accordingly. It can also collect information on newly discovered fraud techniques and incorporate this into the system. Furthermore, the user feedback unit can periodically evaluate user satisfaction and identify areas for system improvement. This improves both the system's accuracy and user satisfaction.

[0058] The fraud detection system can also include a data visualization unit. This unit visually displays detected fraud patterns and trends, making them easily understandable to users. For example, it can display the frequency and trends of fraud occurrences in graphs and charts. It can also provide detailed information about specific transaction patterns through an interactive dashboard. Furthermore, it can display abnormal transaction patterns in real time, enabling users to respond quickly. This allows users to intuitively grasp the risk of fraud and take appropriate measures.

[0059] A fraud detection system can also include an education support department. This department provides fraud prevention education to employees within the company, raising awareness. For example, it could offer online courses on fraud methods and countermeasures. It could also regularly hold seminars and workshops to update employee knowledge. Furthermore, it could provide checklists and guidelines to help employees detect signs of fraud early. This raises fraud prevention awareness throughout the company and reduces the risk of fraud.

[0060] The fraud detection system may also include a data reliability evaluation unit. This unit assesses the reliability of the collected data and excludes unreliable data. For example, it evaluates the data source and collection method, using only reliable data. It can also check the consistency and integrity of the data and detect anomalous data. Furthermore, it evaluates the frequency and recency of the data, excluding outdated data. This improves the accuracy of fraud detection by relying on reliable data.

[0061] The fraud detection system may also include a data correlation analysis unit. This unit analyzes the correlations between collected data and identifies signs of fraud. For example, it can analyze the correlation between specific transaction patterns and the frequency of fraud occurrence. It can also identify the correlation between employee behavior patterns and the risk of fraud. Furthermore, it can analyze correlations between different data sources to detect signs of fraud early. This allows for the effective identification of fraud risks by leveraging the correlations between data.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The anonymization unit anonymizes the records of fraud cases within the company. The anonymization unit generalizes the data by, for example, removing personal and confidential information. Specifically, it removes personal information such as names, addresses, and phone numbers, and expresses specific transaction amounts within a range. Step 2: The collection unit collects records of fraud cases that have been anonymized by the anonymization unit. The collection unit periodically collects anonymized data from various departments within a company, for example, and stores it in a database. It is also possible to set the scope of collection and collect only the necessary data. Step 3: The Identification Unit learns from the records of fraud cases collected by the Collection Unit and identifies and detects fraud patterns. The Identification Unit, for example, uses LLM to learn from past fraud case data and regularly updates the data to grasp new fraud methods and trends. It detects abnormal transaction patterns and identifies signs of fraud. Step 4: The service provider provides early detection and prevention measures for fraud based on the fraud patterns identified and detected by the identification department. For example, if a particular transaction pattern is a sign of fraud, the service provider will identify that pattern and issue an early warning. They will learn fraud trends to watch out for in each industry and efficiently implement fraud prevention and compliance enhancement. They will provide preventive measures to minimize the risk of fraud to the company's internal audit department, legal department, risk management department, etc.

[0064] (Example of form 2) The fraud detection system according to an embodiment of the present invention is a system that anonymizes records of fraud incidents within a company and identifies and detects fraud patterns using LLM. The fraud detection system anonymizes records of fraud incidents that occur within a company, protecting personal and confidential information. Next, the anonymized records of fraud incidents are input into LLM to identify and detect fraud patterns. LLM can learn from past fraud data and grasp new fraud methods and trends. This system can also learn about frauds and troubles that are likely to occur in each industry, enabling efficient fraud prevention and compliance strengthening. For example, in a financial institution, if certain transaction patterns are often signs of fraud, LLM can identify those patterns and issue warnings early. Furthermore, this system can be used by the company's internal audit department, legal department, risk management department, etc. This minimizes the risk of fraud throughout the entire company. By introducing this system, companies can take measures for early detection and prevention of fraud, minimizing damages and risks caused by fraud. In addition, by learning the trends of fraud that should be watched out for in each industry, it becomes possible to efficiently prevent fraud and strengthen compliance. This allows fraud detection systems to anonymize records of fraud incidents within a company and identify and detect patterns of fraud, enabling early detection and prevention of fraud.

[0065] The fraud detection system according to the embodiment comprises an anonymization unit, a collection unit, an identification unit, and a provision unit. The anonymization unit anonymizes records of fraud cases within a company. The anonymization unit generalizes the data by, for example, removing personal and confidential information. The anonymization unit removes personal information such as names, addresses, and telephone numbers. The anonymization unit can also generalize confidential documents and specific transaction information. For example, the anonymization unit expresses a specific transaction amount as a range. The collection unit collects the records of fraud cases anonymized by the anonymization unit. The collection unit collects anonymized data from each department within a company, for example. The collection unit periodically collects data and stores it in a database, for example. The collection unit sets the scope of data collection and collects only the necessary data, for example. The identification unit learns from the records of fraud cases collected by the collection unit and identifies and detects fraud patterns. The identification unit learns from past fraud case data using, for example, LLM. The identification unit periodically updates the data to grasp new fraud methods and trends, for example. The identification unit, for example, detects abnormal transaction patterns and identifies signs of fraud. The provision unit provides early detection and prevention measures for fraud based on the fraud patterns identified and detected by the identification unit. For example, if a particular transaction pattern is a sign of fraud, the provision unit identifies that pattern and issues an early warning. For example, the provision unit learns fraud trends that should be watched out for in each industry and efficiently implements fraud prevention and compliance strengthening. For example, the provision unit provides preventive measures to minimize the risk of fraud to the internal audit department, legal department, risk management department, etc. of a company. As a result, the fraud detection system according to the embodiment enables early detection and prevention of fraud by anonymizing records of fraud cases within a company and identifying and detecting fraud patterns.

[0066] The anonymization unit anonymizes records of fraud cases within a company. Specifically, the anonymization unit removes personal and confidential information and generalizes the data. For example, when removing personal information such as names, addresses, and phone numbers, the unit either leaves the corresponding fields in the database blank or replaces them with a specific pattern. When generalizing confidential documents or specific transaction information, it expresses specific transaction amounts as a range. For example, if the transaction amount is in the range of 1 million to 2 million yen, it is expressed as "1 million to 2 million". Furthermore, the anonymization unit also has a checking function to verify that the data anonymization process has been performed appropriately. For example, it randomly extracts data after anonymization and compares it with the original data to check whether personal and confidential information has been properly removed. In this way, the anonymization unit can securely anonymize records of fraud cases within a company and protect data privacy.

[0067] The collection unit collects records of fraud cases that have been anonymized by the anonymization unit. Specifically, the collection unit collects anonymized data from various departments within a company. For example, it collects data periodically and stores it in a database. The collection unit has the ability to set the scope of data collection and collect only the necessary data. For example, it can be set to collect only data from a specific period or data from a specific department. Furthermore, the collection unit also has a filtering function to ensure data quality. For example, it can automatically detect and remove duplicate or incomplete data. The collection unit also has a scheduling function to automate the data collection process. For example, it can be set to collect data at a fixed time every day. This allows the collection unit to collect data efficiently and effectively, improving the overall system performance.

[0068] The identification unit learns from records of fraud cases collected by the collection unit and identifies and detects fraud patterns. Specifically, the identification unit learns from past fraud case data using an LLM (Large-Scale Language Model). The LLM has the ability to extract fraud patterns and trends based on a vast dataset. For example, the identification unit detects unusual transaction patterns and identifies signs of fraud. The LLM analyzes characteristics such as the content, timing, and amount of transactions to find patterns that are different from the norm. In addition, the identification unit regularly updates the data to grasp new fraud methods and trends. For example, by incorporating data from the latest fraud cases and retraining the model, it can always respond to the latest fraud methods. Furthermore, the identification unit can use anomaly detection algorithms to detect unusual patterns and abnormal data and issue warnings early. As a result, the identification unit can not only grasp the situation in real time but also handle long-term risk management and anomaly detection, improving the reliability and security of the entire system.

[0069] The Service Provider provides early detection and prevention measures for fraud based on fraud patterns identified and detected by the Specialized Services Department. Specifically, if a particular transaction pattern is a sign of fraud, the Service Provider identifies that pattern and issues an early warning. For example, if an unusual transaction is detected, an alert is issued in real time and relevant parties are notified. The Service Provider also learns the fraud trends that should be watched out for in each industry and efficiently implements fraud prevention and compliance enhancement. For example, in the financial industry, certain transaction patterns are often signs of fraud, but different patterns may be signs of fraud in the manufacturing industry. The Service Provider learns these industry-specific characteristics and provides appropriate preventive measures. Furthermore, the Service Provider provides preventive measures to minimize fraud risk to the company's internal audit department, legal department, risk management department, etc. For example, it proposes strengthening audits of specific transaction patterns to the internal audit department and assists the legal department in assessing legal risks related to fraud. It also assists the risk management department in assessing fraud risk and developing countermeasures. In this way, the Service Provider supports the management and prevention of fraud risk throughout the company, enabling early detection and prevention of fraud.

[0070] The anonymization unit can remove personal and confidential information and generalize the data. For example, the anonymization unit can remove personal and confidential information and generalize the data. For example, the anonymization unit can remove personal information such as names, addresses, and telephone numbers. The anonymization unit can also generalize confidential documents and specific transaction information. For example, the anonymization unit can represent specific transaction amounts as a range. This enhances privacy protection by removing personal and confidential information and generalizing the data. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can anonymize data using an AI model for removing personal and confidential information.

[0071] The collection unit can collect anonymized records of fraud cases. The collection unit can, for example, collect anonymized data from various departments within a company. The collection unit can, for example, periodically collect data and store it in a database. The collection unit can, for example, set the scope of data collection and collect only the necessary data. This enables centralized data management by collecting anonymized records of fraud cases. Some or all of the above processes in the collection unit may be performed using AI, for example, or not using AI. For example, the collection unit can collect data using an AI model to set the scope of data collection.

[0072] The identification unit can learn from data on past fraud cases to identify new fraud methods and trends. The identification unit can learn from data on past fraud cases using, for example, an LLM. The identification unit can periodically update data to identify new fraud methods and trends. The identification unit can detect unusual transaction patterns and identify signs of fraud. In this way, new fraud methods and trends can be identified by learning from data on past fraud cases. Some or all of the above processing in the identification unit may be performed using, for example, AI, or not using AI. For example, the identification unit can identify fraud patterns using an AI model for learning from data on past fraud cases.

[0073] The service provider can identify specific transaction patterns that are signs of fraud and issue early warnings. For example, the service provider can identify specific transaction patterns that are signs of fraud and issue early warnings. For example, the service provider can detect unusual transaction frequencies or a large number of small transactions and issue warnings. The service provider can also learn fraud trends that should be watched out for in each industry and efficiently implement fraud prevention and compliance strengthening. For example, the service provider can learn specific transaction patterns in financial institutions and detect signs of fraud early. This enables early detection of fraud by identifying specific transaction patterns that are signs of fraud and issuing early warnings. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can use an AI model to identify specific transaction patterns to detect signs of fraud.

[0074] The service provider can learn the trends of fraud that should be watched out for in each industry, enabling efficient fraud prevention and compliance strengthening. For example, the service provider can learn specific transaction patterns in financial institutions to detect signs of fraud early. Furthermore, the service provider can learn specific fraud patterns in manufacturing and provide fraud prevention measures. This allows for efficient fraud prevention and compliance strengthening by learning the trends of fraud that should be watched out for in each industry. Some or all of the above processes in the service provider may be performed using AI, for example, or not. For example, the service provider can use an AI model to learn the trends of fraud that should be watched out for in each industry to prevent fraud and strengthen compliance.

[0075] The anonymization unit can estimate the user's emotions and adjust the anonymization method based on the estimated emotions. For example, if the user is stressed, the anonymization unit simplifies and speeds up the anonymization process. For example, if the user is relaxed, the anonymization unit provides detailed anonymization options and suggests a customizable anonymization method. For example, if the user is in a hurry, the anonymization unit prioritizes anonymizing the most important information and completes the process quickly. This reduces the user's burden by adjusting the anonymization method based on their emotions. 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. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can adjust the anonymization method using an AI model for estimating the user's emotions.

[0076] The anonymization unit can adjust the level of anonymization detail based on the importance of the data. For example, the anonymization unit applies a more rigorous anonymization algorithm to high-importance data. For example, the anonymization unit applies a simpler anonymization algorithm to low-importance data to improve processing speed. For example, the anonymization unit adjusts the level of anonymization detail in stages according to the importance of the data. This enables efficient anonymization by adjusting the level of anonymization detail based on the importance of the data. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can adjust the level of anonymization detail using an AI model to evaluate the importance of the data.

[0077] The anonymization unit can apply different anonymization algorithms depending on the data category. For example, the anonymization unit applies a specific anonymization algorithm to personal information to ensure confidentiality. For example, the anonymization unit applies a different anonymization algorithm to financial data to maintain data integrity. For example, the anonymization unit selects and applies the optimal anonymization algorithm for each data category. This ensures data confidentiality and integrity by applying the optimal anonymization algorithm according to the data category. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can use an AI model to classify data categories and apply the optimal anonymization algorithm.

[0078] The anonymization unit can estimate the user's emotions and determine the priority of data to anonymize based on the estimated user emotions. For example, if the user is stressed, the anonymization unit will prioritize anonymizing high-priority data. If the user is relaxed, the anonymization unit will anonymize all data equally. If the user is in a hurry, the anonymization unit will anonymize the most important data first and process it quickly. This allows for anonymization tailored to the user's needs by prioritizing data based on the user's emotions. 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. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can determine the priority of data using an AI model for estimating the user's emotions.

[0079] The anonymization unit can determine the priority of anonymization based on the data submission date. For example, the anonymization unit prioritizes anonymizing the most recent data and processes it quickly. For example, the anonymization unit postpones anonymizing older data. For example, the anonymization unit dynamically adjusts the anonymization priority according to the submission date. This enables efficient data processing by determining the anonymization priority based on the data submission date. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can determine the anonymization priority using an AI model to evaluate the data submission date.

[0080] The anonymization unit can adjust the order of anonymization based on the relevance of the data. For example, the anonymization unit can anonymize highly relevant data preferentially to maintain data integrity. For example, the anonymization unit can anonymize less relevant data later. For example, the anonymization unit can dynamically adjust the order of anonymization according to the relevance of the data. This ensures data integrity by adjusting the order of anonymization based on the relevance of the data. Some or all of the above processing in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can adjust the order of anonymization using an AI model to evaluate the relevance of the data.

[0081] The data collection unit can estimate the user's emotions and adjust the collection method based on the estimated emotions. For example, if the user is stressed, the data collection unit can simplify and expedite the collection process. For example, if the user is relaxed, the data collection unit can provide detailed collection options and suggest a customizable collection method. For example, if the user is in a hurry, the data collection unit can prioritize collecting the most important information and complete the processing quickly. This reduces the user's burden by adjusting the collection method based on their emotions. 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. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can adjust the collection method using an AI model for estimating the user's emotions.

[0082] The data collection unit can adjust the level of detail of the data collection based on its importance. For example, the data collection unit collects highly important data in more detail. For example, it collects less important data simply to improve processing speed. For example, the data collection unit adjusts the level of detail of the data collection in stages according to its importance. This allows for efficient data collection by adjusting the level of detail of the data collection based on its importance. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can adjust the level of detail of the data collection using an AI model to evaluate the importance of the data.

[0083] The data collection unit can apply different collection algorithms depending on the data category. For example, the data collection unit can apply a specific collection algorithm to personal information to ensure confidentiality. For example, the data collection unit can apply a different collection algorithm to financial data to maintain data integrity. For example, the data collection unit can select and apply the most suitable collection algorithm for each data category. This ensures data confidentiality and integrity by applying the most suitable collection algorithm according to the data category. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can use an AI model to classify data categories and apply the most suitable collection algorithm.

[0084] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit will prioritize collecting high-priority data. If the user is relaxed, the data collection unit will collect all data equally. If the user is in a hurry, the data collection unit will collect the most important data first and process it quickly. This allows for data collection tailored to the user's needs by prioritizing data based on the user's emotions. 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. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can determine the priority of data using an AI model for estimating the user's emotions.

[0085] The data collection unit can determine the priority of data collection based on the submission date. For example, the data collection unit may prioritize the collection of the most recent data and process it quickly. For example, the data collection unit may postpone the collection of older data. For example, the data collection unit may dynamically adjust the collection priority according to the submission date. This enables efficient data processing by determining the collection priority based on the data submission date. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit may use an AI model to evaluate the data submission date to determine the collection priority.

[0086] The data collection unit can adjust the order of collection based on the relevance of the data. For example, the data collection unit can prioritize the collection of highly relevant data to maintain data integrity. For example, the data collection unit can postpone the collection of less relevant data. For example, the data collection unit can dynamically adjust the order of collection according to the relevance of the data. This ensures data integrity by adjusting the order of collection based on the relevance of the data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can adjust the order of collection using an AI model to evaluate the relevance of the data.

[0087] The identification unit can estimate the user's emotions and adjust specific methods based on the estimated emotions. For example, if the user is stressed, the identification unit can simplify and expedite the identification process. For example, if the user is relaxed, the identification unit can provide detailed identification options and suggest customizable identification methods. For example, if the user is in a hurry, the identification unit can prioritize identifying the most important information and complete the process quickly. This reduces the user's burden by adjusting specific methods based on their emotions. 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. Some or all of the above-described processes in the identification unit may be performed using AI or not. For example, the identification unit can adjust specific methods using an AI model for estimating the user's emotions.

[0088] The identification unit can adjust the level of detail based on the importance of the data. For example, the identification unit identifies highly important data in more detail. For example, the identification unit identifies less important data simply to improve processing speed. For example, the identification unit adjusts the level of detail in stages according to the importance of the data. This enables efficient data identification by adjusting the level of detail based on the importance of the data. Some or all of the above processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can adjust the level of detail using an AI model to evaluate the importance of the data.

[0089] The specific unit can apply different specific algorithms depending on the data category. For example, the specific unit applies a specific algorithm to personal information to ensure confidentiality. For example, the specific unit applies a different specific algorithm to financial data to maintain data integrity. The specific unit selects and applies the most suitable specific algorithm for each data category. This ensures data confidentiality and integrity by applying the most suitable specific algorithm according to the data category. Some or all of the above processing in the specific unit may be performed using AI, for example, or without AI. For example, the specific unit can use an AI model to classify data categories and apply the most suitable specific algorithm.

[0090] The identification unit can estimate the user's emotions and determine the priority of data to identify based on the estimated user emotions. For example, if the user is stressed, the identification unit will prioritize identifying high-priority data. If the user is relaxed, the identification unit will identify all data equally. If the user is in a hurry, the identification unit will identify the most important data first and process it quickly. This allows for data identification tailored to the user's needs by prioritizing data based on the user's emotions. 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. Some or all of the processing described above in the identification unit may be performed using AI, for example, or not using AI. For example, the identification unit can determine the priority of data using an AI model for estimating the user's emotions.

[0091] The identification unit can determine specific priorities based on the timing of data submission. For example, the identification unit prioritizes identifying the most recent data and processes it quickly. For example, it may postpone identifying older data. The identification unit can dynamically adjust specific priorities according to the submission timing. This enables efficient data processing by determining specific priorities based on the timing of data submission. Some or all of the above processing in the identification unit may be performed using AI, for example, or not using AI. For example, the identification unit can determine specific priorities using an AI model to evaluate the timing of data submission.

[0092] The identification unit can adjust a specific order based on the relevance of the data. For example, the identification unit can prioritize the identification of highly relevant data to maintain data integrity. For example, the identification unit can postpone the identification of less relevant data. For example, the identification unit can dynamically adjust the specific order according to the relevance of the data. This ensures data integrity by adjusting the specific order based on the relevance of the data. Some or all of the above processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can adjust the specific order using an AI model to evaluate the relevance of the data.

[0093] The service provider can estimate the user's emotions when providing early detection and prevention of fraud, and adjust the delivery method based on the estimated user emotions. For example, if the user is stressed, the service provider can provide concise and easy-to-understand prevention measures. If the user is relaxed, the service provider can provide detailed prevention measures and suggest customizable options. If the user is in a hurry, the service provider can prioritize providing the most important prevention measures and respond quickly. This reduces the burden on the user by adjusting the delivery method based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can adjust the delivery method using an AI model for estimating the user's emotions.

[0094] The service provider can adjust the level of detail provided based on the importance of the data. For example, the service provider might provide detailed explanations and specific steps for preventative measures based on high-importance data, or concise explanations and only an overview for preventative measures based on low-importance data. The service provider might adjust the level of detail of the preventative measures provided in stages, depending on the importance of the data. This allows for the efficient provision of preventative measures by adjusting the level of detail based on the importance of the data. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can adjust the level of detail using an AI model to evaluate the importance of the data.

[0095] The data delivery unit can apply different delivery algorithms depending on the data category. For example, the data delivery unit can apply a specific delivery algorithm to ensure confidentiality for personal information. For example, the data delivery unit can apply a different delivery algorithm to maintain data integrity for financial data. The data delivery unit can select and apply the optimal delivery algorithm for each data category. This ensures data confidentiality and integrity by applying the optimal delivery algorithm according to the data category. Some or all of the above processing in the data delivery unit may be performed using AI, for example, or without AI. For example, the data delivery unit can use an AI model to classify data categories and apply the optimal delivery algorithm.

[0096] The service provider can estimate the user's emotions and prioritize the data to be provided based on the estimated emotions. For example, if the user is stressed, the service provider will prioritize providing high-priority preventative measures. If the user is relaxed, the service provider will provide all preventative measures equally. If the user is in a hurry, the service provider will provide the most important preventative measures first and respond quickly. This allows for the provision of preventative measures tailored to the user's needs by prioritizing data based on the user's emotions. 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. Some or all of the processing described above in the service provider may be performed using AI or not. For example, the service provider can use an AI model to estimate the user's emotions to prioritize data.

[0097] The service provider can determine the priority of service provision based on the timing of data submission. For example, the service provider may prioritize and respond quickly to preventative measures based on the latest data. For example, the service provider may postpone the provision of preventative measures based on older data. The service provider may dynamically adjust the priority of service provision according to the submission timing. This enables efficient data processing by determining the priority of service provision based on the timing of data submission. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider may use an AI model to evaluate the timing of data submission to determine the priority of service provision.

[0098] The delivery unit can adjust the order of delivery based on the relevance of the data. For example, the delivery unit can prioritize the delivery of preventive measures based on highly relevant data to maintain data integrity. For example, the delivery unit can postpone the delivery of preventive measures based on less relevant data. The delivery unit can dynamically adjust the order of delivery according to the relevance of the data. This ensures data integrity by adjusting the order of delivery based on the relevance of the data. Some or all of the above processing in the delivery unit may be performed using AI, for example, or not using AI. For example, the delivery unit can adjust the order of delivery using an AI model to evaluate the relevance of the data.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The fraud detection system can also be equipped with a real-time monitoring unit. This unit monitors internal company transactions and communications in real time, instantly detecting any unusual patterns. For example, it can detect and warn of large-scale fund transfers occurring outside of normal business hours. It can also monitor suspicious access from specific IP addresses and issue immediate alerts. Furthermore, it can learn employee behavior patterns and warn of any unusual behavior. This enables early detection and rapid response to fraud.

[0101] The fraud detection system may also include a user feedback unit. This unit collects user feedback on the system's detection results to improve the system's accuracy. For example, it collects user ratings of false positive fraud alerts and adjusts the system's algorithms accordingly. It can also collect information on newly discovered fraud techniques and incorporate this into the system. Furthermore, the user feedback unit can periodically evaluate user satisfaction and identify areas for system improvement. This improves both the system's accuracy and user satisfaction.

[0102] The fraud detection system may also include an emotion estimation unit. This unit estimates the user's emotions and adjusts the system's interface based on the estimated emotions. For example, if the user is stressed, the emotion estimation unit simplifies the system's interface and simplifies operation. If the user is relaxed, the emotion estimation unit can also offer detailed options and suggest a customizable interface. Furthermore, if the user is in a hurry, the emotion estimation unit prioritizes displaying the most important information, allowing for quick completion of operations. This provides a flexible interface that responds to the user's emotions, reducing user burden.

[0103] The fraud detection system can also include a data visualization unit. This unit visually displays detected fraud patterns and trends, making them easily understandable to users. For example, it can display the frequency and trends of fraud occurrences in graphs and charts. It can also provide detailed information about specific transaction patterns through an interactive dashboard. Furthermore, it can display abnormal transaction patterns in real time, enabling users to respond quickly. This allows users to intuitively grasp the risk of fraud and take appropriate measures.

[0104] A fraud detection system can also include an education support department. This department provides fraud prevention education to employees within the company, raising awareness. For example, it could offer online courses on fraud methods and countermeasures. It could also regularly hold seminars and workshops to update employee knowledge. Furthermore, it could provide checklists and guidelines to help employees detect signs of fraud early. This raises fraud prevention awareness throughout the company and reduces the risk of fraud.

[0105] The fraud detection system can further use sentiment estimation to adjust the priority of warnings based on the user's emotions. For example, if the user is stressed, the most important warnings will be displayed first to allow for a quick response. If the user is relaxed, all warnings can be displayed equally, providing detailed information. Furthermore, if the user is in a hurry, the most important warnings will be displayed first to allow for a quick response. This provides flexible warning displays that respond to the user's emotions, reducing the user's burden.

[0106] The fraud detection system may also include a data reliability evaluation unit. This unit assesses the reliability of the collected data and excludes unreliable data. For example, it evaluates the data source and collection method, using only reliable data. It can also check the consistency and integrity of the data and detect anomalous data. Furthermore, it evaluates the frequency and recency of the data, excluding outdated data. This improves the accuracy of fraud detection by relying on reliable data.

[0107] The fraud detection system can further utilize sentiment estimation capabilities to tailor its notification methods based on the user's emotions. For example, if a user is stressed, it can send concise and easy-to-understand notifications to enable quick action. If a user is relaxed, it can send detailed notifications and offer customizable options. Furthermore, if a user is in a hurry, it can prioritize sending the most important notifications to enable quick action. This provides a flexible notification method that responds to the user's emotions, reducing their burden.

[0108] The fraud detection system may also include a data correlation analysis unit. This unit analyzes the correlations between collected data and identifies signs of fraud. For example, it can analyze the correlation between specific transaction patterns and the frequency of fraud occurrence. It can also identify the correlation between employee behavior patterns and the risk of fraud. Furthermore, it can analyze correlations between different data sources to detect signs of fraud early. This allows for the effective identification of fraud risks by leveraging the correlations between data.

[0109] The fraud detection system can further utilize emotion estimation capabilities to adjust the system's operation guide based on the user's emotions. For example, if the user is stressed, it can provide a concise and easy-to-understand operation guide to help them complete the operation quickly. If the user is relaxed, it can provide a detailed operation guide and suggest customizable options. Furthermore, if the user is in a hurry, it can prioritize displaying the most important steps to allow them to proceed quickly. This provides a flexible operation guide that responds to the user's emotions, reducing the user's burden.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The anonymization unit anonymizes the records of fraud cases within the company. The anonymization unit generalizes the data by, for example, removing personal and confidential information. Specifically, it removes personal information such as names, addresses, and phone numbers, and expresses specific transaction amounts within a range. Step 2: The collection unit collects records of fraud cases that have been anonymized by the anonymization unit. The collection unit periodically collects anonymized data from various departments within a company, for example, and stores it in a database. It is also possible to set the scope of collection and collect only the necessary data. Step 3: The Identification Unit learns from the records of fraud cases collected by the Collection Unit and identifies and detects fraud patterns. The Identification Unit, for example, uses LLM to learn from past fraud case data and regularly updates the data to grasp new fraud methods and trends. It detects abnormal transaction patterns and identifies signs of fraud. Step 4: The service provider provides early detection and prevention measures for fraud based on the fraud patterns identified and detected by the identification department. For example, if a particular transaction pattern is a sign of fraud, the service provider will identify that pattern and issue an early warning. They will learn fraud trends to watch out for in each industry and efficiently implement fraud prevention and compliance enhancement. They will provide preventive measures to minimize the risk of fraud to the company's internal audit department, legal department, risk management department, etc.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] Each of the multiple elements described above, including the anonymization unit, collection unit, identification unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes records of fraud cases within a company. The collection unit is implemented by the control unit 46A of the smart device 14 and collects the anonymized data. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies and detects fraud patterns using LLM. The provision unit is implemented by the control unit 46A of the smart device 14 and provides early detection and prevention measures for fraud. 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.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] Each of the multiple elements described above, including the anonymization unit, collection unit, identification unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the anonymization unit is implemented by the identification processing unit 290 of the data processing device 12 and anonymizes records of fraud cases within a company. The collection unit is implemented by the control unit 46A of the smart glasses 214 and collects the anonymized data. The identification unit is implemented by the identification processing unit 290 of the data processing device 12 and identifies and detects fraud patterns using LLM. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides early detection and prevention measures for fraud. 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.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] 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.

[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 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.

[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 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.

[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 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.

[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 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.

[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 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.

[0147] Each of the multiple elements described above, including the anonymization unit, collection unit, identification unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes records of fraud cases within a company. The collection unit is implemented by the control unit 46A of the headset terminal 314 and collects the anonymized data. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies and detects fraud patterns using LLM. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides early detection and prevention measures for fraud. 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.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] 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.

[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 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.

[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 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).

[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] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] Each of the multiple elements described above, including the anonymization unit, collection unit, identification unit, and provision unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes records of fraud cases within a company. The collection unit is implemented, for example, by the control unit 46A of the robot 414 and collects the anonymized data. The identification unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and identifies and detects fraud patterns using LLM. The provision unit is implemented, for example, by the control unit 46A of the robot 414 and provides early detection and prevention measures for fraud. 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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."

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] (Note 1) An anonymization department that anonymizes records of fraud cases within companies, A collection unit that collects records of fraud cases anonymized by the aforementioned anonymization unit, The identification unit learns from the records of fraud cases collected by the aforementioned collection unit and identifies and detects patterns of fraud, The system includes a provisioning unit that provides early detection and prevention measures for fraud based on the fraud patterns identified and detected by the aforementioned identification unit. A system characterized by the following features. (Note 2) The anonymization unit is, Remove personal and confidential information and generalize the data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Collecting anonymized records of fraud cases. The system described in Appendix 1, characterized by the features described herein. (Note 4) The specified part is, By learning from data on past fraud cases, we can identify new fraud methods and trends. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, If a particular trading pattern is a sign of fraud, we will identify that pattern and issue a warning early. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, Learn about the types of fraud to watch out for in each industry, and efficiently implement fraud prevention and compliance strengthening measures. The system described in Appendix 1, characterized by the features described herein. (Note 7) The anonymization unit is, The system estimates the user's emotions and adjusts the anonymization method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The anonymization unit is, Adjust the level of anonymization based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The anonymization unit is, Apply different anonymization algorithms depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 10) The anonymization unit is, We estimate user sentiment and determine the priority of data to anonymize based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The anonymization unit is, Anonymization priorities are determined based on the data submission date. The system described in Appendix 1, characterized by the features described herein. (Note 12) The anonymization unit is, Adjust the anonymization order based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is We estimate the user's emotions and adjust the data collection method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is Adjust the level of detail in data collection based on its importance. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is Apply different collection algorithms depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned collection unit is Prioritize data collection based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned collection unit is Adjust the order of data collection based on data relevance. The system described in Appendix 1, characterized by the features described herein. (Note 19) The specified part is, It estimates the user's emotions and adjusts specific methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The specified part is, Adjust specific levels of detail based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The specified part is, Apply different specific algorithms depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The specified part is, It estimates the user's emotions and prioritizes the data to identify based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The specified part is, Determine specific priorities based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The specified part is, Adjust a specific order based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing early detection and prevention measures for fraud, we estimate the user's sentiment and adjust the delivery method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, Adjust the level of detail provided based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, Apply different delivery algorithms depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, It estimates the user's emotions and prioritizes the data to be provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, Prioritizing data provision based on the submission timing. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, The order of data delivery will be adjusted based on its relevance. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0184] 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. An anonymization department that anonymizes records of fraud cases within companies, A collection unit that collects records of fraud cases anonymized by the aforementioned anonymization unit, The identification unit learns from the records of fraud cases collected by the aforementioned collection unit and identifies and detects patterns of fraud, The system includes a provisioning unit that provides early detection and prevention measures for fraud based on the fraud patterns identified and detected by the aforementioned identification unit. A system characterized by the following features.

2. The anonymization unit is, Remove personal and confidential information and generalize the data. The system according to feature 1.

3. The aforementioned collection unit is Collecting anonymized records of fraud cases. The system according to feature 1.

4. The specified part is, By learning from data on past fraud cases, we can identify new fraud methods and trends. The system according to feature 1.

5. The aforementioned supply unit is, If a particular trading pattern is a sign of fraud, we will identify that pattern and issue a warning early. The system according to feature 1.

6. The aforementioned supply unit is, Learn about the types of fraud to watch out for in each industry, and efficiently implement fraud prevention and compliance strengthening measures. The system according to feature 1.

7. The anonymization unit is, The system estimates the user's emotions and adjusts the anonymization method based on those estimated emotions. The system according to feature 1.

8. The anonymization unit is, Adjust the level of anonymization based on the importance of the data. The system according to feature 1.

Images