System

Abstract

An object of a system according to an embodiment is to quickly and accurately detect an abnormality in transaction data and take appropriate measures.SOLUTION: A system according to an embodiment includes a collection unit, an analysis unit, a detection unit, a warning unit, a notification unit, and a stop unit. The collection unit collects transaction data. The analysis unit analyzes the data collected by the collection unit. The detection unit detects an abnormality based on the data analyzed by the analysis unit. The warning unit issues a warning when an abnormality is detected by the detection unit. The notification unit asks the user for confirmation when the warning unit issues a warning. The stop unit suspends the transaction when the user is not confirmed by the notification unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to quickly and accurately detect abnormalities in transaction data and take appropriate measures.

[0005] The system according to the embodiment aims to quickly and accurately detect abnormalities in transaction data and take appropriate measures. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a detection unit, a warning unit, a notification unit, and a stop unit. The collection unit collects transaction data. The analysis unit analyzes the data collected by the collection unit. The detection unit detects anomalies based on the data analyzed by the analysis unit. The warning unit issues a warning when an anomaly is detected by the detection unit. The notification unit requests confirmation from the user when a warning is issued by the warning unit. The stop unit suspends the transaction when the notification unit is unable to obtain confirmation from the user. [Effects of the Invention]

[0007] The system according to the embodiment can quickly and accurately detect abnormalities in transaction data and take appropriate measures. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

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

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) A tool according to an embodiment of the present invention is a system for detecting and guarding against cash card fraud. This system collects transaction data, analyzes it using AI, and detects abnormal transaction patterns. If an abnormality is detected, it immediately issues a warning and suspends the transaction. Furthermore, it sends a notification to the user requesting confirmation and determines whether to resume the transaction after the user confirms. For example, the system collects detailed data on cash card usage history and transaction data, such as the date, time, location, and amount of the transaction. The collected data is then analyzed using AI. The AI ​​detects abnormal transactions that deviate from normal transaction patterns, such as high-value transactions, multiple transactions in a short period of time, transactions in a location other than the usual transaction area, or transactions occurring late at night. If an abnormality is detected, it immediately issues a warning and suspends the transaction. Furthermore, it sends a notification to the user requesting confirmation. Multiple notification methods are available, including phone, email, and app notifications. The system determines whether to resume the transaction after the user confirms. If the user's confirmation cannot be obtained, it takes measures such as suspending the transaction for a certain period of time. This allows the system to detect cash card fraud early and minimize damage. This allows the system to detect cash card fraud early and minimize damage. For example, the system collects detailed cash card usage history and transaction data and uses AI to analyze it to detect abnormal transaction patterns. If an abnormality is detected, it immediately issues a warning and suspends the transaction. It also sends a notification to the user requesting confirmation, and after the user confirms, it decides whether to resume the transaction. This allows the system to detect cash card fraud early and minimize damage.

[0029] A cash card fraud detection system according to an embodiment includes a collection unit, an analysis unit, a detection unit, a warning unit, a notification unit, and a stopping unit. The collection unit collects transaction data. The transaction data includes, but is not limited to, financial transaction data and e-commerce transaction data. The collection unit collects detailed data, such as transaction date, time, location, and amount. The collection unit can also analyze a user's past transaction history and select an optimal collection method. For example, the collection unit selects an optimal collection method based on the user's frequent transaction patterns in the past. The analysis unit uses AI to analyze the data collected by the collection unit. The analysis unit detects, for example, high-value transactions that differ from normal transaction patterns or multiple transactions in a short period of time as anomalies. The analysis unit can also detect, as anomalies, transactions in locations other than normal transaction areas or transactions occurring late at night. Furthermore, the analysis unit can include past fraud cases as training data. The detection unit detects anomalies based on the data analyzed by the analysis unit. The detection unit can improve the accuracy of anomaly detection by, for example, taking into account the correlation between transactions. The detection unit can also weight anomaly detection based on the frequency of transaction occurrence. The warning unit issues a warning when an anomaly is detected by the detection unit. The warning unit, for example, estimates a user's emotion and adjusts the display method of the warning based on the estimated user's emotion. The warning unit can also adjust the level of detail of the warning based on the importance of the transaction. The notification unit requests confirmation from the user when the warning unit issues a warning. The notification unit requests confirmation from the user by means of, for example, telephone, email, or app notification. The notification unit can also estimate a user's emotion and adjust the display method of the notification based on the estimated user's emotion. The stopping unit temporarily suspends the transaction when the notification unit cannot obtain user confirmation. The stopping unit, for example, estimates a user's emotion and adjusts the timing of suspending the transaction based on the estimated user's emotion. The stopping unit can also adjust the level of detail of the suspension based on the importance of the transaction. As a result, the cash card fraud detection system according to the embodiment can detect cash card fraud early and minimize damage.

[0030] The analysis unit can detect transactions above a specific amount that differ from normal transaction patterns or multiple transactions within a specific period as abnormal. For example, the analysis unit detects transactions above a specific amount as abnormal. For example, the analysis unit detects transactions above 1 million yen as abnormal. The analysis unit can also detect multiple transactions within a specific period as abnormal. For example, the analysis unit can detect multiple transactions within a 24-hour period as abnormal. The analysis unit can also detect multiple transactions within a week as abnormal. This enables early detection of fraud by detecting high-value transactions or multiple transactions within a short period as abnormal. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input transaction data into a generation AI and have the generation AI detect abnormal transactions.

[0031] The analysis unit can detect transactions in locations different from the usual trading area or late-night transactions as abnormal. For example, the analysis unit detects transactions in locations different from the usual trading area as abnormal. For example, the analysis unit detects transactions in locations different from the user's residence as abnormal. The analysis unit can also detect transactions in locations different from previous trading areas as abnormal. Furthermore, the analysis unit can detect transactions in late-night hours as abnormal. For example, the analysis unit detects transactions between 11:00 PM and 5:00 AM as abnormal. This enables early detection of fraud by detecting transactions in locations different from the usual trading area or late-night transactions as abnormal. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data into a generation AI and have the generation AI detect abnormal transactions.

[0032] The notification unit can request confirmation from the user by any of the following means: telephone, email, or app notification. The notification unit, for example, requests confirmation from the user by telephone. For example, the notification unit can request confirmation from the user using an automated voice call. The notification unit can also request confirmation from the user by email. For example, the notification unit can send an email containing transaction details and request confirmation from the user. The notification unit can also request confirmation from the user by app notification. For example, the notification unit can send a notification to the user through a smartphone app and request confirmation. This allows for a quick response by requesting confirmation from the user through multiple means. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can estimate the user's emotions and adjust the notification display method based on the estimated user emotions.

[0033] The halting unit can halt trading for a certain period of time if user confirmation cannot be obtained. For example, the halting unit halts trading for 30 minutes if user confirmation cannot be obtained. For example, the halting unit can halt trading for one hour if user confirmation cannot be obtained. The halting unit can also halt trading for 24 hours if user confirmation cannot be obtained. This prevents fraud by halting trading if user confirmation cannot be obtained. Some or all of the above-mentioned processing in the halting unit may be performed using AI, for example, or may be performed without using AI. For example, the halting unit can estimate the user's emotions and adjust the timing of halting trading based on the estimated user's emotions.

[0034] The analysis unit can include past fraud cases as training data. The analysis unit, for example, includes past fraud cases as training data. For example, the analysis unit includes past fraud methods as training data. The analysis unit can also include the amount of damage caused by past frauds as training data. Furthermore, the analysis unit can also include the locations where past frauds occurred as training data. By including past fraud cases as training data, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past fraud cases into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0035] When collecting transaction data, the collection unit can analyze the user's past transaction history and select the optimal collection method. The collection unit selects the optimal collection method based on, for example, the user's frequent transaction patterns in the past. The collection unit can also identify time periods during which abnormalities are likely to occur from the user's past transaction history and focus data collection on those time periods. Furthermore, the collection unit can analyze the user's past transaction history and select a collection method according to a specific transaction method (ATM, online banking, etc.). In this way, the optimal collection method can be selected by analyzing the user's past transaction history. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without AI. For example, the collection unit can input the user's past transaction history data into the generation AI and have the generation AI select the optimal collection method.

[0036] When collecting transaction data, the collection unit can select a collection method depending on the type of transaction. For example, in the case of online transactions, the collection unit collects internet banking log data. In the case of offline transactions, the collection unit can also collect ATM usage history. Furthermore, in the case of a user who conducts both online and offline transactions, the collection unit can also collect integrated data from both. This enables efficient data collection by selecting a collection method depending on the type of transaction. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input transaction data to a generation AI and have the generation AI select a collection method.

[0037] When collecting transaction data, the collection unit can adjust the collection range taking into account the user's current geographical location information. For example, if the user is in a specific area, the collection unit can focus on collecting transaction data in that area. Also, if the user is traveling, the collection unit can collect transaction data at the user's travel destination. Furthermore, if the user is at home, the collection unit can collect transaction data around the user's home. This enables appropriate data collection by taking the user's geographical location information into account. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to adjust the collection range.

[0038] When collecting transaction data, the collection unit can analyze the user's social media activities and collect related transaction data. For example, the collection unit collects transaction data from locations where the user has checked in on social media. The collection unit can also analyze the content of the user's social media posts and collect related transaction data. Furthermore, the collection unit can collect related transaction data by referring to the activities of the user's friends on social media. In this way, related transaction data can be efficiently collected by analyzing the user's social media activities. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's social media data into a generation AI and cause the generation AI to collect related transaction data.

[0039] When collecting transaction data, the collection unit can customize the collection method by reflecting the user's past feedback. The collection unit customizes the collection method, for example, based on feedback provided by the user in the past. The collection unit can also adjust the collection method for a specific transaction instrument based on the user's past feedback. Furthermore, the collection unit can also adjust the collection frequency and timing by reflecting the user's past feedback. In this way, the collection method can be optimized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the collection method.

[0040] When collecting transaction data, the collection unit can select the optimal collection means by taking into account the user's device information. For example, if the user uses a smartphone, the collection unit collects smartphone transaction data. Furthermore, if the user uses a tablet, the collection unit can also collect tablet transaction data. Furthermore, if the user uses a personal computer, the collection unit can also collect personal computer transaction data. This allows the optimal collection means to be selected by taking into account the user's device information. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's device information into the generation AI and cause the generation AI to select the optimal collection means.

[0041] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the transaction. For example, the analysis unit performs a detailed analysis in the case of a high-value transaction. The analysis unit can also perform a simplified analysis in the case of a normal transaction. The analysis unit can also perform a detailed analysis in the case of a transaction suspected of being abnormal. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the transaction. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data to a generation AI and have the generation AI adjust the level of detail of the analysis.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the transaction category. For example, in the case of an online transaction, the analysis unit applies a specific analysis algorithm. In addition, in the case of an offline transaction, the analysis unit can also apply a different analysis algorithm. Furthermore, in the case of an ATM transaction, the analysis unit can apply an even different analysis algorithm. In this way, by applying different analysis algorithms depending on the transaction category, highly accurate analysis is possible. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data to a generation AI and have the generation AI apply the analysis algorithm.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also learn specific patterns from the user's past analysis results and improve the analysis accuracy. Furthermore, the analysis unit can adjust the anomaly detection threshold by referring to the user's past analysis results. This improves the accuracy of the analysis by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0044] During analysis, the analysis unit can determine the priority of analysis based on the time of transaction occurrence. For example, the analysis unit prioritizes analysis of transactions made during late night hours. The analysis unit can also prioritize analysis of transactions made multiple times in a short period of time. The analysis unit can also prioritize analysis of transactions made on specific days of the week or during specific time periods. In this way, by determining the priority of analysis based on the time of transaction occurrence, important transactions can be analyzed preferentially. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data into a generation AI and have the generation AI determine the analysis priority.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the transactions. For example, the analysis unit groups related transactions and analyzes them in order. The analysis unit can also prioritize analysis of highly related transactions. The analysis unit can also postpone analysis of less related transactions. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the transactions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data into a generation AI and have the generation AI adjust the order of analysis.

[0046] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can use detailed technical terminology. Furthermore, if the user does not have technical expertise, the analysis unit can explain the analysis results in simple terms. Furthermore, the analysis unit can adjust the way the analysis results are presented according to the user's level of expertise. By adjusting the use of technical terminology in the analysis according to the user's level of expertise, analysis results that are easy for the user to understand can be provided. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise data into the generation AI and have the generation AI use technical terminology in the analysis.

[0047] The detection unit can improve the accuracy of anomaly detection by taking into account the interrelationships between transactions during detection. For example, the detection unit groups related transactions and detects anomalies by taking into account the interrelationships. The detection unit can also analyze the interrelationships between transactions to improve the accuracy of anomaly detection. The detection unit can also adjust the anomaly detection threshold by taking into account the interrelationships between transactions. This improves the accuracy of anomaly detection by taking into account the interrelationships between transactions. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input transaction data to a generation AI and have the generation AI improve the accuracy of anomaly detection.

[0048] The detection unit can weight anomaly detection based on the frequency of transactions during detection. For example, the detection unit can assign a higher weight to anomaly detection for transactions that occur multiple times in a short period of time. The detection unit can also assign a lower weight to anomaly detection for transactions that occur over a long period of time. The detection unit can also adjust the weight to anomaly detection for transactions that occur during a specific time period. In this way, weighting anomaly detection based on the frequency of transactions allows for priority detection of important anomalies. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input transaction data to a generation AI and have the generation AI perform anomaly detection weighting.

[0049] The detection unit can adjust the anomaly detection criteria based on the location of the transaction at the time of detection. For example, the detection unit can set stricter anomaly detection criteria for transactions in locations different from normal transaction areas. The detection unit can also set normal anomaly detection criteria for transactions in normal transaction areas. The detection unit can also adjust the anomaly detection criteria for transactions in specific regions. This allows for appropriate anomaly detection by adjusting the anomaly detection criteria based on the location of the transaction. Some or all of the above-described processing in the detection unit can be performed using, for example, AI, or can be performed without using AI. For example, the detection unit can input transaction data to a generation AI and have the generation AI adjust the anomaly detection criteria.

[0050] The detection unit can detect anomalies by taking into account the geographic distribution of transactions. For example, the detection unit detects transactions in locations different from normal transaction areas as anomalies. The detection unit can also prioritize detection of transactions in specific regions. The detection unit can also improve the accuracy of anomaly detection by taking into account the geographic distribution. This improves the accuracy of anomaly detection by taking into account the geographic distribution of transactions. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input transaction data into a generation AI and have the generation AI improve the accuracy of anomaly detection.

[0051] The detection unit can improve the accuracy of anomaly detection by referring to literature related to the transaction during detection. The detection unit, for example, refers to the relevant literature and adjusts the anomaly detection algorithm. The detection unit can also improve the accuracy of anomaly detection based on knowledge obtained from the relevant literature. The detection unit can also adjust the anomaly detection threshold by referring to the relevant literature. In this way, the accuracy of anomaly detection is improved by referring to literature related to the transaction. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input related literature data into the generation AI and cause the generation AI to improve the accuracy of anomaly detection.

[0052] The detection unit can detect anomalies by taking into account the market value of the transaction. For example, the detection unit can set stricter anomaly detection standards for high-value transactions. The detection unit can also set looser anomaly detection standards for transactions with low market value. The detection unit can also adjust the weighting of anomaly detection by taking into account the market value. This allows for priority detection of important anomalies by taking into account the market value of the transaction. Some or all of the above-mentioned processing in the detection unit can be performed using, for example, AI, or can be performed without using AI. For example, the detection unit can input transaction data to a generation AI and have the generation AI adjust the anomaly detection standards.

[0053] When issuing a warning, the warning unit can adjust the level of detail of the warning based on the importance of the transaction. For example, in the case of a high-value transaction, the warning unit displays a detailed warning. In addition, the warning unit can also display a simplified warning in the case of a normal transaction. In addition, the warning unit can also display a detailed warning in the case of a transaction suspected of being abnormal. In this way, by adjusting the level of detail of the warning based on the importance of the transaction, it is possible to provide an appropriate warning for important transactions. Some or all of the above-mentioned processing in the warning unit may be performed, for example, using AI, or may be performed without using AI. For example, the warning unit can input transaction data to a generation AI and have the generation AI adjust the level of detail of the warning.

[0054] When issuing a warning, the warning unit can apply different warning algorithms depending on the category of the transaction. For example, the warning unit applies a specific warning algorithm in the case of an online transaction. The warning unit can also apply a different warning algorithm in the case of an offline transaction. Furthermore, the warning unit can apply an even different warning algorithm in the case of an ATM transaction. This allows for highly accurate warnings by applying different warning algorithms depending on the category of the transaction. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input transaction data to a generation AI and have the generation AI apply a warning algorithm.

[0055] When issuing a warning, the warning unit can improve the accuracy of the warning by referring to the user's past warning results. The warning unit, for example, adjusts the warning algorithm based on the user's past warning results. The warning unit can also learn specific patterns from the user's past warning results and improve the accuracy of the warning. Furthermore, the warning unit can adjust the anomaly detection threshold by referring to the user's past warning results. In this way, the accuracy of the warning is improved by referring to the user's past warning results. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the user's past warning result data into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0056] When issuing a warning, the warning unit can determine the priority of the warning based on the time of transaction occurrence. For example, the warning unit can prioritize warnings for transactions that occur late at night. The warning unit can also prioritize warnings for transactions that occur multiple times in a short period of time. The warning unit can also prioritize warnings for transactions that occur on specific days of the week or during specific time periods. In this way, by determining the priority of warnings based on the time of transaction occurrence, warnings can be given priority for important transactions. Some or all of the above-mentioned processing in the warning unit may be performed using, or without, AI. For example, the warning unit can input transaction data into a generation AI and have the generation AI determine the priority of warnings.

[0057] When issuing a warning, the warning unit can adjust the order of warnings based on the relevance of the transactions. For example, the warning unit groups related transactions and displays warnings in an orderly manner. The warning unit can also prioritize highly related transactions. The warning unit can also postpone warnings for less related transactions. This allows for efficient warnings by adjusting the order of warnings based on the relevance of the transactions. Some or all of the above-described processing in the warning unit may be performed using, or without, AI. For example, the warning unit can input transaction data into a generation AI and have the generation AI adjust the order of warnings.

[0058] When issuing a warning, the warning unit can adjust the use of technical terminology in the warning depending on the user's level of expertise. For example, if the user has technical expertise, the warning unit can use detailed technical terminology. If the user does not have technical expertise, the warning unit can also explain the warning in simple terms. The warning unit can also adjust the way the warning is expressed depending on the user's level of expertise. This makes it possible to provide a warning that is easy for the user to understand by adjusting the use of technical terminology in the warning depending on the user's level of expertise. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input the user's level of expertise data into the generation AI and have the generation AI use technical terminology in the warning.

[0059] The notification unit can adjust the level of detail of the notification based on the importance of the transaction when making a notification. For example, in the case of a high-value transaction, the notification unit displays a detailed notification. The notification unit can also display a simplified notification for a normal transaction. The notification unit can also display a detailed notification for a transaction suspected of being abnormal. In this way, by adjusting the level of detail of the notification based on the importance of the transaction, appropriate notifications can be provided for important transactions. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input transaction data to a generation AI and have the generation AI adjust the level of detail of the notification.

[0060] The notification unit can apply different notification algorithms depending on the transaction category when notifying. For example, the notification unit applies a specific notification algorithm in the case of an online transaction. The notification unit can also apply a different notification algorithm in the case of an offline transaction. Furthermore, the notification unit can apply an even different notification algorithm in the case of an ATM transaction. This enables highly accurate notifications by applying different notification algorithms depending on the transaction category. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input transaction data to a generation AI and have the generation AI apply the notification algorithm.

[0061] The notification unit can improve the accuracy of notifications by referring to the user's past notification results when sending notifications. The notification unit, for example, adjusts the notification algorithm based on the user's past notification results. The notification unit can also improve the accuracy of notifications by learning specific patterns from the user's past notification results. Furthermore, the notification unit can also adjust the anomaly detection threshold by referring to the user's past notification results. This improves the accuracy of notifications by referring to the user's past notification results. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's past notification result data into the generation AI and cause the generation AI to improve the accuracy of notifications.

[0062] The notification unit can determine the priority of notifications based on the time of transaction occurrence when issuing notifications. For example, the notification unit can prioritize displaying notifications for transactions that occurred late at night. The notification unit can also prioritize displaying notifications for transactions that occurred multiple times in a short period of time. The notification unit can also prioritize displaying notifications for transactions that occurred on a specific day of the week or during a specific time period. In this way, by determining the priority of notifications based on the time of transaction occurrence, notifications can be provided preferentially for important transactions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input transaction data into a generation AI and have the generation AI determine the priority of notifications.

[0063] The notification unit can adjust the order of notifications based on the relevance of the transactions when notifying. For example, the notification unit groups related transactions and displays the notifications in an orderly manner. The notification unit can also prioritize notifications of highly related transactions. The notification unit can also postpone notifications of less related transactions. This allows for efficient notifications by adjusting the order of notifications based on the relevance of the transactions. Some or all of the above-described processing in the notification unit may be performed using, or without, AI, for example. For example, the notification unit can input transaction data into a generation AI and have the generation AI adjust the order of notifications.

[0064] The notification unit can adjust the use of technical terminology in the notification according to the user's level of expertise when providing a notification. For example, if the user has technical expertise, the notification unit can use detailed technical terminology. If the user does not have technical expertise, the notification unit can also explain the notification in simple terms. The notification unit can also adjust the way the notification is expressed according to the user's level of expertise. This allows the notification to be provided in a way that is easy for the user to understand by adjusting the use of technical terminology in the notification according to the user's level of expertise. Some or all of the above-described processing in the notification unit can be performed using AI, for example, or without AI. For example, the notification unit can input the user's level of expertise data into a generation AI and have the generation AI use technical terminology in the notification.

[0065] When halting a transaction, the halting unit can adjust the level of detail of the halt based on the importance of the transaction. For example, the halting unit performs detailed halt procedures for high-value transactions. The halting unit can also perform simplified halt procedures for normal transactions. The halting unit can also perform detailed halt procedures for transactions suspected of being abnormal. In this way, by adjusting the level of detail of the halt based on the importance of the transaction, appropriate halt procedures can be performed for important transactions. Some or all of the above-mentioned processing in the halting unit may be performed using AI, for example, or may be performed without using AI. For example, the halting unit can input transaction data into a generating AI and have the generating AI adjust the level of detail of the halt.

[0066] When halting a transaction, the halting unit can apply different halting algorithms depending on the category of the transaction. For example, in the case of an online transaction, the halting unit applies a specific halting algorithm. In addition, in the case of an offline transaction, the halting unit can also apply a different halting algorithm. Furthermore, in the case of an ATM transaction, the halting unit can apply an even different halting algorithm. In this way, applying different halting algorithms depending on the category of the transaction enables highly accurate halting. Some or all of the above-mentioned processing in the halting unit may be performed using, for example, AI, or may be performed without using AI. For example, the halting unit can input transaction data to a generation AI and cause the generation AI to apply a halting algorithm.

[0067] When halting trading, the halting unit can improve the accuracy of halting by referring to the user's past halting results. The halting unit, for example, adjusts the halting algorithm based on the user's past halting results. The halting unit can also learn specific patterns from the user's past halting results and improve halting accuracy. Furthermore, the halting unit can adjust the anomaly detection threshold by referring to the user's past halting results. This improves halting accuracy by referring to the user's past halting results. Some or all of the above-mentioned processing in the halting unit may be performed using, for example, AI, or may be performed without using AI. For example, the halting unit can input the user's past halting result data into the generation AI and cause the generation AI to improve halting accuracy.

[0068] When halting trading, the halting unit can determine the priority of halting based on the time of transaction occurrence. For example, the halting unit can prioritize halting transactions that occur late at night. The halting unit can also prioritize halting transactions that occur multiple times in a short period of time. The halting unit can also prioritize halting transactions that occur on specific days of the week or during specific time periods. In this way, by determining the priority of halting based on the time of transaction occurrence, important transactions can be halted preferentially. Some or all of the above-mentioned processing in the halting unit may be performed using, or without, AI. For example, the halting unit can input transaction data into a generation AI and have the generation AI determine the priority of halting.

[0069] When halting transactions, the halting unit can adjust the order of halting transactions based on the relevance of the transactions. For example, the halting unit groups related transactions and halts them in an orderly manner. The halting unit can also prioritize halting highly related transactions. The halting unit can also halt less related transactions later. This allows for efficient halting of transactions by adjusting the order of halting transactions based on the relevance of the transactions. Some or all of the above-described processing in the halting unit may be performed using, or without, AI. For example, the halting unit can input transaction data into a generating AI and have the generating AI adjust the order of halting transactions.

[0070] When halting trading, the halting unit can adjust the use of halting terminology depending on the user's level of expertise. For example, if the user has expertise, the halting unit can use detailed terminology. Alternatively, if the user does not have expertise, the halting unit can explain the halting procedure in simple terms. The halting unit can also adjust the way the halting procedure is expressed depending on the user's level of expertise. This allows for adjusting the use of halting terminology depending on the user's level of expertise, thereby providing a halting procedure that is easy for the user to understand. Some or all of the above-described processing in the halting unit may be performed using AI, for example, or may be performed without using AI. For example, the halting unit can input the user's expertise level data into the generating AI and cause the generating AI to use halting terminology.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The collection unit can adjust the frequency of collecting transaction data taking into account the remaining battery level of the user's device. For example, when the battery level is low, the collection unit reduces the frequency of data collection to reduce battery consumption. When the battery level is sufficient, the collection unit can collect data at a normal frequency. Furthermore, when the battery level is very high, the collection unit can increase the frequency of data collection to collect more detailed data. This enables efficient data collection according to the battery status of the device.

[0073] When analyzing transaction data, the analysis unit can adjust the analysis algorithm by taking into account the user's past behavioral patterns. For example, it can set an anomaly detection threshold based on the user's frequent past transaction patterns. It can also prioritize analysis of transactions that occurred during specific time periods or locations based on the user's past behavioral patterns. It can also learn the user's past behavioral patterns and optimize the analysis algorithm. This improves the accuracy of analysis by taking into account the user's past behavioral patterns.

[0074] When collecting transaction data, the collection unit can adjust the collection method taking into account the user's internet connection status. For example, if the internet connection is unstable, the collection unit can reduce the frequency of data collection and wait until the connection stabilizes. Alternatively, if the internet connection is stable, the collection unit can collect data at a normal frequency. Furthermore, if a high-speed internet connection is available, the collection unit can increase the frequency of data collection and collect more detailed data. This allows for efficient data collection depending on the internet connection status.

[0075] When collecting transaction data, the collection unit can adjust the collection method taking into account the security status of the user's device. For example, if the device security is low, the collection unit can reduce the frequency of data collection and wait until security improves. Alternatively, if the device security is high, the collection unit can collect data at a normal frequency. Furthermore, if the device security is very high, the collection unit can increase the frequency of data collection and collect more detailed data. This enables efficient data collection according to the device security status.

[0076] When analyzing transaction data, the analysis unit can adjust the analysis algorithm by taking into account the user's past feedback. For example, the analysis algorithm can be optimized based on feedback provided by the user in the past. The analysis method for a specific transaction pattern can also be adjusted based on the user's past feedback. Furthermore, the analysis algorithm can be improved by learning from the user's past feedback. In this way, the accuracy of the analysis can be improved by taking into account the user's past feedback.

[0077] The processing flow of the first embodiment will be briefly explained below.

[0078] Step 1: The collection unit collects transaction data. This data includes financial transaction data and e-commerce transaction data. The collection unit collects detailed data such as the date, time, location, and amount of the transaction, and analyzes the user's past transaction history to select the optimal collection method. Step 2: The analysis unit uses AI to analyze the data collected by the collection unit. The analysis unit detects anomalies such as high-value transactions that differ from normal transaction patterns, multiple transactions in a short period of time, transactions in locations other than normal trading areas, and transactions during late night hours. Past fraud cases can also be included as learning data. Step 3: The detection unit detects anomalies based on the data analyzed by the analysis unit. The detection unit can improve the accuracy of anomaly detection by taking into account the interrelationships between transactions and can weight anomaly detection based on the frequency of transaction occurrence. Step 4: The warning unit issues a warning when the detection unit detects an abnormality. The warning unit can estimate the user's emotions, adjust the warning display method based on the estimated user emotions, and adjust the level of detail of the warning based on the importance of the transaction. Step 5: The notification unit asks the user for confirmation when the warning unit issues a warning. The notification unit asks the user for confirmation by any of a phone call, email, or app notification, estimates the user's emotions, and can adjust the notification display method based on the estimated user emotions. Step 6: The halting unit suspends the transaction if the notification unit cannot obtain user confirmation. The halting unit can estimate the user's sentiment, adjust the timing of halting the transaction based on the estimated user's sentiment, and adjust the level of detail of the halt based on the importance of the transaction.

[0079] (Example 2) A tool according to an embodiment of the present invention is a system for detecting and guarding against cash card fraud. This system collects transaction data, analyzes it using AI, and detects abnormal transaction patterns. If an abnormality is detected, it immediately issues a warning and suspends the transaction. Furthermore, it sends a notification to the user requesting confirmation and determines whether to resume the transaction after the user confirms. For example, the system collects detailed data on cash card usage history and transaction data, such as the date, time, location, and amount of the transaction. The collected data is then analyzed using AI. The AI ​​detects abnormal transactions that deviate from normal transaction patterns, such as high-value transactions, multiple transactions in a short period of time, transactions in a location other than the usual transaction area, or transactions occurring late at night. If an abnormality is detected, it immediately issues a warning and suspends the transaction. Furthermore, it sends a notification to the user requesting confirmation. Multiple notification methods are available, including phone, email, and app notifications. The system determines whether to resume the transaction after the user confirms. If the user's confirmation cannot be obtained, it takes measures such as suspending the transaction for a certain period of time. This allows the system to detect cash card fraud early and minimize damage. This allows the system to detect cash card fraud early and minimize damage. For example, the system collects detailed cash card usage history and transaction data and uses AI to analyze it to detect abnormal transaction patterns. If an abnormality is detected, it immediately issues a warning and suspends the transaction. It also sends a notification to the user requesting confirmation, and after the user confirms, it decides whether to resume the transaction. This allows the system to detect cash card fraud early and minimize damage.

[0080] A cash card fraud detection system according to an embodiment includes a collection unit, an analysis unit, a detection unit, a warning unit, a notification unit, and a stopping unit. The collection unit collects transaction data. The transaction data includes, but is not limited to, financial transaction data and e-commerce transaction data. The collection unit collects detailed data, such as transaction date, time, location, and amount. The collection unit can also analyze a user's past transaction history and select an optimal collection method. For example, the collection unit selects an optimal collection method based on the user's frequent transaction patterns in the past. The analysis unit uses AI to analyze the data collected by the collection unit. The analysis unit detects, for example, high-value transactions that differ from normal transaction patterns or multiple transactions in a short period of time as anomalies. The analysis unit can also detect, as anomalies, transactions in locations other than normal transaction areas or transactions occurring late at night. Furthermore, the analysis unit can include past fraud cases as training data. The detection unit detects anomalies based on the data analyzed by the analysis unit. The detection unit can improve the accuracy of anomaly detection by, for example, taking into account the correlation between transactions. The detection unit can also weight anomaly detection based on the frequency of transaction occurrence. The warning unit issues a warning when an anomaly is detected by the detection unit. The warning unit, for example, estimates a user's emotion and adjusts the display method of the warning based on the estimated user's emotion. The warning unit can also adjust the level of detail of the warning based on the importance of the transaction. The notification unit requests confirmation from the user when the warning unit issues a warning. The notification unit requests confirmation from the user by means of, for example, telephone, email, or app notification. The notification unit can also estimate a user's emotion and adjust the display method of the notification based on the estimated user's emotion. The stopping unit temporarily suspends the transaction when the notification unit cannot obtain user confirmation. The stopping unit, for example, estimates a user's emotion and adjusts the timing of suspending the transaction based on the estimated user's emotion. The stopping unit can also adjust the level of detail of the suspension based on the importance of the transaction. As a result, the cash card fraud detection system according to the embodiment can detect cash card fraud early and minimize damage.

[0081] The analysis unit can detect transactions above a specific amount that differ from normal transaction patterns or multiple transactions within a specific period as abnormal. For example, the analysis unit detects transactions above a specific amount as abnormal. For example, the analysis unit detects transactions above 1 million yen as abnormal. The analysis unit can also detect multiple transactions within a specific period as abnormal. For example, the analysis unit can detect multiple transactions within a 24-hour period as abnormal. The analysis unit can also detect multiple transactions within a week as abnormal. This enables early detection of fraud by detecting high-value transactions or multiple transactions within a short period as abnormal. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input transaction data into a generation AI and have the generation AI detect abnormal transactions.

[0082] The analysis unit can detect transactions in locations different from the usual trading area or late-night transactions as abnormal. For example, the analysis unit detects transactions in locations different from the usual trading area as abnormal. For example, the analysis unit detects transactions in locations different from the user's residence as abnormal. The analysis unit can also detect transactions in locations different from previous trading areas as abnormal. Furthermore, the analysis unit can detect transactions in late-night hours as abnormal. For example, the analysis unit detects transactions between 11:00 PM and 5:00 AM as abnormal. This enables early detection of fraud by detecting transactions in locations different from the usual trading area or late-night transactions as abnormal. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data into a generation AI and have the generation AI detect abnormal transactions.

[0083] The notification unit can request confirmation from the user by any of the following means: telephone, email, or app notification. The notification unit, for example, requests confirmation from the user by telephone. For example, the notification unit can request confirmation from the user using an automated voice call. The notification unit can also request confirmation from the user by email. For example, the notification unit can send an email containing transaction details and request confirmation from the user. The notification unit can also request confirmation from the user by app notification. For example, the notification unit can send a notification to the user through a smartphone app and request confirmation. This allows for a quick response by requesting confirmation from the user through multiple means. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can estimate the user's emotions and adjust the notification display method based on the estimated user emotions.

[0084] The halting unit can halt trading for a certain period of time if user confirmation cannot be obtained. For example, the halting unit halts trading for 30 minutes if user confirmation cannot be obtained. For example, the halting unit can halt trading for one hour if user confirmation cannot be obtained. The halting unit can also halt trading for 24 hours if user confirmation cannot be obtained. This prevents fraud by halting trading if user confirmation cannot be obtained. Some or all of the above-mentioned processing in the halting unit may be performed using AI, for example, or may be performed without using AI. For example, the halting unit can estimate the user's emotions and adjust the timing of halting trading based on the estimated user's emotions.

[0085] The analysis unit can include past fraud cases as training data. The analysis unit, for example, includes past fraud cases as training data. For example, the analysis unit includes past fraud methods as training data. The analysis unit can also include the amount of damage caused by past frauds as training data. Furthermore, the analysis unit can also include the locations where past frauds occurred as training data. By including past fraud cases as training data, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past fraud cases into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0086] The collection unit can estimate the user's emotions and adjust the timing of collecting transaction data based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can collect transaction data more frequently to detect abnormalities early. Furthermore, if the user is relaxed, the collection unit can set the frequency of collecting transaction data lower than usual. Furthermore, if the user is in a hurry, the collection unit can quickly collect transaction data and immediately send it for analysis. By adjusting the collection timing based on the user's emotions, abnormalities can be detected early. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, an AI, or without an AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI adjust the collection timing.

[0087] When collecting transaction data, the collection unit can analyze the user's past transaction history and select the optimal collection method. The collection unit selects the optimal collection method based on, for example, the user's frequent transaction patterns in the past. The collection unit can also identify time periods during which abnormalities are likely to occur from the user's past transaction history and focus data collection on those time periods. Furthermore, the collection unit can analyze the user's past transaction history and select a collection method according to a specific transaction method (ATM, online banking, etc.). In this way, the optimal collection method can be selected by analyzing the user's past transaction history. Some or all of the above-described processing in the collection unit may be performed, for example, using AI or without AI. For example, the collection unit can input the user's past transaction history data into the generation AI and have the generation AI select the optimal collection method.

[0088] When collecting transaction data, the collection unit can select a collection method depending on the type of transaction. For example, in the case of online transactions, the collection unit collects internet banking log data. In the case of offline transactions, the collection unit can also collect ATM usage history. Furthermore, in the case of a user who conducts both online and offline transactions, the collection unit can also collect integrated data from both. This enables efficient data collection by selecting a collection method depending on the type of transaction. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input transaction data to a generation AI and have the generation AI select a collection method.

[0089] When collecting transaction data, the collection unit can adjust the collection range taking into account the user's current geographical location information. For example, if the user is in a specific area, the collection unit can focus on collecting transaction data in that area. Also, if the user is traveling, the collection unit can collect transaction data at the user's travel destination. Furthermore, if the user is at home, the collection unit can collect transaction data around the user's home. This enables appropriate data collection by taking the user's geographical location information into account. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to adjust the collection range.

[0090] The collection unit can estimate the user's emotions and determine the priority of the transaction data to be collected based on the estimated user emotions. For example, if the user is feeling anxious, the collection unit can prioritize collecting high-value transaction data. Furthermore, if the user is relaxed, the collection unit can prioritize collecting normal transaction data. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting transaction data that has been performed multiple times in a short period of time. This allows important data to be collected preferentially by prioritizing the collected data based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, an AI, or without an AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of the collected data.

[0091] When collecting transaction data, the collection unit can analyze the user's social media activities and collect related transaction data. For example, the collection unit collects transaction data from locations where the user has checked in on social media. The collection unit can also analyze the content of the user's social media posts and collect related transaction data. Furthermore, the collection unit can collect related transaction data by referring to the activities of the user's friends on social media. In this way, related transaction data can be efficiently collected by analyzing the user's social media activities. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's social media data into a generation AI and cause the generation AI to collect related transaction data.

[0092] When collecting transaction data, the collection unit can customize the collection method by reflecting the user's past feedback. The collection unit customizes the collection method, for example, based on feedback provided by the user in the past. The collection unit can also adjust the collection method for a specific transaction instrument based on the user's past feedback. Furthermore, the collection unit can also adjust the collection frequency and timing by reflecting the user's past feedback. In this way, the collection method can be optimized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the collection method.

[0093] When collecting transaction data, the collection unit can select the optimal collection means by taking into account the user's device information. For example, if the user uses a smartphone, the collection unit collects smartphone transaction data. Furthermore, if the user uses a tablet, the collection unit can also collect tablet transaction data. Furthermore, if the user uses a personal computer, the collection unit can also collect personal computer transaction data. This allows the optimal collection means to be selected by taking into account the user's device information. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's device information into the generation AI and cause the generation AI to select the optimal collection means.

[0094] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis based on the estimated user's emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible analysis result. Furthermore, if the user is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the user is in a hurry, the analysis unit can provide a summary analysis result. By adjusting the presentation method of the analysis based on the user's emotions, it is possible to provide an analysis result that is easy for the user to understand. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the presentation method of the analysis.

[0095] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the transaction. For example, the analysis unit performs a detailed analysis in the case of a high-value transaction. The analysis unit can also perform a simplified analysis in the case of a normal transaction. The analysis unit can also perform a detailed analysis in the case of a transaction suspected of being abnormal. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the transaction. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data to a generation AI and have the generation AI adjust the level of detail of the analysis.

[0096] During analysis, the analysis unit can apply different analysis algorithms depending on the transaction category. For example, in the case of an online transaction, the analysis unit applies a specific analysis algorithm. In addition, in the case of an offline transaction, the analysis unit can also apply a different analysis algorithm. Furthermore, in the case of an ATM transaction, the analysis unit can apply an even different analysis algorithm. In this way, by applying different analysis algorithms depending on the transaction category, highly accurate analysis is possible. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data to a generation AI and have the generation AI apply the analysis algorithm.

[0097] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also learn specific patterns from the user's past analysis results and improve the analysis accuracy. Furthermore, the analysis unit can adjust the anomaly detection threshold by referring to the user's past analysis results. This improves the accuracy of the analysis by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0098] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can perform a short, concise analysis. If the user is relaxed, the analysis unit can also perform a detailed analysis. If the user is excited, the analysis unit can also provide a visually stimulating analysis result. By adjusting the length of the analysis based on the user's emotions, an analysis result of an appropriate length for the user can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the analysis.

[0099] During analysis, the analysis unit can determine the priority of analysis based on the time of transaction occurrence. For example, the analysis unit prioritizes analysis of transactions made during late night hours. The analysis unit can also prioritize analysis of transactions made multiple times in a short period of time. The analysis unit can also prioritize analysis of transactions made on specific days of the week or during specific time periods. In this way, by determining the priority of analysis based on the time of transaction occurrence, important transactions can be analyzed preferentially. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data into a generation AI and have the generation AI determine the analysis priority.

[0100] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the transactions. For example, the analysis unit groups related transactions and analyzes them in order. The analysis unit can also prioritize analysis of highly related transactions. The analysis unit can also postpone analysis of less related transactions. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the transactions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input transaction data into a generation AI and have the generation AI adjust the order of analysis.

[0101] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can use detailed technical terminology. Furthermore, if the user does not have technical expertise, the analysis unit can explain the analysis results in simple terms. Furthermore, the analysis unit can adjust the way the analysis results are presented according to the user's level of expertise. By adjusting the use of technical terminology in the analysis according to the user's level of expertise, analysis results that are easy for the user to understand can be provided. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise data into the generation AI and have the generation AI use technical terminology in the analysis.

[0102] The detection unit can estimate the user's emotions and adjust the anomaly detection criteria based on the estimated user emotions. For example, if the user is feeling anxious, the detection unit can set the anomaly detection criteria to be strict. Furthermore, if the user is relaxed, the detection unit can also set the anomaly detection criteria to be normal. Furthermore, if the user is in a hurry, the detection unit can also quickly set the anomaly detection criteria. This enables more appropriate anomaly detection by adjusting the anomaly detection criteria based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can input the user's emotion data into the generation AI and have the generation AI adjust the anomaly detection criteria.

[0103] The detection unit can improve the accuracy of anomaly detection by taking into account the interrelationships between transactions during detection. For example, the detection unit groups related transactions and detects anomalies by taking into account the interrelationships. The detection unit can also analyze the interrelationships between transactions to improve the accuracy of anomaly detection. The detection unit can also adjust the anomaly detection threshold by taking into account the interrelationships between transactions. This improves the accuracy of anomaly detection by taking into account the interrelationships between transactions. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input transaction data to a generation AI and have the generation AI improve the accuracy of anomaly detection.

[0104] The detection unit can weight anomaly detection based on the frequency of transactions during detection. For example, the detection unit can assign a higher weight to anomaly detection for transactions that occur multiple times in a short period of time. The detection unit can also assign a lower weight to anomaly detection for transactions that occur over a long period of time. The detection unit can also adjust the weight to anomaly detection for transactions that occur during a specific time period. In this way, weighting anomaly detection based on the frequency of transactions allows for priority detection of important anomalies. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input transaction data to a generation AI and have the generation AI perform anomaly detection weighting.

[0105] The detection unit can adjust the anomaly detection criteria based on the location of the transaction at the time of detection. For example, the detection unit can set stricter anomaly detection criteria for transactions in locations different from normal transaction areas. The detection unit can also set normal anomaly detection criteria for transactions in normal transaction areas. The detection unit can also adjust the anomaly detection criteria for transactions in specific regions. This allows for appropriate anomaly detection by adjusting the anomaly detection criteria based on the location of the transaction. Some or all of the above-described processing in the detection unit can be performed using, for example, AI, or can be performed without using AI. For example, the detection unit can input transaction data to a generation AI and have the generation AI adjust the anomaly detection criteria.

[0106] The detection unit can estimate the user's emotions and adjust the order in which the anomaly detection results are displayed based on the estimated user's emotions. For example, if the user is feeling anxious, the detection unit can display the most important anomaly detection results first. Alternatively, if the user is relaxed, the detection unit can display the anomaly detection results in the normal order. Alternatively, if the user is in a hurry, the detection unit can display the anomaly detection results that highlight the main points first. By adjusting the order in which the anomaly detection results are displayed based on the user's emotions, important information can be provided to the user preferentially. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit can be performed using, for example, an AI, or without an AI. For example, the detection unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the display order of the anomaly detection results.

[0107] The detection unit can detect anomalies by taking into account the geographic distribution of transactions. For example, the detection unit detects transactions in locations different from normal transaction areas as anomalies. The detection unit can also prioritize detection of transactions in specific regions. The detection unit can also improve the accuracy of anomaly detection by taking into account the geographic distribution. This improves the accuracy of anomaly detection by taking into account the geographic distribution of transactions. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input transaction data into a generation AI and have the generation AI improve the accuracy of anomaly detection.

[0108] The detection unit can improve the accuracy of anomaly detection by referring to literature related to the transaction during detection. The detection unit, for example, refers to the relevant literature and adjusts the anomaly detection algorithm. The detection unit can also improve the accuracy of anomaly detection based on knowledge obtained from the relevant literature. The detection unit can also adjust the anomaly detection threshold by referring to the relevant literature. In this way, the accuracy of anomaly detection is improved by referring to literature related to the transaction. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input related literature data into the generation AI and cause the generation AI to improve the accuracy of anomaly detection.

[0109] The detection unit can detect anomalies by taking into account the market value of the transaction. For example, the detection unit can set stricter anomaly detection standards for high-value transactions. The detection unit can also set looser anomaly detection standards for transactions with low market value. The detection unit can also adjust the weighting of anomaly detection by taking into account the market value. This allows for priority detection of important anomalies by taking into account the market value of the transaction. Some or all of the above-mentioned processing in the detection unit can be performed using, for example, AI, or can be performed without using AI. For example, the detection unit can input transaction data to a generation AI and have the generation AI adjust the anomaly detection standards.

[0110] The warning unit can estimate the user's emotions and adjust the warning display method based on the estimated user emotions. For example, if the user is nervous, the warning unit can display a simple, highly visible warning. Furthermore, if the user is relaxed, the warning unit can display a detailed warning. Furthermore, if the user is in a hurry, the warning unit can display a warning that focuses on the main points. By adjusting the warning display method based on the user's emotions, it is possible to provide a warning that is easy for the user to understand. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the warning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the warning unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the warning display method.

[0111] When issuing a warning, the warning unit can adjust the level of detail of the warning based on the importance of the transaction. For example, in the case of a high-value transaction, the warning unit displays a detailed warning. In addition, the warning unit can also display a simplified warning in the case of a normal transaction. In addition, the warning unit can also display a detailed warning in the case of a transaction suspected of being abnormal. In this way, by adjusting the level of detail of the warning based on the importance of the transaction, it is possible to provide an appropriate warning for important transactions. Some or all of the above-mentioned processing in the warning unit may be performed, for example, using AI, or may be performed without using AI. For example, the warning unit can input transaction data to a generation AI and have the generation AI adjust the level of detail of the warning.

[0112] When issuing a warning, the warning unit can apply different warning algorithms depending on the category of the transaction. For example, the warning unit applies a specific warning algorithm in the case of an online transaction. The warning unit can also apply a different warning algorithm in the case of an offline transaction. Furthermore, the warning unit can apply an even different warning algorithm in the case of an ATM transaction. This allows for highly accurate warnings by applying different warning algorithms depending on the category of the transaction. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input transaction data to a generation AI and have the generation AI apply a warning algorithm.

[0113] When issuing a warning, the warning unit can improve the accuracy of the warning by referring to the user's past warning results. The warning unit, for example, adjusts the warning algorithm based on the user's past warning results. The warning unit can also learn specific patterns from the user's past warning results and improve the accuracy of the warning. Furthermore, the warning unit can adjust the anomaly detection threshold by referring to the user's past warning results. In this way, the accuracy of the warning is improved by referring to the user's past warning results. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the user's past warning result data into the generation AI and cause the generation AI to improve the accuracy of the warning.

[0114] The warning unit can estimate the user's emotions and adjust the length of the warning based on the estimated user emotions. For example, if the user is in a hurry, the warning unit can display a short and to-the-point warning. The warning unit can also display a detailed warning if the user is relaxed. The warning unit can also display a visually stimulating warning if the user is excited. By adjusting the length of the warning based on the user's emotions, a warning of an appropriate length can be provided to the user. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the warning unit can be performed using, for example, AI, or without AI. For example, the warning unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the warning.

[0115] When issuing a warning, the warning unit can determine the priority of the warning based on the time of transaction occurrence. For example, the warning unit can prioritize warnings for transactions that occur late at night. The warning unit can also prioritize warnings for transactions that occur multiple times in a short period of time. The warning unit can also prioritize warnings for transactions that occur on specific days of the week or during specific time periods. In this way, by determining the priority of warnings based on the time of transaction occurrence, warnings can be given priority for important transactions. Some or all of the above-mentioned processing in the warning unit may be performed using, or without, AI. For example, the warning unit can input transaction data into a generation AI and have the generation AI determine the priority of warnings.

[0116] When issuing a warning, the warning unit can adjust the order of warnings based on the relevance of the transactions. For example, the warning unit groups related transactions and displays warnings in an orderly manner. The warning unit can also prioritize highly related transactions. The warning unit can also postpone warnings for less related transactions. This allows for efficient warnings by adjusting the order of warnings based on the relevance of the transactions. Some or all of the above-described processing in the warning unit may be performed using, or without, AI. For example, the warning unit can input transaction data into a generation AI and have the generation AI adjust the order of warnings.

[0117] When issuing a warning, the warning unit can adjust the use of technical terminology in the warning depending on the user's level of expertise. For example, if the user has technical expertise, the warning unit can use detailed technical terminology. If the user does not have technical expertise, the warning unit can also explain the warning in simple terms. The warning unit can also adjust the way the warning is expressed depending on the user's level of expertise. This makes it possible to provide a warning that is easy for the user to understand by adjusting the use of technical terminology in the warning depending on the user's level of expertise. Some or all of the above-mentioned processing in the warning unit may be performed using AI, for example, or may be performed without using AI. For example, the warning unit can input the user's level of expertise data into the generation AI and have the generation AI use technical terminology in the warning.

[0118] The notification unit can estimate the user's emotions and adjust the notification display method based on the estimated user emotions. For example, if the user is nervous, the notification unit can display a simple, highly visible notification. Furthermore, if the user is relaxed, the notification unit can also display a detailed notification. Furthermore, if the user is in a hurry, the notification unit can also display a notification that focuses on the main points. By adjusting the notification display method based on the user's emotions, notifications that are easy for the user to understand can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the notification unit can be performed using, for example, AI, or without AI. For example, the notification unit can input the user's emotion data into the generation AI and have the generation AI adjust the notification display method.

[0119] The notification unit can adjust the level of detail of the notification based on the importance of the transaction when making a notification. For example, in the case of a high-value transaction, the notification unit displays a detailed notification. The notification unit can also display a simplified notification for a normal transaction. The notification unit can also display a detailed notification for a transaction suspected of being abnormal. In this way, by adjusting the level of detail of the notification based on the importance of the transaction, appropriate notifications can be provided for important transactions. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input transaction data to a generation AI and have the generation AI adjust the level of detail of the notification.

[0120] The notification unit can apply different notification algorithms depending on the transaction category when notifying. For example, the notification unit applies a specific notification algorithm in the case of an online transaction. The notification unit can also apply a different notification algorithm in the case of an offline transaction. Furthermore, the notification unit can apply an even different notification algorithm in the case of an ATM transaction. This enables highly accurate notifications by applying different notification algorithms depending on the transaction category. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input transaction data to a generation AI and have the generation AI apply the notification algorithm.

[0121] The notification unit can improve the accuracy of notifications by referring to the user's past notification results when sending notifications. The notification unit, for example, adjusts the notification algorithm based on the user's past notification results. The notification unit can also improve the accuracy of notifications by learning specific patterns from the user's past notification results. Furthermore, the notification unit can also adjust the anomaly detection threshold by referring to the user's past notification results. This improves the accuracy of notifications by referring to the user's past notification results. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's past notification result data into the generation AI and cause the generation AI to improve the accuracy of notifications.

[0122] The notification unit can estimate the user's emotions and adjust the length of the notification based on the estimated user's emotions. For example, if the user is in a hurry, the notification unit can display a short and to-the-point notification. The notification unit can also display a detailed notification if the user is relaxed. The notification unit can also display a visually stimulating notification if the user is excited. By adjusting the length of the notification based on the user's emotions, it is possible to provide notifications of an appropriate length for the user. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the notification unit can be performed using, for example, an AI, or without an AI. For example, the notification unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the notification.

[0123] The notification unit can determine the priority of notifications based on the time of transaction occurrence when issuing notifications. For example, the notification unit can prioritize displaying notifications for transactions that occurred late at night. The notification unit can also prioritize displaying notifications for transactions that occurred multiple times in a short period of time. The notification unit can also prioritize displaying notifications for transactions that occurred on a specific day of the week or during a specific time period. In this way, by determining the priority of notifications based on the time of transaction occurrence, notifications can be provided preferentially for important transactions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input transaction data into a generation AI and have the generation AI determine the priority of notifications.

[0124] The notification unit can adjust the order of notifications based on the relevance of the transactions when notifying. For example, the notification unit groups related transactions and displays the notifications in an orderly manner. The notification unit can also prioritize notifications of highly related transactions. The notification unit can also postpone notifications of less related transactions. This allows for efficient notifications by adjusting the order of notifications based on the relevance of the transactions. Some or all of the above-described processing in the notification unit may be performed using, or without, AI, for example. For example, the notification unit can input transaction data into a generation AI and have the generation AI adjust the order of notifications.

[0125] The notification unit can adjust the use of technical terminology in the notification according to the user's level of expertise when providing a notification. For example, if the user has technical expertise, the notification unit can use detailed technical terminology. If the user does not have technical expertise, the notification unit can also explain the notification in simple terms. The notification unit can also adjust the way the notification is expressed according to the user's level of expertise. This allows the notification to be provided in a way that is easy for the user to understand by adjusting the use of technical terminology in the notification according to the user's level of expertise. Some or all of the above-described processing in the notification unit can be performed using AI, for example, or without AI. For example, the notification unit can input the user's level of expertise data into a generation AI and have the generation AI use technical terminology in the notification.

[0126] The halting unit can estimate the user's emotions and adjust the timing of halting trading based on the estimated user emotions. For example, the halting unit can immediately halt trading if the user is feeling anxious. The halting unit can also halt trading at a normal timing if the user is relaxed. The halting unit can also quickly halt trading if the user is in a hurry. By adjusting the timing of halting trading based on the user's emotions, trading can be halted at an appropriate timing. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the halting unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the halting unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the timing of halting trading.

[0127] When halting a transaction, the halting unit can adjust the level of detail of the halt based on the importance of the transaction. For example, the halting unit performs detailed halt procedures for high-value transactions. The halting unit can also perform simplified halt procedures for normal transactions. The halting unit can also perform detailed halt procedures for transactions suspected of being abnormal. In this way, by adjusting the level of detail of the halt based on the importance of the transaction, appropriate halt procedures can be performed for important transactions. Some or all of the above-mentioned processing in the halting unit may be performed using AI, for example, or may be performed without using AI. For example, the halting unit can input transaction data into a generating AI and have the generating AI adjust the level of detail of the halt.

[0128] When halting a transaction, the halting unit can apply different halting algorithms depending on the category of the transaction. For example, in the case of an online transaction, the halting unit applies a specific halting algorithm. In addition, in the case of an offline transaction, the halting unit can also apply a different halting algorithm. Furthermore, in the case of an ATM transaction, the halting unit can apply an even different halting algorithm. In this way, applying different halting algorithms depending on the category of the transaction enables highly accurate halting. Some or all of the above-mentioned processing in the halting unit may be performed using, for example, AI, or may be performed without using AI. For example, the halting unit can input transaction data to a generation AI and cause the generation AI to apply a halting algorithm.

[0129] When halting trading, the halting unit can improve the accuracy of halting by referring to the user's past halting results. The halting unit, for example, adjusts the halting algorithm based on the user's past halting results. The halting unit can also learn specific patterns from the user's past halting results and improve halting accuracy. Furthermore, the halting unit can adjust the anomaly detection threshold by referring to the user's past halting results. This improves halting accuracy by referring to the user's past halting results. Some or all of the above-mentioned processing in the halting unit may be performed using, for example, AI, or may be performed without using AI. For example, the halting unit can input the user's past halting result data into the generation AI and cause the generation AI to improve halting accuracy.

[0130] The halting unit can estimate the user's emotions and adjust the length of the trading halt based on the estimated user emotions. For example, if the user is in a hurry, the halting unit can resume trading in a short time. The halting unit can also set a normal halt time if the user is relaxed. The halting unit can also set a longer halt time if the user is feeling anxious. This allows for an appropriate length of trading halt by adjusting the length of the trading halt based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the halting unit can be performed using AI, for example, or without AI. For example, the halting unit can input user emotion data into the generation AI and cause the generation AI to adjust the length of the trading halt.

[0131] When halting trading, the halting unit can determine the priority of halting based on the time of transaction occurrence. For example, the halting unit can prioritize halting transactions that occur late at night. The halting unit can also prioritize halting transactions that occur multiple times in a short period of time. The halting unit can also prioritize halting transactions that occur on specific days of the week or during specific time periods. In this way, by determining the priority of halting based on the time of transaction occurrence, important transactions can be halted preferentially. Some or all of the above-mentioned processing in the halting unit may be performed using, or without, AI. For example, the halting unit can input transaction data into a generation AI and have the generation AI determine the priority of halting.

[0132] When halting transactions, the halting unit can adjust the order of halting transactions based on the relevance of the transactions. For example, the halting unit groups related transactions and halts them in an orderly manner. The halting unit can also prioritize halting highly related transactions. The halting unit can also halt less related transactions later. This allows for efficient halting of transactions by adjusting the order of halting transactions based on the relevance of the transactions. Some or all of the above-described processing in the halting unit may be performed using, or without, AI. For example, the halting unit can input transaction data into a generating AI and have the generating AI adjust the order of halting transactions.

[0133] When halting trading, the halting unit can adjust the use of halting terminology depending on the user's level of expertise. For example, if the user has expertise, the halting unit can use detailed terminology. Alternatively, if the user does not have expertise, the halting unit can explain the halting procedure in simple terms. The halting unit can also adjust the way the halting procedure is expressed depending on the user's level of expertise. This allows for adjusting the use of halting terminology depending on the user's level of expertise, thereby providing a halting procedure that is easy for the user to understand. Some or all of the above-described processing in the halting unit may be performed using AI, for example, or may be performed without using AI. For example, the halting unit can input the user's expertise level data into the generating AI and cause the generating AI to use halting terminology. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, detection unit, warning unit, notification unit, and stopping unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by the computer 36 of the smart device 14 and collects transaction data. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using AI. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects anomalies based on the analyzed data. The warning unit is realized by the control unit 46A of the smart device 14 and issues an alarm when an anomaly is detected. The notification unit is realized by the control unit 46A of the smart device 14 and sends a notification requesting user confirmation. The stopping unit is realized by the specific processing unit 290 of the data processing device 12 and suspends a transaction when user confirmation is not obtained. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, detection unit, warning unit, notification unit, and stopping unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the computer 36 of the smart glasses 214 and collects transaction data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects anomalies based on the analyzed data. The warning unit is realized, for example, by the control unit 46A of the smart glasses 214 and issues an alarm when an anomaly is detected. The notification unit is realized, for example, by the control unit 46A of the smart glasses 214 and sends a notification requesting confirmation from the user. The stopping unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suspends the transaction if user confirmation is not obtained. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, detection unit, warning unit, notification unit, and stopping unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit is realized by the computer 36 of the headset type terminal 314 and collects transaction data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects anomalies based on the analyzed data. The warning unit is realized, for example, by the control unit 46A of the headset type terminal 314 and issues an alarm when an anomaly is detected. The notification unit is realized, for example, by the control unit 46A of the headset type terminal 314 and sends a notification requesting confirmation from the user. The stopping unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suspends the transaction if user confirmation is not obtained. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, detection unit, warning unit, notification unit, and stopping unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by the computer 36 of the robot 414 and collects transaction data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects anomalies based on the analyzed data. The warning unit is realized, for example, by the control unit 46A of the robot 414 and issues an alarm when an anomaly is detected. The notification unit is realized, for example, by the control unit 46A of the robot 414 and sends a notification requesting confirmation from the user. The stopping unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suspends the transaction if user confirmation is not obtained.

[0134] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0135] The analysis unit can estimate the user's emotions and determine the priorities of analysis based on the estimated user emotions. For example, if the user is feeling anxious, the analysis unit will prioritize analyzing high-value transactions or transactions suspected of being abnormal. Also, if the user is relaxed, the analysis unit can prioritize analyzing normal transactions. Furthermore, if the user is in a hurry, the analysis unit can prioritize analyzing transactions that have been made multiple times in a short period of time. In this way, by determining the priorities of analysis based on the user's emotions, important transactions can be analyzed quickly.

[0136] The collection unit can adjust the frequency of collecting transaction data taking into account the remaining battery level of the user's device. For example, when the battery level is low, the collection unit reduces the frequency of data collection to reduce battery consumption. When the battery level is sufficient, the collection unit can collect data at a normal frequency. Furthermore, when the battery level is very high, the collection unit can increase the frequency of data collection to collect more detailed data. This enables efficient data collection according to the battery status of the device.

[0137] The notification unit can estimate the user's emotions and adjust the timing of notifications based on the estimated user emotions. For example, if the user is feeling stressed, the notification unit can delay notifications to reduce the user's burden. Also, if the user is relaxed, the notification unit can send notifications immediately. Furthermore, if the user is in a hurry, the notification unit can send important notifications with priority. In this way, by adjusting the timing of notifications based on the user's emotions, notifications can be provided at the optimal timing for the user.

[0138] When analyzing transaction data, the analysis unit can adjust the analysis algorithm by taking into account the user's past behavioral patterns. For example, it can set an anomaly detection threshold based on the user's frequent past transaction patterns. It can also prioritize analysis of transactions that occurred during specific time periods or locations based on the user's past behavioral patterns. It can also learn the user's past behavioral patterns and optimize the analysis algorithm. This improves the accuracy of analysis by taking into account the user's past behavioral patterns.

[0139] The halting unit can estimate the user's emotions and adjust the method of notifying the user of a trading halt based on the estimated user's emotions. For example, if the user feels anxious, the halting unit can send a notification including a detailed explanation. If the user feels relaxed, the halting unit can send a concise notification. Furthermore, if the user is in a hurry, the halting unit can send a notification that focuses on the main points. In this way, by adjusting the method of notifying the user of a trading halt based on the user's emotions, it is possible to provide a notification that is easy for the user to understand.

[0140] When collecting transaction data, the collection unit can adjust the collection method taking into account the user's internet connection status. For example, if the internet connection is unstable, the collection unit can reduce the frequency of data collection and wait until the connection stabilizes. Alternatively, if the internet connection is stable, the collection unit can collect data at a normal frequency. Furthermore, if a high-speed internet connection is available, the collection unit can increase the frequency of data collection and collect more detailed data. This allows for efficient data collection depending on the internet connection status.

[0141] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can display simple, highly visible results. If the user is relaxed, the analysis unit can display detailed analysis results. Furthermore, if the user is in a hurry, the analysis unit can display analysis results that are concise. In this way, by adjusting the display method of the analysis results based on the user's emotions, it is possible to provide results that are easy for the user to understand.

[0142] When collecting transaction data, the collection unit can adjust the collection method taking into account the security status of the user's device. For example, if the device security is low, the collection unit can reduce the frequency of data collection and wait until security improves. Alternatively, if the device security is high, the collection unit can collect data at a normal frequency. Furthermore, if the device security is very high, the collection unit can increase the frequency of data collection and collect more detailed data. This enables efficient data collection according to the device security status.

[0143] The notification unit can estimate the user's emotions and adjust the content of the notification based on the estimated user's emotions. For example, if the user is feeling anxious, the notification unit can send a notification with a detailed explanation. If the user is feeling relaxed, the notification unit can send a concise notification. Furthermore, if the user is in a hurry, the notification unit can send a notification that is brief. In this way, by adjusting the content of the notification based on the user's emotions, it is possible to provide notifications that are easy for the user to understand.

[0144] When analyzing transaction data, the analysis unit can adjust the analysis algorithm by taking into account the user's past feedback. For example, the analysis algorithm can be optimized based on feedback provided by the user in the past. The analysis method for a specific transaction pattern can also be adjusted based on the user's past feedback. Furthermore, the analysis algorithm can be improved by learning from the user's past feedback. In this way, the accuracy of the analysis can be improved by taking into account the user's past feedback.

[0145] The processing flow of the second embodiment will be briefly explained below.

[0146] Step 1: The collection unit collects transaction data. This data includes financial transaction data and e-commerce transaction data. The collection unit collects detailed data such as the date, time, location, and amount of the transaction, and analyzes the user's past transaction history to select the optimal collection method. Step 2: The analysis unit uses AI to analyze the data collected by the collection unit. The analysis unit detects anomalies such as high-value transactions that differ from normal transaction patterns, multiple transactions in a short period of time, transactions in locations other than normal trading areas, and transactions during late night hours. Past fraud cases can also be included as learning data. Step 3: The detection unit detects anomalies based on the data analyzed by the analysis unit. The detection unit can improve the accuracy of anomaly detection by taking into account the interrelationships between transactions and can weight anomaly detection based on the frequency of transaction occurrence. Step 4: The warning unit issues a warning when the detection unit detects an abnormality. The warning unit can estimate the user's emotions, adjust the warning display method based on the estimated user emotions, and adjust the level of detail of the warning based on the importance of the transaction. Step 5: The notification unit asks the user for confirmation when the warning unit issues a warning. The notification unit asks the user for confirmation by any of a phone call, email, or app notification, estimates the user's emotions, and can adjust the notification display method based on the estimated user emotions. Step 6: The halting unit suspends the transaction if the notification unit cannot obtain user confirmation. The halting unit can estimate the user's sentiment, adjust the timing of halting the transaction based on the estimated user's sentiment, and adjust the level of detail of the halt based on the importance of the transaction.

[0147] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0152] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0154] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0155] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0157] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0158] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0159] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0163] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0165] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0168] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0169] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0170] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0171] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0173] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0174] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0175] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0176] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0177] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0178] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0179] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0180] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0181] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0182] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0183] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0184] 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.

[0185] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0186] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0187] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0188] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0189] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0190] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0191] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0192] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0193] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0194] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0195] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0196] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0197] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0198] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0199] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0200] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0201] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0202] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0203] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0204] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0205] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0206] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0207] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0208] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0209] 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.

[0210] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0211] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0212] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0213] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0214] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0215] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0216] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0217] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0218] [Explanation of symbols]

[0219] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects transaction data; an analysis unit that analyzes the data collected by the collection unit; a detection unit that detects an abnormality based on the data analyzed by the analysis unit; a warning unit that issues a warning when an abnormality is detected by the detection unit; a notification unit that requests a user to confirm when a warning is issued by the warning unit; a suspending unit that suspends the transaction when the notification unit cannot obtain confirmation from the user; Equipped with A system characterized by:

2. The analysis unit Transactions above a certain amount that differ from normal transaction patterns or multiple transactions within a certain period are detected as anomalies.

2. The system of claim 1.

3. The analysis unit Detecting abnormalities in transactions occurring in locations other than normal trading areas or late-night transactions 2. The system of claim 1.

4. The notification unit Ask the user for confirmation via phone, email, or app notification 2. The system of claim 1.

5. The stop portion is If user confirmation cannot be obtained, trading will be suspended for a certain period of time.

2. The system of claim 1.

6. The analysis unit Include past fraud cases as training data 2. The system of claim 1.

7. The collecting unit Estimate user emotions and adjust the timing of collecting transaction data based on the estimated user emotions.

2. The system of claim 1.

8. The collecting unit When collecting transaction data, analyze the user's past transaction history and select the optimal collection method.

2. The system of claim 1.

Images