system

Abstract

The system according to this embodiment aims to appropriately identify the risk of violating the Labor Standards Act and to provide specific advice for compliance with the law. [Solution] The system according to the embodiment comprises a collection unit, an anonymization unit, a learning unit, an advice unit, a risk identification unit, and a caution point presentation unit. The collection unit collects records of violations of the Labor Standards Act. The anonymization unit anonymizes the records collected by the collection unit. The learning unit learns the data anonymized by the anonymization unit. The advice unit provides advice on legal compliance based on the data learned by the learning unit. The risk identification unit identifies risks of legal violations based on the advice provided by the advice unit. The caution point presentation unit presents caution points tailored to the industry, occupation, and office environment based on the risks identified by the risk identification unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to appropriately grasp the risk of violating the Labor Standards Act and provide specific advice for compliance with the law.

[0005] The system according to the embodiment aims to appropriately grasp the risk of violating the Labor Standards Act and provide specific advice for compliance with the law.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an anonymization unit, a learning unit, an advice unit, a risk identification unit, and a caution point presentation unit. The collection unit collects records of violations of the Labor Standards Act. The anonymization unit anonymizes the records collected by the collection unit. The learning unit learns from the data anonymized by the anonymization unit. The advice unit provides advice on legal compliance based on the data learned by the learning unit. The risk identification unit identifies risks of legal violations based on the advice provided by the advice unit. The caution point presentation unit presents caution points tailored to the industry, occupation, and office environment based on the risks identified by the risk identification unit. [Effects of the Invention]

[0007] The system according to this embodiment can appropriately identify the risk of violating the Labor Standards Act and provide specific advice for compliance with the law. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The compliance support system according to an embodiment of the present invention anonymizes records of violations of the Labor Standards Act, trains the LLM (Large-Scale Language Model) on them, and provides advice on legal compliance while also pointing out specific risks that may lead to legal violations. The compliance support system collects and anonymizes records of violations of the Labor Standards Act. Next, the anonymized data is trained on the LLM. The LLM learns from past violation records and provides specific advice for legal compliance. For example, it suggests specific areas for improvement, such as managing working hours and ensuring break times. Furthermore, the LLM also points out specific risks that may lead to legal violations. For example, it points out the risk of death from overwork and the risk of employee turnover due to deteriorating working conditions, and alerts companies to these risks. It also suggests points of caution tailored to the industry, job type, and office environment. For example, in the manufacturing industry, it suggests points of caution regarding the safety of machine operation, and in the IT industry, it points out the risk of long working hours. This allows each company to take specific measures according to its industry and job type. This system is particularly useful for small venture companies and SMEs. These companies often lack the resources to provide specific guidance to ensure legal compliance and the specialized knowledge needed to understand the law. This system allows companies to deepen their awareness and understanding of legal compliance and minimize legal risks. Furthermore, changes in the work environment (teleworking, diversity, etc.) have altered traditional labor laws, making it crucial to understand and apply new regulations and rules. This system addresses the latest labor laws and regulations, supporting companies in creating sustainable workplaces. Ultimately, this compliance support system enables companies to deepen their awareness and understanding of legal compliance and minimize legal risks.

[0029] The compliance support system according to the embodiment comprises a collection unit, an anonymization unit, a learning unit, an advice unit, a risk identification unit, and a point of caution presentation unit. The collection unit collects records of violations of the Labor Standards Act. For example, the collection unit collects records of violations of the Labor Standards Act from each company. The collection unit can collect records such as excessive working hours, unpaid wages, and insufficient rest periods. The collection unit can also automatically collect records of violations of the Labor Standards Act using AI, for example. The anonymization unit anonymizes the records collected by the collection unit. The anonymization unit performs tasks such as deleting personal information or masking data. The anonymization unit can also automatically anonymize data using AI, for example. The anonymization unit can also anonymize data by hiding parts of it, for example. The learning unit learns from the data anonymized by the anonymization unit. The learning unit learns from data using LLM, for example. The learning unit learns from past violation records and provides specific advice for compliance. The learning unit can, for example, learn patterns of labor law violations using LLM. The advice unit provides advice on legal compliance based on the data learned by the learning unit. The advice unit suggests specific areas for improvement, such as managing working hours and ensuring break times. The advice unit can also automatically provide advice on legal compliance using, for example, AI. The advice unit can also provide advice based on the articles of the Labor Standards Act. The risk identification unit identifies risks of legal violations based on the advice provided by the advice unit. The risk identification unit identifies risks such as the risk of death from overwork or the risk of employee turnover due to deteriorating working conditions. The risk identification unit can also automatically identify risks of legal violations using, for example, AI. The risk identification unit can also evaluate risks of labor law violations, for example. The caution point presentation unit presents caution points tailored to the industry, job type, and office environment based on the risks identified by the risk identification unit. The caution point presentation unit presents caution points regarding machine operation safety in the manufacturing industry, for example. The caution point presentation unit points out the risk of long working hours in the IT industry, for example. The section that displays points to note can, for example, use AI to automatically display points to note that are tailored to the industry or job type.The cautionary note display section can, for example, display cautionary notes tailored to the office environment. As a result, the compliance support system according to this embodiment can anonymize records of violations of the Labor Standards Act, train the system using LLM, provide advice on legal compliance, point out the risks of legal violations, and display cautionary notes tailored to the industry, occupation, and office environment.

[0030] The data collection unit collects records of violations of the Labor Standards Act. Specifically, it collects records of violations by each company, and can gather detailed data such as excessive working hours, unpaid wages, and insufficient rest periods. The data collection unit can also use AI to automatically collect records of violations of the Labor Standards Act, thereby enabling efficient and accurate data collection. For example, it can automatically retrieve information from internal company systems and publicly available databases, and record details such as the type, frequency, and scope of impact of violations. Furthermore, the data collection unit can centrally manage the collected data and link it with other departments and systems as needed. For example, the collected data can be stored on a cloud server and made accessible to the anonymization unit and the learning unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. As a result, the data collection unit can collect data efficiently and effectively, improving the overall performance of the system.

[0031] The anonymization unit anonymizes the records collected by the collection unit. Specifically, it protects privacy by deleting personal information and masking data. For example, it anonymizes data by deleting personal information such as employee names, addresses, and contact information, and by hiding parts of the data. The anonymization unit can also automatically anonymize data using AI, which allows for fast and accurate data processing. For example, it can use natural language processing technology to extract personal information from text data and automatically delete or mask it. The anonymization unit can also evaluate the quality of the anonymized data and re-anonymize it as needed. This allows the anonymization unit to securely manage the collected data, protect privacy, and improve the reliability of the entire system.

[0032] The learning unit learns from data anonymized by the anonymization unit. Specifically, it uses an LLM (Large-Scale Language Model) to learn from the data and provide specific advice for legal compliance. For example, it learns from past violation records to identify patterns of labor law violations and suggests specific areas for improvement for companies to comply with the law. The learning unit can also learn patterns of labor law violations using AI, enabling it to provide highly accurate advice. For example, it can analyze the frequency and scope of violations to identify risk factors in specific industries and occupations. Furthermore, the learning unit can utilize historical data and statistical information to perform long-term risk assessments and trend analyses. This allows the learning unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the reliability and security of the entire system.

[0033] The Advice Unit provides legal compliance advice based on data learned by the Learning Unit. Specifically, it suggests concrete areas for improvement, such as managing working hours and ensuring adequate rest periods. For example, it can identify specific items that companies must comply with based on the provisions of the Labor Standards Act and propose improvement measures. The Advice Unit can also automatically provide legal compliance advice using AI, enabling it to provide advice quickly and accurately. For example, it can integrate with a company's working hours management system to detect overwork in real time and propose appropriate actions. Furthermore, the Advice Unit can provide customized advice tailored to the characteristics and industry of each company. This allows the Advice Unit to provide concrete support to companies in complying with laws and improving their working environment.

[0034] The Risk Identification Department identifies risks of legal violations based on advice provided by the Advisory Department. Specifically, it identifies risks such as death from overwork and employee turnover due to deteriorating working conditions. For example, it points out that the risk of death from overwork increases if excessive working hours continue, and encourages appropriate action. The Risk Identification Department can also automatically identify risks of legal violations using AI, enabling rapid and accurate risk assessment. For example, it can calculate the probability of a risk occurring under specific conditions based on past data and provide companies with a concrete risk assessment. Furthermore, the Risk Identification Department can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the Risk Identification Department to help companies identify risks of legal violations early and take appropriate measures.

[0035] The cautionary point presentation section presents cautionary points tailored to the industry, job type, and office environment, based on the risks identified by the risk identification section. Specifically, in the manufacturing industry, it presents cautionary points regarding the safety of machine operation, and in the IT industry, it points out the risks of long working hours. For example, in the manufacturing industry, it presents specific cautionary points regarding machine operation procedures and the use of safety devices to ensure worker safety. In the IT industry, it points out the health risks of prolonged working hours and encourages appropriate breaks and management of working hours. The cautionary point presentation section can also use AI to automatically present cautionary points tailored to the industry and job type, thereby providing cautionary points quickly and accurately. For example, it can identify specific risk factors based on data related to a company's industry and job type and present specific cautionary points. Furthermore, the cautionary point presentation section can also present cautionary points tailored to the office environment. For example, it can propose appropriate work environment measures and safety measures based on the office layout and equipment. In this way, the cautionary point presentation section can help companies understand specific cautionary points tailored to their industry, job type, and office environment, and support them in improving their working environment.

[0036] The data collection unit can analyze each company's past violation records and select the optimal collection method. For example, the data collection unit can perform periodic collection for specific companies based on past violation records. The data collection unit can also efficiently collect data by changing the collection method according to the frequency of past violation records. For example, the data collection unit can select a collection method that focuses on specific violation items based on the content of past violation records. This allows for efficient data collection by selecting the optimal collection method based on past violation records. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input past violation record data into a generating AI and have the generating AI select the optimal collection method.

[0037] The data collection unit can filter data based on the size and industry of the company when collecting records of violations of the Labor Standards Act. For example, the data collection unit can set different collection criteria for large companies and small and medium-sized enterprises to collect appropriate data. The data collection unit can also apply different filtering criteria for manufacturing and service industries to collect data appropriate to the industry. The data collection unit can also adjust the scope of data to be collected based on the number of employees of a company. This allows for the collection of appropriate data by filtering based on the size and industry of the company. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input company size and industry data into a generating AI and have the generating AI set the filtering criteria.

[0038] The collection unit can prioritize the collection of records of violations of the Labor Standards Act based on the geographical location information of companies. For example, the collection unit can prioritize the collection of records from geographically close companies to understand violation trends in each region. For example, if there are many violations in a particular region, the collection unit can also focus on collecting records from companies in that region. The collection unit can also prioritize the collection of records from highly relevant companies based on geographical location information. This allows for the understanding of violation trends in each region by prioritizing the collection of highly relevant records based on the geographical location information of companies. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input geographical location data of companies into a generating AI and have the generating AI select highly relevant records.

[0039] The data collection unit can analyze a company's social media activity and collect relevant records when collecting records of violations of the Labor Standards Act. For example, the data collection unit can analyze a company's reputation on social media and collect records of companies that are likely to be in violation. For example, the data collection unit can analyze employee posts on social media and collect records of companies that show signs of violation. For example, the data collection unit can monitor a company's activity on social media and collect records of companies that are at high risk of violation. This allows for the efficient collection of records of companies that are likely to be in violation by analyzing a company's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input social media data into a generating AI and have the generating AI collect relevant records.

[0040] The anonymization unit can adjust the level of detail of anonymization based on the importance of the data during the anonymization process. For example, the anonymization unit can apply a detailed anonymization method to data with high importance. For example, the anonymization unit can also apply a simpler anonymization method to data with low importance. The anonymization unit can also adjust the level of detail of anonymization in stages according to the importance of the data. This allows for appropriate anonymization by adjusting the level of detail of anonymization based on the importance of the data. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of detail of anonymization.

[0041] The anonymization unit can apply different anonymization algorithms depending on the data category during anonymization. For example, the anonymization unit can apply a specific anonymization algorithm to personal information. For example, the anonymization unit can also apply a different anonymization algorithm to corporate information. The anonymization unit can also select the optimal anonymization algorithm for each data category. This allows for appropriate anonymization by applying the optimal anonymization algorithm according to the data category. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the data category into a generating AI and have the generating AI select the optimal anonymization algorithm.

[0042] The anonymization unit can determine the priority of anonymization based on the data submission date during the anonymization process. For example, the anonymization unit may prioritize anonymizing older data. For example, the anonymization unit may also postpone anonymizing newer data. For example, the anonymization unit may also adjust the anonymization priority in stages according to the submission date. This allows for efficient data anonymization by determining the anonymization priority based on the data submission date. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the data submission date into a generating AI and have the generating AI determine the anonymization priority.

[0043] The anonymization unit can adjust the order of anonymization based on the relevance of the data. For example, the anonymization unit can prioritize anonymizing highly relevant data. For example, the anonymization unit can also postpone anonymizing less relevant data. For example, the anonymization unit can also adjust the order of anonymization in stages according to the relevance of the data. This allows for efficient data anonymization by adjusting the order of anonymization based on the relevance of the data. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the anonymization order.

[0044] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also analyze trends in past learning data and adjust the learning algorithm. For example, the learning unit can optimize the parameters of the learning algorithm by referring to past learning data. This allows for efficient data learning by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0045] The learning unit can apply different learning methods to each data category during the learning process. For example, the learning unit can apply a specific learning method to personal information data. For example, the learning unit can also apply a different learning method to corporate information data. The learning unit can also select the optimal learning method for each data category. This allows for efficient data learning by applying the optimal learning method to each data category. Some or all of the above-described processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the data categories into a generating AI and have the generating AI select the optimal learning method.

[0046] The learning unit can weight the training data based on the data submission date during training. For example, the learning unit can assign lower weights to older data. For example, it can assign higher weights to newer data. The learning unit can also adjust the weighting of the training data in stages according to the submission date. This allows for efficient data learning by weighting the training data based on the data submission date. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the data submission date into a generating AI and have the generating AI perform the weighting of the training data.

[0047] The learning unit can perform learning by referring to relevant market data during the learning process. For example, the learning unit can select the optimal learning method based on the relevant market data. The learning unit can also analyze trends in the relevant market data and adjust the learning algorithm. For example, the learning unit can optimize the weighting of the learning data by referring to the relevant market data. This allows for efficient learning of the data by referring to the relevant market data during the learning process. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input relevant market data into a generating AI and have the generating AI select the learning method and adjust the algorithm.

[0048] The advice unit can adjust the level of detail of the advice based on the importance of the data when providing advice. For example, the advice unit can provide detailed advice for highly important data. For example, the advice unit can also provide concise advice for less important data. The advice unit can also adjust the level of detail of the advice in stages according to the importance of the data. This allows for efficient advice provision by adjusting the level of detail of the advice based on the importance of the data. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of detail of the advice.

[0049] The advice unit can apply different advice algorithms depending on the data category when providing advice. For example, the advice unit can apply a specific advice algorithm to data related to working hours. For example, the advice unit can apply a different advice algorithm to data related to break times. The advice unit can also select the optimal advice algorithm for each data category. This allows for efficient advice provision by applying the optimal advice algorithm according to the data category. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the data category into a generating AI and have the generating AI select the optimal advice algorithm.

[0050] The advice unit can determine the priority of advice based on the data submission date when providing advice. For example, the advice unit may prioritize advice for older data. For example, the advice unit may also postpone advice for newer data. The advice unit may also adjust the priority of advice in stages according to the submission date. This allows for efficient advice provision by determining the priority of advice based on the data submission date. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the data submission date into a generating AI and have the generating AI determine the priority of advice.

[0051] The advice unit can adjust the order of advice based on the relevance of the data when providing advice. For example, the advice unit can prioritize providing advice to highly relevant data. For example, the advice unit can also postpone providing advice to less relevant data. For example, the advice unit can also adjust the order of advice in stages according to the relevance of the data. This allows for efficient advice provision by adjusting the order of advice based on the relevance of the data. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the order of advice.

[0052] The risk identification unit can adjust the level of detail of risk identification based on the importance of the data when identifying risks. For example, the risk identification unit can provide detailed risk identification for data with high importance. For example, the risk identification unit can also provide concise risk identification for data with low importance. For example, the risk identification unit can also adjust the level of detail of risk identification in stages according to the importance of the data. This allows for efficient risk identification by adjusting the level of detail of risk identification based on the importance of the data. Some or all of the above processing in the risk identification unit may be performed using AI, for example, or without AI. For example, the risk identification unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of detail of the risk identification.

[0053] The risk identification unit can apply different risk identification algorithms depending on the data category when identifying risks. For example, the risk identification unit can apply a specific risk identification algorithm to data related to working hours. For example, the risk identification unit can also apply a different risk identification algorithm to data related to break times. The risk identification unit can also select the optimal risk identification algorithm for each data category. This allows for efficient risk identification by applying the optimal risk identification algorithm according to the data category. Some or all of the above processing in the risk identification unit may be performed using AI, for example, or without AI. For example, the risk identification unit can input the data category into a generating AI and have the generating AI select the optimal risk identification algorithm.

[0054] The risk identification unit can determine the priority of risk identification based on the data submission date when identifying risks. For example, the risk identification unit can prioritize identifying risks in older data. For example, the risk identification unit can also postpone identifying risks in newer data. For example, the risk identification unit can also adjust the priority of risk identification in stages according to the submission date. This allows for efficient risk identification by determining the priority of risk identification based on the data submission date. Some or all of the above processing in the risk identification unit may be performed using AI, for example, or without AI. For example, the risk identification unit can input the data submission date into a generating AI and have the generating AI determine the priority of risk identification.

[0055] The risk identification unit can adjust the order of risk identification based on the relevance of the data. For example, the risk identification unit can prioritize identifying risks in highly relevant data. For example, the risk identification unit can also postpone identifying risks in less relevant data. For example, the risk identification unit can also adjust the order of risk identification in stages according to the relevance of the data. This allows for efficient risk identification by adjusting the order of risk identification based on the relevance of the data. Some or all of the above processing in the risk identification unit may be performed using AI, for example, or without AI. For example, the risk identification unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the order of risk identification.

[0056] The caution point presentation unit can adjust the level of detail of caution points based on the importance of the data when presenting caution points. For example, the caution point presentation unit can present detailed caution points for data with high importance. For example, the caution point presentation unit can also present concise caution points for data with low importance. For example, the caution point presentation unit can adjust the level of detail of caution points in stages according to the importance of the data. This allows for efficient presentation of caution points by adjusting the level of detail of caution points based on the importance of the data. Some or all of the above processing in the caution point presentation unit may be performed using AI, for example, or without using AI. For example, the caution point presentation unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of detail of the caution points.

[0057] The caution point presentation unit can apply different caution point presentation algorithms depending on the data category when presenting caution points. For example, the caution point presentation unit can apply a specific caution point presentation algorithm to data related to working hours. For example, it can also apply a different caution point presentation algorithm to data related to break times. The caution point presentation unit can also select the optimal caution point presentation algorithm for each data category. This allows for efficient presentation of caution points by applying the optimal caution point presentation algorithm according to the data category. Some or all of the above processing in the caution point presentation unit may be performed using AI, for example, or without AI. For example, the caution point presentation unit can input the data category into a generating AI and have the generating AI select the optimal caution point presentation algorithm.

[0058] The caution point presentation unit can determine the priority of caution points based on the data submission date when presenting them. For example, the caution point presentation unit can prioritize presenting caution points to older data. For example, the caution point presentation unit can also postpone presenting caution points to newer data. For example, the caution point presentation unit can also adjust the priority of caution points in stages according to the submission date. This allows for efficient presentation of caution points by determining the priority of caution points based on the data submission date. Some or all of the above processing in the caution point presentation unit may be performed using AI, for example, or without AI. For example, the caution point presentation unit can input the data submission date into a generating AI and have the generating AI determine the priority of caution points.

[0059] The attention-displaying unit can adjust the order of attention points based on the relevance of the data when displaying them. For example, the attention-displaying unit can prioritize displaying attention points for highly relevant data. For example, the attention-displaying unit can also postpone displaying attention points for less relevant data. For example, the attention-displaying unit can also adjust the order of attention points in stages according to the relevance of the data. This allows for efficient display of attention points by adjusting the order of attention points based on the relevance of the data. Some or all of the above processing in the attention-displaying unit may be performed using AI, for example, or without AI. For example, the attention-displaying unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the order of attention points.

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

[0061] The compliance support system may also include a data reliability evaluation unit. This unit evaluates the reliability of collected records of labor law violations. For example, it can verify the source of the data and the consistency of the records, and exclude unreliable data. It can also prioritize the data provided to the learning unit based on its reliability. This allows for more accurate compliance advice by using reliable data for LLM training. Furthermore, the data reliability evaluation unit can collect feedback on data reliability and suggest improvements to the collection unit. This enables the collection unit to efficiently collect reliable data.

[0062] The compliance support system may also include a user feedback collection unit. This unit collects user feedback on the advice and risk identification provided. For example, it can collect opinions on the results of users implementing the advice and the usefulness of the risk identification. The collected feedback is provided to the learning unit and used as learning data for the LLM (Limited Liability Management) system. This allows the system to be improved based on users' actual experiences, providing more effective compliance support. Furthermore, the user feedback collection unit can also suggest improvements to the advice unit and risk identification unit based on the feedback. This improves the overall accuracy and usefulness of the system.

[0063] The compliance support system can also include a data visualization section. This section visually displays the collected records of labor law violations, the advice provided, and the content of risk assessments. For example, it can display trends in violation records and the distribution of risks using graphs and charts. This makes it easier for users to intuitively understand the overall picture of the data. Furthermore, the data visualization section can provide interactive functions that allow users to view detailed information on specific data. This enables users to quickly obtain the necessary information and take appropriate action.

[0064] The compliance support system can also include a predictive analytics unit. The predictive analytics unit predicts the risk of future labor law violations based on collected data. For example, it can analyze past violation records and industry-specific trends to predict future risks for specific companies or industries. This allows companies to identify risks in advance and take preventative measures. Furthermore, the predictive analytics unit can propose specific countermeasures to the advisory and risk identification units based on the prediction results. This enables the system to provide more proactive compliance support.

[0065] The compliance support system can also include a user education department. This department provides educational content related to legal compliance. For example, it can offer online courses and webinars on basic knowledge of labor standards law and specific compliance methods. This allows company employees to understand the importance of legal compliance and take appropriate action. Furthermore, the user education department can customize individual training programs based on the advice and risk assessments provided. This allows companies to receive training tailored to their specific needs.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The collection unit collects records of violations of the Labor Standards Act. For example, it can collect records of violations of the Labor Standards Act by each company, such as excessive working hours, unpaid wages, and insufficient rest periods. The collection unit can also use AI to automatically collect records of violations of the Labor Standards Act. Step 2: The anonymization unit anonymizes the records collected by the collection unit. For example, it can delete personal information, mask data, or automatically anonymize data using AI. Anonymization can also be achieved by hiding parts of the data. Step 3: The learning unit learns from the anonymized data by the anonymization unit. For example, it can learn from data using LLM, learn from past violation records, and provide specific advice for legal compliance. It can also learn patterns of labor law violations using LLM. Step 4: The advice unit provides compliance advice based on the data learned by the learning unit. For example, it can suggest specific areas for improvement, such as managing working hours and ensuring adequate rest periods, and can automatically provide compliance advice using AI. It can also provide advice based on the articles of the Labor Standards Act. Step 5: The risk identification unit identifies risks of legal violations based on the advice provided by the advice unit. For example, it can identify risks such as the risk of death from overwork or the risk of employee turnover due to deteriorating working conditions, and can also automatically identify risks of legal violations using AI. It can also assess the risk of violations of labor standards laws. Step 6: The cautionary point presentation section presents cautionary points tailored to the industry, job type, and office environment, based on the risks identified by the risk identification section. For example, in the manufacturing industry, cautionary points regarding machine operation safety are presented, and in the IT industry, the risk of long working hours is pointed out. It is also possible to use AI to automatically present cautionary points tailored to the industry and job type. It is also possible to present cautionary points tailored to the office environment.

[0068] (Example of form 2) The compliance support system according to an embodiment of the present invention anonymizes records of violations of the Labor Standards Act, trains the LLM (Large-Scale Language Model) on them, and provides advice on legal compliance while also pointing out specific risks that may lead to legal violations. The compliance support system collects and anonymizes records of violations of the Labor Standards Act. Next, the anonymized data is trained on the LLM. The LLM learns from past violation records and provides specific advice for legal compliance. For example, it suggests specific areas for improvement, such as managing working hours and ensuring break times. Furthermore, the LLM also points out specific risks that may lead to legal violations. For example, it points out the risk of death from overwork and the risk of employee turnover due to deteriorating working conditions, and alerts companies to these risks. It also suggests points of caution tailored to the industry, job type, and office environment. For example, in the manufacturing industry, it suggests points of caution regarding the safety of machine operation, and in the IT industry, it points out the risk of long working hours. This allows each company to take specific measures according to its industry and job type. This system is particularly useful for small venture companies and SMEs. These companies often lack the resources to provide specific guidance to ensure legal compliance and the specialized knowledge needed to understand the law. This system allows companies to deepen their awareness and understanding of legal compliance and minimize legal risks. Furthermore, changes in the work environment (teleworking, diversity, etc.) have altered traditional labor laws, making it crucial to understand and apply new regulations and rules. This system addresses the latest labor laws and regulations, supporting companies in creating sustainable workplaces. Ultimately, this compliance support system enables companies to deepen their awareness and understanding of legal compliance and minimize legal risks.

[0069] The compliance support system according to the embodiment comprises a collection unit, an anonymization unit, a learning unit, an advice unit, a risk identification unit, and a point of caution presentation unit. The collection unit collects records of violations of the Labor Standards Act. For example, the collection unit collects records of violations of the Labor Standards Act from each company. The collection unit can collect records such as excessive working hours, unpaid wages, and insufficient rest periods. The collection unit can also automatically collect records of violations of the Labor Standards Act using AI, for example. The anonymization unit anonymizes the records collected by the collection unit. The anonymization unit performs tasks such as deleting personal information or masking data. The anonymization unit can also automatically anonymize data using AI, for example. The anonymization unit can also anonymize data by hiding parts of it, for example. The learning unit learns from the data anonymized by the anonymization unit. The learning unit learns from data using LLM, for example. The learning unit learns from past violation records and provides specific advice for compliance. The learning unit can, for example, learn patterns of labor law violations using LLM. The advice unit provides advice on legal compliance based on the data learned by the learning unit. The advice unit suggests specific areas for improvement, such as managing working hours and ensuring break times. The advice unit can also automatically provide advice on legal compliance using, for example, AI. The advice unit can also provide advice based on the articles of the Labor Standards Act. The risk identification unit identifies risks of legal violations based on the advice provided by the advice unit. The risk identification unit identifies risks such as the risk of death from overwork or the risk of employee turnover due to deteriorating working conditions. The risk identification unit can also automatically identify risks of legal violations using, for example, AI. The risk identification unit can also evaluate risks of labor law violations, for example. The caution point presentation unit presents caution points tailored to the industry, job type, and office environment based on the risks identified by the risk identification unit. The caution point presentation unit presents caution points regarding machine operation safety in the manufacturing industry, for example. The caution point presentation unit points out the risk of long working hours in the IT industry, for example. The section that displays points to note can, for example, use AI to automatically display points to note that are tailored to the industry or job type.The cautionary note display section can, for example, display cautionary notes tailored to the office environment. As a result, the compliance support system according to this embodiment can anonymize records of violations of the Labor Standards Act, train the system using LLM, provide advice on legal compliance, point out the risks of legal violations, and display cautionary notes tailored to the industry, occupation, and office environment.

[0070] The data collection unit collects records of violations of the Labor Standards Act. Specifically, it collects records of violations by each company, and can gather detailed data such as excessive working hours, unpaid wages, and insufficient rest periods. The data collection unit can also use AI to automatically collect records of violations of the Labor Standards Act, thereby enabling efficient and accurate data collection. For example, it can automatically retrieve information from internal company systems and publicly available databases, and record details such as the type, frequency, and scope of impact of violations. Furthermore, the data collection unit can centrally manage the collected data and link it with other departments and systems as needed. For example, the collected data can be stored on a cloud server and made accessible to the anonymization unit and the learning unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. As a result, the data collection unit can collect data efficiently and effectively, improving the overall performance of the system.

[0071] The anonymization unit anonymizes the records collected by the collection unit. Specifically, it protects privacy by deleting personal information and masking data. For example, it anonymizes data by deleting personal information such as employee names, addresses, and contact information, and by hiding parts of the data. The anonymization unit can also automatically anonymize data using AI, which allows for fast and accurate data processing. For example, it can use natural language processing technology to extract personal information from text data and automatically delete or mask it. The anonymization unit can also evaluate the quality of the anonymized data and re-anonymize it as needed. This allows the anonymization unit to securely manage the collected data, protect privacy, and improve the reliability of the entire system.

[0072] The learning unit learns from data anonymized by the anonymization unit. Specifically, it uses an LLM (Large-Scale Language Model) to learn from the data and provide specific advice for legal compliance. For example, it learns from past violation records to identify patterns of labor law violations and suggests specific areas for improvement for companies to comply with the law. The learning unit can also learn patterns of labor law violations using AI, enabling it to provide highly accurate advice. For example, it can analyze the frequency and scope of violations to identify risk factors in specific industries and occupations. Furthermore, the learning unit can utilize historical data and statistical information to perform long-term risk assessments and trend analyses. This allows the learning unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, improving the reliability and security of the entire system.

[0073] The Advice Unit provides legal compliance advice based on data learned by the Learning Unit. Specifically, it suggests concrete areas for improvement, such as managing working hours and ensuring adequate rest periods. For example, it can identify specific items that companies must comply with based on the provisions of the Labor Standards Act and propose improvement measures. The Advice Unit can also automatically provide legal compliance advice using AI, enabling it to provide advice quickly and accurately. For example, it can integrate with a company's working hours management system to detect overwork in real time and propose appropriate actions. Furthermore, the Advice Unit can provide customized advice tailored to the characteristics and industry of each company. This allows the Advice Unit to provide concrete support to companies in complying with laws and improving their working environment.

[0074] The Risk Identification Department identifies risks of legal violations based on advice provided by the Advisory Department. Specifically, it identifies risks such as death from overwork and employee turnover due to deteriorating working conditions. For example, it points out that the risk of death from overwork increases if excessive working hours continue, and encourages appropriate action. The Risk Identification Department can also automatically identify risks of legal violations using AI, enabling rapid and accurate risk assessment. For example, it can calculate the probability of a risk occurring under specific conditions based on past data and provide companies with a concrete risk assessment. Furthermore, the Risk Identification Department can use anomaly detection algorithms to detect unusual patterns and abnormal data, issuing early warnings. This allows the Risk Identification Department to help companies identify risks of legal violations early and take appropriate measures.

[0075] The cautionary point presentation section presents cautionary points tailored to the industry, job type, and office environment, based on the risks identified by the risk identification section. Specifically, in the manufacturing industry, it presents cautionary points regarding the safety of machine operation, and in the IT industry, it points out the risks of long working hours. For example, in the manufacturing industry, it presents specific cautionary points regarding machine operation procedures and the use of safety devices to ensure worker safety. In the IT industry, it points out the health risks of prolonged working hours and encourages appropriate breaks and management of working hours. The cautionary point presentation section can also use AI to automatically present cautionary points tailored to the industry and job type, thereby providing cautionary points quickly and accurately. For example, it can identify specific risk factors based on data related to a company's industry and job type and present specific cautionary points. Furthermore, the cautionary point presentation section can also present cautionary points tailored to the office environment. For example, it can propose appropriate work environment measures and safety measures based on the office layout and equipment. In this way, the cautionary point presentation section can help companies understand specific cautionary points tailored to their industry, job type, and office environment, and support them in improving their working environment.

[0076] The data collection unit can estimate the user's emotions and adjust the timing of data collection for violations of labor laws based on the estimated emotions. For example, if the user is stressed, the data collection unit can delay the collection timing to reduce the user's burden. For example, if the user is relaxed, the data collection unit can advance the collection timing to collect data quickly. For example, if the user is in a hurry, the data collection unit can optimize the collection timing to collect data efficiently. This reduces the user's burden and allows for efficient data collection by adjusting the collection timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0077] The data collection unit can analyze each company's past violation records and select the optimal collection method. For example, the data collection unit can perform periodic collection for specific companies based on past violation records. The data collection unit can also efficiently collect data by changing the collection method according to the frequency of past violation records. For example, the data collection unit can select a collection method that focuses on specific violation items based on the content of past violation records. This allows for efficient data collection by selecting the optimal collection method based on past violation records. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input past violation record data into a generating AI and have the generating AI select the optimal collection method.

[0078] The data collection unit can filter data based on the size and industry of the company when collecting records of violations of the Labor Standards Act. For example, the data collection unit can set different collection criteria for large companies and small and medium-sized enterprises to collect appropriate data. The data collection unit can also apply different filtering criteria for manufacturing and service industries to collect data appropriate to the industry. The data collection unit can also adjust the scope of data to be collected based on the number of employees of a company. This allows for the collection of appropriate data by filtering based on the size and industry of the company. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input company size and industry data into a generating AI and have the generating AI set the filtering criteria.

[0079] The data collection unit can estimate the user's emotions and determine the priority of the records to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit may postpone collecting less important records. For example, if the user is relaxed, the data collection unit may prioritize collecting more important records. For example, if the user is in a hurry, the data collection unit may prioritize records that can be collected quickly. This allows for efficient data collection by prioritizing the records to be collected based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0080] The collection unit can prioritize the collection of records of violations of the Labor Standards Act based on the geographical location information of companies. For example, the collection unit can prioritize the collection of records from geographically close companies to understand violation trends in each region. For example, if there are many violations in a particular region, the collection unit can also focus on collecting records from companies in that region. The collection unit can also prioritize the collection of records from highly relevant companies based on geographical location information. This allows for the understanding of violation trends in each region by prioritizing the collection of highly relevant records based on the geographical location information of companies. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input geographical location data of companies into a generating AI and have the generating AI select highly relevant records.

[0081] The data collection unit can analyze a company's social media activity and collect relevant records when collecting records of violations of the Labor Standards Act. For example, the data collection unit can analyze a company's reputation on social media and collect records of companies that are likely to be in violation. For example, the data collection unit can analyze employee posts on social media and collect records of companies that show signs of violation. For example, the data collection unit can monitor a company's activity on social media and collect records of companies that are at high risk of violation. This allows for the efficient collection of records of companies that are likely to be in violation by analyzing a company's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input social media data into a generating AI and have the generating AI collect relevant records.

[0082] The anonymization unit can estimate the user's emotions and adjust the anonymization method based on the estimated emotions. For example, if the user is stressed, the anonymization unit can apply a simple anonymization method for rapid processing. For example, if the user is relaxed, the anonymization unit can also apply a more detailed anonymization method to improve data accuracy. For example, if the user is in a hurry, the anonymization unit can select a method that allows for rapid anonymization. This allows for rapid and appropriate data anonymization by adjusting the anonymization method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the anonymization unit may be performed using AI or not. For example, the anonymization unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0083] The anonymization unit can adjust the level of detail of anonymization based on the importance of the data during the anonymization process. For example, the anonymization unit can apply a detailed anonymization method to data with high importance. For example, the anonymization unit can also apply a simpler anonymization method to data with low importance. The anonymization unit can also adjust the level of detail of anonymization in stages according to the importance of the data. This allows for appropriate anonymization by adjusting the level of detail of anonymization based on the importance of the data. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of detail of anonymization.

[0084] The anonymization unit can apply different anonymization algorithms depending on the data category during anonymization. For example, the anonymization unit can apply a specific anonymization algorithm to personal information. For example, the anonymization unit can also apply a different anonymization algorithm to corporate information. The anonymization unit can also select the optimal anonymization algorithm for each data category. This allows for appropriate anonymization by applying the optimal anonymization algorithm according to the data category. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the data category into a generating AI and have the generating AI select the optimal anonymization algorithm.

[0085] The anonymization unit can estimate the user's emotions and determine the priority of anonymization based on the estimated user emotions. For example, if the user is stressed, the anonymization unit may postpone anonymizing less important data. For example, if the user is relaxed, the anonymization unit may prioritize anonymizing more important data. For example, if the user is in a hurry, the anonymization unit may prioritize data that can be anonymized quickly. This allows for efficient data anonymization by determining the priority of anonymization based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the anonymization unit may be performed using AI or not. For example, the anonymization unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0086] The anonymization unit can determine the priority of anonymization based on the data submission date during the anonymization process. For example, the anonymization unit may prioritize anonymizing older data. For example, the anonymization unit may also postpone anonymizing newer data. For example, the anonymization unit may also adjust the anonymization priority in stages according to the submission date. This allows for efficient data anonymization by determining the anonymization priority based on the data submission date. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the data submission date into a generating AI and have the generating AI determine the anonymization priority.

[0087] The anonymization unit can adjust the order of anonymization based on the relevance of the data. For example, the anonymization unit can prioritize anonymizing highly relevant data. For example, the anonymization unit can also postpone anonymizing less relevant data. For example, the anonymization unit can also adjust the order of anonymization in stages according to the relevance of the data. This allows for efficient data anonymization by adjusting the order of anonymization based on the relevance of the data. Some or all of the above-described processes in the anonymization unit may be performed using AI, for example, or without AI. For example, the anonymization unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the anonymization order.

[0088] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is stressed, the learning unit will prioritize learning simple data. For example, if the user is relaxed, the learning unit can also prioritize learning detailed data. For example, if the user is in a hurry, the learning unit can also prioritize data that can be learned quickly. This allows for efficient data learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0089] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also analyze trends in past learning data and adjust the learning algorithm. For example, the learning unit can optimize the parameters of the learning algorithm by referring to past learning data. This allows for efficient data learning by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0090] The learning unit can apply different learning methods to each data category during the learning process. For example, the learning unit can apply a specific learning method to personal information data. For example, the learning unit can also apply a different learning method to corporate information data. The learning unit can also select the optimal learning method for each data category. This allows for efficient data learning by applying the optimal learning method to each data category. Some or all of the above-described processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the data categories into a generating AI and have the generating AI select the optimal learning method.

[0091] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can set a lower learning frequency. For example, if the user is relaxed, the learning unit can also set a higher learning frequency. For example, if the user is in a hurry, the learning unit can set a frequency that allows for rapid learning. This allows for efficient data learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not using AI. For example, the learning unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0092] The learning unit can weight the training data based on the data submission date during training. For example, the learning unit can assign lower weights to older data. For example, it can assign higher weights to newer data. The learning unit can also adjust the weighting of the training data in stages according to the submission date. This allows for efficient data learning by weighting the training data based on the data submission date. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the data submission date into a generating AI and have the generating AI perform the weighting of the training data.

[0093] The learning unit can perform learning by referring to relevant market data during the learning process. For example, the learning unit can select the optimal learning method based on the relevant market data. The learning unit can also analyze trends in the relevant market data and adjust the learning algorithm. For example, the learning unit can optimize the weighting of the learning data by referring to the relevant market data. This allows for efficient learning of the data by referring to the relevant market data during the learning process. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input relevant market data into a generating AI and have the generating AI select the learning method and adjust the algorithm.

[0094] The advice unit can estimate the user's emotions and adjust the way it expresses advice based on the estimated emotions. For example, if the user is stressed, the advice unit can provide concise and easy-to-understand advice. For example, if the user is relaxed, the advice unit can also provide advice that includes detailed explanations. For example, if the user is in a hurry, the advice unit can also provide advice that can be quickly understood. This allows for efficient advice delivery by adjusting the way it expresses advice based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the advice unit may be performed using AI or not. For example, the advice unit can input user facial expression data into the generative AI and have the generative AI perform the user's emotion estimation.

[0095] The advice unit can adjust the level of detail of the advice based on the importance of the data when providing advice. For example, the advice unit can provide detailed advice for highly important data. For example, the advice unit can also provide concise advice for less important data. The advice unit can also adjust the level of detail of the advice in stages according to the importance of the data. This allows for efficient advice provision by adjusting the level of detail of the advice based on the importance of the data. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of detail of the advice.

[0096] The advice unit can apply different advice algorithms depending on the data category when providing advice. For example, the advice unit can apply a specific advice algorithm to data related to working hours. For example, the advice unit can apply a different advice algorithm to data related to break times. The advice unit can also select the optimal advice algorithm for each data category. This allows for efficient advice provision by applying the optimal advice algorithm according to the data category. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the data category into a generating AI and have the generating AI select the optimal advice algorithm.

[0097] The advice unit can estimate the user's emotions and adjust the length of the advice based on the estimated emotions. For example, if the user is stressed, the advice unit will provide short, concise advice. If the user is relaxed, the advice unit may provide longer advice with more detailed explanations. If the user is in a hurry, the advice unit may provide short, easily understandable advice. This allows for efficient advice delivery by adjusting the length of the advice based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the advice unit may be performed using AI or not. For example, the advice unit can input user facial expression data into the generative AI and have the generative AI perform the user's emotion estimation.

[0098] The advice unit can determine the priority of advice based on the data submission date when providing advice. For example, the advice unit may prioritize advice for older data. For example, the advice unit may also postpone advice for newer data. The advice unit may also adjust the priority of advice in stages according to the submission date. This allows for efficient advice provision by determining the priority of advice based on the data submission date. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the data submission date into a generating AI and have the generating AI determine the priority of advice.

[0099] The advice unit can adjust the order of advice based on the relevance of the data when providing advice. For example, the advice unit can prioritize providing advice to highly relevant data. For example, the advice unit can also postpone providing advice to less relevant data. For example, the advice unit can also adjust the order of advice in stages according to the relevance of the data. This allows for efficient advice provision by adjusting the order of advice based on the relevance of the data. Some or all of the above processing in the advice unit may be performed using AI, for example, or without AI. For example, the advice unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the order of advice.

[0100] The risk identification unit can estimate the user's emotions and adjust its risk identification method based on the estimated emotions. For example, if the user is stressed, the risk identification unit can provide a concise and easy-to-understand risk identification method. For example, if the user is relaxed, the risk identification unit can also provide a risk identification method that includes detailed explanations. For example, if the user is in a hurry, the risk identification unit can also provide a risk identification method that can be quickly understood. This allows for efficient risk identification by adjusting the risk identification method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the risk identification unit may be performed using AI or not. For example, the risk identification unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0101] The risk identification unit can adjust the level of detail of risk identification based on the importance of the data when identifying risks. For example, the risk identification unit can provide detailed risk identification for data with high importance. For example, the risk identification unit can also provide concise risk identification for data with low importance. For example, the risk identification unit can also adjust the level of detail of risk identification in stages according to the importance of the data. This allows for efficient risk identification by adjusting the level of detail of risk identification based on the importance of the data. Some or all of the above processing in the risk identification unit may be performed using AI, for example, or without AI. For example, the risk identification unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of detail of the risk identification.

[0102] The risk identification unit can apply different risk identification algorithms depending on the data category when identifying risks. For example, the risk identification unit can apply a specific risk identification algorithm to data related to working hours. For example, the risk identification unit can also apply a different risk identification algorithm to data related to break times. The risk identification unit can also select the optimal risk identification algorithm for each data category. This allows for efficient risk identification by applying the optimal risk identification algorithm according to the data category. Some or all of the above processing in the risk identification unit may be performed using AI, for example, or without AI. For example, the risk identification unit can input the data category into a generating AI and have the generating AI select the optimal risk identification algorithm.

[0103] The risk identification unit can estimate the user's emotions and determine the priority of risk identification based on the estimated emotions. For example, if the user is stressed, the risk identification unit may postpone low-priority risks. For example, if the user is relaxed, the risk identification unit may prioritize high-priority risks. For example, if the user is in a hurry, the risk identification unit may prioritize risks that can be identified quickly. This allows for efficient risk identification by determining the priority of risk identification based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the risk identification unit may be performed using AI or not. For example, the risk identification unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0104] The risk identification unit can determine the priority of risk identification based on the data submission date when identifying risks. For example, the risk identification unit can prioritize identifying risks in older data. For example, the risk identification unit can also postpone identifying risks in newer data. For example, the risk identification unit can also adjust the priority of risk identification in stages according to the submission date. This allows for efficient risk identification by determining the priority of risk identification based on the data submission date. Some or all of the above processing in the risk identification unit may be performed using AI, for example, or without AI. For example, the risk identification unit can input the data submission date into a generating AI and have the generating AI determine the priority of risk identification.

[0105] The risk identification unit can adjust the order of risk identification based on the relevance of the data. For example, the risk identification unit can prioritize identifying risks in highly relevant data. For example, the risk identification unit can also postpone identifying risks in less relevant data. For example, the risk identification unit can also adjust the order of risk identification in stages according to the relevance of the data. This allows for efficient risk identification by adjusting the order of risk identification based on the relevance of the data. Some or all of the above processing in the risk identification unit may be performed using AI, for example, or without AI. For example, the risk identification unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the order of risk identification.

[0106] The attention-displaying unit can estimate the user's emotions and adjust the method of presenting attention-displaying information based on the estimated emotions. For example, if the user is stressed, the attention-displaying unit provides a concise and easy-to-understand method of presenting attention-displaying information. For example, if the user is relaxed, the attention-displaying unit may also provide a method of presenting attention-displaying information that includes detailed explanations. For example, if the user is in a hurry, the attention-displaying unit may also provide a method of presenting attention-displaying information that can be quickly understood. This allows for efficient presentation of attention-displaying information by adjusting the method of presentation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the attention-displaying unit may be performed using AI, for example, or not using AI. For example, the attention-displaying unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0107] The caution point presentation unit can adjust the level of detail of caution points based on the importance of the data when presenting caution points. For example, the caution point presentation unit can present detailed caution points for data with high importance. For example, the caution point presentation unit can also present concise caution points for data with low importance. For example, the caution point presentation unit can adjust the level of detail of caution points in stages according to the importance of the data. This allows for efficient presentation of caution points by adjusting the level of detail of caution points based on the importance of the data. Some or all of the above processing in the caution point presentation unit may be performed using AI, for example, or without using AI. For example, the caution point presentation unit can input the importance of the data into a generating AI and have the generating AI perform the adjustment of the level of detail of the caution points.

[0108] The caution point presentation unit can apply different caution point presentation algorithms depending on the data category when presenting caution points. For example, the caution point presentation unit can apply a specific caution point presentation algorithm to data related to working hours. For example, it can also apply a different caution point presentation algorithm to data related to break times. The caution point presentation unit can also select the optimal caution point presentation algorithm for each data category. This allows for efficient presentation of caution points by applying the optimal caution point presentation algorithm according to the data category. Some or all of the above processing in the caution point presentation unit may be performed using AI, for example, or without AI. For example, the caution point presentation unit can input the data category into a generating AI and have the generating AI select the optimal caution point presentation algorithm.

[0109] The attention-suggestion unit can estimate the user's emotions and determine the priority of attention points based on the estimated emotions. For example, if the user is stressed, the attention-suggestion unit will postpone less important attention points. For example, if the user is relaxed, the attention-suggestion unit can prioritize presenting more important attention points. For example, if the user is in a hurry, the attention-suggestion unit can prioritize presenting attention points that can be presented quickly. This allows for efficient presentation of attention points by determining the priority of attention points based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the attention-suggestion unit may be performed using AI or not. For example, the attention-suggestion unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0110] The caution point presentation unit can determine the priority of caution points based on the data submission date when presenting them. For example, the caution point presentation unit can prioritize presenting caution points to older data. For example, the caution point presentation unit can also postpone presenting caution points to newer data. For example, the caution point presentation unit can also adjust the priority of caution points in stages according to the submission date. This allows for efficient presentation of caution points by determining the priority of caution points based on the data submission date. Some or all of the above processing in the caution point presentation unit may be performed using AI, for example, or without AI. For example, the caution point presentation unit can input the data submission date into a generating AI and have the generating AI determine the priority of caution points.

[0111] The attention-displaying unit can adjust the order of attention points based on the relevance of the data when displaying them. For example, the attention-displaying unit can prioritize displaying attention points for highly relevant data. For example, the attention-displaying unit can also postpone displaying attention points for less relevant data. For example, the attention-displaying unit can also adjust the order of attention points in stages according to the relevance of the data. This allows for efficient display of attention points by adjusting the order of attention points based on the relevance of the data. Some or all of the above processing in the attention-displaying unit may be performed using AI, for example, or without AI. For example, the attention-displaying unit can input the relevance of the data into a generating AI and have the generating AI perform the adjustment of the order of attention points.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The compliance support system may also include a data reliability evaluation unit. This unit evaluates the reliability of collected records of labor law violations. For example, it can verify the source of the data and the consistency of the records, and exclude unreliable data. It can also prioritize the data provided to the learning unit based on its reliability. This allows for more accurate compliance advice by using reliable data for LLM training. Furthermore, the data reliability evaluation unit can collect feedback on data reliability and suggest improvements to the collection unit. This enables the collection unit to efficiently collect reliable data.

[0114] The compliance support system may also include a user feedback collection unit. This unit collects user feedback on the advice and risk identification provided. For example, it can collect opinions on the results of users implementing the advice and the usefulness of the risk identification. The collected feedback is provided to the learning unit and used as learning data for the LLM (Limited Liability Management) system. This allows the system to be improved based on users' actual experiences, providing more effective compliance support. Furthermore, the user feedback collection unit can also suggest improvements to the advice unit and risk identification unit based on the feedback. This improves the overall accuracy and usefulness of the system.

[0115] The compliance support system can also include a data visualization section. This section visually displays the collected records of labor law violations, the advice provided, and the content of risk assessments. For example, it can display trends in violation records and the distribution of risks using graphs and charts. This makes it easier for users to intuitively understand the overall picture of the data. Furthermore, the data visualization section can provide interactive functions that allow users to view detailed information on specific data. This enables users to quickly obtain the necessary information and take appropriate action.

[0116] The compliance support system can also include a predictive analytics unit. The predictive analytics unit predicts the risk of future labor law violations based on collected data. For example, it can analyze past violation records and industry-specific trends to predict future risks for specific companies or industries. This allows companies to identify risks in advance and take preventative measures. Furthermore, the predictive analytics unit can propose specific countermeasures to the advisory and risk identification units based on the prediction results. This enables the system to provide more proactive compliance support.

[0117] The compliance support system can also include a user education department. This department provides educational content related to legal compliance. For example, it can offer online courses and webinars on basic knowledge of labor standards law and specific compliance methods. This allows company employees to understand the importance of legal compliance and take appropriate action. Furthermore, the user education department can customize individual training programs based on the advice and risk assessments provided. This allows companies to receive training tailored to their specific needs.

[0118] The compliance support system can further adjust the timing of advice based on the user's emotions using an emotion estimation function. For example, if the user is feeling stressed, the provision of advice can be temporarily delayed. Conversely, if the user is relaxed, advice can be provided quickly. This allows advice to be provided at the appropriate time according to the user's emotional state, improving user acceptance. The emotion estimation function can also adjust the content and expression of advice based on the user's emotions. This allows advice to be provided in the most optimal way for the user.

[0119] The compliance support system can further adjust the priority of risk identification based on the user's emotions using an emotion estimation function. For example, if the user is stressed, lower-priority risk identification can be postponed. Conversely, if the user is relaxed, higher-priority risks can be prioritized. This allows risks to be identified with appropriate priorities according to the user's emotional state, reducing the user's burden. The emotion estimation function can also adjust the way risk identification is presented based on the user's emotions. This allows risks to be presented in a way that is easy for the user to understand.

[0120] The compliance support system can further adjust how warnings are presented based on the user's emotions using an emotion estimation function. For example, if the user is stressed, it can present concise and easy-to-understand warnings. Conversely, if the user is relaxed, it can present warnings with detailed explanations. This allows warnings to be presented in an appropriate manner according to the user's emotional state, deepening their understanding. The emotion estimation function can also adjust the priority of warnings based on the user's emotions. This allows important warnings to be presented preferentially to the user.

[0121] The legal compliance support system can further select training data based on the user's emotions using an emotion estimation function. For example, if the user is stressed, simpler data can be prioritized for training. Conversely, if the user is relaxed, more detailed data can be prioritized for training. This allows the system to learn appropriate data according to the user's emotional state, improving the system's accuracy. The emotion estimation function can also adjust the training frequency based on the user's emotions. This allows for efficient training while reducing the burden on the user.

[0122] The compliance support system can further adjust the anonymization method based on the user's emotions using an emotion estimation function. For example, if the user is stressed, a simple anonymization method can be applied for quick processing. Conversely, if the user is relaxed, a more detailed anonymization method can be applied to improve data accuracy. This allows data to be anonymized in an appropriate way according to the user's emotional state, reducing the user's burden. The emotion estimation function can also adjust the anonymization priority based on the user's emotions. This allows data that is important to the user to be anonymized preferentially.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The collection unit collects records of violations of the Labor Standards Act. For example, it can collect records of violations of the Labor Standards Act by each company, such as excessive working hours, unpaid wages, and insufficient rest periods. The collection unit can also use AI to automatically collect records of violations of the Labor Standards Act. Step 2: The anonymization unit anonymizes the records collected by the collection unit. For example, it can delete personal information, mask data, or automatically anonymize data using AI. Anonymization can also be achieved by hiding parts of the data. Step 3: The learning unit learns from the anonymized data by the anonymization unit. For example, it can learn from data using LLM, learn from past violation records, and provide specific advice for legal compliance. It can also learn patterns of labor law violations using LLM. Step 4: The advice unit provides compliance advice based on the data learned by the learning unit. For example, it can suggest specific areas for improvement, such as managing working hours and ensuring adequate rest periods, and can automatically provide compliance advice using AI. It can also provide advice based on the articles of the Labor Standards Act. Step 5: The risk identification unit identifies risks of legal violations based on the advice provided by the advice unit. For example, it can identify risks such as the risk of death from overwork or the risk of employee turnover due to deteriorating working conditions, and can also automatically identify risks of legal violations using AI. It can also assess the risk of violations of labor standards laws. Step 6: The cautionary point presentation section presents cautionary points tailored to the industry, job type, and office environment, based on the risks identified by the risk identification section. For example, in the manufacturing industry, cautionary points regarding machine operation safety are presented, and in the IT industry, the risk of long working hours is pointed out. It is also possible to use AI to automatically present cautionary points tailored to the industry and job type. It is also possible to present cautionary points tailored to the office environment.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the collection unit, anonymization unit, learning unit, advice unit, risk identification unit, and caution point presentation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects records of violations of the Labor Standards Act. The anonymization unit is implemented by the identification processing unit 290 of the data processing device 12 and anonymizes the collected records. The learning unit is implemented by the identification processing unit 290 of the data processing device 12 and learns the anonymized data. The advice unit is implemented by the identification processing unit 290 of the data processing device 12 and provides advice on legal compliance. The risk identification unit is implemented by the identification processing unit 290 of the data processing device 12 and points out the risk of legal violations. The caution point presentation unit is implemented by the control unit 46A of the smart device 14 and presents caution points tailored to the industry, occupation, and office environment. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the collection unit, anonymization unit, learning unit, advice unit, risk identification unit, and caution point presentation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects records of violations of the Labor Standards Act. The anonymization unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and anonymizes the collected records. The learning unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and learns the anonymized data. The advice unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and provides advice on legal compliance. The risk identification unit is implemented, for example, by the identification processing unit 290 of the data processing device 12 and points out the risk of legal violations. The caution point presentation unit is implemented, for example, by the control unit 46A of the smart glasses 214 and presents caution points tailored to the industry, occupation, and office environment. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the collection unit, anonymization unit, learning unit, advice unit, risk identification unit, and caution point presentation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects records of violations of the Labor Standards Act. The anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes the collected records. The learning unit is implemented by the identification processing unit 290 of the data processing unit 12 and learns the anonymized data. The advice unit is implemented by the identification processing unit 290 of the data processing unit 12 and provides advice on legal compliance. The risk identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and points out the risk of legal violations. The caution point presentation unit is implemented by the control unit 46A of the headset terminal 314 and presents caution points tailored to the industry, occupation, and office environment. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0170] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the collection unit, anonymization unit, learning unit, advice unit, risk identification unit, and caution point presentation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects records of violations of the Labor Standards Act. The anonymization unit is implemented by the identification processing unit 290 of the data processing unit 12 and anonymizes the collected records. The learning unit is implemented by the identification processing unit 290 of the data processing unit 12 and learns the anonymized data. The advice unit is implemented by the identification processing unit 290 of the data processing unit 12 and provides advice on legal compliance. The risk identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and points out the risk of legal violations. The caution point presentation unit is implemented by the control unit 46A of the robot 414 and presents caution points tailored to the industry, occupation, and office environment. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0178] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0180] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0181] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0182] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0187] 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.

[0188] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0189] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0191] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0195] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0196] (Note 1) The collection department collects records of violations of the Labor Standards Act, An anonymization unit that anonymizes the records collected by the aforementioned collection unit, A learning unit that learns data anonymized by the anonymization unit, An advice unit provides advice on legal compliance based on the data learned by the aforementioned learning unit, A risk identification unit that identifies the risk of legal violations based on the advice provided by the aforementioned advisory unit, The system includes a cautionary point presentation unit that presents cautionary points tailored to the industry, job type, and office environment based on the risks identified by the aforementioned risk identification unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is The system estimates user sentiment and adjusts the timing of collecting records of labor law violations based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is We analyze each company's past violation records and select the most optimal collection method. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is When collecting records of violations of the Labor Standards Act, filtering is performed based on the size and industry of the company. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is It estimates the user's emotions and determines the priority of the records to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting records of violations of the Labor Standards Act, the collection of highly relevant records will be prioritized based on the geographical location information of the company. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting records of violations of labor standards laws, we analyze companies' social media activities and collect relevant records. The system described in Appendix 1, characterized by the features described herein. (Note 8) The anonymization unit is, The system estimates the user's emotions and adjusts the anonymization method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The anonymization unit is, During anonymization, adjust the level of anonymization based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The anonymization unit is, When anonymizing data, different anonymization algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 11) The anonymization unit is, The system estimates the user's emotions and determines the priority of anonymization based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The anonymization unit is, When anonymizing data, the priority of anonymization is determined based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 13) The anonymization unit is, During anonymization, the order of anonymization is adjusted based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned learning unit, During training, different learning methods are applied to each data category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned learning unit, During training, the training data is weighted based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned learning unit, During training, the system uses relevant market data as a reference. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned advice section, It estimates the user's emotions and adjusts the way advice is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned advice section, When providing advice, adjust the level of detail of the advice based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned advice section, When providing advice, different advice algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned advice section, It estimates the user's emotions and adjusts the length of the advice based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned advice section, When providing advice, we prioritize the advice based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned advice section, When providing advice, we adjust the order of advice based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned risk identification section is, We estimate user sentiment and adjust the risk identification method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned risk identification section is, When identifying risks, adjust the level of detail in the risk assessment based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned risk identification section is, When identifying risks, different risk identification algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned risk identification section is, The system estimates user sentiment and prioritizes risk identification based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned risk identification section is, When identifying risks, prioritize the risk identification based on the timing of data submission. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned risk identification section is, When identifying risks, adjust the order of risk identification based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned section for displaying points of caution is The system estimates the user's emotions and adjusts how warnings are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned section for displaying points of caution is When presenting cautionary notes, adjust the level of detail based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned section for displaying points of caution is When presenting cautionary notes, different cautionary note presentation algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned section for displaying points of caution is The system estimates the user's emotions and prioritizes points of attention based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned section for displaying points of caution is When presenting points to note, prioritize those points based on the data submission timing. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned section for displaying points of caution is When presenting cautionary notes, adjust the order of the notes based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection department collects records of violations of the Labor Standards Act, An anonymization unit that anonymizes the records collected by the aforementioned collection unit, A learning unit that learns data anonymized by the anonymization unit, An advice unit provides advice on legal compliance based on the data learned by the aforementioned learning unit, A risk identification unit that identifies the risk of legal violations based on the advice provided by the aforementioned advisory unit, The system includes a cautionary point presentation unit that presents cautionary points tailored to the industry, job type, and office environment based on the risks identified by the aforementioned risk identification unit. A system characterized by the following features.

2. The aforementioned collection unit is The system estimates user sentiment and adjusts the timing of collecting records of labor law violations based on the estimated user sentiment. The system according to feature 1.

3. The aforementioned collection unit is We analyze each company's past violation records and select the most optimal collection method. The system according to feature 1.

4. The aforementioned collection unit is When collecting records of violations of the Labor Standards Act, filtering is performed based on the size and industry of the company. The system according to feature 1.

5. The aforementioned collection unit is It estimates the user's emotions and determines the priority of the records to collect based on the estimated user emotions. The system according to feature 1.

6. The aforementioned collection unit is When collecting records of violations of the Labor Standards Act, the collection of highly relevant records will be prioritized based on the geographical location information of the company. The system according to feature 1.

7. The aforementioned collection unit is When collecting records of violations of labor standards laws, we analyze companies' social media activities and collect relevant records. The system according to feature 1.

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

Images