System

Abstract

An object of the system according to the embodiment is to analyze the ranking of companies and the correlation of disclosed information and create a new benchmark.SOLUTION: A system according to an embodiment includes a data collection unit, a correlation analysis unit, a benchmark creation unit, a report generation unit, a chatbot providing unit, and a report selling unit. The processing circuitry is configured to collect AI using the generated dataset. The correlation analysis unit analyzes the correlation of the data collected by the data collection unit. The benchmark creation unit creates a new benchmark based on the data analyzed by the correlation analysis unit. The report generation unit automatically generates a report by comparing the benchmark created by the benchmark creation unit with the company's own data. The chatbot providing unit provides information on the report generated by the report generation unit to the chatbot. The report sales unit sells the report generated by the report generation unit to another company.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 technology has faced the challenge of making it difficult to efficiently analyze the correlation between corporate rankings and disclosed information and create new benchmarks.

[0005] The system according to the embodiment aims to analyze the correlation between corporate rankings and disclosed information and to create new benchmarks. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, a correlation analysis unit, a benchmark creation unit, a report generation unit, a chatbot provision unit, and a report sales unit. The data collection unit collects data using a generation AI. The correlation analysis unit analyzes the correlation of the data collected by the data collection unit. The benchmark creation unit creates a new benchmark based on the data analyzed by the correlation analysis unit. The report creation unit automatically generates a report by comparing the benchmark created by the benchmark creation unit with the company's own data. The chatbot provision unit provides information on the report created by the report creation unit via a chatbot. The report sales unit sells the reports created by the report creation unit to other companies. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the correlation between company rankings and disclosed information and create new benchmarks. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A benchmark creation system according to an embodiment of the present invention analyzes correlations between rankings published by companies and information disclosed on their corporate websites, and creates new benchmarks that take various factors into account. This system uses a generation AI to collect and analyze data, compares it with the company's own data, and automatically generates a report for improvement. The system also uses the generation AI to provide information based on the analysis results via a chatbot at any time, and sells reports and provides know-how to other companies. This allows the benchmark creation system to efficiently analyze corporate data and identify improvement measures. Furthermore, providing reports and know-how to other companies can create new business opportunities.

[0029] A benchmark creation system according to an embodiment includes a data collection unit, a correlation analysis unit, a benchmark creation unit, a report generation unit, a chatbot provision unit, and a report sales unit. The data collection unit collects data using a generation AI. For example, the generation AI collects data such as a company's sales, number of employees, and research and development expenses. The generation AI can also collect data on a company's social media activities and customer reviews. The generation AI can also collect data from different industries and data that takes geographical factors into account. The correlation analysis unit analyzes the correlation between the data collected by the data collection unit. For example, the generation AI analyzes the correlation between the collected data using the Pearson correlation coefficient or the Spearman rank correlation coefficient. The generation AI can also apply an anomaly detection algorithm to evaluate the reliability of the data. The benchmark creation unit creates a new benchmark based on the data analyzed by the correlation analysis unit. For example, the generation AI sets indicators for evaluating a company's growth potential, efficiency, competitiveness, etc., and evaluates the company based on these indicators. The generation AI can also create a benchmark that takes into account a company's sustainability indicators and innovation activities. The report generation unit automatically generates reports by comparing the benchmarks created by the benchmark creation unit with the company's data. For example, the generation AI compares data such as a company's sales, number of employees, and research and development expenses with the new benchmarks to identify areas for improvement and strengthening. The generation AI can also generate reports that include specific action plans and timelines. The chatbot provision unit provides information from the reports generated by the report generation unit via a chatbot. For example, the generation AI generates answers to user questions and provides them through the chatbot. The generation AI can also provide information including the latest industry news and trend information. The report sales unit sells the reports generated by the report generation unit to other companies. For example, the generation AI generates reports that include customized improvement measures and proposals based on other companies' data. The generation AI can also generate reports that include other companies' success stories and best practices.As a result, the benchmark creation system according to the embodiment can perform an integrated process from data collection to report generation, provision, and sales. For example, companies can strengthen their competitiveness and improve their standing within the industry. Furthermore, they can build new business models based on data provided by other companies.

[0030] The data collection unit can collect a company's social media activity or customer reviews and analyze the correlation with business performance data. For example, the data collection unit uses generation AI to collect a company's social media activity (e.g., Twitter or Facebook posts) and analyze the correlation between this data and the company's sales or number of employees. Specifically, it compares social media engagement rates with the company's business performance data. The data collection unit also uses generation AI to collect reviews on customer review sites (e.g., Amazon or Yelp) and analyze the correlation between this data and the company's business performance data. Specifically, it compares customer satisfaction scores with the company's sales or profit margins. The data collection unit also uses generation AI to collect a company's social media activity and customer reviews and analyze the correlation between this data and the company's stock price data. Specifically, it compares the number of positive social media posts with stock price fluctuations. This makes it possible to collect data including social media activity and customer reviews and analyze the correlation with business performance data.

[0031] The data collection unit can apply an anomaly detection algorithm to the data to evaluate its reliability. For example, the data collection unit applies an anomaly detection algorithm to data such as a company's sales revenue and number of employees collected by the generation AI to evaluate the reliability of the data. Specifically, it detects abnormal values ​​and outliers and checks the quality of the data. The data collection unit also applies an anomaly detection algorithm to data on social media activities and customer reviews collected by the generation AI to evaluate the reliability of the data. Specifically, it detects spam posts and fake reviews and ensures the accuracy of the data. The data collection unit also applies an anomaly detection algorithm to a company's financial data collected by the generation AI to evaluate the reliability of the data. Specifically, it detects abnormal financial ratios and unnatural data patterns and checks the reliability of the data. This allows the anomaly detection algorithm to be applied to evaluate the reliability of the data.

[0032] The data collection unit can collect data from different industries and analyze cross-industry correlations. For example, the data collection unit uses generation AI to collect data from different industries (e.g., manufacturing and service industries) and analyze cross-industry correlations. Specifically, it compares productivity data from the manufacturing industry with customer satisfaction data from the service industry. The data collection unit also uses generation AI to collect data from different industries (e.g., IT and healthcare) and analyze cross-industry correlations. Specifically, it compares technological innovation data from the IT industry with patient satisfaction data from the healthcare industry. The data collection unit also uses generation AI to collect data from different industries (e.g., finance and retail industries) and analyze cross-industry correlations. Specifically, it compares risk management data from the finance industry with sales data from the retail industry. This makes it possible to collect data from different industries and analyze cross-industry correlations.

[0033] The data collection unit can analyze the data by region based on geographical factors. For example, the data collection unit analyzes data such as company sales and number of employees collected by the generation AI by region, taking geographical factors into account. Specifically, it analyzes the distribution of sales and number of employees by region. The data collection unit also analyzes social media activity and customer review data collected by the generation AI by region, taking geographical factors into account. Specifically, it analyzes customer satisfaction and engagement rates by region. The data collection unit also analyzes company financial data collected by the generation AI by region, taking geographical factors into account. Specifically, it analyzes the distribution of financial ratios and profit margins by region. This makes it possible to analyze the data by region, taking geographical factors into account.

[0034] The benchmark creation unit can add a company's sustainability indicators to a new benchmark and evaluate its environmental impact. The benchmark creation unit, for example, uses generation AI to collect a company's sustainability indicators (e.g., CO2 emissions and energy consumption) and add them to a new benchmark. Specifically, it sets indicators for evaluating a company's environmental impact. The benchmark creation unit also uses generation AI to collect a company's sustainability indicators and create a benchmark for evaluating its environmental impact. Specifically, it calculates a score for evaluating the company's environmental performance. The benchmark creation unit also uses generation AI to collect a company's sustainability indicators and create a new benchmark for evaluating its environmental impact. Specifically, it sets indicators for evaluating a company's contribution to the environment. This allows the company's sustainability indicators to be added to the benchmark and its environmental impact to be evaluated.

[0035] The benchmark creation unit can create a benchmark by taking into account the innovation activities of the company. For example, the benchmark creation unit takes into account the number of patent applications filed by the company to evaluate the innovation activities. Specifically, it sets an index to evaluate the company's level of technological innovation based on the number of patent applications. The benchmark creation unit also takes into account the number of research and development projects the company has undertaken to evaluate the innovation activities of the company to the benchmark created by the generation AI. Specifically, it sets an index to evaluate the company's level of innovation based on the number of research and development projects. The benchmark creation unit also takes into account the company's innovation activities (for example, the number of new product developments and the number of technical alliances) to evaluate the company's competitiveness. Specifically, it sets an index to evaluate the company's competitiveness based on its innovation activities. This makes it possible to take into account the company's innovation activities in the benchmark and evaluate them.

[0036] The benchmark creation unit can subdivide the benchmark by industry and set indicators specific to each industry. For example, the benchmark creation unit uses generation AI to subdivide the benchmark by industry, such as manufacturing, service, or IT, and set indicators specific to each industry. Specifically, it sets productivity indicators for the manufacturing industry and customer satisfaction indicators for the service industry. The benchmark creation unit also uses generation AI to subdivide the benchmark by industry and set indicators specific to each industry. Specifically, it sets technological innovation indicators for the IT industry and patient satisfaction indicators for the medical industry. The benchmark creation unit also uses generation AI to subdivide the benchmark by industry and set indicators specific to each industry. Specifically, it sets risk management indicators for the financial industry and sales indicators for the retail industry. This makes it possible to subdivide the benchmark by industry and set indicators specific to each industry.

[0037] The benchmark creation unit can compare the benchmark created by the generation AI with the company's historical data to evaluate long-term performance. For example, the benchmark creation unit compares the benchmark created by the generation AI with the company's sales data for the past 10 years to evaluate long-term performance. Specifically, the evaluation is based on the growth rate and fluctuations in sales. The benchmark creation unit also compares the benchmark created by the generation AI with the company's employee number data for the past five years to evaluate long-term performance. Specifically, the evaluation is based on the increase / decrease and stability of the number of employees. The benchmark creation unit also compares the benchmark created by the generation AI with the company's research and development expense data for the past 20 years to evaluate long-term performance. Specifically, the evaluation is based on the amount of research and development expense investment and results. This makes it possible to compare the benchmark created by the generation AI with the company's historical data to evaluate long-term performance.

[0038] The report generation unit can use the generation AI to compare the company's data with that of competitors in detail and evaluate its competitive advantage. For example, the report generation unit uses the generation AI to compare data such as the company's sales revenue and number of employees in detail with that of competitors and evaluate its competitive advantage. Specifically, the evaluation is made based on the sales growth rate and the increase or decrease in the number of employees. The report generation unit also uses the generation AI to compare data such as the company's research and development expenses and number of patent applications in detail with that of competitors and evaluate its competitive advantage. Specifically, the evaluation is made based on the amount of research and development investment and the number of patent applications. The report generation unit also uses the generation AI to compare data such as the company's customer satisfaction and retention rate in detail with that of competitors and evaluate its competitive advantage. Specifically, the evaluation is made based on the customer satisfaction score and retention rate. This makes it possible to compare the company's data with that of competitors in detail and evaluate its competitive advantage.

[0039] The report generation unit can include specific action plans and timelines in reports generated by the generation AI. For example, the report generation unit includes specific action plans in reports generated by the generation AI. For example, it proposes specific measures and steps for improving sales. The report generation unit also includes timelines in reports generated by the generation AI. For example, it presents schedules and milestones for implementing improvement measures. The report generation unit also includes specific action plans and timelines in reports generated by the generation AI. For example, it proposes investment plans for research and development expenses and schedules for patent applications. This makes it possible to generate reports that include specific action plans and timelines.

[0040] The report generation unit can use the generation AI to compare its own data with data from different regions and propose a strategy for each region. For example, the report generation unit uses the generation AI to compare data such as the company's sales revenue and number of employees with data from different regions and propose a strategy for each region. Specifically, it proposes a strategy based on the distribution of sales revenue and number of employees by region. The report generation unit also uses the generation AI to compare data such as the company's research and development expenses and number of patent applications with data from different regions and propose a strategy for each region. Specifically, it proposes a strategy based on the amount of research and development expenses invested and the number of patent applications by region. The report generation unit also uses the generation AI to compare data such as the company's customer satisfaction and retention rate with data from different regions and propose a strategy for each region. Specifically, it proposes a strategy based on the customer satisfaction score and retention rate for each region. This makes it possible to compare the company's data with data from different regions and propose a strategy for each region.

[0041] The report generation unit makes extensive use of visual data in the reports generated by the generation AI, making them easier to understand visually. For example, the report generation unit displays data such as sales revenue and number of employees in graphs and charts in the reports generated by the generation AI, making them easier to understand visually. Specifically, the data is visualized using line graphs and bar graphs. The report generation unit also displays data such as research and development expenses and number of patent applications in graphs and charts in the reports generated by the generation AI, making them easier to understand visually. Specifically, the data is visualized using pie charts and histograms. The report generation unit also displays data such as customer satisfaction and retention rates in graphs and charts in the reports generated by the generation AI, making them easier to understand visually. Specifically, the data is visualized using scatter plots and radar charts. This makes it possible to generate reports that make extensive use of visual data and are easier to understand visually.

[0042] The chatbot providing unit can use the generation AI to include industry news and trend information in the information provided by the chatbot. For example, the chatbot providing unit uses the generation AI to include the latest industry news in the information provided by the chatbot. Specifically, the latest industry trends and important news are provided in real time. The chatbot providing unit also uses the generation AI to include the latest trend information in the information provided by the chatbot. Specifically, information reflecting industry trends and market changes is provided. The chatbot providing unit also uses the generation AI to include the latest industry news and trend information in the information provided by the chatbot. Specifically, information reflecting the competitive environment of companies and market trends is provided. This allows the latest industry news and trend information to be included in the information provided by the chatbot.

[0043] The chatbot providing unit can include specific examples and case studies in the answers generated by the generation AI. For example, the chatbot providing unit includes specific examples in the answers generated by the generation AI. For example, it provides specific advice based on success stories and failure stories of other companies. The chatbot providing unit also includes case studies in the answers generated by the generation AI. For example, it presents specific countermeasures and solutions for specific situations. The chatbot providing unit also includes specific examples and case studies in the answers generated by the generation AI. For example, it makes specific suggestions based on past data and track record. This makes it possible to generate answers that include specific examples and case studies.

[0044] The chatbot providing unit uses generation AI to enable the chatbot to respond in different languages, thereby supporting international users. For example, the chatbot providing unit uses generation AI to enable the chatbot to respond in multiple languages, such as English, French, and Chinese. Specifically, the chatbot automatically switches languages ​​according to the user's language setting. The chatbot providing unit also uses generation AI to enable the chatbot to respond in different languages, thereby supporting international users. Specifically, a language translation function is incorporated to perform translation in real time. The chatbot providing unit also uses generation AI to enable the chatbot to respond in different languages, thereby supporting international users. Specifically, the chatbot automatically detects the user's input language and generates a response in the appropriate language. This enables the chatbot to respond in different languages, thereby supporting international users.

[0045] The chatbot providing unit can include audio and video content in the answers generated by the generation AI, thereby realizing multimedia support. For example, the chatbot providing unit includes audio content in the answers generated by the generation AI. Specifically, answers to user questions are provided in audio format, making them accessible to visually impaired people. The chatbot providing unit also includes video content in the answers generated by the generation AI. Specifically, answers to user questions are provided in video format, making them easier to understand visually. The chatbot providing unit also includes audio and video content in the answers generated by the generation AI. Specifically, answers to user questions are provided in multimedia format, improving the user experience. This makes it possible to realize multimedia support, including audio and video content.

[0046] The report sales department can use the generation AI to include customized improvement measures and proposals in reports for other companies. For example, the report sales department uses the generation AI to include customized improvement measures in reports for other companies. Specifically, it provides specific improvement proposals based on the other company's data. The report sales department also uses the generation AI to include customized proposals in reports for other companies. Specifically, it provides proposals that take into account the industry characteristics and market conditions of the other company. The report sales department also uses the generation AI to include customized improvement measures and proposals in reports for other companies. Specifically, it provides specific action plans based on the other company's data. This makes it possible to include customized improvement measures and proposals in reports for other companies.

[0047] The report sales department can include success stories and best practices in the reports generated by the generation AI. For example, the report sales department can include success stories from other companies in the reports generated by the generation AI. Specifically, they can introduce the specific measures implemented by other companies and their results. The report sales department can also include best practices in the reports generated by the generation AI. Specifically, they can introduce the best methods and success stories within the industry. The report sales department can also include success stories and best practices from other companies in the reports generated by the generation AI. Specifically, they can introduce the details of the measures implemented by other companies and their effects. This makes it possible to generate reports that include success stories and best practices from other companies.

[0048] The report sales department can use generation AI to subdivide reports for other companies by industry and propose improvement measures specific to each industry. For example, the report sales department can use generation AI to subdivide reports for other companies by industry, such as manufacturing, services, or IT, and propose improvement measures specific to each industry. Specifically, it proposes productivity improvement measures for the manufacturing industry and customer satisfaction improvement measures for the service industry. The report sales department can also use generation AI to subdivide reports for other companies by industry and propose improvement measures specific to each industry. Specifically, it proposes technological innovation measures for the IT industry and measures to improve patient satisfaction in the medical industry. The report sales department can also use generation AI to subdivide reports for other companies by industry and propose improvement measures specific to each industry. Specifically, it proposes risk management measures for the financial industry and sales improvement measures for the retail industry. This makes it possible to subdivide reports for other companies by industry and propose improvement measures specific to each industry.

[0049] The report sales department can include data from different regions in the reports generated by the generation AI and propose strategies for each region. For example, the report sales department includes data from different regions in the reports generated by the generation AI. Specifically, it proposes strategies for each region based on data on sales revenue and number of employees by region. The report sales department also includes data from different regions in the reports generated by the generation AI. Specifically, it proposes strategies for each region based on data on R&D expenses and number of patent applications by region. The report sales department also includes data from different regions in the reports generated by the generation AI. Specifically, it proposes strategies for each region based on data on customer satisfaction and retention rates by region. This makes it possible to generate reports that include data from different regions and propose strategies for each region.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The data collection department can collect employee skill data and perform skill matching. For example, generative AI can be used to collect employee skill sets and qualifications and match the best talent to projects and positions within the company. The data collection department can also collect employee skill data and identify skill gaps. Specifically, it analyzes the difference between required skills and current skills and proposes training programs. The data collection department can also collect employee skill data and analyze skill trends. This allows companies to optimally utilize employee skills and efficiently allocate personnel.

[0052] The data collection department can collect a company's supply chain data and assess supply risks. For example, generative AI can be used to collect data on supplier delivery delays and quality issues to assess supply risks. The data collection department can also assess geographic risks in the supply chain. Specifically, it collects data that takes natural disasters and political risks into account and performs risk assessments. The data collection department can also collect supply chain cost data and make suggestions for cost reduction. This allows companies to manage supply chain risks and achieve efficient operations.

[0053] The data collection unit can collect health data of a company's employees and propose health management programs. For example, generative AI can be used to collect employees' health checkup results and fitness data and evaluate their health risks. The data collection unit can also collect employees' health data and evaluate their stress levels. Specifically, it analyzes heart rate and sleep data to evaluate stress levels. The data collection unit can also collect employees' health data and propose health management programs. This allows companies to manage their employees' health and improve labor productivity.

[0054] The data collection unit can collect a company's energy consumption data and evaluate its energy efficiency. For example, generative AI can be used to collect data on a company's electricity and gas consumption and evaluate its energy efficiency. The data collection unit can also collect energy consumption data and make suggestions for reducing energy costs. Specifically, it can identify peak energy consumption times and propose cost-cutting measures. The data collection unit can also collect energy consumption data and evaluate its impact on the environment. This allows companies to improve their energy efficiency and achieve both cost reduction and environmental protection.

[0055] The data collection department can collect a company's product quality data and make suggestions for quality control. For example, it can use generative AI to collect data on product defect rates and customer complaints and identify areas for improvement in quality control. The data collection department can also collect product quality data and analyze quality trends. Specifically, it analyzes product quality data over time and evaluates quality fluctuations. The data collection department can also collect product quality data and suggest training programs for quality control. This allows companies to improve product quality and increase customer satisfaction.

[0056] The data collection unit can collect a company's financial data and evaluate its financial soundness. For example, it can use generative AI to collect data on a company's profitability and debt ratio to evaluate its financial soundness. The data collection unit can also collect financial data and perform cash flow analysis. Specifically, it analyzes cash flow patterns and evaluates financing risks. The data collection unit can also collect financial data and evaluate the effectiveness of investments. This allows a company to understand its financial soundness and formulate an appropriate financial strategy.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The data collection unit uses the generation AI to collect data. For example, the generation AI collects data such as a company's sales, number of employees, and R&D expenses. The generation AI can also collect the company's social media activity and customer reviews. Furthermore, the generation AI collects data from different industries and takes geographical factors into account. Step 2: The correlation analysis unit analyzes the correlation between the data collected by the data collection unit. For example, the generation AI analyzes the correlation between the collected data using the Pearson correlation coefficient or Spearman's rank correlation coefficient. The generation AI can also apply an anomaly detection algorithm to evaluate the reliability of the data. Step 3: The benchmark creation unit creates new benchmarks based on the data analyzed by the correlation analysis unit. For example, the generation AI sets indicators to evaluate a company's growth potential, efficiency, competitiveness, etc., and evaluates the company based on those indicators. The generation AI can also create benchmarks that take into account a company's sustainability indicators and innovation activities. Step 4: The report generation unit compares the company's data with the benchmark created by the benchmark creation unit and automatically generates a report. For example, the generation AI can compare data such as the company's sales, number of employees, and research and development expenses with the new benchmark to identify areas for improvement and strengthening. The generation AI can also generate reports that include specific action plans and timelines. Step 5: The chatbot provision unit provides the information in the report generated by the report generation unit via the chatbot. For example, the generation AI generates answers to user questions and provides them through the chatbot. The generation AI can also provide information including the latest industry news and trend information. Step 6: The report sales department sells the reports generated by the report generation department to other companies. For example, the generation AI generates reports that include customized improvement measures and proposals based on other companies' data. The generation AI can also generate reports that include other companies' success stories and best practices.

[0059] (Example 2) A benchmark creation system according to an embodiment of the present invention analyzes correlations between rankings published by companies and information disclosed on their corporate websites, and creates new benchmarks that take various factors into account. This system uses a generation AI to collect and analyze data, compares it with the company's own data, and automatically generates a report for improvement. The system also uses the generation AI to provide information based on the analysis results via a chatbot at any time, and sells reports and provides know-how to other companies. This allows the benchmark creation system to efficiently analyze corporate data and identify improvement measures. Furthermore, providing reports and know-how to other companies can create new business opportunities.

[0060] A benchmark creation system according to an embodiment includes a data collection unit, a correlation analysis unit, a benchmark creation unit, a report generation unit, a chatbot provision unit, and a report sales unit. The data collection unit collects data using a generation AI. For example, the generation AI collects data such as a company's sales, number of employees, and research and development expenses. The generation AI can also collect data on a company's social media activities and customer reviews. The generation AI can also collect data from different industries and data that takes geographical factors into account. The correlation analysis unit analyzes the correlation between the data collected by the data collection unit. For example, the generation AI analyzes the correlation between the collected data using the Pearson correlation coefficient or the Spearman rank correlation coefficient. The generation AI can also apply an anomaly detection algorithm to evaluate the reliability of the data. The benchmark creation unit creates a new benchmark based on the data analyzed by the correlation analysis unit. For example, the generation AI sets indicators for evaluating a company's growth potential, efficiency, competitiveness, etc., and evaluates the company based on these indicators. The generation AI can also create a benchmark that takes into account a company's sustainability indicators and innovation activities. The report generation unit automatically generates reports by comparing the benchmarks created by the benchmark creation unit with the company's data. For example, the generation AI compares data such as a company's sales, number of employees, and research and development expenses with the new benchmarks to identify areas for improvement and strengthening. The generation AI can also generate reports that include specific action plans and timelines. The chatbot provision unit provides information from the reports generated by the report generation unit via a chatbot. For example, the generation AI generates answers to user questions and provides them through the chatbot. The generation AI can also provide information including the latest industry news and trend information. The report sales unit sells the reports generated by the report generation unit to other companies. For example, the generation AI generates reports that include customized improvement measures and proposals based on other companies' data. The generation AI can also generate reports that include other companies' success stories and best practices.As a result, the benchmark creation system according to the embodiment can perform an integrated process from data collection to report generation, provision, and sales. For example, companies can strengthen their competitiveness and improve their standing within the industry. Furthermore, they can build new business models based on data provided by other companies.

[0061] The data collection unit can collect a company's social media activity or customer reviews and analyze the correlation with business performance data. For example, the data collection unit uses generation AI to collect a company's social media activity (e.g., Twitter or Facebook posts) and analyze the correlation between this data and the company's sales or number of employees. Specifically, it compares social media engagement rates with the company's business performance data. The data collection unit also uses generation AI to collect reviews on customer review sites (e.g., Amazon or Yelp) and analyze the correlation between this data and the company's business performance data. Specifically, it compares customer satisfaction scores with the company's sales or profit margins. The data collection unit also uses generation AI to collect a company's social media activity and customer reviews and analyze the correlation between this data and the company's stock price data. Specifically, it compares the number of positive social media posts with stock price fluctuations. This makes it possible to collect data including social media activity and customer reviews and analyze the correlation with business performance data.

[0062] The data collection unit can apply an anomaly detection algorithm to the data to evaluate its reliability. For example, the data collection unit applies an anomaly detection algorithm to data such as a company's sales revenue and number of employees collected by the generation AI to evaluate the reliability of the data. Specifically, it detects abnormal values ​​and outliers and checks the quality of the data. The data collection unit also applies an anomaly detection algorithm to data on social media activities and customer reviews collected by the generation AI to evaluate the reliability of the data. Specifically, it detects spam posts and fake reviews and ensures the accuracy of the data. The data collection unit also applies an anomaly detection algorithm to a company's financial data collected by the generation AI to evaluate the reliability of the data. Specifically, it detects abnormal financial ratios and unnatural data patterns and checks the reliability of the data. This allows the anomaly detection algorithm to be applied to evaluate the reliability of the data.

[0063] The data collection unit can use the emotion estimation function to collect emotion data of company employees and analyze the correlation between employee satisfaction and company performance. For example, the data collection unit uses the emotion estimation function to collect emotion data of company employees and analyze the correlation between employee satisfaction and the company's sales and profit margin. Specifically, it compares the employee's positive emotion score with company performance. The data collection unit also uses the emotion estimation function to collect emotion data of company employees and analyze the correlation between employee satisfaction and the company's employee turnover rate. Specifically, it compares the employee's negative emotion score with the turnover rate. The data collection unit also uses the emotion estimation function to collect emotion data of company employees and analyze the correlation between employee satisfaction and company productivity. Specifically, it compares the employee's emotion score with a productivity index (e.g., sales / number of employees). This makes it possible to collect employee emotion data and analyze the correlation between satisfaction and company performance.

[0064] The data collection unit can collect data from different industries and analyze cross-industry correlations. For example, the data collection unit uses generation AI to collect data from different industries (e.g., manufacturing and service industries) and analyze cross-industry correlations. Specifically, it compares productivity data from the manufacturing industry with customer satisfaction data from the service industry. The data collection unit also uses generation AI to collect data from different industries (e.g., IT and healthcare) and analyze cross-industry correlations. Specifically, it compares technological innovation data from the IT industry with patient satisfaction data from the healthcare industry. The data collection unit also uses generation AI to collect data from different industries (e.g., finance and retail industries) and analyze cross-industry correlations. Specifically, it compares risk management data from the finance industry with sales data from the retail industry. This makes it possible to collect data from different industries and analyze cross-industry correlations.

[0065] The data collection unit can analyze the data by region based on geographical factors. For example, the data collection unit analyzes data such as company sales and number of employees collected by the generation AI by region, taking geographical factors into account. Specifically, it analyzes the distribution of sales and number of employees by region. The data collection unit also analyzes social media activity and customer review data collected by the generation AI by region, taking geographical factors into account. Specifically, it analyzes customer satisfaction and engagement rates by region. The data collection unit also analyzes company financial data collected by the generation AI by region, taking geographical factors into account. Specifically, it analyzes the distribution of financial ratios and profit margins by region. This makes it possible to analyze the data by region, taking geographical factors into account.

[0066] The data collection unit can use the emotion estimation function to collect customer emotion data and analyze the correlation between customer satisfaction and corporate performance. For example, the data collection unit uses the emotion estimation function to collect customer emotion data and analyze the correlation between customer satisfaction and corporate sales and profit margins. Specifically, it compares the customer's positive emotion score with corporate performance. The data collection unit also uses the emotion estimation function to collect customer emotion data and analyze the correlation between customer satisfaction and a corporate customer retention rate. Specifically, it compares the customer's negative emotion score with the retention rate. The data collection unit also uses the emotion estimation function to collect customer emotion data and analyze the correlation between customer satisfaction and a corporate market share. Specifically, it compares the customer's emotion score with the market share. In this way, it is possible to collect customer emotion data and analyze the correlation between satisfaction and corporate performance.

[0067] The benchmark creation unit can add a company's sustainability indicators to a new benchmark and evaluate its environmental impact. The benchmark creation unit, for example, uses generation AI to collect a company's sustainability indicators (e.g., CO2 emissions and energy consumption) and add them to a new benchmark. Specifically, it sets indicators for evaluating a company's environmental impact. The benchmark creation unit also uses generation AI to collect a company's sustainability indicators and create a benchmark for evaluating its environmental impact. Specifically, it calculates a score for evaluating the company's environmental performance. The benchmark creation unit also uses generation AI to collect a company's sustainability indicators and create a new benchmark for evaluating its environmental impact. Specifically, it sets indicators for evaluating a company's contribution to the environment. This allows the company's sustainability indicators to be added to the benchmark and its environmental impact to be evaluated.

[0068] The benchmark creation unit can create a benchmark by taking into account the innovation activities of the company. For example, the benchmark creation unit takes into account the number of patent applications filed by the company to evaluate the innovation activities. Specifically, it sets an index to evaluate the company's level of technological innovation based on the number of patent applications. The benchmark creation unit also takes into account the number of research and development projects the company has undertaken to evaluate the innovation activities of the company to the benchmark created by the generation AI. Specifically, it sets an index to evaluate the company's level of innovation based on the number of research and development projects. The benchmark creation unit also takes into account the company's innovation activities (for example, the number of new product developments and the number of technical alliances) to evaluate the company's competitiveness. Specifically, it sets an index to evaluate the company's competitiveness based on its innovation activities. This makes it possible to take into account the company's innovation activities in the benchmark and evaluate them.

[0069] The benchmark creation unit can use the emotion estimation function to reflect consumer emotions toward a company's brand image in the benchmark. The benchmark creation unit, for example, uses the emotion estimation function to collect consumer emotion data and reflect the emotions toward the company's brand image in the benchmark. Specifically, it sets an index for evaluating the brand image based on the consumer's positive emotion score. The benchmark creation unit also uses the emotion estimation function to collect consumer emotion data and reflect the emotions toward the company's brand image in the benchmark. Specifically, it sets an index for evaluating the brand image based on the consumer's negative emotion score. The benchmark creation unit also uses the emotion estimation function to collect consumer emotion data and reflect the emotions toward the company's brand image in the benchmark. Specifically, it sets a new index for evaluating the brand image based on the consumer's emotion score. This makes it possible to reflect consumer emotions toward the company's brand image in the benchmark.

[0070] The benchmark creation unit can subdivide the benchmark by industry and set indicators specific to each industry. For example, the benchmark creation unit uses generation AI to subdivide the benchmark by industry, such as manufacturing, service, or IT, and set indicators specific to each industry. Specifically, it sets productivity indicators for the manufacturing industry and customer satisfaction indicators for the service industry. The benchmark creation unit also uses generation AI to subdivide the benchmark by industry and set indicators specific to each industry. Specifically, it sets technological innovation indicators for the IT industry and patient satisfaction indicators for the medical industry. The benchmark creation unit also uses generation AI to subdivide the benchmark by industry and set indicators specific to each industry. Specifically, it sets risk management indicators for the financial industry and sales indicators for the retail industry. This makes it possible to subdivide the benchmark by industry and set indicators specific to each industry.

[0071] The benchmark creation unit can compare the benchmark created by the generation AI with the company's historical data to evaluate long-term performance. For example, the benchmark creation unit compares the benchmark created by the generation AI with the company's sales data for the past 10 years to evaluate long-term performance. Specifically, the evaluation is based on the growth rate and fluctuations in sales. The benchmark creation unit also compares the benchmark created by the generation AI with the company's employee number data for the past five years to evaluate long-term performance. Specifically, the evaluation is based on the increase / decrease and stability of the number of employees. The benchmark creation unit also compares the benchmark created by the generation AI with the company's research and development expense data for the past 20 years to evaluate long-term performance. Specifically, the evaluation is based on the amount of research and development expense investment and results. This makes it possible to compare the benchmark created by the generation AI with the company's historical data to evaluate long-term performance.

[0072] The benchmark creation unit uses the emotion estimation function to reflect employee emotion data in a benchmark, thereby enabling evaluation of the company's internal environment. For example, the benchmark creation unit uses the emotion estimation function to collect employee emotion data and reflect it in a benchmark for evaluating the company's internal environment. Specifically, an index for evaluating the internal environment is set based on the employee's positive emotion score. The benchmark creation unit also uses the emotion estimation function to collect employee emotion data and reflect it in a benchmark for evaluating the company's internal environment. Specifically, an index for evaluating the internal environment is set based on the employee's negative emotion score. The benchmark creation unit also uses the emotion estimation function to collect employee emotion data and create a new benchmark for evaluating the company's internal environment. Specifically, an index for evaluating the internal environment is set based on the employee's emotion score. In this way, the employee emotion data can be reflected in the benchmark, enabling evaluation of the company's internal environment.

[0073] The report generation unit can use the generation AI to compare the company's data with that of competitors in detail and evaluate its competitive advantage. For example, the report generation unit uses the generation AI to compare data such as the company's sales revenue and number of employees in detail with that of competitors and evaluate its competitive advantage. Specifically, the evaluation is made based on the sales growth rate and the increase or decrease in the number of employees. The report generation unit also uses the generation AI to compare data such as the company's research and development expenses and number of patent applications in detail with that of competitors and evaluate its competitive advantage. Specifically, the evaluation is made based on the amount of research and development investment and the number of patent applications. The report generation unit also uses the generation AI to compare data such as the company's customer satisfaction and retention rate in detail with that of competitors and evaluate its competitive advantage. Specifically, the evaluation is made based on the customer satisfaction score and retention rate. This makes it possible to compare the company's data with that of competitors in detail and evaluate its competitive advantage.

[0074] The report generation unit can include specific action plans and timelines in reports generated by the generation AI. For example, the report generation unit includes specific action plans in reports generated by the generation AI. For example, it proposes specific measures and steps for improving sales. The report generation unit also includes timelines in reports generated by the generation AI. For example, it presents schedules and milestones for implementing improvement measures. The report generation unit also includes specific action plans and timelines in reports generated by the generation AI. For example, it proposes investment plans for research and development expenses and schedules for patent applications. This makes it possible to generate reports that include specific action plans and timelines.

[0075] The report generation unit uses the emotion estimation function to reflect the emotion data of its employees in the report and make suggestions to improve employee satisfaction. The report generation unit, for example, uses the emotion estimation function to collect emotion data of its employees and reflect it in the report. Specifically, it makes suggestions to improve employee satisfaction based on the employees' positive emotion scores. The report generation unit also uses the emotion estimation function to collect emotion data of its employees and reflect it in the report. Specifically, it makes suggestions to improve employee satisfaction based on the employees' negative emotion scores. The report generation unit also uses the emotion estimation function to collect emotion data of its employees and reflect it in the report. Specifically, it makes new suggestions to improve employee satisfaction based on the employees' emotion scores. In this way, it is possible to reflect the emotion data of its employees in the report and make suggestions to improve employee satisfaction.

[0076] The report generation unit can use the generation AI to compare its own data with data from different regions and propose a strategy for each region. For example, the report generation unit uses the generation AI to compare data such as the company's sales revenue and number of employees with data from different regions and propose a strategy for each region. Specifically, it proposes a strategy based on the distribution of sales revenue and number of employees by region. The report generation unit also uses the generation AI to compare data such as the company's research and development expenses and number of patent applications with data from different regions and propose a strategy for each region. Specifically, it proposes a strategy based on the amount of research and development expenses invested and the number of patent applications by region. The report generation unit also uses the generation AI to compare data such as the company's customer satisfaction and retention rate with data from different regions and propose a strategy for each region. Specifically, it proposes a strategy based on the customer satisfaction score and retention rate for each region. This makes it possible to compare the company's data with data from different regions and propose a strategy for each region.

[0077] The report generation unit makes extensive use of visual data in the reports generated by the generation AI, making them easier to understand visually. For example, the report generation unit displays data such as sales revenue and number of employees in graphs and charts in the reports generated by the generation AI, making them easier to understand visually. Specifically, the data is visualized using line graphs and bar graphs. The report generation unit also displays data such as research and development expenses and number of patent applications in graphs and charts in the reports generated by the generation AI, making them easier to understand visually. Specifically, the data is visualized using pie charts and histograms. The report generation unit also displays data such as customer satisfaction and retention rates in graphs and charts in the reports generated by the generation AI, making them easier to understand visually. Specifically, the data is visualized using scatter plots and radar charts. This makes it possible to generate reports that make extensive use of visual data and are easier to understand visually.

[0078] The report generation unit uses the emotion estimation function to reflect customer emotion data in a report and make suggestions for improving customer satisfaction. The report generation unit, for example, uses the emotion estimation function to collect customer emotion data and reflect it in a report. Specifically, a suggestion for improving customer satisfaction is made based on the customer's positive emotion score. The report generation unit also uses the emotion estimation function to collect customer emotion data and reflect it in a report. Specifically, a suggestion for improving customer satisfaction is made based on the customer's negative emotion score. The report generation unit also uses the emotion estimation function to collect customer emotion data and reflect it in a report. Specifically, a new suggestion for improving customer satisfaction is made based on the customer's emotion score. In this way, the customer's emotion data can be reflected in a report and suggestions for improving customer satisfaction can be made.

[0079] The chatbot providing unit can use the generation AI to include industry news and trend information in the information provided by the chatbot. For example, the chatbot providing unit uses the generation AI to include the latest industry news in the information provided by the chatbot. Specifically, the latest industry trends and important news are provided in real time. The chatbot providing unit also uses the generation AI to include the latest trend information in the information provided by the chatbot. Specifically, information reflecting industry trends and market changes is provided. The chatbot providing unit also uses the generation AI to include the latest industry news and trend information in the information provided by the chatbot. Specifically, information reflecting the competitive environment of companies and market trends is provided. This allows the latest industry news and trend information to be included in the information provided by the chatbot.

[0080] The chatbot providing unit can include specific examples and case studies in the answers generated by the generation AI. For example, the chatbot providing unit includes specific examples in the answers generated by the generation AI. For example, it provides specific advice based on success stories and failure stories of other companies. The chatbot providing unit also includes case studies in the answers generated by the generation AI. For example, it presents specific countermeasures and solutions for specific situations. The chatbot providing unit also includes specific examples and case studies in the answers generated by the generation AI. For example, it makes specific suggestions based on past data and track record. This makes it possible to generate answers that include specific examples and case studies.

[0081] The chatbot providing unit uses the emotion estimation function to generate a response according to the user's emotion, thereby improving the user experience. The chatbot providing unit, for example, uses the emotion estimation function to analyze the user's emotion in real time and generate a response according to the emotion. Specifically, if the user has positive emotions, the chatbot providing unit provides a response including words of encouragement or praise. The chatbot providing unit also uses the emotion estimation function to analyze the user's emotion and generate a response according to the emotion. Specifically, if the user has negative emotions, the chatbot providing unit provides a response including comfort or a solution. The chatbot providing unit also uses the emotion estimation function to analyze the user's emotion and generate a response according to the emotion. Specifically, the chatbot providing unit provides an optimal response based on the user's emotion score. This allows the chatbot to generate a response according to the user's emotion and improve the user experience.

[0082] The chatbot providing unit uses generation AI to enable the chatbot to respond in different languages, thereby supporting international users. For example, the chatbot providing unit uses generation AI to enable the chatbot to respond in multiple languages, such as English, French, and Chinese. Specifically, the chatbot automatically switches languages ​​according to the user's language setting. The chatbot providing unit also uses generation AI to enable the chatbot to respond in different languages, thereby supporting international users. Specifically, a language translation function is incorporated to perform translation in real time. The chatbot providing unit also uses generation AI to enable the chatbot to respond in different languages, thereby supporting international users. Specifically, the chatbot automatically detects the user's input language and generates a response in the appropriate language. This enables the chatbot to respond in different languages, thereby supporting international users.

[0083] The chatbot providing unit can include audio and video content in the answers generated by the generation AI, thereby realizing multimedia support. For example, the chatbot providing unit includes audio content in the answers generated by the generation AI. Specifically, answers to user questions are provided in audio format, making them accessible to visually impaired people. The chatbot providing unit also includes video content in the answers generated by the generation AI. Specifically, answers to user questions are provided in video format, making them easier to understand visually. The chatbot providing unit also includes audio and video content in the answers generated by the generation AI. Specifically, answers to user questions are provided in multimedia format, improving the user experience. This makes it possible to realize multimedia support, including audio and video content.

[0084] The chatbot providing unit can use the emotion estimation function to collect user emotion data and continuously improve the response accuracy of the chatbot. The chatbot providing unit, for example, uses the emotion estimation function to collect user emotion data and improve the response accuracy of the chatbot. Specifically, the response content is adjusted based on the user's emotion score. The chatbot providing unit also uses the emotion estimation function to collect user emotion data and improve the response accuracy of the chatbot. Specifically, the user's emotional response is analyzed and the response algorithm is improved. The chatbot providing unit also uses the emotion estimation function to collect user emotion data and improve the response accuracy of the chatbot. Specifically, the user emotion data is incorporated into a feedback loop to continuously improve the response accuracy. In this way, the user emotion data can be collected and the response accuracy of the chatbot can be continuously improved.

[0085] The report sales department can use the generation AI to include customized improvement measures and proposals in reports for other companies. For example, the report sales department uses the generation AI to include customized improvement measures in reports for other companies. Specifically, it provides specific improvement proposals based on the other company's data. The report sales department also uses the generation AI to include customized proposals in reports for other companies. Specifically, it provides proposals that take into account the industry characteristics and market conditions of the other company. The report sales department also uses the generation AI to include customized improvement measures and proposals in reports for other companies. Specifically, it provides specific action plans based on the other company's data. This makes it possible to include customized improvement measures and proposals in reports for other companies.

[0086] The report sales department can include success stories and best practices in the reports generated by the generation AI. For example, the report sales department can include success stories from other companies in the reports generated by the generation AI. Specifically, they can introduce the specific measures implemented by other companies and their results. The report sales department can also include best practices in the reports generated by the generation AI. Specifically, they can introduce the best methods and success stories within the industry. The report sales department can also include success stories and best practices from other companies in the reports generated by the generation AI. Specifically, they can introduce the details of the measures implemented by other companies and their effects. This makes it possible to generate reports that include success stories and best practices from other companies.

[0087] The report sales department can use the emotion estimation function to reflect emotion data of employees at other companies in reports and make proposals to improve employee satisfaction. The report sales department, for example, uses the emotion estimation function to collect emotion data of employees at other companies and reflect it in reports. Specifically, it makes proposals to improve employee satisfaction based on employees' positive emotion scores. The report sales department also uses the emotion estimation function to collect emotion data of employees at other companies and reflect it in reports. Specifically, it makes proposals to improve employee satisfaction based on employees' negative emotion scores. The report sales department also uses the emotion estimation function to collect emotion data of employees at other companies and reflect it in reports. Specifically, it makes new proposals to improve employee satisfaction based on employees' emotion scores. In this way, it is possible to reflect emotion data of employees at other companies in reports and make proposals to improve employee satisfaction.

[0088] The report sales department can use generation AI to subdivide reports for other companies by industry and propose improvement measures specific to each industry. For example, the report sales department can use generation AI to subdivide reports for other companies by industry, such as manufacturing, services, or IT, and propose improvement measures specific to each industry. Specifically, it proposes productivity improvement measures for the manufacturing industry and customer satisfaction improvement measures for the service industry. The report sales department can also use generation AI to subdivide reports for other companies by industry and propose improvement measures specific to each industry. Specifically, it proposes technological innovation measures for the IT industry and measures to improve patient satisfaction in the medical industry. The report sales department can also use generation AI to subdivide reports for other companies by industry and propose improvement measures specific to each industry. Specifically, it proposes risk management measures for the financial industry and sales improvement measures for the retail industry. This makes it possible to subdivide reports for other companies by industry and propose improvement measures specific to each industry.

[0089] The report sales department can include data from different regions in the reports generated by the generation AI and propose strategies for each region. For example, the report sales department includes data from different regions in the reports generated by the generation AI. Specifically, it proposes strategies for each region based on data on sales revenue and number of employees by region. The report sales department also includes data from different regions in the reports generated by the generation AI. Specifically, it proposes strategies for each region based on data on R&D expenses and number of patent applications by region. The report sales department also includes data from different regions in the reports generated by the generation AI. Specifically, it proposes strategies for each region based on data on customer satisfaction and retention rates by region. This makes it possible to generate reports that include data from different regions and propose strategies for each region.

[0090] The report sales department uses the emotion estimation function to reflect emotion data of other companies' customers in the report and can make proposals to improve customer satisfaction. The report sales department, for example, uses the emotion estimation function to collect emotion data of other companies' customers and reflect it in the report. Specifically, it makes proposals to improve customer satisfaction based on the customer's positive emotion score. The report sales department also uses the emotion estimation function to collect emotion data of other companies' customers and reflect it in the report. Specifically, it makes proposals to improve customer satisfaction based on the customer's negative emotion score. The report sales department also uses the emotion estimation function to collect emotion data of other companies' customers and reflect it in the report. Specifically, it makes new proposals to improve customer satisfaction based on the customer's emotion score. In this way, it is possible to reflect emotion data of other companies' customers in the report and make proposals to improve customer satisfaction.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The data collection department can collect employee skill data and perform skill matching. For example, generative AI can be used to collect employee skill sets and qualifications and match the best talent to projects and positions within the company. The data collection department can also collect employee skill data and identify skill gaps. Specifically, it analyzes the difference between required skills and current skills and proposes training programs. The data collection department can also collect employee skill data and analyze skill trends. This allows companies to optimally utilize employee skills and efficiently allocate personnel.

[0093] The data collection department can collect a company's supply chain data and assess supply risks. For example, generative AI can be used to collect data on supplier delivery delays and quality issues to assess supply risks. The data collection department can also assess geographic risks in the supply chain. Specifically, it collects data that takes natural disasters and political risks into account and performs risk assessments. The data collection department can also collect supply chain cost data and make suggestions for cost reduction. This allows companies to manage supply chain risks and achieve efficient operations.

[0094] The data collection unit can use the emotion estimation function to estimate customers' purchasing intent and optimize marketing strategies. For example, the emotion estimation function can be used to analyze customers' purchasing intent in real time and provide optimal marketing messages. The data collection unit can also use the emotion estimation function to estimate customers' purchasing intent and evaluate the effectiveness of promotions. Specifically, the emotion scores of customers before and after a promotion are compared to evaluate the effectiveness. The data collection unit can also use the emotion estimation function to estimate customers' purchasing intent and determine the direction of product development. This allows companies to understand customers' purchasing intent and implement effective marketing strategies.

[0095] The data collection unit can collect health data of a company's employees and propose health management programs. For example, generative AI can be used to collect employees' health checkup results and fitness data and evaluate their health risks. The data collection unit can also collect employees' health data and evaluate their stress levels. Specifically, it analyzes heart rate and sleep data to evaluate stress levels. The data collection unit can also collect employees' health data and propose health management programs. This allows companies to manage their employees' health and improve labor productivity.

[0096] The data collection unit can use the emotion estimation function to collect customer emotion data and improve the quality of customer support. For example, the emotion estimation function can be used to analyze customer emotions in real time and provide optimal support responses. The data collection unit can also use the emotion estimation function to collect customer emotion data and propose training programs for support staff. Specifically, the need for training can be evaluated based on the customer emotion score. The data collection unit can also use the emotion estimation function to collect customer emotion data and identify areas for improvement in customer support. This allows companies to understand customer emotions and provide high-quality customer support.

[0097] The data collection unit can collect a company's energy consumption data and evaluate its energy efficiency. For example, generative AI can be used to collect data on a company's electricity and gas consumption and evaluate its energy efficiency. The data collection unit can also collect energy consumption data and make suggestions for reducing energy costs. Specifically, it can identify peak energy consumption times and propose cost-cutting measures. The data collection unit can also collect energy consumption data and evaluate its impact on the environment. This allows companies to improve their energy efficiency and achieve both cost reduction and environmental protection.

[0098] The data collection unit can use the emotion estimation function to collect employee emotion data and make suggestions for team building. For example, the emotion estimation function can be used to analyze employee emotions in real time and evaluate team dynamics. The data collection unit can also use the emotion estimation function to collect employee emotion data and make suggestions for team building activities. Specifically, the optimal team building activity is selected based on the employee emotion score. The data collection unit can also use the emotion estimation function to collect employee emotion data and make suggestions to improve team performance. This allows companies to understand employee emotions and implement effective team building.

[0099] The data collection department can collect a company's product quality data and make suggestions for quality control. For example, it can use generative AI to collect data on product defect rates and customer complaints and identify areas for improvement in quality control. The data collection department can also collect product quality data and analyze quality trends. Specifically, it analyzes product quality data over time and evaluates quality fluctuations. The data collection department can also collect product quality data and suggest training programs for quality control. This allows companies to improve product quality and increase customer satisfaction.

[0100] The data collection unit can use the emotion estimation function to collect customer emotion data and provide insights for product development. For example, the emotion estimation function can be used to analyze customer emotions in real time and evaluate new product concepts. The data collection unit can also use the emotion estimation function to collect customer emotion data and identify areas for improvement in existing products. Specifically, the data collection unit can suggest product improvements based on the customer emotion score. The data collection unit can also use the emotion estimation function to collect customer emotion data and analyze market trends. This allows companies to understand customer emotions and develop effective products.

[0101] The data collection unit can collect a company's financial data and evaluate its financial soundness. For example, it can use generative AI to collect data on a company's profitability and debt ratio to evaluate its financial soundness. The data collection unit can also collect financial data and perform cash flow analysis. Specifically, it analyzes cash flow patterns and evaluates financing risks. The data collection unit can also collect financial data and evaluate the effectiveness of investments. This allows a company to understand its financial soundness and formulate an appropriate financial strategy.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The data collection unit uses the generation AI to collect data. For example, the generation AI collects data such as a company's sales, number of employees, and R&D expenses. The generation AI can also collect the company's social media activity and customer reviews. Furthermore, the generation AI collects data from different industries and takes geographical factors into account. Step 2: The correlation analysis unit analyzes the correlation between the data collected by the data collection unit. For example, the generation AI analyzes the correlation between the collected data using the Pearson correlation coefficient or Spearman's rank correlation coefficient. The generation AI can also apply an anomaly detection algorithm to evaluate the reliability of the data. Step 3: The benchmark creation unit creates new benchmarks based on the data analyzed by the correlation analysis unit. For example, the generation AI sets indicators to evaluate a company's growth potential, efficiency, competitiveness, etc., and evaluates the company based on those indicators. The generation AI can also create benchmarks that take into account a company's sustainability indicators and innovation activities. Step 4: The report generation unit compares the company's data with the benchmark created by the benchmark creation unit and automatically generates a report. For example, the generation AI can compare data such as the company's sales, number of employees, and research and development expenses with the new benchmark to identify areas for improvement and strengthening. The generation AI can also generate reports that include specific action plans and timelines. Step 5: The chatbot provision unit provides the information in the report generated by the report generation unit via the chatbot. For example, the generation AI generates answers to user questions and provides them through the chatbot. The generation AI can also provide information including the latest industry news and trend information. Step 6: The report sales department sells the reports generated by the report generation department to other companies. For example, the generation AI generates reports that include customized improvement measures and proposals based on other companies' data. The generation AI can also generate reports that include other companies' success stories and best practices.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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]

[0171] 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 collection unit that collects data using a generation AI; a correlation analysis unit that analyzes correlations of the data collected by the data collection unit; a benchmark creation unit that creates a new benchmark based on the data analyzed by the correlation analysis unit; a report generation unit that compares the benchmark created by the benchmark creation unit with the company's own data and automatically generates a report; a chatbot providing unit that provides information on the report generated by the report generating unit by a chatbot; a report sales unit that sells the report generated by the report generation unit to other companies. A system characterized by:

2. The data collection unit Collecting a company's social media activity or customer reviews and correlating them with business performance data 2. The system of claim 1.

3. The data collection unit Applying an anomaly detection algorithm to the data to assess the reliability of the data 2. The system of claim 1.

4. The data collection unit Collecting employee sentiment data and analyzing the correlation between employee satisfaction and the company's performance 2. The system of claim 1.

5. The data collection unit Collect data from different industries and analyze cross-industry correlations 2. The system of claim 1.

6. The data collection unit Analyzing said data by region based on geographic factors 2. The system of claim 1.

Images