system

Abstract

An object of a system according to an embodiment is to support a small business owner to follow a target number in daily business activities.SOLUTION: A system according to an embodiment includes a data analysis unit, a notification unit, an expectation calculation unit, and an action presentation unit. The data analytics analyzes the enterprise's KPIs, financial breakdown, and other information. The notification unit notifies the automated calculation result through a smartphone or a tablet terminal. An expectation calculation part calculates an expectation number based on weather information, the latest result or the like, and presents a difference between the result and the expectation. The measure presentation part presents a measure plan for filling a difference between the result and the expectation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately support small business owners in pursuing target figures in their daily business activities, and there is room for improvement.

[0005] The system according to the embodiment aims to support small business owners in pursuing target figures in their daily business activities. [Means for solving the problem]

[0006] The system according to the embodiment includes a data analysis unit, a notification unit, a forecast calculation unit, and a measure presentation unit. The data analysis unit analyzes a company's KPIs, financial journal entries, and other information. The notification unit notifies the user of the automated calculation results via a smartphone or tablet device. The forecast calculation unit calculates forecast figures based on weather information and recent performance data, and presents the difference between the actual results and the forecast. The measure presentation unit presents proposed measures to close the gap between the actual results and the forecast. [Effects of the Invention]

[0007] The system according to the embodiment can help small business owners pursue target figures in their daily business activities. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The management support system according to an embodiment of the present invention is a system that notifies small business owners of restaurants and other retail businesses of daily target figures. This system analyzes a company's KPIs, financial journal entries, and other information, and automates the various calculations, investment management, and calculation of projected results performed by the corporate planning department. As a result, the management support system allows small business owners to clarify their goals in their daily business activities and manage their business efficiently.

[0029] The management support system according to the embodiment includes a data analysis unit, a notification unit, a forecast calculation unit, and a policy proposal unit. The data analysis unit analyzes a company's KPIs, financial journal entries, and other information. For example, using sales data, cost data, inventory data, and other input information, the generation AI analyzes this data and automates various estimates, investment management, and calculation of expected results performed by the corporate planning department. The generation AI analyzes the data using text generation AI (e.g., LLM) and multimodal generation AI to provide information necessary for management decisions. The notification unit notifies the automated calculation results via a smartphone or tablet device. For example, by notifying target figures for daily sales activities, small business owners can pursue their goals. The notification unit notifies information such as target figures and management indicators output by the generation AI. The forecast calculation unit calculates forecast figures based on weather information, recent performance, etc., and presents the difference between the actual results and the forecast. For example, it calculates sales forecasts based on weather information and forecast figures based on recent performance, and presents the difference from the actual results. The forecast calculation unit presents forecast figures and variance information output by the generation AI. The measure presentation unit presents measure proposals to close the gap between actual results and forecasts. For example, it presents promotion proposals to increase sales and measure proposals to reduce costs. The measure presentation unit presents information on the measure proposals output by the generation AI. As a result, the management support system according to the embodiment enables small business owners to clarify goals in their daily sales activities and manage their businesses efficiently. For example, the output unit displays the scoring results to students and teachers via a web application or mobile application. If students or teachers wish to receive feedback in paper form, the results are printed using a printer. Sending the results by email provides quick feedback by sending the results directly to students and parents.

[0030] The data analysis department analyzes sales data, cost data, and inventory data, and can automate the various estimates, investment management, and calculation of expected results performed by the corporate planning department. The data analysis department, for example, analyzes sales data to understand sales trends and patterns. For example, based on sales data, it analyzes monthly sales increases and decreases and makes sales forecasts. The data analysis department also analyzes cost data to understand cost breakdowns and factors behind fluctuations. For example, it analyzes the ratio of fixed costs to variable costs and identifies areas for cost reduction. The data analysis department also analyzes inventory data to understand the appropriate inventory amount and turnover rate. For example, based on inventory data, it analyzes inventory surpluses and shortages and calculates the appropriate inventory amount. This makes it possible to automate the work of the corporate planning department and improve efficiency.

[0031] The notification unit can notify the target figures for daily sales activities. For example, the notification unit may notify the daily sales target. For example, the sales target may be notified via a push notification on a smartphone. The notification unit may also notify the daily customer acquisition target. For example, the customer acquisition target may be notified via a notification function on a tablet. The notification unit may also notify the daily cost reduction target. For example, the cost reduction target may be notified via email. This allows small business owners to clarify their daily targets and carry out sales activities efficiently.

[0032] The forecast calculation unit can make a sales forecast based on weather information and present the difference from actual results. The forecast calculation unit makes a sales forecast based on, for example, weather information. For example, it makes a sales forecast for a sunny day and compares it with actual results. The forecast calculation unit also makes a sales forecast based on the most recent results. For example, it makes a sales forecast for the next week based on sales results for the past week and compares it with actual results. The forecast calculation unit also makes a sales forecast by combining weather information and the most recent results. For example, it makes a sales forecast for the next month based on weather information and sales results for the past month and compares it with actual results. This makes it possible to make a sales forecast based on weather information and clearly show the difference from actual results.

[0033] The policy presentation unit can present promotion proposals for increasing sales and policy proposals for reducing costs. The policy presentation unit, for example, presents promotion proposals for increasing sales. For example, it proposes discount campaigns and point redemption measures. The policy presentation unit also presents policy proposals for reducing costs. For example, it proposes measures to reduce purchasing costs and energy costs. The policy presentation unit also presents policy proposals for achieving both increased sales and reduced costs. For example, it proposes measures for efficient inventory management and improving business processes. This makes it possible to present specific policy proposals for increasing sales and reducing costs.

[0034] The data analysis department analyzes employee performance data and customer feedback data to perform more detailed management analysis. For example, the data analysis department analyzes employee performance data to understand work efficiency. For example, it analyzes employee attendance status and task completion rates to perform performance evaluations. The data analysis department also analyzes customer feedback data to understand customer satisfaction. For example, it analyzes the contents of customer surveys and reviews to consider measures to improve customer satisfaction. The data analysis department also combines and analyzes employee performance data and customer feedback data to identify areas for management improvement. For example, it analyzes the relationship between employee performance and customer satisfaction and proposes improvement measures. This allows for more detailed management analysis to be performed based on employee performance and customer feedback.

[0035] The data analysis unit can add an anomaly detection function and notify of abnormal patterns and trends in real time. The data analysis unit, for example, detects abnormal patterns in sales data and notifies in real time. For example, it detects a sudden decrease in sales or an abnormal increase in sales and issues an alert. The data analysis unit also detects abnormal trends in cost data and notifies in real time. For example, it detects a sudden increase in cost or an abnormal cost reduction and issues an alert. The data analysis unit also detects abnormal fluctuations in inventory data and notifies in real time. For example, it detects a sudden decrease in inventory or an abnormal increase in inventory and issues an alert. This makes it possible to detect and notify of abnormal patterns and trends in real time.

[0036] The data analysis department analyzes data from other industries and can incorporate best practices from those industries. For example, the data analysis department analyzes sales data from other industries and incorporates best practices. For example, efficient inventory management techniques from the manufacturing industry can be applied to the food and beverage industry. The data analysis department also analyzes cost data from other industries and incorporates best practices. For example, cost reduction techniques from the IT industry can be applied to the retail industry. The data analysis department also analyzes customer data from other industries and incorporates best practices. For example, customer satisfaction improvement techniques from the service industry can be applied to the manufacturing industry. This makes it possible to analyze data from other industries and incorporate best practices from those industries.

[0037] The data analysis unit can propose a customized management strategy that takes into account the characteristics of each region. The data analysis unit, for example, proposes a management strategy that takes into account the sales characteristics of each region. For example, it reflects the differences in sales patterns between urban and rural areas. The data analysis unit also proposes a management strategy that takes into account the consumer behavior of each region. For example, it reflects the purchasing behavior and preferences of consumers in each region. The data analysis unit also proposes a management strategy that takes into account the competitive situation of each region. For example, it reflects the trends of competitors in each region. This makes it possible to propose a customized management strategy that takes into account the characteristics of each region.

[0038] The notification unit can provide notifications through a voice assistant, enabling hands-free confirmation. The notification unit, for example, notifies a sales target through the voice assistant. For example, a smart speaker is used to notify a daily sales target by voice. The notification unit can also notify a customer acquisition target through the voice assistant. For example, a voice assistant is used to notify a daily customer acquisition target by voice. The notification unit can also notify a cost reduction target through the voice assistant. For example, a voice assistant is used to notify a daily cost reduction target by voice. This allows notifications to be provided through the voice assistant, enabling hands-free confirmation.

[0039] The notification unit can customize the notification content and provide information according to the role and interests of each user. For example, the notification unit notifies sales targets to managers. For example, the notification unit notifies sales targets and profit margins to managers. The notification unit also notifies business targets to employees. For example, the notification unit notifies business achievement rates and individual business targets to employees. The notification unit also notifies promotion targets to marketing personnel. For example, the notification unit notifies marketing personnel of the progress and effects of promotions. This makes it possible to customize the notification content and provide information according to the role and interests of each user.

[0040] The notification unit can also be made compatible with wearable devices such as smartwatches and smartglasses. For example, the notification unit can be made compatible with smartwatches to notify sales targets. For example, the sales targets can be displayed on the screen of the smartwatch. The notification unit can also be made compatible with smartglasses to notify customer acquisition targets. For example, the customer acquisition targets can be displayed on the display of the smartglasses. The notification unit can also be made compatible with other wearable devices to notify cost reduction targets. For example, the cost reduction targets can be displayed on the screen of a fitness tracker. This allows the notification content to be compatible with wearable devices such as smartwatches and smartglasses.

[0041] The notification unit can automatically translate the notification content into different languages, thereby achieving multilingual support. The notification unit, for example, automatically translates the notification content into English. For example, it translates a sales target into English and notifies an English-speaking user. The notification unit can also automatically translate the notification content into French. For example, it can translate a customer acquisition target into French and notify a French-speaking user. The notification unit can also automatically translate the notification content into Chinese. For example, it can translate a cost reduction target into Chinese and notify a Chinese-speaking user. This allows the notification content to be automatically translated into different languages, thereby achieving multilingual support.

[0042] The forecast calculation unit can add a prediction that takes seasonality and event information into account to the forecast figures calculated by the generation AI. For example, the forecast calculation unit adds a prediction that takes seasonality into account to the forecast figures calculated by the generation AI. For example, it reflects sales fluctuations in summer and winter. The forecast calculation unit also adds a prediction that takes event information into account to the forecast figures calculated by the generation AI. For example, it reflects the impact of specific events or campaigns. The forecast calculation unit also adds a prediction that combines seasonality and event information to the forecast figures calculated by the generation AI. For example, it reflects the impact of specific summer events. In this way, it is possible to add a prediction that takes seasonality and event information into account to the forecast figures calculated by the generation AI.

[0043] The forecast calculation unit incorporates competitors' data when calculating forecast figures, enabling more accurate predictions. The forecast calculation unit, for example, incorporates competitors' sales data and reflects it in calculating forecast figures. For example, it makes a sales forecast for the company based on competitors' sales trends. The forecast calculation unit also incorporates competitors' cost data and reflects it in calculating forecast figures. For example, it makes a cost forecast for the company based on competitors' cost structures. The forecast calculation unit also incorporates competitors' inventory data and reflects it in calculating forecast figures. For example, it makes an inventory forecast for the company based on competitors' inventory turnover rates. In this way, it is possible to incorporate competitors' data when calculating forecast figures, enabling more accurate predictions.

[0044] The forecast calculation unit can incorporate social media trend data and reflect real-time market trends. The forecast calculation unit, for example, incorporates social media trend data and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the popularity of a specific hashtag. The forecast calculation unit also incorporates social media engagement data and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the number of likes and shares of a post. The forecast calculation unit also incorporates social media comment data and reflects it in the calculation of forecast figures. For example, the content of the comments is analyzed to make a sales forecast. In this way, social media trend data can be incorporated and real-time market trends can be reflected.

[0045] The forecast calculation unit can incorporate data from different regions and cultural spheres to make predictions from a global perspective. The forecast calculation unit, for example, incorporates sales data from different regions and reflects it in the calculation of forecast figures. For example, a global sales forecast is made based on sales trends for each region. The forecast calculation unit also incorporates consumer behavior data from different cultural spheres and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the purchasing behavior and preferences of consumers for each cultural sphere. The forecast calculation unit also incorporates competitor data from different regions and cultural spheres and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the trends of competitors in each region. This makes it possible to incorporate data from different regions and cultural spheres and make predictions from a global perspective.

[0046] The policy suggestion unit can add risk assessments based on past success cases and failure cases. The policy suggestion unit, for example, adds a risk assessment based on past success cases. For example, it proposes low-risk measures by referring to past success cases. The policy suggestion unit also adds a risk assessment based on past failure cases. For example, it avoids high-risk measures by referring to past failure cases. The policy suggestion unit also adds a risk assessment that combines past success cases and failure cases. For example, it proposes measures that balance risks by referring to both success cases and failure cases. In this way, it is possible to add risk assessments based on past success cases and failure cases.

[0047] The policy presentation unit can incorporate real-time market data and make immediate proposals. The policy presentation unit, for example, incorporates real-time sales data and makes immediate proposals. For example, it proposes promotional measures based on the latest sales data. The policy presentation unit also incorporates real-time inventory data and makes immediate proposals. For example, it proposes inventory management measures based on the latest inventory data. The policy presentation unit also incorporates real-time customer data and makes immediate proposals. For example, it proposes customer response measures based on the latest customer data. This makes it possible to incorporate real-time market data and make immediate proposals.

[0048] The Policy Presentation Department can incorporate best practices from other industries and propose new approaches. For example, the Policy Presentation Department presents policy proposals that incorporate best practices from other industries. For example, applying efficient inventory management techniques from the manufacturing industry to the food and beverage industry. The Policy Presentation Department also presents policy proposals based on successful cases from other industries. For example, applying cost reduction techniques from the IT industry to the retail industry. The Policy Presentation Department also presents policy proposals based on failure cases from other industries. For example, proposing low-risk measures based on failure cases from the service industry. This makes it possible to incorporate best practices from other industries and propose new approaches.

[0049] The policy presentation unit can make customized proposals that take into account the characteristics of each region. The policy presentation unit, for example, presents policy proposals that take into account the sales characteristics of each region. For example, differences in sales patterns between urban and rural areas can be reflected. The policy presentation unit also presents policy proposals that take into account consumer behavior in each region. For example, the purchasing behavior and preferences of consumers in each region can be reflected. The policy presentation unit also presents policy proposals that take into account the competitive situation in each region. For example, the trends of competitors in each region can be reflected. This makes it possible to make customized proposals that take into account the characteristics of each region.

[0050] The policy execution unit can set multiple scenarios and compare the results of each scenario. The policy execution unit, for example, sets multiple sales scenarios and compares the results of each scenario. For example, it simulates the impact of price revisions and promotions. The policy execution unit also sets multiple cost scenarios and compares the results of each scenario. For example, it simulates the impact of cost reduction measures. The policy execution unit also sets multiple inventory scenarios and compares the results of each scenario. For example, it simulates the impact of inventory management measures. This makes it possible to set multiple scenarios and compare the results of each scenario.

[0051] The policy execution unit adds a risk assessment to the simulation results, and can avoid high-risk measures in advance. The policy execution unit, for example, adds a risk assessment to the simulation results, and avoids high-risk measures in advance. For example, it determines the priority of measures based on a risk score. The policy execution unit also adds a risk assessment to the simulation results, and prioritizes low-risk measures. For example, it selects measures based on a risk matrix. The policy execution unit also adds a risk assessment to the simulation results, and proposes measures that balance risks. For example, it proposes measures that take into account the balance between risk and return. This makes it possible to add a risk assessment to the simulation results, and avoid high-risk measures in advance.

[0052] The policy execution unit can visualize the simulation results on different devices to enable intuitive understanding. For example, the policy execution unit visualizes the simulation results on a VR headset to enable the user to intuitively understand. For example, sales forecasts and cost analyses are displayed in 3D graphs. The policy execution unit can also visualize the simulation results on AR glasses to enable the user to intuitively understand. For example, inventory management simulation results are displayed in AR. The policy execution unit can also visualize the simulation results on other devices to enable the user to intuitively understand. For example, the simulation results are displayed on a tablet or smartphone. This allows the simulation results to be visualized on different devices to enable intuitive understanding.

[0053] The policy execution department can apply the simulation results to different industries and applications to discover new business opportunities. For example, the policy execution department applies the simulation results to different industries to discover new business opportunities. For example, the simulation results for the manufacturing industry are applied to the service industry. The policy execution department can also apply the simulation results to different applications to discover new business opportunities. For example, the simulation results for the logistics industry are applied to the retail industry. The policy execution department can also apply the simulation results to different industries and applications to propose new business models. For example, a new service can be proposed based on the simulation results for the IT industry. In this way, the simulation results can be applied to different industries and applications to discover new business opportunities.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The management support system can further include a purchase history analysis unit that analyzes customer purchase histories. The purchase history analysis unit, for example, analyzes customers' past purchase data to understand repeat purchase trends. For example, it analyzes which customer segments are popular with specific products and conducts targeted marketing. The purchase history analysis unit also analyzes customers' purchase frequency and purchase amounts to measure the effectiveness of loyalty programs. For example, it analyzes the usage of point systems and discount coupons to consider measures to improve customer loyalty. The purchase history analysis unit also analyzes customers' purchasing patterns to identify opportunities for cross-selling and up-selling. For example, sales can be increased by suggesting related products to customers who have purchased a specific product. This makes it possible to develop detailed marketing strategies based on customers' purchase histories.

[0056] The data analysis unit may further include a health data analysis unit that analyzes employee health data. The health data analysis unit, for example, analyzes data obtained from employees' fitness trackers or health apps to understand their health status. For example, it analyzes employees' step counts and heart rates to predict health risks. The health data analysis unit also proposes health promotion programs based on employees' health data. For example, it proposes fitness challenges to employees who are not getting enough exercise. The health data analysis unit also considers measures to improve the working environment based on employees' health data. For example, it proposes relaxation programs to employees with high stress levels. This allows management decisions to be made based on employees' health status.

[0057] The notification unit can further include an emergency notification function. The emergency notification function issues an alert, for example, if sales suddenly decrease. For example, if sales fall significantly below forecast values, a push notification is sent to a smartphone. The emergency notification function also issues an alert if inventory suddenly decreases. For example, if inventory falls below a certain threshold, a notification is sent to a tablet. The emergency notification function also issues an alert if costs suddenly increase. For example, if costs significantly exceed the budget, a notification is sent by email. This allows for a rapid response to emergencies.

[0058] The forecast calculation unit can further incorporate social media trend data to reflect real-time market trends. The forecast calculation unit, for example, incorporates social media trend data and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the popularity of a specific hashtag. The forecast calculation unit also incorporates social media engagement data and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the number of likes and shares of a post. The forecast calculation unit also incorporates social media comment data and reflects it in the calculation of forecast figures. For example, the content of the comments is analyzed to make a sales forecast. In this way, social media trend data can be incorporated to reflect real-time market trends.

[0059] The policy proposal department can further incorporate best practices from other industries and propose new approaches. For example, the policy proposal department will propose policy proposals that incorporate best practices from other industries. For example, applying efficient inventory management techniques from the manufacturing industry to the food and beverage industry. The policy proposal department will also propose policy proposals based on successful cases from other industries. For example, applying cost reduction techniques from the IT industry to the retail industry. The policy proposal department will also propose policy proposals based on failure cases from other industries. For example, proposing low-risk measures based on failure cases from the service industry. This makes it possible to incorporate best practices from other industries and propose new approaches.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The Data Analysis Department analyzes the company's KPIs, financial entries, and other information. For example, sales data, cost data, inventory data, etc. are used as input, and the Generation AI analyzes this data to automate the various estimates, investment management, and calculation of expected results performed by the Corporate Planning Department. The Generation AI uses text generation AI (e.g., LLM) and multimodal generation AI to analyze the data and provide the information necessary for management decisions. Step 2: The notification unit notifies the user of the automated calculation results via a smartphone or tablet. For example, by notifying the user of the target figures for daily sales activities, the small business owner can track their goals. The notification unit notifies the user of information such as the target figures and management indicators output by the generation AI. Step 3: The forecast calculation unit calculates forecast figures based on weather information and recent performance data, and displays the difference between the actual results and the forecast. For example, it calculates sales forecasts based on weather information and forecast figures based on recent performance data, and displays the difference from the actual results. The forecast calculation unit displays the forecast figures and difference information output by the generation AI. Step 4: The measure presentation unit presents measures to close the gap between actual results and forecasts. For example, it presents promotional measures to increase sales or measures to reduce costs. The measure presentation unit presents information about the measures output by the generation AI.

[0062] (Example 2) The management support system according to an embodiment of the present invention is a system that notifies small business owners of restaurants and other retail businesses of daily target figures. This system analyzes a company's KPIs, financial journal entries, and other information, and automates the various calculations, investment management, and calculation of projected results performed by the corporate planning department. As a result, the management support system allows small business owners to clarify their goals in their daily business activities and manage their business efficiently.

[0063] The management support system according to the embodiment includes a data analysis unit, a notification unit, a forecast calculation unit, and a policy proposal unit. The data analysis unit analyzes a company's KPIs, financial journal entries, and other information. For example, using sales data, cost data, inventory data, and other input information, the generation AI analyzes this data and automates various estimates, investment management, and calculation of expected results performed by the corporate planning department. The generation AI analyzes the data using text generation AI (e.g., LLM) and multimodal generation AI to provide information necessary for management decisions. The notification unit notifies the automated calculation results via a smartphone or tablet device. For example, by notifying target figures for daily sales activities, small business owners can pursue their goals. The notification unit notifies information such as target figures and management indicators output by the generation AI. The forecast calculation unit calculates forecast figures based on weather information, recent performance, etc., and presents the difference between the actual results and the forecast. For example, it calculates sales forecasts based on weather information and forecast figures based on recent performance, and presents the difference from the actual results. The forecast calculation unit presents forecast figures and variance information output by the generation AI. The measure presentation unit presents measure proposals to close the gap between actual results and forecasts. For example, it presents promotion proposals to increase sales and measure proposals to reduce costs. The measure presentation unit presents information on the measure proposals output by the generation AI. As a result, the management support system according to the embodiment enables small business owners to clarify goals in their daily sales activities and manage their businesses efficiently. For example, the output unit displays the scoring results to students and teachers via a web application or mobile application. If students or teachers wish to receive feedback in paper form, the results are printed using a printer. Sending the results by email provides quick feedback by sending the results directly to students and parents.

[0064] The data analysis department analyzes sales data, cost data, and inventory data, and can automate the various estimates, investment management, and calculation of expected results performed by the corporate planning department. The data analysis department, for example, analyzes sales data to understand sales trends and patterns. For example, based on sales data, it analyzes monthly sales increases and decreases and makes sales forecasts. The data analysis department also analyzes cost data to understand cost breakdowns and factors behind fluctuations. For example, it analyzes the ratio of fixed costs to variable costs and identifies areas for cost reduction. The data analysis department also analyzes inventory data to understand the appropriate inventory amount and turnover rate. For example, based on inventory data, it analyzes inventory surpluses and shortages and calculates the appropriate inventory amount. This makes it possible to automate the work of the corporate planning department and improve efficiency.

[0065] The notification unit can notify the target figures for daily sales activities. For example, the notification unit may notify the daily sales target. For example, the sales target may be notified via a push notification on a smartphone. The notification unit may also notify the daily customer acquisition target. For example, the customer acquisition target may be notified via a notification function on a tablet. The notification unit may also notify the daily cost reduction target. For example, the cost reduction target may be notified via email. This allows small business owners to clarify their daily targets and carry out sales activities efficiently.

[0066] The forecast calculation unit can make a sales forecast based on weather information and present the difference from actual results. The forecast calculation unit makes a sales forecast based on, for example, weather information. For example, it makes a sales forecast for a sunny day and compares it with actual results. The forecast calculation unit also makes a sales forecast based on the most recent results. For example, it makes a sales forecast for the next week based on sales results for the past week and compares it with actual results. The forecast calculation unit also makes a sales forecast by combining weather information and the most recent results. For example, it makes a sales forecast for the next month based on weather information and sales results for the past month and compares it with actual results. This makes it possible to make a sales forecast based on weather information and clearly show the difference from actual results.

[0067] The policy presentation unit can present promotion proposals for increasing sales and policy proposals for reducing costs. The policy presentation unit, for example, presents promotion proposals for increasing sales. For example, it proposes discount campaigns and point redemption measures. The policy presentation unit also presents policy proposals for reducing costs. For example, it proposes measures to reduce purchasing costs and energy costs. The policy presentation unit also presents policy proposals for achieving both increased sales and reduced costs. For example, it proposes measures for efficient inventory management and improving business processes. This makes it possible to present specific policy proposals for increasing sales and reducing costs.

[0068] The data analysis department analyzes employee performance data and customer feedback data to perform more detailed management analysis. For example, the data analysis department analyzes employee performance data to understand work efficiency. For example, it analyzes employee attendance status and task completion rates to perform performance evaluations. The data analysis department also analyzes customer feedback data to understand customer satisfaction. For example, it analyzes the contents of customer surveys and reviews to consider measures to improve customer satisfaction. The data analysis department also combines and analyzes employee performance data and customer feedback data to identify areas for management improvement. For example, it analyzes the relationship between employee performance and customer satisfaction and proposes improvement measures. This allows for more detailed management analysis to be performed based on employee performance and customer feedback.

[0069] The data analysis unit can add an anomaly detection function and notify of abnormal patterns and trends in real time. The data analysis unit, for example, detects abnormal patterns in sales data and notifies in real time. For example, it detects a sudden decrease in sales or an abnormal increase in sales and issues an alert. The data analysis unit also detects abnormal trends in cost data and notifies in real time. For example, it detects a sudden increase in cost or an abnormal cost reduction and issues an alert. The data analysis unit also detects abnormal fluctuations in inventory data and notifies in real time. For example, it detects a sudden decrease in inventory or an abnormal increase in inventory and issues an alert. This makes it possible to detect and notify of abnormal patterns and trends in real time.

[0070] The data analysis unit uses the emotion estimation function to analyze employee and customer emotion data, allowing for emotional factors to be incorporated into management decisions. The data analysis unit, for example, analyzes employee emotion data and reflects it in management decisions. For example, it understands employee stress levels and motivation and considers measures to improve the working environment. The data analysis unit also analyzes customer emotion data and reflects it in marketing strategies. For example, it understands customer satisfaction and dissatisfaction and considers promotional measures. The data analysis unit also combines and analyzes employee and customer emotion data to make comprehensive management decisions. For example, it analyzes the relationship between employee motivation and customer satisfaction and proposes improvement measures. This makes it possible to incorporate emotional factors into management decisions based on employee and customer emotion data.

[0071] The data analysis department analyzes data from other industries and can incorporate best practices from those industries. For example, the data analysis department analyzes sales data from other industries and incorporates best practices. For example, efficient inventory management techniques from the manufacturing industry can be applied to the food and beverage industry. The data analysis department also analyzes cost data from other industries and incorporates best practices. For example, cost reduction techniques from the IT industry can be applied to the retail industry. The data analysis department also analyzes customer data from other industries and incorporates best practices. For example, customer satisfaction improvement techniques from the service industry can be applied to the manufacturing industry. This makes it possible to analyze data from other industries and incorporate best practices from those industries.

[0072] The data analysis unit can propose a customized management strategy that takes into account the characteristics of each region. The data analysis unit, for example, proposes a management strategy that takes into account the sales characteristics of each region. For example, it reflects the differences in sales patterns between urban and rural areas. The data analysis unit also proposes a management strategy that takes into account the consumer behavior of each region. For example, it reflects the purchasing behavior and preferences of consumers in each region. The data analysis unit also proposes a management strategy that takes into account the competitive situation of each region. For example, it reflects the trends of competitors in each region. This makes it possible to propose a customized management strategy that takes into account the characteristics of each region.

[0073] The data analysis unit can use the emotion estimation function to analyze customer emotion data and reflect it in a marketing strategy. The data analysis unit, for example, analyzes customer emotion data and reflects it in a marketing strategy. For example, an advertisement that elicits positive emotions is created based on the customer emotion score. The data analysis unit also analyzes customer emotion data and reflects it in promotional measures. For example, effective promotional measures are proposed based on the customer emotion score. The data analysis unit also analyzes customer emotion data and reflects it in product development. For example, a new product that meets customer needs is developed based on the customer emotion score. In this way, the customer emotion data can be reflected in a marketing strategy.

[0074] The notification unit can provide notifications through a voice assistant, enabling hands-free confirmation. The notification unit, for example, notifies a sales target through the voice assistant. For example, a smart speaker is used to notify a daily sales target by voice. The notification unit can also notify a customer acquisition target through the voice assistant. For example, a voice assistant is used to notify a daily customer acquisition target by voice. The notification unit can also notify a cost reduction target through the voice assistant. For example, a voice assistant is used to notify a daily cost reduction target by voice. This allows notifications to be provided through the voice assistant, enabling hands-free confirmation.

[0075] The notification unit can customize the notification content and provide information according to the role and interests of each user. For example, the notification unit notifies sales targets to managers. For example, the notification unit notifies sales targets and profit margins to managers. The notification unit also notifies business targets to employees. For example, the notification unit notifies business achievement rates and individual business targets to employees. The notification unit also notifies promotion targets to marketing personnel. For example, the notification unit notifies marketing personnel of the progress and effects of promotions. This makes it possible to customize the notification content and provide information according to the role and interests of each user.

[0076] The notification unit can use the emotion estimation function to analyze the user's emotional response to the notification content and optimize the notification method. The notification unit, for example, analyzes the user's emotional response to the notification content and optimizes the notification method. For example, the notification unit selects a notification method that elicits positive emotions based on the user's emotion score. The notification unit also analyzes the user's emotional response to the notification content and optimizes the notification timing. For example, the notification unit selects the optimal notification timing based on the user's emotion score. The notification unit also analyzes the user's emotional response to the notification content and optimizes the notification format. For example, the notification unit selects the optimal notification format based on the user's emotion score. In this way, the user's emotional response to the notification content can be analyzed and the notification method can be optimized.

[0077] The notification unit can also be made compatible with wearable devices such as smartwatches and smartglasses. For example, the notification unit can be made compatible with smartwatches to notify sales targets. For example, the sales targets can be displayed on the screen of the smartwatch. The notification unit can also be made compatible with smartglasses to notify customer acquisition targets. For example, the customer acquisition targets can be displayed on the display of the smartglasses. The notification unit can also be made compatible with other wearable devices to notify cost reduction targets. For example, the cost reduction targets can be displayed on the screen of a fitness tracker. This allows the notification content to be compatible with wearable devices such as smartwatches and smartglasses.

[0078] The notification unit can automatically translate the notification content into different languages, thereby achieving multilingual support. The notification unit, for example, automatically translates the notification content into English. For example, it translates a sales target into English and notifies an English-speaking user. The notification unit can also automatically translate the notification content into French. For example, it can translate a customer acquisition target into French and notify a French-speaking user. The notification unit can also automatically translate the notification content into Chinese. For example, it can translate a cost reduction target into Chinese and notify a Chinese-speaking user. This allows the notification content to be automatically translated into different languages, thereby achieving multilingual support.

[0079] The notification unit can use the emotion estimation function to monitor the user's emotional reaction to the notification content in real time and optimize the timing of notification. The notification unit, for example, monitors the user's emotional reaction to the notification content in real time and optimizes the timing of notification. For example, it analyzes the user's facial expressions and voice and selects the optimal notification timing based on an emotion score. The notification unit also monitors the user's emotional reaction to the notification content in real time and optimizes the frequency of notifications. For example, it selects the optimal notification frequency based on the user's emotion score. The notification unit also monitors the user's emotional reaction to the notification content in real time and optimizes the notification format. For example, it selects the optimal notification format based on the user's emotion score. In this way, the user's emotional reaction to the notification content can be monitored in real time and the timing of notification can be optimized.

[0080] The forecast calculation unit can add a prediction that takes seasonality and event information into account to the forecast figures calculated by the generation AI. For example, the forecast calculation unit adds a prediction that takes seasonality into account to the forecast figures calculated by the generation AI. For example, it reflects sales fluctuations in summer and winter. The forecast calculation unit also adds a prediction that takes event information into account to the forecast figures calculated by the generation AI. For example, it reflects the impact of specific events or campaigns. The forecast calculation unit also adds a prediction that combines seasonality and event information to the forecast figures calculated by the generation AI. For example, it reflects the impact of specific summer events. In this way, it is possible to add a prediction that takes seasonality and event information into account to the forecast figures calculated by the generation AI.

[0081] The forecast calculation unit incorporates competitors' data when calculating forecast figures, enabling more accurate predictions. The forecast calculation unit, for example, incorporates competitors' sales data and reflects it in calculating forecast figures. For example, it makes a sales forecast for the company based on competitors' sales trends. The forecast calculation unit also incorporates competitors' cost data and reflects it in calculating forecast figures. For example, it makes a cost forecast for the company based on competitors' cost structures. The forecast calculation unit also incorporates competitors' inventory data and reflects it in calculating forecast figures. For example, it makes an inventory forecast for the company based on competitors' inventory turnover rates. In this way, it is possible to incorporate competitors' data when calculating forecast figures, enabling more accurate predictions.

[0082] The forecast calculation unit can use the emotion estimation function to predict sales based on customer emotion data. The forecast calculation unit, for example, uses the emotion estimation function to predict sales based on customer emotion data. For example, it predicts sales during periods when customers have strong positive emotions. The forecast calculation unit also uses the emotion estimation function to predict the effectiveness of a promotion based on customer emotion data. For example, it predicts the effectiveness of a promotion based on a customer emotion score. The forecast calculation unit also uses the emotion estimation function to predict sales of a new product based on customer emotion data. For example, it predicts sales of a new product based on a customer emotion score. In this way, it is possible to use the emotion estimation function to predict sales based on customer emotion data.

[0083] The forecast calculation unit can incorporate social media trend data and reflect real-time market trends. The forecast calculation unit, for example, incorporates social media trend data and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the popularity of a specific hashtag. The forecast calculation unit also incorporates social media engagement data and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the number of likes and shares of a post. The forecast calculation unit also incorporates social media comment data and reflects it in the calculation of forecast figures. For example, the content of the comments is analyzed to make a sales forecast. In this way, social media trend data can be incorporated and real-time market trends can be reflected.

[0084] The forecast calculation unit can incorporate data from different regions and cultural spheres to make predictions from a global perspective. The forecast calculation unit, for example, incorporates sales data from different regions and reflects it in the calculation of forecast figures. For example, a global sales forecast is made based on sales trends for each region. The forecast calculation unit also incorporates consumer behavior data from different cultural spheres and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the purchasing behavior and preferences of consumers for each cultural sphere. The forecast calculation unit also incorporates competitor data from different regions and cultural spheres and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the trends of competitors in each region. This makes it possible to incorporate data from different regions and cultural spheres and make predictions from a global perspective.

[0085] The expectation calculation unit can use the emotion estimation function to predict productivity based on employee emotion data. The expectation calculation unit, for example, uses the emotion estimation function to predict productivity based on employee emotion data. For example, it predicts productivity during periods when an employee has strong positive emotions. The expectation calculation unit also uses the emotion estimation function to predict work efficiency based on employee emotion data. For example, it predicts fluctuations in work efficiency based on employee emotion scores. The expectation calculation unit also uses the emotion estimation function to predict team performance based on employee emotion data. For example, it predicts the performance of the entire team based on employee emotion scores. In this way, it is possible to use the emotion estimation function to predict productivity based on employee emotion data.

[0086] The policy suggestion unit can add risk assessments based on past success cases and failure cases. The policy suggestion unit, for example, adds a risk assessment based on past success cases. For example, it proposes low-risk measures by referring to past success cases. The policy suggestion unit also adds a risk assessment based on past failure cases. For example, it avoids high-risk measures by referring to past failure cases. The policy suggestion unit also adds a risk assessment that combines past success cases and failure cases. For example, it proposes measures that balance risks by referring to both success cases and failure cases. In this way, it is possible to add risk assessments based on past success cases and failure cases.

[0087] The policy presentation unit can incorporate real-time market data and make immediate proposals. The policy presentation unit, for example, incorporates real-time sales data and makes immediate proposals. For example, it proposes promotional measures based on the latest sales data. The policy presentation unit also incorporates real-time inventory data and makes immediate proposals. For example, it proposes inventory management measures based on the latest inventory data. The policy presentation unit also incorporates real-time customer data and makes immediate proposals. For example, it proposes customer response measures based on the latest customer data. This makes it possible to incorporate real-time market data and make immediate proposals.

[0088] The policy presentation unit can use the emotion estimation function to present policy proposals based on employee and customer emotion data. The policy presentation unit, for example, uses the emotion estimation function to present policy proposals based on employee emotion data. For example, it proposes policies to increase employee motivation. The policy presentation unit also uses the emotion estimation function to present policy proposals based on customer emotion data. For example, it proposes policies to improve customer satisfaction. The policy presentation unit also uses the emotion estimation function to present policy proposals that combine employee and customer emotion data. For example, it proposes policies to improve both employee motivation and customer satisfaction. In this way, it is possible to present policy proposals based on employee and customer emotion data using the emotion estimation function.

[0089] The Policy Presentation Department can incorporate best practices from other industries and propose new approaches. For example, the Policy Presentation Department presents policy proposals that incorporate best practices from other industries. For example, applying efficient inventory management techniques from the manufacturing industry to the food and beverage industry. The Policy Presentation Department also presents policy proposals based on successful cases from other industries. For example, applying cost reduction techniques from the IT industry to the retail industry. The Policy Presentation Department also presents policy proposals based on failure cases from other industries. For example, proposing low-risk measures based on failure cases from the service industry. This makes it possible to incorporate best practices from other industries and propose new approaches.

[0090] The policy presentation unit can make customized proposals that take into account the characteristics of each region. The policy presentation unit, for example, presents policy proposals that take into account the sales characteristics of each region. For example, differences in sales patterns between urban and rural areas can be reflected. The policy presentation unit also presents policy proposals that take into account consumer behavior in each region. For example, the purchasing behavior and preferences of consumers in each region can be reflected. The policy presentation unit also presents policy proposals that take into account the competitive situation in each region. For example, the trends of competitors in each region can be reflected. This makes it possible to make customized proposals that take into account the characteristics of each region.

[0091] The policy presentation unit can use the emotion estimation function to monitor the user's emotional reaction to the proposed policy in real time and optimize the proposal content. The policy presentation unit, for example, uses the emotion estimation function to monitor the user's emotional reaction to the proposed policy in real time and optimize the proposal content. For example, it analyzes the user's facial expressions and voice and selects an optimal policy based on an emotion score. The policy presentation unit also uses the emotion estimation function to monitor the user's emotional reaction to the proposed policy in real time and optimizes the timing of the proposal. For example, it selects the optimal timing of the proposal based on the user's emotion score. The policy presentation unit also uses the emotion estimation function to monitor the user's emotional reaction to the proposed policy in real time and optimizes the format of the proposal. For example, it selects the optimal format of the proposal based on the user's emotion score. In this way, the emotion estimation function can be used to monitor the user's emotional reaction to the proposed policy in real time and optimize the proposal content.

[0092] The policy execution unit can set multiple scenarios and compare the results of each scenario. The policy execution unit, for example, sets multiple sales scenarios and compares the results of each scenario. For example, it simulates the impact of price revisions and promotions. The policy execution unit also sets multiple cost scenarios and compares the results of each scenario. For example, it simulates the impact of cost reduction measures. The policy execution unit also sets multiple inventory scenarios and compares the results of each scenario. For example, it simulates the impact of inventory management measures. This makes it possible to set multiple scenarios and compare the results of each scenario.

[0093] The policy execution unit adds a risk assessment to the simulation results, and can avoid high-risk measures in advance. The policy execution unit, for example, adds a risk assessment to the simulation results, and avoids high-risk measures in advance. For example, it determines the priority of measures based on a risk score. The policy execution unit also adds a risk assessment to the simulation results, and prioritizes low-risk measures. For example, it selects measures based on a risk matrix. The policy execution unit also adds a risk assessment to the simulation results, and proposes measures that balance risks. For example, it proposes measures that take into account the balance between risk and return. This makes it possible to add a risk assessment to the simulation results, and avoid high-risk measures in advance.

[0094] The policy execution unit can use the emotion estimation function to reflect the emotional reactions of employees and customers when a policy is implemented in a simulation. The policy execution unit, for example, uses the emotion estimation function to reflect the emotional reactions of employees when a policy is implemented in a simulation. For example, it simulates the impact of employee motivation on a policy. The policy execution unit also uses the emotion estimation function to reflect the emotional reactions of customers when a policy is implemented in a simulation. For example, it simulates the impact of customer satisfaction on a policy. The policy execution unit also uses the emotion estimation function to reflect the emotional reactions of employees and customers when a policy is implemented in a simulation. For example, it simulates the impact of both employee motivation and customer satisfaction on a policy. In this way, the emotion estimation function can be used to reflect the emotional reactions of employees and customers when a policy is implemented in a simulation.

[0095] The policy execution unit can visualize the simulation results on different devices to enable intuitive understanding. For example, the policy execution unit visualizes the simulation results on a VR headset to enable the user to intuitively understand. For example, sales forecasts and cost analyses are displayed in 3D graphs. The policy execution unit can also visualize the simulation results on AR glasses to enable the user to intuitively understand. For example, inventory management simulation results are displayed in AR. The policy execution unit can also visualize the simulation results on other devices to enable the user to intuitively understand. For example, the simulation results are displayed on a tablet or smartphone. This allows the simulation results to be visualized on different devices to enable intuitive understanding.

[0096] The policy execution department can apply the simulation results to different industries and applications to discover new business opportunities. For example, the policy execution department applies the simulation results to different industries to discover new business opportunities. For example, the simulation results for the manufacturing industry are applied to the service industry. The policy execution department can also apply the simulation results to different applications to discover new business opportunities. For example, the simulation results for the logistics industry are applied to the retail industry. The policy execution department can also apply the simulation results to different industries and applications to propose new business models. For example, a new service can be proposed based on the simulation results for the IT industry. In this way, the simulation results can be applied to different industries and applications to discover new business opportunities.

[0097] The policy execution unit can use the emotion estimation function to monitor the user's emotional response to the simulation results in real time and select the optimal policy. The policy execution unit, for example, uses the emotion estimation function to monitor the user's emotional response to the simulation results in real time and select the optimal policy. For example, it analyzes the user's facial expressions and voice and selects the optimal policy based on an emotion score. The policy execution unit also uses the emotion estimation function to monitor the user's emotional response to the simulation results in real time and optimizes the timing of the policy. For example, it selects the optimal timing of the policy based on the user's emotion score. The policy execution unit also uses the emotion estimation function to monitor the user's emotional response to the simulation results in real time and optimizes the form of the policy. For example, it selects the optimal form of the policy based on the user's emotion score. In this way, the emotion estimation function can be used to monitor the user's emotional response to the simulation results in real time and select the optimal policy.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The management support system can further include a purchase history analysis unit that analyzes customer purchase histories. The purchase history analysis unit, for example, analyzes customers' past purchase data to understand repeat purchase trends. For example, it analyzes which customer segments are popular with specific products and conducts targeted marketing. The purchase history analysis unit also analyzes customers' purchase frequency and purchase amounts to measure the effectiveness of loyalty programs. For example, it analyzes the usage of point systems and discount coupons to consider measures to improve customer loyalty. The purchase history analysis unit also analyzes customers' purchasing patterns to identify opportunities for cross-selling and up-selling. For example, sales can be increased by suggesting related products to customers who have purchased a specific product. This makes it possible to develop detailed marketing strategies based on customers' purchase histories.

[0100] The data analysis unit may further include a health data analysis unit that analyzes employee health data. The health data analysis unit, for example, analyzes data obtained from employees' fitness trackers or health apps to understand their health status. For example, it analyzes employees' step counts and heart rates to predict health risks. The health data analysis unit also proposes health promotion programs based on employees' health data. For example, it proposes fitness challenges to employees who are not getting enough exercise. The health data analysis unit also considers measures to improve the working environment based on employees' health data. For example, it proposes relaxation programs to employees with high stress levels. This allows management decisions to be made based on employees' health status.

[0101] The notification unit can further include an emergency notification function. The emergency notification function issues an alert, for example, if sales suddenly decrease. For example, if sales fall significantly below forecast values, a push notification is sent to a smartphone. The emergency notification function also issues an alert if inventory suddenly decreases. For example, if inventory falls below a certain threshold, a notification is sent to a tablet. The emergency notification function also issues an alert if costs suddenly increase. For example, if costs significantly exceed the budget, a notification is sent by email. This allows for a rapid response to emergencies.

[0102] The forecast calculation unit can further incorporate social media trend data to reflect real-time market trends. The forecast calculation unit, for example, incorporates social media trend data and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the popularity of a specific hashtag. The forecast calculation unit also incorporates social media engagement data and reflects it in the calculation of forecast figures. For example, a sales forecast is made based on the number of likes and shares of a post. The forecast calculation unit also incorporates social media comment data and reflects it in the calculation of forecast figures. For example, the content of the comments is analyzed to make a sales forecast. In this way, social media trend data can be incorporated to reflect real-time market trends.

[0103] The policy proposal department can further incorporate best practices from other industries and propose new approaches. For example, the policy proposal department will propose policy proposals that incorporate best practices from other industries. For example, applying efficient inventory management techniques from the manufacturing industry to the food and beverage industry. The policy proposal department will also propose policy proposals based on successful cases from other industries. For example, applying cost reduction techniques from the IT industry to the retail industry. The policy proposal department will also propose policy proposals based on failure cases from other industries. For example, proposing low-risk measures based on failure cases from the service industry. This makes it possible to incorporate best practices from other industries and propose new approaches.

[0104] The data analysis unit uses the emotion estimation function to analyze employee and customer emotion data, allowing for emotional factors to be incorporated into management decisions. The data analysis unit, for example, analyzes employee emotion data and reflects it in management decisions. For example, it understands employee stress levels and motivation and considers measures to improve the working environment. The data analysis unit also analyzes customer emotion data and reflects it in marketing strategies. For example, it understands customer satisfaction and dissatisfaction and considers promotional measures. The data analysis unit also combines and analyzes employee and customer emotion data to make comprehensive management decisions. For example, it analyzes the relationship between employee motivation and customer satisfaction and proposes improvement measures. This makes it possible to incorporate emotional factors into management decisions based on employee and customer emotion data.

[0105] The notification unit can use the emotion estimation function to analyze the user's emotional response to the notification content and optimize the notification method. The notification unit, for example, analyzes the user's emotional response to the notification content and optimizes the notification method. For example, the notification unit selects a notification method that elicits positive emotions based on the user's emotion score. The notification unit also analyzes the user's emotional response to the notification content and optimizes the notification timing. For example, the notification unit selects the optimal notification timing based on the user's emotion score. The notification unit also analyzes the user's emotional response to the notification content and optimizes the notification format. For example, the notification unit selects the optimal notification format based on the user's emotion score. In this way, the user's emotional response to the notification content can be analyzed and the notification method can be optimized.

[0106] The forecast calculation unit can use the emotion estimation function to predict sales based on customer emotion data. The forecast calculation unit, for example, uses the emotion estimation function to predict sales based on customer emotion data. For example, it predicts sales during periods when customers have strong positive emotions. The forecast calculation unit also uses the emotion estimation function to predict the effectiveness of a promotion based on customer emotion data. For example, it predicts the effectiveness of a promotion based on a customer emotion score. The forecast calculation unit also uses the emotion estimation function to predict sales of a new product based on customer emotion data. For example, it predicts sales of a new product based on a customer emotion score. In this way, it is possible to use the emotion estimation function to predict sales based on customer emotion data.

[0107] The policy presentation unit can use the emotion estimation function to present policy proposals based on employee and customer emotion data. The policy presentation unit, for example, uses the emotion estimation function to present policy proposals based on employee emotion data. For example, it proposes policies to increase employee motivation. The policy presentation unit also uses the emotion estimation function to present policy proposals based on customer emotion data. For example, it proposes policies to improve customer satisfaction. The policy presentation unit also uses the emotion estimation function to present policy proposals that combine employee and customer emotion data. For example, it proposes policies to improve both employee motivation and customer satisfaction. In this way, it is possible to present policy proposals based on employee and customer emotion data using the emotion estimation function.

[0108] The policy execution unit can use the emotion estimation function to monitor the user's emotional response to the simulation results in real time and select the optimal policy. The policy execution unit, for example, uses the emotion estimation function to monitor the user's emotional response to the simulation results in real time and select the optimal policy. For example, it analyzes the user's facial expressions and voice and selects the optimal policy based on an emotion score. The policy execution unit also uses the emotion estimation function to monitor the user's emotional response to the simulation results in real time and optimizes the timing of the policy. For example, it selects the optimal timing of the policy based on the user's emotion score. The policy execution unit also uses the emotion estimation function to monitor the user's emotional response to the simulation results in real time and optimizes the form of the policy. For example, it selects the optimal form of the policy based on the user's emotion score. In this way, the emotion estimation function can be used to monitor the user's emotional response to the simulation results in real time and select the optimal policy.

[0109] The processing flow of the second embodiment will be briefly explained below.

[0110] Step 1: The Data Analysis Department analyzes the company's KPIs, financial entries, and other information. For example, sales data, cost data, inventory data, etc. are used as input, and the Generation AI analyzes this data to automate the various estimates, investment management, and calculation of expected results performed by the Corporate Planning Department. The Generation AI uses text generation AI (e.g., LLM) and multimodal generation AI to analyze the data and provide the information necessary for management decisions. Step 2: The notification unit notifies the user of the automated calculation results via a smartphone or tablet. For example, by notifying the user of the target figures for daily sales activities, the small business owner can track their goals. The notification unit notifies the user of information such as the target figures and management indicators output by the generation AI. Step 3: The forecast calculation unit calculates forecast figures based on weather information and recent performance data, and displays the difference between the actual results and the forecast. For example, it calculates sales forecasts based on weather information and forecast figures based on recent performance data, and displays the difference from the actual results. The forecast calculation unit displays the forecast figures and difference information output by the generation AI. Step 4: The measure presentation unit presents measures to close the gap between actual results and forecasts. For example, it presents promotional measures to increase sales or measures to reduce costs. The measure presentation unit presents information about the measures output by the generation AI.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0113] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 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.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0121] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0129] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0130] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0132] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

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

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0136] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0139] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0144] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0145] 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.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0147] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0148] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0150] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0151] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0152] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0155] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0157] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0159] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0160] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0161] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0162] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0163] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0164] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0165] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0167] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0168] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0169] 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.

[0170] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0171] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0172] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0173] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0174] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0175] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0176] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0177] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A data analysis department that analyzes company KPIs, financial entries, and other information; A notification section that notifies the automated calculation results via smartphone or tablet device, a forecast calculation unit that calculates forecast figures based on weather information and recent performance data, and presents the difference between the performance data and forecast figures; A measure presentation unit that presents a measure proposal to close the gap between the actual results and the forecast. A system characterized by:

2. The data analysis unit Analyze sales data, cost data, and inventory data to automate the various calculations, investment management, and calculation of expected results performed by the Corporate Planning Department. The system of claim 1 .

3. The notification unit Notify daily sales activity targets The system of claim 1 .

4. The prospect calculation unit A sales forecast is made based on the weather information, and the difference from the actual results is presented. The system of claim 1 .

5. The policy presentation unit Present promotional ideas to increase sales and cost reduction measures. The system of claim 1 .

6. The data analysis unit Use emotion estimation to analyze employee and customer emotion data and incorporate emotional factors into business decisions. The system of claim 1 .

7. The notification unit Using emotion estimation functionality, we analyze the user's emotional response to the notification content and optimize the notification method. The system of claim 1 .

8. The prospect calculation unit Use emotion estimation to predict sales based on customer emotion data The system of claim 1 .

Images