system

Abstract

The system according to this embodiment aims to efficiently identify business opportunities and risks by anonymizing, integrating, and analyzing data within a company. [Solution] The system according to the embodiment comprises an anonymization unit, an integration unit, an analysis unit, an identification unit, and a proposal unit. The anonymization unit anonymizes the data. The integration unit integrates the data anonymized by the anonymization unit. The analysis unit analyzes the data integrated by the integration unit. The identification unit identifies business opportunities and risks based on the data analyzed by the analysis unit. The proposal unit makes proposals based on the business opportunities and risks identified by the identification unit.

Description

Technical Field

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

Background Art

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

[0007] The system according to this embodiment can anonymize, integrate, and analyze data within a company to efficiently identify business opportunities and risks. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between 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 AI ​​agent system according to an embodiment of the present invention is a system that combines a vector database and a generative AI. This AI agent system anonymizes all internal data of each group company using the generative AI and integrates it into the vector database. Next, it utilizes the generative AI and the company-wide vector database to automatically discover and propose all business opportunities and potential risks that may go unnoticed by the person in charge or management. This promotes and strengthens cooperation among group companies and improves overall competitiveness by integrating and gaining an overview of data across the entire group. Furthermore, this system does not provide external services and is used solely to strengthen the competitiveness of the group. For example, all internal data of each group company is anonymized using the generative AI and integrated into the vector database. In this process, the generative AI analyzes the data of each company and anonymizes personal information. For example, personal information such as employee salary information and performance data is anonymized and stored in the integrated vector database. This allows the data to be used without violating the Personal Information Protection Act. Next, it utilizes the generative AI and the company-wide vector database to automatically discover and propose all business opportunities and potential risks that may go unnoticed by the person in charge or management. The generative AI analyzes the data stored in the vector database to identify new business opportunities and potential risks. For example, it identifies untapped areas within the group and proposes new business ventures. It also suggests ways to optimally utilize the group's assets. This can improve the overall competitiveness of the group. Furthermore, by integrating and gaining a comprehensive overview of group-wide data, it promotes and strengthens cooperation among group companies. The generating AI analyzes data from each company and identifies potential for cooperation. For example, by sharing technology and assets within the group, it reduces the cost and time required to launch new businesses. It also accelerates collaboration within the group and improves the speed of project launches. This can improve the overall competitiveness of the group. This system is not used to provide external services and is used solely to strengthen the group's competitiveness. The generating AI analyzes data within the group and makes optimal suggestions. For example, it proposes new business ventures and ways to optimally utilize assets. This can improve the overall competitiveness of the group. As a result, the AI ​​agent system can integrate data from across the group and automatically discover and propose business opportunities and risks.

[0029] The AI ​​agent system according to this embodiment comprises an anonymization unit, an integration unit, an analysis unit, a specification unit, and a proposal unit. The anonymization unit anonymizes data. The anonymization unit anonymizes personal information such as employee salary information and performance data. The anonymization unit can anonymize personal information using a generation AI by methods such as data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit inputs a prompt to the generation AI saying, "Please anonymize this data," and the generation AI analyzes the data and performs anonymization. The integration unit integrates the data anonymized by the anonymization unit. The integration unit integrates the anonymized data into a vector database, for example. The integration unit can integrate data using a generation AI based on the type of database and the integration algorithm. For example, the integration unit inputs a prompt to the generation AI saying, "Please integrate this data into a vector database," and the generation AI analyzes the data and performs integration. The analysis unit analyzes the data integrated by the integration unit. The analysis unit analyzes the data stored in the vector database, for example. The Analysis Department can analyze data based on statistical analysis and machine learning algorithms using generative AI. For example, the Analysis Department can input a prompt to the generative AI such as "Please analyze this data," and the generative AI will analyze the data and extract useful information. The Identification Department identifies business opportunities and risks based on the data analyzed by the Analysis Department. For example, the Identification Department can identify untapped areas within the group and propose new businesses. The Identification Department can use generative AI to make identifications based on evaluation criteria for business opportunities and risks. For example, the Identification Department can input a prompt to the generative AI such as "Please identify business opportunities from this data," and the generative AI will analyze the data and identify business opportunities. The Proposal Department makes proposals based on the business opportunities and risks identified by the Identification Department. For example, the Proposal Department can propose ways to optimally utilize assets within the group. The Proposal Department can use generative AI to make proposals based on evaluation criteria for proposal format and content. For example, the Proposal Department can input a prompt to the generative AI such as "Please make a proposal for this business opportunity," and the generative AI will analyze the data and make a proposal.As a result, the AI ​​agent system according to this embodiment can automatically discover and propose business opportunities and risks through data anonymization, integration, analysis, identification, and suggestion.

[0030] The anonymization unit anonymizes data. For example, the anonymization unit anonymizes personal information such as employee salary information and performance data. Specifically, the anonymization unit can anonymize personal information using generational AI through methods such as data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit inputs a prompt to the generational AI, "Please anonymize this data," and the generational AI analyzes the data and performs anonymization. The generational AI first analyzes the content of the data and identifies personal information. Next, it applies masking, pseudo-anonymization, or complete anonymization techniques to the identified personal information. Masking hides personal information by replacing specific strings. Pseudo-anonymization converts personal information into a unique identifier, making it impossible to restore the original information. Complete anonymization completely deletes personal information, leaving no trace of the original information. This allows the anonymization unit to protect data privacy while retaining information necessary for analysis and integration. Furthermore, the anonymization unit can adapt to specific requirements and regulations by adjusting the accuracy and method of anonymization. For example, it can set the level of anonymization based on specific legal regulations and re-anonymize the data as needed. This allows the anonymization unit to balance data privacy protection with usability.

[0031] The integration unit integrates data anonymized by the anonymization unit. For example, the integration unit integrates anonymized data into a vector database. Specifically, the integration unit can use a generative AI to integrate data based on the database type and integration algorithm. For example, the integration unit prompts the generative AI with "Integrate this data into the vector database," and the generative AI analyzes the data and performs the integration. The generative AI first analyzes the data format and structure and generates an appropriate database schema. Next, it converts the data content into vector format and stores it in the vector database. This allows the integration unit to centrally manage data of different formats and structures and perform efficient searching and analysis. Furthermore, the integration unit has a mechanism to handle data updates and additions, enabling real-time data integration. For example, when new data is added, the generative AI automatically analyzes the data and integrates it into the existing database. The integration unit also has a checking function to maintain data integrity and consistency, preventing data duplication and inconsistencies. This allows the integration unit to perform data integration and management efficiently and accurately, improving the overall system performance.

[0032] The analysis unit analyzes data integrated by the integration unit. For example, the analysis unit analyzes data stored in a vector database. Specifically, the analysis unit can use generative AI to analyze data based on statistical analysis and machine learning algorithms. For example, the analysis unit can input a prompt to the generative AI such as "Please analyze this data," and the generative AI will analyze the data and extract useful information. The generative AI first preprocesses the data, such as imputing missing values ​​and detecting outliers. Next, it applies statistical analysis and machine learning algorithms to extract data patterns and trends. For example, it can use regression analysis to predict sales or clustering to identify customer segments. Furthermore, the analysis unit can also use generative AI to visualize data. For example, it can input a prompt to the generative AI such as "Please visualize this data," and the generative AI will analyze the data and generate graphs and charts. This allows the analysis unit to provide data analysis results in an intuitively understandable format. Additionally, because the analysis unit can perform data analysis in real time, it can support rapid decision-making. For example, it can analyze data that is updated in real time and detect abnormal patterns and trends early. This allows the analysis unit to perform data analysis efficiently and accurately, supporting business decision-making.

[0033] The Identification Department identifies business opportunities and risks based on data analyzed by the Analysis Department. For example, the Identification Department can identify untapped areas within the group and propose new business ventures. Specifically, the Identification Department can use generative AI to identify business opportunities and risks based on evaluation criteria. For example, the Identification Department can input a prompt to the generative AI such as "Identify business opportunities from this data," and the generative AI will analyze the data to identify business opportunities. The generative AI first analyzes the content of the data and extracts patterns and trends related to business opportunities and risks. Next, it evaluates specific business opportunities and risks based on evaluation criteria for business opportunities and risks. For example, it can evaluate the demand and competitive situation of new markets and identify business opportunities in untapped areas. In risk assessment, it can evaluate the risks associated with specific business activities and propose risk mitigation measures. This allows the Identification Department to quickly and accurately identify business opportunities and risks and support business decision-making. Furthermore, the Identification Department can also use generative AI to perform simulations for the identified business opportunities and risks. For example, it can perform scenario analysis for identified business opportunities and propose optimal strategies. This allows the specific department to not only identify business opportunities and risks, but also propose concrete countermeasures and strategies.

[0034] The proposal department makes proposals based on business opportunities and risks identified by specific departments. For example, the proposal department might propose ways to optimally utilize assets within the group. Specifically, the proposal department can use generative AI to make proposals based on the format and evaluation criteria of the proposal content. For example, the proposal department can input a prompt to the generative AI such as "Please make a proposal for this business opportunity," and the generative AI will analyze the data and make a proposal. The generative AI first analyzes data related to the identified business opportunity and risk and generates the optimal proposal content. Next, it organizes the proposal content based on the format and evaluation criteria of the proposal and creates a specific proposal document. For example, it can evaluate the resources, costs, and risks required to launch a new business and propose the optimal strategy. It can also propose improvement measures and risk reduction measures for existing businesses, supporting business efficiency and risk management. This allows the proposal department to make specific proposals for business opportunities and risks quickly and accurately, supporting business decision-making. Furthermore, the proposal department can also use generative AI to simulate the content of the proposal. For example, it can simulate the implementation scenario of the proposed strategy and evaluate the expected results and risks. This allows the proposal department to evaluate the feasibility and effectiveness of the proposed content in advance, enabling them to make more accurate proposals.

[0035] The anonymization unit can anonymize personal information such as employee salary information and performance data. For example, the anonymization unit can anonymize employee salary information using a generation AI. For instance, the anonymization unit inputs a prompt to the generation AI such as "Anonymize this salary information," and the generation AI analyzes the data and performs the anonymization. The anonymization unit can also anonymize performance data using the generation AI. For example, the anonymization unit inputs a prompt to the generation AI such as "Anonymize this performance data," and the generation AI analyzes the data and performs the anonymization. Furthermore, the anonymization unit can also anonymize other personal information using the generation AI. For example, the anonymization unit inputs a prompt to the generation AI such as "Anonymize this personal information," and the generation AI analyzes the data and performs the anonymization. By anonymizing personal information, data security can be ensured while utilizing the data.

[0036] The integration unit can integrate anonymized data into a vector database. For example, the integration unit can integrate anonymized data into a vector database using a generative AI. For instance, the integration unit can input a prompt to the generative AI such as, "Integrate this anonymized data into the vector database," and the generative AI will analyze the data and perform the integration. The integration unit can also integrate data from different databases using the generative AI. For example, the integration unit can input a prompt to the generative AI such as, "Integrate the data from this database," and the generative AI will analyze the data and perform the integration. Furthermore, the integration unit can apply different integration algorithms to the generative AI depending on the type of data. For example, the integration unit can input a prompt to the generative AI such as, "Apply an integration algorithm suitable for this data," and the generative AI will analyze the data and apply the appropriate integration algorithm. This enables centralized data management by integrating anonymized data into a vector database.

[0037] The analysis unit can analyze data stored in a vector database. For example, the analysis unit can analyze data stored in a vector database using a generative AI. For instance, the analysis unit can input a prompt to the generative AI such as "Analyze the data in this vector database," and the generative AI will analyze the data and extract useful information. The analysis unit can also apply statistical analysis and machine learning algorithms using the generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Apply statistical analysis to this data," and the generative AI will analyze the data and extract statistical information. Furthermore, the analysis unit can also analyze the interrelationships between data using the generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Analyze the interrelationships between this data," and the generative AI will analyze the data and identify the interrelationships. In this way, useful information can be extracted from the data by analyzing the data stored in the vector database.

[0038] The Specialist Department can identify unentered areas within the group and propose new business ventures. For example, the Specialist Department can use generative AI to identify unentered areas within the group. For instance, the Specialist Department can input a prompt to the generative AI such as, "Identify unentered areas from this data," and the generative AI will analyze the data to identify these areas. The Specialist Department can also use generative AI to propose new business ventures. For example, the Specialist Department can input a prompt to the generative AI such as, "Propose a new business venture for this unentered area," and the generative AI will analyze the data to propose a new business venture. Furthermore, the Specialist Department can also use generative AI to apply criteria for evaluating business opportunities and risks. For example, the Specialist Department can input a prompt to the generative AI such as, "Apply the criteria for evaluating this business opportunity," and the generative AI will analyze the data to evaluate the business opportunity. This allows the Specialist Department to expand business opportunities by identifying unentered areas and proposing new business ventures.

[0039] The proposal department can propose ways to optimally utilize assets within the group. For example, the proposal department can propose ways to optimally utilize assets within the group using a generative AI. For instance, the proposal department can input a prompt to the generative AI such as, "Please propose a way to optimally utilize this asset," and the generative AI will analyze the data and propose an optimal utilization method. The proposal department can also apply asset evaluation criteria and details of utilization methods using the generative AI. For example, the proposal department can input a prompt to the generative AI such as, "Please apply the evaluation criteria for this asset," and the generative AI will analyze the data and evaluate the asset. Furthermore, the proposal department can also propose ways to share assets within the group using the generative AI. For example, the proposal department can input a prompt to the generative AI such as, "Please propose a way to share this asset," and the generative AI will analyze the data and propose a sharing method. In this way, by proposing ways to optimally utilize assets within the group, effective utilization of assets becomes possible.

[0040] The proposal department can accelerate collaboration within the group and improve the speed of project launch. For example, the proposal department can propose methods to accelerate collaboration within the group using generative AI. For instance, the proposal department can input a prompt into the generative AI such as, "Please propose a way to accelerate this collaboration," and the generative AI will analyze the data and propose a method to accelerate it. The proposal department can also propose methods to improve the speed of project launch using generative AI. For example, the proposal department can input a prompt into the generative AI such as, "Please propose a way to improve the speed of this project launch," and the generative AI will analyze the data and propose a method to improve it. Furthermore, the proposal department can also optimize the means of collaboration and the project launch process using generative AI. For example, the proposal department can input a prompt into the generative AI such as, "Please optimize the means of collaboration," and the generative AI will analyze the data and perform the optimization. By accelerating collaboration within the group and improving the speed of project launch, competitiveness can be strengthened.

[0041] The anonymization unit can apply different anonymization algorithms depending on the type of data. For example, the anonymization unit can apply a sophisticated encryption algorithm to employee salary information. The anonymization unit can use a generative AI to select and apply an appropriate anonymization algorithm depending on the type of data. For example, the anonymization unit can input a prompt to the generative AI such as, "Apply an appropriate anonymization algorithm according to the type of data," and the generative AI will analyze the data and apply the appropriate anonymization algorithm. The anonymization unit can also anonymize performance data using data masking technology. For example, the anonymization unit can input a prompt to the generative AI such as, "Apply data masking technology to this performance data," and the generative AI will analyze the data and perform data masking. Furthermore, the anonymization unit can anonymize customer information using pseudo-data generation technology. For example, the anonymization unit can input a prompt to the generative AI such as, "Apply pseudo-data generation technology to this customer information," and the generative AI will analyze the data and generate pseudo-data. By applying an anonymization algorithm according to the type of data, the security and usability of the data can be optimized.

[0042] The anonymization unit can adjust the level of anonymization based on the importance of the data. For example, the anonymization unit can perform detailed anonymization on highly important data to enhance the protection of personal information. The anonymization unit can use generative AI to adjust the level of anonymization based on the importance of the data. For example, the anonymization unit can input a prompt to the generative AI such as "Adjust the level of anonymization based on the importance of this data," and the generative AI will analyze the data and adjust the level of anonymization. The anonymization unit can also perform simplified anonymization on less important data to increase its usability. For example, the anonymization unit can input a prompt to the generative AI such as "Perform simplified anonymization based on the importance of this data," and the generative AI will analyze the data and perform anonymization. Furthermore, the anonymization unit can perform balanced anonymization on data of moderate importance. For example, the anonymization unit can input a prompt to the generative AI such as "Perform balanced anonymization based on the importance of this data," and the generative AI will analyze the data and perform anonymization. This allows for a good balance between data protection and availability by adjusting the level of anonymization based on the importance of the data.

[0043] The anonymization unit can determine the priority of anonymization based on the data submission date. For example, the anonymization unit can prioritize anonymizing the most recent data. The anonymization unit can use a generative AI to determine the priority of anonymization based on the data submission date. For example, the anonymization unit can input a prompt to the generative AI such as, "Determine the priority of anonymization based on the submission date of this data," and the generative AI will analyze the data to identify the submission date and determine the priority of anonymization. The anonymization unit can also postpone older data. For example, the anonymization unit can input a prompt to the generative AI such as, "Postpone older data based on the submission date of this data," and the generative AI will analyze the data to identify the submission date and perform anonymization. Furthermore, if the submission dates are concentrated within a specific period, the anonymization unit can prioritize anonymizing data from that period. For example, the anonymization unit can input a prompt to the generative AI such as, "Prioritize anonymizing data from a specific period based on the submission date of this data," and the generative AI will analyze the data to identify the submission date and perform anonymization. This allows for prioritizing the processing of the most recent data by determining anonymization priorities based on when the data was submitted.

[0044] The anonymization unit can adjust the anonymization order based on the relevance of the data. For example, the anonymization unit can anonymize highly relevant data in a batch. The anonymization unit can use a generative AI to adjust the anonymization order based on the relevance of the data. For example, the anonymization unit can input a prompt to the generative AI such as "Adjust the anonymization order based on the relevance of this data," and the generative AI will analyze the data, identify the relevance, and adjust the anonymization order. The anonymization unit can also anonymize less relevant data individually. For example, the anonymization unit can input a prompt to the generative AI such as "Anonymize this data individually based on the relevance," and the generative AI will analyze the data, identify the relevance, and perform the anonymization. Furthermore, the anonymization unit can dynamically adjust the anonymization order according to the relevance of the data. For example, the anonymization unit can input a prompt to the generative AI such as "Dynamically adjust the anonymization order based on the relevance of this data," and the generative AI will analyze the data, identify the relevance, and dynamically adjust the anonymization order. This allows for efficient data processing by adjusting the anonymization order based on the relevance of the data.

[0045] The integration unit can improve the accuracy of integration by considering the interrelationships of data. For example, the integration unit can analyze the interrelationships of data and prioritize the integration of highly relevant data. The integration unit can use generative AI to improve the accuracy of integration by considering the interrelationships of data. For example, the integration unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and improve the accuracy of integration," and the generative AI will analyze the data, identify the interrelationships, and improve the accuracy of integration. The integration unit can also optimize the order of integration by considering the interrelationships of data. For example, the integration unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and optimize the order of integration," and the generative AI will analyze the data, identify the interrelationships, and optimize the order of integration. Furthermore, the integration unit can apply algorithms to improve the accuracy of integration based on the interrelationships of data. For example, the integration unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and apply an algorithm to improve the accuracy of integration," and the generative AI will analyze the data, identify the interrelationships, and apply the algorithm. As a result, by considering the interrelationships of data, the accuracy of integration is improved and data consistency is maintained.

[0046] The integration unit can apply different integration algorithms depending on the data category. For example, the integration unit can apply a specific integration algorithm to financial data. The integration unit can use generative AI to select and apply the appropriate integration algorithm according to the data category. For example, the integration unit can input a prompt to the generative AI such as, "Apply the appropriate integration algorithm according to this data category," and the generative AI will analyze the data and apply the appropriate integration algorithm. The integration unit can also apply a different integration algorithm to human resources data. For example, the integration unit can input a prompt to the generative AI such as, "Apply the appropriate integration algorithm to this human resources data," and the generative AI will analyze the data and apply the appropriate integration algorithm. Furthermore, the integration unit can apply yet another different integration algorithm to customer data. For example, the integration unit can input a prompt to the generative AI such as, "Apply the appropriate integration algorithm to this customer data," and the generative AI will analyze the data and apply the appropriate integration algorithm. By applying integration algorithms according to the data category, the accuracy of data integration is improved.

[0047] The integration unit can perform integration while considering the geographical distribution of the data. For example, the integration unit can prioritize the integration of data that is geographically close. The integration unit can use generative AI to perform integration while considering the geographical distribution of the data. For example, the integration unit can input a prompt to the generative AI such as "Please perform integration while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and perform the integration. The integration unit can also postpone the integration of data that is geographically far away. For example, the integration unit can input a prompt to the generative AI such as "Please postpone the integration of data that is far away while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and perform the integration. Furthermore, the integration unit can optimize the order of integration based on geographical distribution. For example, the integration unit can input a prompt to the generative AI such as "Please optimize the order of integration while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and optimize the order of integration. This makes efficient data integration possible by considering the geographical distribution of the data.

[0048] The integration unit can improve the accuracy of integration by referring to relevant literature for the data. For example, the integration unit can optimize the data integration method based on relevant literature. The integration unit can improve the accuracy of integration by referring to relevant literature for the data using generative AI. For example, the integration unit can input a prompt to the generative AI such as "Refer to relevant literature for this data to improve the accuracy of integration," and the generative AI will analyze the data, identify relevant literature, and improve the accuracy of integration. The integration unit can also apply algorithms that improve the accuracy of integration by referring to relevant literature. For example, the integration unit can input a prompt to the generative AI such as "Refer to relevant literature for this data to apply the algorithm," and the generative AI will analyze the data, identify relevant literature, and apply the algorithm. Furthermore, the integration unit can also optimize the data integration order based on relevant literature. For example, the integration unit can input a prompt to the generative AI such as "Refer to relevant literature for this data to optimize the integration order," and the generative AI will analyze the data, identify relevant literature, and optimize the integration order. As a result, by referring to relevant literature for the data, the accuracy of integration is improved and data consistency is maintained.

[0049] The analysis unit can improve the accuracy of the analysis by considering the interrelationships between data. For example, the analysis unit can analyze the interrelationships between data and prioritize the analysis of highly relevant data. The analysis unit can improve the accuracy of the analysis by considering the interrelationships between data using generative AI. For example, the analysis unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and improve the accuracy of the analysis," and the generative AI will analyze the data, identify the interrelationships, and improve the accuracy of the analysis. The analysis unit can also optimize the order of analysis by considering the interrelationships between data. For example, the analysis unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and optimize the order of analysis," and the generative AI will analyze the data, identify the interrelationships, and optimize the order of analysis. Furthermore, the analysis unit can apply algorithms to improve the accuracy of the analysis based on the interrelationships between data. For example, the analysis unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and apply an algorithm to improve the accuracy of the analysis," and the generative AI will analyze the data, identify the interrelationships, and apply the algorithm. As a result, by considering the interrelationships between data, the accuracy of the analysis is improved and data consistency is maintained.

[0050] The analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit can apply a specific analysis algorithm to financial data. The analysis unit can use a generative AI to select and apply an appropriate analysis algorithm according to the data category. For example, the analysis unit can input a prompt to the generative AI saying, "Apply an appropriate analysis algorithm according to this data category," and the generative AI will analyze the data and apply the appropriate analysis algorithm. The analysis unit can also apply a different analysis algorithm to human resources data. For example, the analysis unit can input a prompt to the generative AI saying, "Apply an appropriate analysis algorithm to this human resources data," and the generative AI will analyze the data and apply the appropriate analysis algorithm. Furthermore, the analysis unit can apply yet another different analysis algorithm to customer data. For example, the analysis unit can input a prompt to the generative AI saying, "Apply an appropriate analysis algorithm to this customer data," and the generative AI will analyze the data and apply the appropriate analysis algorithm. By applying analysis algorithms according to the data category, the accuracy of the analysis is improved.

[0051] The analysis unit can perform analysis while considering the geographical distribution of the data. For example, the analysis unit can prioritize the analysis of geographically close data. The analysis unit can use generative AI to perform analysis while considering the geographical distribution of the data. For example, the analysis unit can input a prompt to the generative AI such as "Please perform analysis while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and perform the analysis. The analysis unit can also postpone the analysis of geographically distant data. For example, the analysis unit can input a prompt to the generative AI such as "Please postpone the analysis of distant data while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and perform the analysis. Furthermore, the analysis unit can optimize the order of analysis based on geographical distribution. For example, the analysis unit can input a prompt to the generative AI such as "Please optimize the order of analysis while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and optimize the order of analysis. This makes efficient data analysis possible by considering the geographical distribution of the data.

[0052] The analysis unit can improve the accuracy of its analysis by referring to relevant literature for the data. For example, the analysis unit can optimize the data analysis method based on relevant literature. The analysis unit can improve the accuracy of its analysis by referring to relevant literature for the data using a generative AI. For example, the analysis unit can input a prompt to the generative AI saying, "Please improve the accuracy of the analysis by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and improve the accuracy of the analysis. The analysis unit can also apply algorithms that improve the accuracy of the analysis by referring to relevant literature. For example, the analysis unit can input a prompt to the generative AI saying, "Please apply the algorithm by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and apply the algorithm. Furthermore, the analysis unit can also optimize the order of data analysis based on relevant literature. For example, the analysis unit can input a prompt to the generative AI saying, "Please optimize the order of analysis by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and optimize the order of analysis. As a result, by referring to relevant literature for the data, the accuracy of the analysis is improved and the consistency of the data is maintained.

[0053] The identification unit can improve specific accuracy by considering the interrelationships of data. For example, the identification unit can analyze the interrelationships of data and prioritize the identification of highly relevant data. The identification unit can improve specific accuracy by considering the interrelationships of data using a generative AI. For example, the identification unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and improve specific accuracy," and the generative AI will analyze the data, identify the interrelationships, and improve specific accuracy. The identification unit can also optimize specific order by considering the interrelationships of data. For example, the identification unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and optimize specific order," and the generative AI will analyze the data, identify the interrelationships, and optimize specific order. Furthermore, the identification unit can apply algorithms that improve specific accuracy based on the interrelationships of data. For example, the identification unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and apply an algorithm that improves specific accuracy," and the generative AI will analyze the data, identify the interrelationships, and apply the algorithm. As a result, by considering the interrelationships of data, specific accuracy is improved and data consistency is maintained.

[0054] The identification unit can apply different identification algorithms depending on the data category. For example, the identification unit can apply a specific algorithm to financial data to identify business opportunities. The identification unit can use generative AI to select and apply the appropriate identification algorithm depending on the data category. For example, the identification unit can input a prompt to the generative AI such as, "Apply the appropriate identification algorithm according to this data category," and the generative AI will analyze the data and apply the appropriate identification algorithm. The identification unit can also apply a different identification algorithm to human resources data to identify potential risks. For example, the identification unit can input a prompt to the generative AI such as, "Apply the appropriate identification algorithm to this human resources data," and the generative AI will analyze the data and apply the appropriate identification algorithm. Furthermore, the identification unit can apply yet another identification algorithm to customer data to identify new business opportunities. For example, the identification unit can input a prompt to the generative AI such as, "Apply the appropriate identification algorithm to this customer data," and the generative AI will analyze the data and apply the appropriate identification algorithm. This improves the accuracy of identification by applying identification algorithms according to the data category.

[0055] The identification unit can perform identification while considering the geographical distribution of the data. For example, the identification unit can prioritize the identification of geographically close data. The identification unit can use a generation AI to perform identification while considering the geographical distribution of the data. For example, the identification unit can input a prompt to the generation AI saying, "Please perform identification while considering the geographical distribution of this data," and the generation AI will analyze the data, identify the geographical distribution, and perform the identification. The identification unit can also postpone the identification of geographically distant data. For example, the identification unit can input a prompt to the generation AI saying, "Please postpone the identification of distant data while considering the geographical distribution of this data," and the generation AI will analyze the data, identify the geographical distribution, and perform the identification. Furthermore, the identification unit can optimize the order of identification based on the geographical distribution. For example, the identification unit can input a prompt to the generation AI saying, "Please optimize the order of identification while considering the geographical distribution of this data," and the generation AI will analyze the data, identify the geographical distribution, and optimize the order of identification. This makes efficient data identification possible by considering the geographical distribution of the data.

[0056] The identification unit can improve the accuracy of identification by referring to relevant literature for the data. For example, the identification unit can optimize the data identification method based on relevant literature. The identification unit can improve the accuracy of identification by referring to relevant literature for the data using a generative AI. For example, the identification unit can input a prompt to the generative AI such as "Improve the accuracy of identification by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and improve the accuracy of identification. The identification unit can also apply an algorithm that improves the accuracy of identification by referring to relevant literature. For example, the identification unit can input a prompt to the generative AI such as "Apply the algorithm by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and apply the algorithm. Furthermore, the identification unit can also optimize the order of identification of data based on relevant literature. For example, the identification unit can input a prompt to the generative AI such as "Optimize the order of identification by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and optimize the order of identification. As a result, by referring to relevant literature for the data, the accuracy of identification is improved and the consistency of the data is maintained.

[0057] The proposal department can adjust the level of detail of its proposals based on the importance of business opportunities and risks. For example, the proposal department can provide detailed proposals for highly important business opportunities. The proposal department can use generative AI to adjust the level of detail of its proposals based on the importance of business opportunities and risks. For example, the proposal department can input a prompt to the generative AI such as, "Adjust the level of detail of this proposal based on the importance of this business opportunity," and the generative AI will analyze the data to identify the importance and adjust the level of detail of the proposal. The proposal department can also provide simplified proposals for less important business opportunities. For example, the proposal department can input a prompt to the generative AI such as, "Provide a simplified proposal based on the importance of this business opportunity," and the generative AI will analyze the data to identify the importance and provide a proposal. Furthermore, the proposal department can provide balanced proposals for business opportunities of moderate importance. For example, the proposal department can input a prompt to the generative AI such as, "Provide a balanced proposal based on the importance of this business opportunity," and the generative AI will analyze the data to identify the importance and provide a proposal. This allows for the creation of appropriate proposals by adjusting the level of detail in the proposal according to the importance of business opportunities and risks.

[0058] The proposal department can apply different proposal algorithms depending on the category of business opportunity or risk. For example, the proposal department can apply a specific proposal algorithm to financial risk. The proposal department can use generative AI to select and apply the appropriate proposal algorithm according to the category of business opportunity or risk. For example, the proposal department can input a prompt to the generative AI such as, "Apply the appropriate proposal algorithm according to this category of business opportunity or risk," and the generative AI will analyze the data and apply the appropriate proposal algorithm. The proposal department can also apply a different proposal algorithm to human resources risk. For example, the proposal department can input a prompt to the generative AI such as, "Apply the appropriate proposal algorithm for this human resources risk," and the generative AI will analyze the data and apply the appropriate proposal algorithm. Furthermore, the proposal department can apply yet another proposal algorithm to customer risk. For example, the proposal department can input a prompt to the generative AI such as, "Apply the appropriate proposal algorithm for this customer risk," and the generative AI will analyze the data and apply the appropriate proposal algorithm. This improves the accuracy of proposals by applying proposal algorithms according to the category of business opportunity or risk.

[0059] The proposal department can prioritize proposals based on the submission timing of business opportunities and risks. For example, the proposal department can prioritize the most recent business opportunities. The proposal department can use generative AI to prioritize proposals based on the submission timing of business opportunities and risks. For example, the proposal department can input a prompt into the generative AI such as, "Please prioritize proposals based on the submission timing of these business opportunities and risks," and the generative AI will analyze the data to identify submission timings and determine the proposal priority. The proposal department can also postpone older business opportunities. For example, the proposal department can input a prompt into the generative AI such as, "Please postpone older business opportunities based on the submission timing of these business opportunities and risks," and the generative AI will analyze the data to identify submission timings and make proposals. Furthermore, if submission timings are concentrated within a specific period, the proposal department can prioritize business opportunities within that period. For example, the proposal department can input a prompt into the generative AI such as, "Please prioritize business opportunities within a specific period based on the submission timing of these business opportunities and risks," and the generative AI will analyze the data to identify submission timings and make proposals. This allows for proposals to be based on the latest information by prioritizing proposals based on the timing of business opportunity and risk presentations.

[0060] The proposal department can adjust the order of proposals based on the relevance of business opportunities and risks. For example, the proposal department can propose highly relevant business opportunities in a group. The proposal department can use generative AI to adjust the order of proposals based on the relevance of business opportunities and risks. For example, the proposal department can input a prompt to the generative AI such as, "Please adjust the order of proposals based on the relevance of these business opportunities and risks," and the generative AI will analyze the data, identify the relevance, and adjust the order of proposals. The proposal department can also propose less relevant business opportunities individually. For example, the proposal department can input a prompt to the generative AI such as, "Please propose individually based on the relevance of these business opportunities and risks," and the generative AI will analyze the data, identify the relevance, and make proposals. Furthermore, the proposal department can dynamically adjust the order of proposals according to the relevance of business opportunities. For example, the proposal department can input a prompt to the generative AI such as, "Please dynamically adjust the order of proposals based on the relevance of these business opportunities and risks," and the generative AI will analyze the data, identify the relevance, and dynamically adjust the order of proposals. This allows for more efficient proposals by adjusting the order of proposals based on the relevance of business opportunities and risks.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes by considering the geographical distribution of the data. For example, the anonymization unit can prioritize anonymizing geographically close data. The integration unit can prioritize integrating geographically close data. The analysis unit can prioritize analyzing geographically close data. The identification unit can prioritize identifying geographically close data. The suggestion unit can prioritize suggesting geographically close business opportunities. This enables efficient data processing by considering the geographical distribution of the data.

[0063] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes based on the timing of data submission. For example, the anonymization unit can prioritize anonymizing the most recent data. The integration unit can prioritize integrating the most recent data. The analysis unit can prioritize analyzing the most recent data. The identification unit can prioritize identifying the most recent data. The suggestion unit can prioritize suggesting the most recent business opportunities. By adjusting each process based on the timing of data submission, data processing based on the latest information becomes possible.

[0064] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and proposal processes by referencing relevant literature on the data. For example, the anonymization unit can improve the accuracy of anonymization based on relevant literature. The integration unit can improve the accuracy of integration based on relevant literature. The analysis unit can improve the accuracy of analysis based on relevant literature. The identification unit can improve the accuracy of identification based on relevant literature. The proposal unit can improve the accuracy of proposals based on relevant literature. As a result, by referring to relevant literature on the data, the accuracy of each process is improved and data consistency is maintained.

[0065] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes by considering the interrelationships of the data. For example, the anonymization unit can analyze the interrelationships of the data and prioritize anonymizing highly relevant data. The integration unit can analyze the interrelationships of the data and prioritize integrating highly relevant data. The analysis unit can analyze the interrelationships of the data and prioritize analyzing highly relevant data. The identification unit can analyze the interrelationships of the data and prioritize identifying highly relevant data. The suggestion unit can analyze the interrelationships of the data and prioritize suggesting highly relevant business opportunities. As a result, by considering the interrelationships of the data, the accuracy of each process is improved and data consistency is maintained.

[0066] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes according to the data category. For example, the anonymization unit can apply advanced encryption algorithms to financial data. The integration unit can apply different integration algorithms to human resources data. The analysis unit can apply yet different analysis algorithms to customer data. The identification unit can apply specific algorithms to financial data to identify business opportunities. The suggestion unit can apply specific suggestion algorithms to customer risks. This improves the accuracy of each process by applying algorithms appropriate to the data category.

[0067] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes based on the importance of the data. For example, the anonymization unit can perform detailed anonymization on high-importance data. The integration unit can prioritize the integration of high-importance data. The analysis unit can prioritize the analysis of high-importance data. The identification unit can prioritize the identification of high-importance data. The suggestion unit can provide detailed suggestions for high-importance business opportunities. By adjusting each process based on the importance of the data, a good balance can be maintained between data protection and availability.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The anonymization unit anonymizes the data. For example, it anonymizes personal information such as employee salary information and performance data. The anonymization unit can anonymize personal information using generation AI through methods such as data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit inputs a prompt to the generation AI saying, "Please anonymize this data," and the generation AI analyzes the data and performs the anonymization. Step 2: The integration unit integrates the data anonymized by the anonymization unit. For example, it integrates the anonymized data into a vector database. The integration unit can use a generative AI to integrate the data based on the database type and integration algorithm. For example, the integration unit prompts the generative AI with "Integrate this data into the vector database," and the generative AI analyzes the data and performs the integration. Step 3: The analysis unit analyzes the data integrated by the integration unit. For example, it analyzes data stored in a vector database. The analysis unit can use a generative AI to analyze the data based on statistical analysis and machine learning algorithms. For example, the analysis unit inputs a prompt to the generative AI, such as "Please analyze this data," and the generative AI analyzes the data and extracts useful information. Step 4: The Identification Department identifies business opportunities and risks based on the data analyzed by the Analysis Department. For example, it identifies untapped areas within the group and proposes new businesses. The Identification Department can use Generative AI to make identifications based on criteria for evaluating business opportunities and risks. For example, the Identification Department inputs a prompt to the Generative AI saying, "Identify business opportunities from this data," and the Generative AI analyzes the data to identify business opportunities. Step 5: The proposal department makes proposals based on the business opportunities and risks identified by the specific department. For example, they might propose ways to optimally utilize assets within the group. The proposal department can use a generation AI to make proposals based on the format and evaluation criteria for the proposal content. For example, the proposal department might input a prompt to the generation AI such as, "Please make a proposal for this business opportunity," and the generation AI would analyze the data and make a proposal.

[0070] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system that combines a vector database and a generative AI. This AI agent system anonymizes all internal data of each group company using the generative AI and integrates it into the vector database. Next, it utilizes the generative AI and the company-wide vector database to automatically discover and propose all business opportunities and potential risks that may go unnoticed by the person in charge or management. This promotes and strengthens cooperation among group companies and improves overall competitiveness by integrating and gaining an overview of data across the entire group. Furthermore, this system does not provide external services and is used solely to strengthen the competitiveness of the group. For example, all internal data of each group company is anonymized using the generative AI and integrated into the vector database. In this process, the generative AI analyzes the data of each company and anonymizes personal information. For example, personal information such as employee salary information and performance data is anonymized and stored in the integrated vector database. This allows the data to be used without violating the Personal Information Protection Act. Next, it utilizes the generative AI and the company-wide vector database to automatically discover and propose all business opportunities and potential risks that may go unnoticed by the person in charge or management. The generative AI analyzes the data stored in the vector database to identify new business opportunities and potential risks. For example, it identifies untapped areas within the group and proposes new business ventures. It also suggests ways to optimally utilize the group's assets. This can improve the overall competitiveness of the group. Furthermore, by integrating and gaining a comprehensive overview of group-wide data, it promotes and strengthens cooperation among group companies. The generating AI analyzes data from each company and identifies potential for cooperation. For example, by sharing technology and assets within the group, it reduces the cost and time required to launch new businesses. It also accelerates collaboration within the group and improves the speed of project launches. This can improve the overall competitiveness of the group. This system is not used to provide external services and is used solely to strengthen the group's competitiveness. The generating AI analyzes data within the group and makes optimal suggestions. For example, it proposes new business ventures and ways to optimally utilize assets. This can improve the overall competitiveness of the group. As a result, the AI ​​agent system can integrate data from across the group and automatically discover and propose business opportunities and risks.

[0071] The AI ​​agent system according to this embodiment comprises an anonymization unit, an integration unit, an analysis unit, a specification unit, and a proposal unit. The anonymization unit anonymizes data. The anonymization unit anonymizes personal information such as employee salary information and performance data. The anonymization unit can anonymize personal information using a generation AI by methods such as data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit inputs a prompt to the generation AI saying, "Please anonymize this data," and the generation AI analyzes the data and performs anonymization. The integration unit integrates the data anonymized by the anonymization unit. The integration unit integrates the anonymized data into a vector database, for example. The integration unit can integrate data using a generation AI based on the type of database and the integration algorithm. For example, the integration unit inputs a prompt to the generation AI saying, "Please integrate this data into a vector database," and the generation AI analyzes the data and performs integration. The analysis unit analyzes the data integrated by the integration unit. The analysis unit analyzes the data stored in the vector database, for example. The Analysis Department can analyze data based on statistical analysis and machine learning algorithms using generative AI. For example, the Analysis Department can input a prompt to the generative AI such as "Please analyze this data," and the generative AI will analyze the data and extract useful information. The Identification Department identifies business opportunities and risks based on the data analyzed by the Analysis Department. For example, the Identification Department can identify untapped areas within the group and propose new businesses. The Identification Department can use generative AI to make identifications based on evaluation criteria for business opportunities and risks. For example, the Identification Department can input a prompt to the generative AI such as "Please identify business opportunities from this data," and the generative AI will analyze the data and identify business opportunities. The Proposal Department makes proposals based on the business opportunities and risks identified by the Identification Department. For example, the Proposal Department can propose ways to optimally utilize assets within the group. The Proposal Department can use generative AI to make proposals based on evaluation criteria for proposal format and content. For example, the Proposal Department can input a prompt to the generative AI such as "Please make a proposal for this business opportunity," and the generative AI will analyze the data and make a proposal.As a result, the AI ​​agent system according to this embodiment can automatically discover and propose business opportunities and risks through data anonymization, integration, analysis, identification, and suggestion.

[0072] The anonymization unit anonymizes data. For example, the anonymization unit anonymizes personal information such as employee salary information and performance data. Specifically, the anonymization unit can anonymize personal information using generational AI through methods such as data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit inputs a prompt to the generational AI, "Please anonymize this data," and the generational AI analyzes the data and performs anonymization. The generational AI first analyzes the content of the data and identifies personal information. Next, it applies masking, pseudo-anonymization, or complete anonymization techniques to the identified personal information. Masking hides personal information by replacing specific strings. Pseudo-anonymization converts personal information into a unique identifier, making it impossible to restore the original information. Complete anonymization completely deletes personal information, leaving no trace of the original information. This allows the anonymization unit to protect data privacy while retaining information necessary for analysis and integration. Furthermore, the anonymization unit can adapt to specific requirements and regulations by adjusting the accuracy and method of anonymization. For example, it can set the level of anonymization based on specific legal regulations and re-anonymize the data as needed. This allows the anonymization unit to balance data privacy protection with usability.

[0073] The integration unit integrates data anonymized by the anonymization unit. For example, the integration unit integrates anonymized data into a vector database. Specifically, the integration unit can use a generative AI to integrate data based on the database type and integration algorithm. For example, the integration unit prompts the generative AI with "Integrate this data into the vector database," and the generative AI analyzes the data and performs the integration. The generative AI first analyzes the data format and structure and generates an appropriate database schema. Next, it converts the data content into vector format and stores it in the vector database. This allows the integration unit to centrally manage data of different formats and structures and perform efficient searching and analysis. Furthermore, the integration unit has a mechanism to handle data updates and additions, enabling real-time data integration. For example, when new data is added, the generative AI automatically analyzes the data and integrates it into the existing database. The integration unit also has a checking function to maintain data integrity and consistency, preventing data duplication and inconsistencies. This allows the integration unit to perform data integration and management efficiently and accurately, improving the overall system performance.

[0074] The analysis unit analyzes data integrated by the integration unit. For example, the analysis unit analyzes data stored in a vector database. Specifically, the analysis unit can use generative AI to analyze data based on statistical analysis and machine learning algorithms. For example, the analysis unit can input a prompt to the generative AI such as "Please analyze this data," and the generative AI will analyze the data and extract useful information. The generative AI first preprocesses the data, such as imputing missing values ​​and detecting outliers. Next, it applies statistical analysis and machine learning algorithms to extract data patterns and trends. For example, it can use regression analysis to predict sales or clustering to identify customer segments. Furthermore, the analysis unit can also use generative AI to visualize data. For example, it can input a prompt to the generative AI such as "Please visualize this data," and the generative AI will analyze the data and generate graphs and charts. This allows the analysis unit to provide data analysis results in an intuitively understandable format. Additionally, because the analysis unit can perform data analysis in real time, it can support rapid decision-making. For example, it can analyze data that is updated in real time and detect abnormal patterns and trends early. This allows the analysis unit to perform data analysis efficiently and accurately, supporting business decision-making.

[0075] The Identification Department identifies business opportunities and risks based on data analyzed by the Analysis Department. For example, the Identification Department can identify untapped areas within the group and propose new business ventures. Specifically, the Identification Department can use generative AI to identify business opportunities and risks based on evaluation criteria. For example, the Identification Department can input a prompt to the generative AI such as "Identify business opportunities from this data," and the generative AI will analyze the data to identify business opportunities. The generative AI first analyzes the content of the data and extracts patterns and trends related to business opportunities and risks. Next, it evaluates specific business opportunities and risks based on evaluation criteria for business opportunities and risks. For example, it can evaluate the demand and competitive situation of new markets and identify business opportunities in untapped areas. In risk assessment, it can evaluate the risks associated with specific business activities and propose risk mitigation measures. This allows the Identification Department to quickly and accurately identify business opportunities and risks and support business decision-making. Furthermore, the Identification Department can also use generative AI to perform simulations for the identified business opportunities and risks. For example, it can perform scenario analysis for identified business opportunities and propose optimal strategies. This allows the specific department to not only identify business opportunities and risks, but also propose concrete countermeasures and strategies.

[0076] The proposal department makes proposals based on business opportunities and risks identified by specific departments. For example, the proposal department might propose ways to optimally utilize assets within the group. Specifically, the proposal department can use generative AI to make proposals based on the format and evaluation criteria of the proposal content. For example, the proposal department can input a prompt to the generative AI such as "Please make a proposal for this business opportunity," and the generative AI will analyze the data and make a proposal. The generative AI first analyzes data related to the identified business opportunity and risk and generates the optimal proposal content. Next, it organizes the proposal content based on the format and evaluation criteria of the proposal and creates a specific proposal document. For example, it can evaluate the resources, costs, and risks required to launch a new business and propose the optimal strategy. It can also propose improvement measures and risk reduction measures for existing businesses, supporting business efficiency and risk management. This allows the proposal department to make specific proposals for business opportunities and risks quickly and accurately, supporting business decision-making. Furthermore, the proposal department can also use generative AI to simulate the content of the proposal. For example, it can simulate the implementation scenario of the proposed strategy and evaluate the expected results and risks. This allows the proposal department to evaluate the feasibility and effectiveness of the proposed content in advance, enabling them to make more accurate proposals.

[0077] The anonymization unit can anonymize personal information such as employee salary information and performance data. For example, the anonymization unit can anonymize employee salary information using a generation AI. For instance, the anonymization unit inputs a prompt to the generation AI such as "Anonymize this salary information," and the generation AI analyzes the data and performs the anonymization. The anonymization unit can also anonymize performance data using the generation AI. For example, the anonymization unit inputs a prompt to the generation AI such as "Anonymize this performance data," and the generation AI analyzes the data and performs the anonymization. Furthermore, the anonymization unit can also anonymize other personal information using the generation AI. For example, the anonymization unit inputs a prompt to the generation AI such as "Anonymize this personal information," and the generation AI analyzes the data and performs the anonymization. By anonymizing personal information, data security can be ensured while utilizing the data.

[0078] The integration unit can integrate anonymized data into a vector database. For example, the integration unit can integrate anonymized data into a vector database using a generative AI. For instance, the integration unit can input a prompt to the generative AI such as, "Integrate this anonymized data into the vector database," and the generative AI will analyze the data and perform the integration. The integration unit can also integrate data from different databases using the generative AI. For example, the integration unit can input a prompt to the generative AI such as, "Integrate the data from this database," and the generative AI will analyze the data and perform the integration. Furthermore, the integration unit can apply different integration algorithms to the generative AI depending on the type of data. For example, the integration unit can input a prompt to the generative AI such as, "Apply an integration algorithm suitable for this data," and the generative AI will analyze the data and apply the appropriate integration algorithm. This enables centralized data management by integrating anonymized data into a vector database.

[0079] The analysis unit can analyze data stored in a vector database. For example, the analysis unit can analyze data stored in a vector database using a generative AI. For instance, the analysis unit can input a prompt to the generative AI such as "Analyze the data in this vector database," and the generative AI will analyze the data and extract useful information. The analysis unit can also apply statistical analysis and machine learning algorithms using the generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Apply statistical analysis to this data," and the generative AI will analyze the data and extract statistical information. Furthermore, the analysis unit can also analyze the interrelationships between data using the generative AI. For example, the analysis unit can input a prompt to the generative AI such as "Analyze the interrelationships between this data," and the generative AI will analyze the data and identify the interrelationships. In this way, useful information can be extracted from the data by analyzing the data stored in the vector database.

[0080] The Specialist Department can identify unentered areas within the group and propose new business ventures. For example, the Specialist Department can use generative AI to identify unentered areas within the group. For instance, the Specialist Department can input a prompt to the generative AI such as, "Identify unentered areas from this data," and the generative AI will analyze the data to identify these areas. The Specialist Department can also use generative AI to propose new business ventures. For example, the Specialist Department can input a prompt to the generative AI such as, "Propose a new business venture for this unentered area," and the generative AI will analyze the data to propose a new business venture. Furthermore, the Specialist Department can also use generative AI to apply criteria for evaluating business opportunities and risks. For example, the Specialist Department can input a prompt to the generative AI such as, "Apply the criteria for evaluating this business opportunity," and the generative AI will analyze the data to evaluate the business opportunity. This allows the Specialist Department to expand business opportunities by identifying unentered areas and proposing new business ventures.

[0081] The proposal department can propose ways to optimally utilize assets within the group. For example, the proposal department can propose ways to optimally utilize assets within the group using a generative AI. For instance, the proposal department can input a prompt to the generative AI such as, "Please propose a way to optimally utilize this asset," and the generative AI will analyze the data and propose an optimal utilization method. The proposal department can also apply asset evaluation criteria and details of utilization methods using the generative AI. For example, the proposal department can input a prompt to the generative AI such as, "Please apply the evaluation criteria for this asset," and the generative AI will analyze the data and evaluate the asset. Furthermore, the proposal department can also propose ways to share assets within the group using the generative AI. For example, the proposal department can input a prompt to the generative AI such as, "Please propose a way to share this asset," and the generative AI will analyze the data and propose a sharing method. In this way, by proposing ways to optimally utilize assets within the group, effective utilization of assets becomes possible.

[0082] The proposal department can accelerate collaboration within the group and improve the speed of project launch. For example, the proposal department can propose methods to accelerate collaboration within the group using generative AI. For instance, the proposal department can input a prompt into the generative AI such as, "Please propose a way to accelerate this collaboration," and the generative AI will analyze the data and propose a method to accelerate it. The proposal department can also propose methods to improve the speed of project launch using generative AI. For example, the proposal department can input a prompt into the generative AI such as, "Please propose a way to improve the speed of this project launch," and the generative AI will analyze the data and propose a method to improve it. Furthermore, the proposal department can also optimize the means of collaboration and the project launch process using generative AI. For example, the proposal department can input a prompt into the generative AI such as, "Please optimize the means of collaboration," and the generative AI will analyze the data and perform the optimization. By accelerating collaboration within the group and improving the speed of project launch, competitiveness can be strengthened.

[0083] The anonymization unit can estimate the user's emotions and adjust the anonymization accuracy based on those emotions. For example, if the user is stressed, the anonymization unit can increase the anonymization accuracy to enhance the protection of personal information. The anonymization unit can use generative AI to estimate the user's emotions and adjust the anonymization accuracy based on those emotions. For example, the anonymization unit can input a prompt to the generative AI such as, "Estimate this user's emotions and adjust the anonymization accuracy," and the generative AI will analyze the data to estimate the emotions and adjust the anonymization accuracy. The anonymization unit can also moderately adjust the anonymization accuracy to improve data usability if the user is relaxed. For example, the anonymization unit can input a prompt to the generative AI such as, "Estimate this user's emotions and moderately adjust the anonymization accuracy," and the generative AI will analyze the data to estimate the emotions and adjust the anonymization accuracy. Furthermore, if the user is in a hurry, the anonymization unit can expedite the anonymization process to improve the speed of data delivery. For example, the anonymization unit prompts the generation AI with "Estimate this user's emotion and quickly perform the anonymization process," and the generation AI analyzes the data to estimate the emotion and quickly performs the anonymization process. This allows for a good balance between data availability and protection by adjusting the anonymization accuracy according to the user's emotion.

[0084] The anonymization unit can apply different anonymization algorithms depending on the type of data. For example, the anonymization unit can apply a sophisticated encryption algorithm to employee salary information. The anonymization unit can use a generative AI to select and apply an appropriate anonymization algorithm depending on the type of data. For example, the anonymization unit can input a prompt to the generative AI such as, "Apply an appropriate anonymization algorithm according to the type of data," and the generative AI will analyze the data and apply the appropriate anonymization algorithm. The anonymization unit can also anonymize performance data using data masking technology. For example, the anonymization unit can input a prompt to the generative AI such as, "Apply data masking technology to this performance data," and the generative AI will analyze the data and perform data masking. Furthermore, the anonymization unit can anonymize customer information using pseudo-data generation technology. For example, the anonymization unit can input a prompt to the generative AI such as, "Apply pseudo-data generation technology to this customer information," and the generative AI will analyze the data and generate pseudo-data. By applying an anonymization algorithm according to the type of data, the security and usability of the data can be optimized.

[0085] The anonymization unit can adjust the level of anonymization based on the importance of the data. For example, the anonymization unit can perform detailed anonymization on highly important data to enhance the protection of personal information. The anonymization unit can use generative AI to adjust the level of anonymization based on the importance of the data. For example, the anonymization unit can input a prompt to the generative AI such as "Adjust the level of anonymization based on the importance of this data," and the generative AI will analyze the data and adjust the level of anonymization. The anonymization unit can also perform simplified anonymization on less important data to increase its usability. For example, the anonymization unit can input a prompt to the generative AI such as "Perform simplified anonymization based on the importance of this data," and the generative AI will analyze the data and perform anonymization. Furthermore, the anonymization unit can perform balanced anonymization on data of moderate importance. For example, the anonymization unit can input a prompt to the generative AI such as "Perform balanced anonymization based on the importance of this data," and the generative AI will analyze the data and perform anonymization. This allows for a good balance between data protection and availability by adjusting the level of anonymization based on the importance of the data.

[0086] The anonymization unit can estimate the user's emotions and determine the anonymization priority based on those emotions. For example, if the user is stressed, the anonymization unit will prioritize the anonymization of important data. The anonymization unit can use generative AI to estimate the user's emotions and determine the anonymization priority based on those emotions. For example, the anonymization unit can input a prompt to the generative AI saying, "Estimate this user's emotions and determine the anonymization priority," and the generative AI will analyze the data to estimate the emotions and determine the anonymization priority. The anonymization unit can also perform even anonymization of the entire data if the user is relaxed. For example, the anonymization unit can input a prompt to the generative AI saying, "Estimate this user's emotions and perform even anonymization," and the generative AI will analyze the data to estimate the emotions and perform anonymization. Furthermore, if the user is in a hurry, the anonymization unit can also prioritize the anonymization of data that can be processed quickly. For example, the anonymization unit prompts the generating AI with the message, "Estimate this user's emotions and prioritize anonymizing data that can be processed quickly." The generating AI then analyzes the data, estimates the emotions, and performs anonymization. This allows for data processing tailored to the user's needs by determining the priority of anonymization based on the user's emotions.

[0087] The anonymization unit can determine the priority of anonymization based on the data submission date. For example, the anonymization unit can prioritize anonymizing the most recent data. The anonymization unit can use a generative AI to determine the priority of anonymization based on the data submission date. For example, the anonymization unit can input a prompt to the generative AI such as, "Determine the priority of anonymization based on the submission date of this data," and the generative AI will analyze the data to identify the submission date and determine the priority of anonymization. The anonymization unit can also postpone older data. For example, the anonymization unit can input a prompt to the generative AI such as, "Postpone older data based on the submission date of this data," and the generative AI will analyze the data to identify the submission date and perform anonymization. Furthermore, if the submission dates are concentrated within a specific period, the anonymization unit can prioritize anonymizing data from that period. For example, the anonymization unit can input a prompt to the generative AI such as, "Prioritize anonymizing data from a specific period based on the submission date of this data," and the generative AI will analyze the data to identify the submission date and perform anonymization. This allows for prioritizing the processing of the most recent data by determining anonymization priorities based on when the data was submitted.

[0088] The anonymization unit can adjust the anonymization order based on the relevance of the data. For example, the anonymization unit can anonymize highly relevant data in a batch. The anonymization unit can use a generative AI to adjust the anonymization order based on the relevance of the data. For example, the anonymization unit can input a prompt to the generative AI such as "Adjust the anonymization order based on the relevance of this data," and the generative AI will analyze the data, identify the relevance, and adjust the anonymization order. The anonymization unit can also anonymize less relevant data individually. For example, the anonymization unit can input a prompt to the generative AI such as "Anonymize this data individually based on the relevance," and the generative AI will analyze the data, identify the relevance, and perform the anonymization. Furthermore, the anonymization unit can dynamically adjust the anonymization order according to the relevance of the data. For example, the anonymization unit can input a prompt to the generative AI such as "Dynamically adjust the anonymization order based on the relevance of this data," and the generative AI will analyze the data, identify the relevance, and dynamically adjust the anonymization order. This allows for efficient data processing by adjusting the anonymization order based on the relevance of the data.

[0089] The integration unit can estimate the user's emotions and adjust the integration method based on those emotions. For example, if the user is stressed, the integration unit can provide a simple integration method. The integration unit can use generative AI to estimate the user's emotions and adjust the integration method based on those emotions. For example, the integration unit can input a prompt to the generative AI saying, "Estimate this user's emotions and adjust the integration method," and the generative AI will analyze the data to estimate the emotions and adjust the integration method. The integration unit can also provide detailed integration options if the user is relaxed. For example, the integration unit can input a prompt to the generative AI saying, "Estimate this user's emotions and provide detailed integration options," and the generative AI will analyze the data to estimate the emotions and provide integration options. Furthermore, if the user is in a hurry, the integration unit can provide a method for rapid integration. For example, the integration unit can input a prompt to the generative AI saying, "Estimate this user's emotions and provide a method for rapid integration," and the generative AI will analyze the data to estimate the emotions and provide integration methods. This allows for data integration tailored to user needs by adjusting the integration method according to the user's emotions.

[0090] The integration unit can improve the accuracy of integration by considering the interrelationships of data. For example, the integration unit can analyze the interrelationships of data and prioritize the integration of highly relevant data. The integration unit can use generative AI to improve the accuracy of integration by considering the interrelationships of data. For example, the integration unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and improve the accuracy of integration," and the generative AI will analyze the data, identify the interrelationships, and improve the accuracy of integration. The integration unit can also optimize the order of integration by considering the interrelationships of data. For example, the integration unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and optimize the order of integration," and the generative AI will analyze the data, identify the interrelationships, and optimize the order of integration. Furthermore, the integration unit can apply algorithms to improve the accuracy of integration based on the interrelationships of data. For example, the integration unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and apply an algorithm to improve the accuracy of integration," and the generative AI will analyze the data, identify the interrelationships, and apply the algorithm. As a result, by considering the interrelationships of data, the accuracy of integration is improved and data consistency is maintained.

[0091] The integration unit can apply different integration algorithms depending on the data category. For example, the integration unit can apply a specific integration algorithm to financial data. The integration unit can use generative AI to select and apply the appropriate integration algorithm according to the data category. For example, the integration unit can input a prompt to the generative AI such as, "Apply the appropriate integration algorithm according to this data category," and the generative AI will analyze the data and apply the appropriate integration algorithm. The integration unit can also apply a different integration algorithm to human resources data. For example, the integration unit can input a prompt to the generative AI such as, "Apply the appropriate integration algorithm to this human resources data," and the generative AI will analyze the data and apply the appropriate integration algorithm. Furthermore, the integration unit can apply yet another different integration algorithm to customer data. For example, the integration unit can input a prompt to the generative AI such as, "Apply the appropriate integration algorithm to this customer data," and the generative AI will analyze the data and apply the appropriate integration algorithm. By applying integration algorithms according to the data category, the accuracy of data integration is improved.

[0092] The integration unit can estimate the user's emotions and determine integration priorities based on those emotions. For example, if the user is stressed, the integration unit will prioritize integrating important data. The integration unit can use generative AI to estimate the user's emotions and determine integration priorities based on those emotions. For example, the integration unit can input a prompt to the generative AI such as, "Estimate this user's emotions and determine integration priorities," and the generative AI will analyze the data, estimate the emotions, and determine the integration priorities. The integration unit can also integrate all data evenly if the user is relaxed. For example, the integration unit can input a prompt to the generative AI such as, "Estimate this user's emotions and integrate evenly," and the generative AI will analyze the data, estimate the emotions, and perform the integration. Furthermore, if the user is in a hurry, the integration unit can prioritize integrating data that can be processed quickly. For example, the integration unit can input a prompt to the generative AI such as, "Estimate this user's emotions and prioritize integrating data that can be processed quickly," and the generative AI will analyze the data, estimate the emotions, and perform the integration. This allows for data integration tailored to user needs by prioritizing integration based on user sentiment.

[0093] The integration unit can perform integration while considering the geographical distribution of the data. For example, the integration unit can prioritize the integration of data that is geographically close. The integration unit can use generative AI to perform integration while considering the geographical distribution of the data. For example, the integration unit can input a prompt to the generative AI such as "Please perform integration while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and perform the integration. The integration unit can also postpone the integration of data that is geographically far away. For example, the integration unit can input a prompt to the generative AI such as "Please postpone the integration of data that is far away while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and perform the integration. Furthermore, the integration unit can optimize the order of integration based on geographical distribution. For example, the integration unit can input a prompt to the generative AI such as "Please optimize the order of integration while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and optimize the order of integration. This makes efficient data integration possible by considering the geographical distribution of the data.

[0094] The integration unit can improve the accuracy of integration by referring to relevant literature for the data. For example, the integration unit can optimize the data integration method based on relevant literature. The integration unit can improve the accuracy of integration by referring to relevant literature for the data using generative AI. For example, the integration unit can input a prompt to the generative AI such as "Refer to relevant literature for this data to improve the accuracy of integration," and the generative AI will analyze the data, identify relevant literature, and improve the accuracy of integration. The integration unit can also apply algorithms that improve the accuracy of integration by referring to relevant literature. For example, the integration unit can input a prompt to the generative AI such as "Refer to relevant literature for this data to apply the algorithm," and the generative AI will analyze the data, identify relevant literature, and apply the algorithm. Furthermore, the integration unit can also optimize the data integration order based on relevant literature. For example, the integration unit can input a prompt to the generative AI such as "Refer to relevant literature for this data to optimize the integration order," and the generative AI will analyze the data, identify relevant literature, and optimize the integration order. As a result, by referring to relevant literature for the data, the accuracy of integration is improved and data consistency is maintained.

[0095] The analysis unit can estimate the user's emotions and adjust the analysis method based on those emotions. For example, if the user is stressed, the analysis unit can provide a simple analysis method. The analysis unit can use generative AI to estimate the user's emotions and adjust the analysis method based on those emotions. For example, the analysis unit can input a prompt to the generative AI saying, "Estimate this user's emotions and adjust the analysis method," and the generative AI will analyze the data to estimate the emotions and adjust the analysis method. The analysis unit can also provide detailed analysis options if the user is relaxed. For example, the analysis unit can input a prompt to the generative AI saying, "Estimate this user's emotions and provide detailed analysis options," and the generative AI will analyze the data to estimate the emotions and provide analysis options. Furthermore, if the user is in a hurry, the analysis unit can provide a method for rapid analysis. For example, the analysis unit can input a prompt to the generative AI saying, "Estimate this user's emotions and provide a method for rapid analysis," and the generative AI will analyze the data to estimate the emotions and provide an analysis method. This allows for data analysis tailored to user needs by adjusting the analysis method according to the user's emotions.

[0096] The analysis unit can improve the accuracy of the analysis by considering the interrelationships between data. For example, the analysis unit can analyze the interrelationships between data and prioritize the analysis of highly relevant data. The analysis unit can improve the accuracy of the analysis by considering the interrelationships between data using generative AI. For example, the analysis unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and improve the accuracy of the analysis," and the generative AI will analyze the data, identify the interrelationships, and improve the accuracy of the analysis. The analysis unit can also optimize the order of analysis by considering the interrelationships between data. For example, the analysis unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and optimize the order of analysis," and the generative AI will analyze the data, identify the interrelationships, and optimize the order of analysis. Furthermore, the analysis unit can apply algorithms to improve the accuracy of the analysis based on the interrelationships between data. For example, the analysis unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and apply an algorithm to improve the accuracy of the analysis," and the generative AI will analyze the data, identify the interrelationships, and apply the algorithm. As a result, by considering the interrelationships between data, the accuracy of the analysis is improved and data consistency is maintained.

[0097] The analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit can apply a specific analysis algorithm to financial data. The analysis unit can use a generative AI to select and apply an appropriate analysis algorithm according to the data category. For example, the analysis unit can input a prompt to the generative AI saying, "Apply an appropriate analysis algorithm according to this data category," and the generative AI will analyze the data and apply the appropriate analysis algorithm. The analysis unit can also apply a different analysis algorithm to human resources data. For example, the analysis unit can input a prompt to the generative AI saying, "Apply an appropriate analysis algorithm to this human resources data," and the generative AI will analyze the data and apply the appropriate analysis algorithm. Furthermore, the analysis unit can apply yet another different analysis algorithm to customer data. For example, the analysis unit can input a prompt to the generative AI saying, "Apply an appropriate analysis algorithm to this customer data," and the generative AI will analyze the data and apply the appropriate analysis algorithm. By applying analysis algorithms according to the data category, the accuracy of the analysis is improved.

[0098] The analysis unit can estimate the user's emotions and determine the analysis priority based on those emotions. For example, if the user is stressed, the analysis unit will prioritize the analysis of important data. The analysis unit can use generative AI to estimate the user's emotions and determine the analysis priority based on those emotions. For example, the analysis unit can input a prompt to the generative AI saying, "Estimate this user's emotions and determine the analysis priority," and the generative AI will analyze the data, estimate the emotions, and determine the analysis priority. The analysis unit can also perform an even distribution of data analysis if the user is relaxed. For example, the analysis unit can input a prompt to the generative AI saying, "Estimate this user's emotions and perform the analysis evenly," and the generative AI will analyze the data, estimate the emotions, and perform the analysis. Furthermore, if the user is in a hurry, the analysis unit can prioritize the analysis of data that can be processed quickly. For example, the analysis unit can input a prompt to the generative AI saying, "Estimate this user's emotions and prioritize the analysis of data that can be processed quickly," and the generative AI will analyze the data, estimate the emotions, and perform the analysis. This allows for data analysis tailored to user needs by prioritizing analysis based on user emotions.

[0099] The analysis unit can perform analysis while considering the geographical distribution of the data. For example, the analysis unit can prioritize the analysis of geographically close data. The analysis unit can use generative AI to perform analysis while considering the geographical distribution of the data. For example, the analysis unit can input a prompt to the generative AI such as "Please perform analysis while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and perform the analysis. The analysis unit can also postpone the analysis of geographically distant data. For example, the analysis unit can input a prompt to the generative AI such as "Please postpone the analysis of distant data while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and perform the analysis. Furthermore, the analysis unit can optimize the order of analysis based on geographical distribution. For example, the analysis unit can input a prompt to the generative AI such as "Please optimize the order of analysis while considering the geographical distribution of this data," and the generative AI will analyze the data, identify the geographical distribution, and optimize the order of analysis. This makes efficient data analysis possible by considering the geographical distribution of the data.

[0100] The analysis unit can improve the accuracy of its analysis by referring to relevant literature for the data. For example, the analysis unit can optimize the data analysis method based on relevant literature. The analysis unit can improve the accuracy of its analysis by referring to relevant literature for the data using a generative AI. For example, the analysis unit can input a prompt to the generative AI saying, "Please improve the accuracy of the analysis by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and improve the accuracy of the analysis. The analysis unit can also apply algorithms that improve the accuracy of the analysis by referring to relevant literature. For example, the analysis unit can input a prompt to the generative AI saying, "Please apply the algorithm by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and apply the algorithm. Furthermore, the analysis unit can also optimize the order of data analysis based on relevant literature. For example, the analysis unit can input a prompt to the generative AI saying, "Please optimize the order of analysis by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and optimize the order of analysis. As a result, by referring to relevant literature for the data, the accuracy of the analysis is improved and the consistency of the data is maintained.

[0101] The identification unit can estimate the user's emotions and adjust specific methods based on those estimated emotions. For example, if the user is stressed, the identification unit can provide a simple identification method. The identification unit can use generative AI to estimate the user's emotions and adjust specific methods based on those emotions. For example, the identification unit can input a prompt to the generative AI saying, "Estimate this user's emotions and adjust specific methods," and the generative AI will analyze the data to estimate the emotions and adjust specific methods. The identification unit can also provide detailed identification options if the user is relaxed. For example, the identification unit can input a prompt to the generative AI saying, "Estimate this user's emotions and provide detailed identification options," and the generative AI will analyze the data to estimate the emotions and provide identification options. Furthermore, if the user is in a hurry, the identification unit can provide a method for quick identification. For example, the identification unit can input a prompt to the generative AI saying, "Estimate this user's emotions and provide a method for quick identification," and the generative AI will analyze the data to estimate the emotions and provide identification methods. This allows for data identification that aligns with user needs by adjusting specific methods based on user emotions.

[0102] The identification unit can improve specific accuracy by considering the interrelationships of data. For example, the identification unit can analyze the interrelationships of data and prioritize the identification of highly relevant data. The identification unit can improve specific accuracy by considering the interrelationships of data using a generative AI. For example, the identification unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and improve specific accuracy," and the generative AI will analyze the data, identify the interrelationships, and improve specific accuracy. The identification unit can also optimize specific order by considering the interrelationships of data. For example, the identification unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and optimize specific order," and the generative AI will analyze the data, identify the interrelationships, and optimize specific order. Furthermore, the identification unit can apply algorithms that improve specific accuracy based on the interrelationships of data. For example, the identification unit can input a prompt to the generative AI such as, "Analyze the interrelationships of this data and apply an algorithm that improves specific accuracy," and the generative AI will analyze the data, identify the interrelationships, and apply the algorithm. As a result, by considering the interrelationships of data, specific accuracy is improved and data consistency is maintained.

[0103] The identification unit can apply different identification algorithms depending on the data category. For example, the identification unit can apply a specific algorithm to financial data to identify business opportunities. The identification unit can use generative AI to select and apply the appropriate identification algorithm depending on the data category. For example, the identification unit can input a prompt to the generative AI such as, "Apply the appropriate identification algorithm according to this data category," and the generative AI will analyze the data and apply the appropriate identification algorithm. The identification unit can also apply a different identification algorithm to human resources data to identify potential risks. For example, the identification unit can input a prompt to the generative AI such as, "Apply the appropriate identification algorithm to this human resources data," and the generative AI will analyze the data and apply the appropriate identification algorithm. Furthermore, the identification unit can apply yet another identification algorithm to customer data to identify new business opportunities. For example, the identification unit can input a prompt to the generative AI such as, "Apply the appropriate identification algorithm to this customer data," and the generative AI will analyze the data and apply the appropriate identification algorithm. This improves the accuracy of identification by applying identification algorithms according to the data category.

[0104] The identification unit can estimate a user's emotions and determine specific priorities based on those emotions. For example, if a user is stressed, the identification unit will prioritize identifying important business opportunities. The identification unit can use generative AI to estimate a user's emotions and determine specific priorities based on those emotions. For example, the identification unit can input a prompt to the generative AI such as, "Estimate this user's emotions and determine specific priorities," and the generative AI will analyze the data to estimate the emotions and determine specific priorities. The identification unit can also identify business opportunities evenly across the board if the user is relaxed. For example, the identification unit can input a prompt to the generative AI such as, "Estimate this user's emotions and identify them evenly," and the generative AI will analyze the data to estimate the emotions and identify them. Furthermore, if a user is in a hurry, the identification unit can prioritize business opportunities that can be identified quickly. For example, the identification unit can input a prompt to the generative AI such as, "Estimate this user's emotions and prioritize business opportunities that can be identified quickly," and the generative AI will analyze the data to estimate the emotions and identify them. This allows for the identification of data that aligns with user needs by determining specific priorities based on user emotions.

[0105] The identification unit can perform identification while considering the geographical distribution of the data. For example, the identification unit can prioritize the identification of geographically close data. The identification unit can use a generation AI to perform identification while considering the geographical distribution of the data. For example, the identification unit can input a prompt to the generation AI saying, "Please perform identification while considering the geographical distribution of this data," and the generation AI will analyze the data, identify the geographical distribution, and perform the identification. The identification unit can also postpone the identification of geographically distant data. For example, the identification unit can input a prompt to the generation AI saying, "Please postpone the identification of distant data while considering the geographical distribution of this data," and the generation AI will analyze the data, identify the geographical distribution, and perform the identification. Furthermore, the identification unit can optimize the order of identification based on the geographical distribution. For example, the identification unit can input a prompt to the generation AI saying, "Please optimize the order of identification while considering the geographical distribution of this data," and the generation AI will analyze the data, identify the geographical distribution, and optimize the order of identification. This makes efficient data identification possible by considering the geographical distribution of the data.

[0106] The identification unit can improve the accuracy of identification by referring to relevant literature for the data. For example, the identification unit can optimize the data identification method based on relevant literature. The identification unit can improve the accuracy of identification by referring to relevant literature for the data using a generative AI. For example, the identification unit can input a prompt to the generative AI such as "Improve the accuracy of identification by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and improve the accuracy of identification. The identification unit can also apply an algorithm that improves the accuracy of identification by referring to relevant literature. For example, the identification unit can input a prompt to the generative AI such as "Apply the algorithm by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and apply the algorithm. Furthermore, the identification unit can also optimize the order of identification of data based on relevant literature. For example, the identification unit can input a prompt to the generative AI such as "Optimize the order of identification by referring to relevant literature for this data," and the generative AI will analyze the data, identify relevant literature, and optimize the order of identification. As a result, by referring to relevant literature for the data, the accuracy of identification is improved and the consistency of the data is maintained.

[0107] The suggestion function can estimate the user's emotions and adjust the way it presents suggestions based on those emotions. For example, if the user is stressed, the suggestion function will provide simple and easy-to-understand suggestions. The suggestion function can use generative AI to estimate the user's emotions and adjust the way it presents suggestions based on those emotions. For example, the suggestion function can input a prompt to the generative AI saying, "Estimate this user's emotions and adjust the way the suggestion is presented," and the generative AI will analyze the data to estimate the emotions and adjust the way the suggestion is presented. The suggestion function can also provide detailed suggestions if the user is relaxed. For example, the suggestion function can input a prompt to the generative AI saying, "Estimate this user's emotions and provide detailed suggestions," and the generative AI will analyze the data to estimate the emotions and provide suggestions. Furthermore, if the user is in a hurry, the suggestion function can provide suggestions that can be quickly understood. For example, the suggestion function can input a prompt to the generative AI saying, "Estimate this user's emotions and provide suggestions that can be quickly understood," and the generative AI will analyze the data to estimate the emotions and provide suggestions. This allows for the presentation of suggestions to be adjusted according to the user's emotions, making it possible to offer suggestions that meet the user's needs.

[0108] The proposal department can adjust the level of detail of its proposals based on the importance of business opportunities and risks. For example, the proposal department can provide detailed proposals for highly important business opportunities. The proposal department can use generative AI to adjust the level of detail of its proposals based on the importance of business opportunities and risks. For example, the proposal department can input a prompt to the generative AI such as, "Adjust the level of detail of this proposal based on the importance of this business opportunity," and the generative AI will analyze the data to identify the importance and adjust the level of detail of the proposal. The proposal department can also provide simplified proposals for less important business opportunities. For example, the proposal department can input a prompt to the generative AI such as, "Provide a simplified proposal based on the importance of this business opportunity," and the generative AI will analyze the data to identify the importance and provide a proposal. Furthermore, the proposal department can provide balanced proposals for business opportunities of moderate importance. For example, the proposal department can input a prompt to the generative AI such as, "Provide a balanced proposal based on the importance of this business opportunity," and the generative AI will analyze the data to identify the importance and provide a proposal. This allows for the creation of appropriate proposals by adjusting the level of detail in the proposal according to the importance of business opportunities and risks.

[0109] The proposal department can apply different proposal algorithms depending on the category of business opportunity or risk. For example, the proposal department can apply a specific proposal algorithm to financial risk. The proposal department can use generative AI to select and apply the appropriate proposal algorithm according to the category of business opportunity or risk. For example, the proposal department can input a prompt to the generative AI such as, "Apply the appropriate proposal algorithm according to this category of business opportunity or risk," and the generative AI will analyze the data and apply the appropriate proposal algorithm. The proposal department can also apply a different proposal algorithm to human resources risk. For example, the proposal department can input a prompt to the generative AI such as, "Apply the appropriate proposal algorithm for this human resources risk," and the generative AI will analyze the data and apply the appropriate proposal algorithm. Furthermore, the proposal department can apply yet another proposal algorithm to customer risk. For example, the proposal department can input a prompt to the generative AI such as, "Apply the appropriate proposal algorithm for this customer risk," and the generative AI will analyze the data and apply the appropriate proposal algorithm. This improves the accuracy of proposals by applying proposal algorithms according to the category of business opportunity or risk.

[0110] The suggestion unit can estimate the user's emotions and prioritize suggestions based on those emotions. For example, if the user is stressed, the suggestion unit will prioritize important suggestions. The suggestion unit can use generative AI to estimate the user's emotions and prioritize suggestions based on those emotions. For example, the suggestion unit can input a prompt to the generative AI such as, "Estimate this user's emotions and prioritize suggestions," and the generative AI will analyze the data to estimate the emotions and determine the priority of suggestions. The suggestion unit can also distribute suggestions evenly if the user is relaxed. For example, the suggestion unit can input a prompt to the generative AI such as, "Estimate this user's emotions and distribute suggestions evenly," and the generative AI will analyze the data to estimate the emotions and make suggestions. Furthermore, if the user is in a hurry, the suggestion unit can prioritize suggestions that can be processed quickly. For example, the suggestion unit can input a prompt to the generative AI such as, "Estimate this user's emotions and prioritize suggestions that can be processed quickly," and the generative AI will analyze the data to estimate the emotions and make suggestions. This allows for prioritizing suggestions based on the user's emotions, enabling suggestions that meet the user's needs.

[0111] The proposal department can prioritize proposals based on the submission timing of business opportunities and risks. For example, the proposal department can prioritize the most recent business opportunities. The proposal department can use generative AI to prioritize proposals based on the submission timing of business opportunities and risks. For example, the proposal department can input a prompt into the generative AI such as, "Please prioritize proposals based on the submission timing of these business opportunities and risks," and the generative AI will analyze the data to identify submission timings and determine the proposal priority. The proposal department can also postpone older business opportunities. For example, the proposal department can input a prompt into the generative AI such as, "Please postpone older business opportunities based on the submission timing of these business opportunities and risks," and the generative AI will analyze the data to identify submission timings and make proposals. Furthermore, if submission timings are concentrated within a specific period, the proposal department can prioritize business opportunities within that period. For example, the proposal department can input a prompt into the generative AI such as, "Please prioritize business opportunities within a specific period based on the submission timing of these business opportunities and risks," and the generative AI will analyze the data to identify submission timings and make proposals. This allows for proposals to be based on the latest information by prioritizing proposals based on the timing of business opportunity and risk presentations.

[0112] The proposal department can adjust the order of proposals based on the relevance of business opportunities and risks. For example, the proposal department can propose highly relevant business opportunities in a group. The proposal department can use generative AI to adjust the order of proposals based on the relevance of business opportunities and risks. For example, the proposal department can input a prompt to the generative AI such as, "Please adjust the order of proposals based on the relevance of these business opportunities and risks," and the generative AI will analyze the data, identify the relevance, and adjust the order of proposals. The proposal department can also propose less relevant business opportunities individually. For example, the proposal department can input a prompt to the generative AI such as, "Please propose individually based on the relevance of these business opportunities and risks," and the generative AI will analyze the data, identify the relevance, and make proposals. Furthermore, the proposal department can dynamically adjust the order of proposals according to the relevance of business opportunities. For example, the proposal department can input a prompt to the generative AI such as, "Please dynamically adjust the order of proposals based on the relevance of these business opportunities and risks," and the generative AI will analyze the data, identify the relevance, and dynamically adjust the order of proposals. This allows for more efficient proposals by adjusting the order of proposals based on the relevance of business opportunities and risks.

[0113] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0114] The AI ​​agent system can further estimate the user's emotions and adjust the data anonymization, integration, analysis, identification, and suggestion processes based on the estimated emotions. For example, the anonymization unit can enhance the protection of personal information by increasing the accuracy of anonymization if the user is stressed. The integration unit can provide a way to quickly integrate data if the user is in a hurry. The analysis unit can provide detailed analysis options if the user is relaxed. The identification unit can provide a simple identification method if the user is stressed. The suggestion unit can provide suggestions that are easy to understand if the user is in a hurry. In this way, by adjusting each process according to the user's emotions, data processing can be tailored to the user's needs.

[0115] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes by considering the geographical distribution of the data. For example, the anonymization unit can prioritize anonymizing geographically close data. The integration unit can prioritize integrating geographically close data. The analysis unit can prioritize analyzing geographically close data. The identification unit can prioritize identifying geographically close data. The suggestion unit can prioritize suggesting geographically close business opportunities. This enables efficient data processing by considering the geographical distribution of the data.

[0116] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes based on the timing of data submission. For example, the anonymization unit can prioritize anonymizing the most recent data. The integration unit can prioritize integrating the most recent data. The analysis unit can prioritize analyzing the most recent data. The identification unit can prioritize identifying the most recent data. The suggestion unit can prioritize suggesting the most recent business opportunities. By adjusting each process based on the timing of data submission, data processing based on the latest information becomes possible.

[0117] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and proposal processes by referencing relevant literature on the data. For example, the anonymization unit can improve the accuracy of anonymization based on relevant literature. The integration unit can improve the accuracy of integration based on relevant literature. The analysis unit can improve the accuracy of analysis based on relevant literature. The identification unit can improve the accuracy of identification based on relevant literature. The proposal unit can improve the accuracy of proposals based on relevant literature. As a result, by referring to relevant literature on the data, the accuracy of each process is improved and data consistency is maintained.

[0118] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes by considering the interrelationships of the data. For example, the anonymization unit can analyze the interrelationships of the data and prioritize anonymizing highly relevant data. The integration unit can analyze the interrelationships of the data and prioritize integrating highly relevant data. The analysis unit can analyze the interrelationships of the data and prioritize analyzing highly relevant data. The identification unit can analyze the interrelationships of the data and prioritize identifying highly relevant data. The suggestion unit can analyze the interrelationships of the data and prioritize suggesting highly relevant business opportunities. As a result, by considering the interrelationships of the data, the accuracy of each process is improved and data consistency is maintained.

[0119] The AI ​​agent system can further estimate the user's emotions and adjust the data anonymization, integration, analysis, identification, and suggestion processes based on the estimated emotions. For example, the anonymization unit can adjust the accuracy of anonymization appropriately to improve data usability when the user is relaxed. The integration unit can provide a simple integration method when the user is stressed. The analysis unit can provide a method for rapid analysis when the user is in a hurry. The identification unit can provide detailed identification options when the user is relaxed. The suggestion unit can provide simple and easy-to-understand suggestions when the user is stressed. In this way, by adjusting each process according to the user's emotions, data processing can be tailored to the user's needs.

[0120] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes according to the data category. For example, the anonymization unit can apply advanced encryption algorithms to financial data. The integration unit can apply different integration algorithms to human resources data. The analysis unit can apply yet different analysis algorithms to customer data. The identification unit can apply specific algorithms to financial data to identify business opportunities. The suggestion unit can apply specific suggestion algorithms to customer risks. This improves the accuracy of each process by applying algorithms appropriate to the data category.

[0121] The AI ​​agent system can further estimate the user's emotions and adjust the data anonymization, integration, analysis, identification, and suggestion processes based on the estimated emotions. For example, the anonymization unit can perform the anonymization process quickly if the user is in a hurry. The integration unit can provide detailed integration options if the user is relaxed. The analysis unit can provide a simple analysis method if the user is stressed. The identification unit can provide a method for quick identification if the user is in a hurry. The suggestion unit can provide detailed suggestions if the user is relaxed. This allows for data processing tailored to the user's needs by adjusting each process according to the user's emotions.

[0122] The AI ​​agent system can further adjust the anonymization, integration, analysis, identification, and suggestion processes based on the importance of the data. For example, the anonymization unit can perform detailed anonymization on high-importance data. The integration unit can prioritize the integration of high-importance data. The analysis unit can prioritize the analysis of high-importance data. The identification unit can prioritize the identification of high-importance data. The suggestion unit can provide detailed suggestions for high-importance business opportunities. By adjusting each process based on the importance of the data, a good balance can be maintained between data protection and availability.

[0123] The AI ​​agent system can further estimate the user's emotions and adjust the data anonymization, integration, analysis, identification, and suggestion processes based on the estimated emotions. For example, the anonymization unit can prioritize the anonymization of important data if the user is stressed. The integration unit can provide a way to quickly integrate data if the user is in a hurry. The analysis unit can provide detailed analysis options if the user is relaxed. The identification unit can provide a simple identification method if the user is stressed. The suggestion unit can provide suggestions that are easy to understand if the user is in a hurry. By adjusting each process according to the user's emotions, data processing can be tailored to the user's needs.

[0124] The following briefly describes the processing flow for example form 2.

[0125] Step 1: The anonymization unit anonymizes the data. For example, it anonymizes personal information such as employee salary information and performance data. The anonymization unit can anonymize personal information using generation AI through methods such as data masking, pseudo-anonymization, and complete anonymization. For example, the anonymization unit inputs a prompt to the generation AI saying, "Please anonymize this data," and the generation AI analyzes the data and performs the anonymization. Step 2: The integration unit integrates the data anonymized by the anonymization unit. For example, it integrates the anonymized data into a vector database. The integration unit can use a generative AI to integrate the data based on the database type and integration algorithm. For example, the integration unit prompts the generative AI with "Integrate this data into the vector database," and the generative AI analyzes the data and performs the integration. Step 3: The analysis unit analyzes the data integrated by the integration unit. For example, it analyzes data stored in a vector database. The analysis unit can use a generative AI to analyze the data based on statistical analysis and machine learning algorithms. For example, the analysis unit inputs a prompt to the generative AI, such as "Please analyze this data," and the generative AI analyzes the data and extracts useful information. Step 4: The Identification Department identifies business opportunities and risks based on the data analyzed by the Analysis Department. For example, it identifies untapped areas within the group and proposes new businesses. The Identification Department can use Generative AI to make identifications based on criteria for evaluating business opportunities and risks. For example, the Identification Department inputs a prompt to the Generative AI saying, "Identify business opportunities from this data," and the Generative AI analyzes the data to identify business opportunities. Step 5: The proposal department makes proposals based on the business opportunities and risks identified by the specific department. For example, they might propose ways to optimally utilize assets within the group. The proposal department can use a generation AI to make proposals based on the format and evaluation criteria for the proposal content. For example, the proposal department might input a prompt to the generation AI such as, "Please make a proposal for this business opportunity," and the generation AI would analyze the data and make a proposal.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the anonymization unit, integration unit, analysis unit, identification unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the anonymization unit is implemented by the control unit 46A of the smart device 14 and anonymizes personal information such as employee salary information and performance data. The integration unit is implemented by the identification processing unit 290 of the data processing unit 12 and integrates the anonymized data into a vector database. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the data stored in the vector database. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies business opportunities and risks. The proposal unit is implemented by the identification processing unit 290 of the data processing unit 12 and makes proposals based on the identified business opportunities and risks. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0130] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the anonymization unit, integration unit, analysis unit, identification unit, and proposal unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the anonymization unit is implemented by the control unit 46A of the smart glasses 214 and anonymizes personal information such as employee salary information and performance data. The integration unit is implemented by the identification processing unit 290 of the data processing unit 12 and integrates the anonymized data into a vector database. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the data stored in the vector database. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies business opportunities and risks. The proposal unit is implemented by the identification processing unit 290 of the data processing unit 12 and makes proposals based on the identified business opportunities and risks. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0146] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the anonymization unit, integration unit, analysis unit, identification unit, and proposal unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the anonymization unit is implemented by the control unit 46A of the headset terminal 314 and anonymizes personal information such as employee salary information and performance data. The integration unit is implemented by the identification processing unit 290 of the data processing unit 12 and integrates the anonymized data into a vector database. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the data stored in the vector database. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies business opportunities and risks. The proposal unit is implemented by the identification processing unit 290 of the data processing unit 12 and makes proposals based on the identified business opportunities and risks. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0162] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements described above, including the anonymization unit, integration unit, analysis unit, identification unit, and proposal unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the anonymization unit is implemented by the control unit 46A of the robot 414 and anonymizes personal information such as employee salary information and performance data. The integration unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and integrates the anonymized data into a vector database. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes the data stored in the vector database. The identification unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and identifies business opportunities and risks. The proposal unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and makes proposals based on the identified business opportunities and risks. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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."

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] (Note 1) An anonymization unit that anonymizes the data, An integration unit that integrates the data anonymized by the anonymization unit, An analysis unit analyzes the data integrated by the aforementioned integration unit, An identification unit identifies business opportunities and risks based on the data analyzed by the aforementioned analysis unit, The system includes a proposal unit that makes proposals based on the business opportunities and risks identified by the aforementioned identification unit. A system characterized by the following features. (Note 2) The anonymization unit is, Anonymizing personal information such as employee salary information and performance data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned integration unit is Integrate anonymized data into a vector database. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit, Analyze data stored in a vector database. The system described in Appendix 1, characterized by the features described herein. (Note 5) The specified part is, Identify untapped areas within the group and propose new business ventures. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned proposal section is, We propose methods for optimally utilizing assets within the group. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned proposal section is, To expedite collaboration within the group and improve the speed of project launches. The system described in Appendix 1, characterized by the features described herein. (Note 8) The anonymization unit is, It estimates the user's emotions and adjusts the accuracy of anonymization based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The anonymization unit is, Apply different anonymization algorithms depending on the type of data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The anonymization unit is, Adjust the level of anonymization based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 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, Anonymization priorities are determined based on the data submission date. The system described in Appendix 1, characterized by the features described herein. (Note 13) The anonymization unit is, Adjust the anonymization order based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned integration unit is It estimates the user's emotions and adjusts the integration method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned integration unit is Improve the accuracy of integration by considering the interrelationships between data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned integration unit is Apply different integration algorithms depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned integration unit is It estimates user sentiment and determines integration priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned integration unit is Integration should be performed considering the geographical distribution of the data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned integration unit is Referencing relevant literature for data improves the accuracy of integration. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, Improve the accuracy of the analysis by considering the interrelationships between data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, Apply different analysis algorithms depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, Perform the analysis while considering the geographical distribution of the data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit, Referencing relevant literature on the data improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 26) The specified part is, It estimates the user's emotions and adjusts specific methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The specified part is, Improve specific accuracy by considering the interrelationships of data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The specified part is, Apply different specific algorithms depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 29) The specified part is, It estimates the user's emotions and determines specific priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The specified part is, Identify the data by considering its geographical distribution. The system described in Appendix 1, characterized by the features described herein. (Note 31) The specified part is, Referencing relevant literature on the data improves specific accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned proposal section is, Adjust the level of detail in your proposal based on the importance of business opportunities and risks. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned proposal section is, Apply different proposal algorithms depending on the category of business opportunity or risk. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned proposal section is, It estimates the user's emotions and determines the priority of suggestions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned proposal section is, Prioritize proposals based on the timing of business opportunity and risk presentation. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned proposal section is, Adjust the order of proposals based on the relevance of business opportunities and risks. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0198] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An anonymization unit that anonymizes the data, An integration unit that integrates the data anonymized by the anonymization unit, An analysis unit analyzes the data integrated by the aforementioned integration unit, An identification unit identifies business opportunities and risks based on the data analyzed by the aforementioned analysis unit, The system includes a proposal unit that makes proposals based on the business opportunities and risks identified by the aforementioned identification unit. A system characterized by the following features.

2. The anonymization unit is, Anonymizing personal information such as employee salary information and performance data. The system according to feature 1.

3. The aforementioned integration unit is Integrate anonymized data into a vector database. The system according to feature 1.

4. The aforementioned analysis unit, Analyze data stored in a vector database. The system according to feature 1.

5. The specified part is, Identify untapped areas within the group and propose new business ventures. The system according to feature 1.

6. The aforementioned proposal section is, We propose methods for optimally utilizing assets within the group. The system according to feature 1.

7. The aforementioned proposal section is, To expedite collaboration within the group and improve the speed of project launches. The system according to feature 1.

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

9. The anonymization unit is, Apply different anonymization algorithms depending on the type of data. The system according to feature 1.

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

Images