system

Abstract

The system according to this embodiment aims to support companies in solving their problems by effectively utilizing past cases. [Solution] The system according to the embodiment comprises a collection unit, a management unit, a reception unit, a search unit, and a provision unit. The collection unit collects information on past cases. The management unit manages the case information collected by the collection unit by creating a database. The reception unit receives information on specific questions or issues from users. The search unit searches for case information related to the information received by the reception unit from the information managed by the management unit. The provision unit provides information to the user based on the search results from the search unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, past cases have not been fully utilized effectively to help solve corporate problems, and there is room for improvement.

[0005] The system according to the embodiment aims to effectively utilize past cases to support corporate problem-solving.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a management unit, a reception unit, a search unit, and a provision unit. The collection unit collects information on past cases. The management unit manages the case information collected by the collection unit by creating a database. The reception unit receives information on specific questions or issues from users. The search unit searches for case information related to the information received by the reception unit from the information managed by the management unit. The provision unit provides information to the user based on the search results from the search unit. [Effects of the Invention]

[0007] The system according to this embodiment can effectively utilize past cases to support companies in solving their challenges. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The decision support system based on historical cases according to an embodiment of the present invention is a system that suggests the optimal direction based on past historical cases in response to challenges and events faced by companies. The decision support system based on historical cases first collects information on past cases and manages it in a database. Next, it receives information on questions and challenges from users and searches for cases related to that information. Based on the search results, it generates solutions and directions using generational AI and provides that information to the user. Furthermore, it explains why the generated solutions and directions are effective based on historical evidence. For example, the collection unit collects information such as success stories and failures of companies, and events with significant social impact. The management unit manages the collected information in a database. This enables the rapid provision of information that users need. When a user inputs information on a question or challenge, the reception unit receives that information. For example, a question such as "I want to know about successful cases regarding the market launch of a new product" may be entered. The information received by the reception unit is sent to the search unit to search for relevant cases from the database managed by the management unit. The search unit searches for cases related to the information received by the reception unit from the information managed by the management unit. For example, it searches for past successful cases regarding the market launch of a new product. Based on search results, the generation unit uses generational AI to generate solutions and directions. For example, it proposes successful strategies and methods for launching new products into the market. The delivery unit provides the information generated by the generation unit to the user. For example, it provides the user with successful case studies and strategies for launching new products into the market. Furthermore, the explanation unit explains why the generated solutions and directions are effective, based on historical evidence. For example, it explains why a particular strategy was effective based on past success stories. This system enables companies to make decisions with minimized risk based on evidence from historical cases. Consulting firms, educational institutions, and government agencies can also utilize this system to produce reliable proposals, educational materials, and policy formulations. In this way, a decision support system based on historical cases can suggest the optimal direction for addressing a company's challenges.

[0029] The decision support system according to this embodiment comprises a collection unit, a management unit, a reception unit, a search unit, and a provision unit. The collection unit collects information on past cases. For example, the collection unit collects information on successful and unsuccessful cases of companies, and events with significant social impact. For example, the collection unit can collect information from publicly available databases on the internet. The collection unit can also collect information from internal company databases. Furthermore, the collection unit can also collect information through surveys and interviews. The management unit databases and manages the information collected by the collection unit. For example, the management unit stores the collected information as digital data and registers it in the database. The management unit optimizes the database structure to enable quick information retrieval and provision. The management unit regularly backs up the data to ensure data security. The reception unit receives information on questions and issues from users. For example, the reception unit receives questions and issues in text format entered by users. The reception unit can also receive questions and issues in multiple-choice format. The reception unit can also receive questions and issues from users using voice input. The search unit searches for cases related to information received by the reception unit from the information managed by the management unit. The search unit can search for related cases using, for example, keyword search. The search unit can also narrow down the search results using filtering. The search unit can also prioritize displaying highly relevant cases using ranking. The provision unit provides information to the user based on the search results from the search unit. The provision unit can, for example, provide the search results to the user in report format. The provision unit can also display the search results in dashboard format. The provision unit can also notify the user of the search results in notification format. As a result, the decision support system according to the embodiment can suggest the optimal direction for a company's challenges based on past cases.

[0030] The data collection unit collects information on past cases. For example, it collects information on corporate successes and failures, and events with significant social impact. Specifically, the unit can collect information from publicly available databases on the internet, such as academic journal databases, industry reports, news articles, and government statistics. It can also collect information from internal corporate databases, including past project reports, customer feedback, sales data, and marketing campaign results. Furthermore, the unit can collect information through surveys and interviews. Surveys are conducted via online forms and email, while interviews are conducted in person or via video call. This allows the unit to gather a wide range of data from diverse sources, accumulating a rich foundation for decision support systems. To ensure the reliability and accuracy of the collected data, the unit implements a data verification process. For example, it verifies the source of data and cross-checks data from multiple sources. The unit also sets data collection and update frequencies to ensure that the latest information is always available. This allows the unit to efficiently collect reliable data and improve the overall accuracy and reliability of the system.

[0031] The management department manages the information collected by the collection department by creating a database. For example, the management department stores the collected information as digital data and registers it in the database. Specifically, the management department optimizes the database structure to enable quick information retrieval and provision. For example, the database is built using relational databases or NoSQL databases, and the appropriate data model is adopted depending on the type and use of the information. The management department ensures data security by regularly backing up the data. Backups are performed both on-site and off-site, enabling data recovery in the event of disasters or system failures. The management department also sets data access permissions to thoroughly protect confidential information. For example, different access levels are set for each user so that only necessary information can be viewed. Furthermore, the management department performs data quality control to maintain the consistency and accuracy of the collected information. For example, it implements processes to detect and correct data duplication and omissions. This allows the management department to manage the collected information efficiently and securely, improving the reliability and performance of the overall system.

[0032] The reception desk receives information about questions and issues from users. For example, the reception desk can receive questions and issues in text format entered by users. Specifically, the reception desk can receive input from users through web forms or chatbots. Users can freely enter questions and issues and attach detailed explanations and related information. The reception desk can also accept questions and issues in multiple-choice format. For example, users can easily submit questions and issues by selecting the appropriate item from predefined options. The reception desk can also receive questions and issues from users using voice input. Using speech recognition technology, the system converts the user's voice into text and inputs it. This improves user convenience and allows the reception desk to support diverse input methods. Furthermore, the reception desk has a function to automatically classify user input and distribute it to the appropriate department or person in charge. For example, using natural language processing technology, it analyzes the content of user questions and issues and extracts relevant keywords and categories. This allows the reception desk to efficiently process user input and enable a quick response.

[0033] The search unit searches for cases related to information received by the reception unit from information managed by the administration unit. For example, the search unit searches for related cases using keyword searches. Specifically, the search unit searches the database based on keywords entered by the user and extracts related cases. The search unit can also narrow down search results using filtering. For example, by narrowing down search results by a specific period, region, or industry, it can quickly provide the information the user is looking for. The search unit can also prioritize displaying highly relevant cases using rankings. For example, it can sort search results in order of relevance and prioritize displaying the information the user needs most. Furthermore, the search unit can improve the accuracy of search results using AI. For example, it can use machine learning algorithms to analyze the user's search history and behavior patterns and provide search results that are optimal for each individual user. In this way, the search unit can provide highly accurate search results that meet the user's needs and maximize the effectiveness of the decision support system.

[0034] The service provider provides users with information based on the search results generated by the search unit. For example, the service provider can provide users with search results in report format. Specifically, the service provider organizes the search results and creates reports in a visually easy-to-understand format. The reports include detailed information on related cases, statistical data, graphs, and charts. The service provider can also display search results in dashboard format. For example, it can provide an interactive dashboard so that users can view search results in real time. The dashboard displays an overview of the search results and key metrics, allowing users to quickly grasp the information they need. The service provider can also notify users of search results in notification format. For example, it can notify users of search results via email, SMS, or push notifications. This allows users to respond quickly without missing important information. Furthermore, the service provider can collect user feedback and continuously improve the quality of the information it provides. For example, when users leave ratings and comments on the information provided, the service provider can gain valuable insights to improve the accuracy and usefulness of the information. This allows the service provider to provide users with high-quality information and maximize the effectiveness of the decision support system.

[0035] The search unit includes a generation unit that generates information indicating solutions or directions based on the search results using a generation AI. The generation unit generates information based on the search results from the search unit using a generation AI. For example, the generation unit generates solutions and directions using natural language generation technology. The generation unit can also generate visual solutions using image generation technology. The generation unit can also generate solutions in audio format using speech generation technology. The generation unit generates specific solutions to the user's questions and problems using a generation AI. For example, in response to the user's question, "I want to know about successful cases regarding the market launch of a new product," the generation unit proposes a specific strategy based on past success stories. The generation unit automates the generation of solutions and directions using a generation AI. This allows the generation unit to generate solutions and directions quickly and efficiently. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate solutions and directions using an AI model that takes the search results from the search unit as input and outputs solutions and directions. This allows the generation unit to provide optimal solutions and directions to the user's questions and problems.

[0036] The generation unit includes an explanation unit that explains the generated solutions or directions. The explanation unit explains why the solutions or directions generated by the generation unit are effective. The explanation unit provides explanations in, for example, text format. The explanation unit can also provide explanations in video format. The explanation unit can also provide explanations visually using infographics. The explanation unit automates the explanation of solutions and directions using generation AI. For example, the explanation unit uses generation AI to explain why a strategy was effective based on past success stories. The explanation unit uses generation AI to explain the background of solutions and directions for user questions and problems. This allows the explanation unit to deepen the user's understanding. Some or all of the above processing in the explanation unit may be performed using, for example, AI, or not using AI. For example, the explanation unit can take the solutions or directions generated by the generation unit as input and provide explanations using an AI model that explains their background and effectiveness. This allows the explanation unit to provide reliable explanations to users.

[0037] The data collection unit can collect specific information on corporate success stories, failures, and events with significant social impact. For example, the unit can collect corporate success stories and failures. As success stories, the unit can collect examples such as increased sales and expanded market share. As failure stories, the unit can collect examples such as project failures and market withdrawals. As events with significant social impact, the unit can collect examples such as legal reforms, disasters, and social movements. The unit can collect information from publicly available databases on the internet, for example. The unit can also collect information from internal corporate databases. The unit can also collect information through surveys and interviews. This allows the unit to cover a wide range of cases. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when collecting information from publicly available databases on the internet, the unit can use AI to automatically extract relevant information. This allows the unit to collect information efficiently.

[0038] The management department can manage the collected information by creating a database. For example, the management department can store the collected information as digital data and register it in the database. The management department can optimize the database structure to enable quick retrieval and provision of information. The management department can regularly back up the data to ensure data security. The management department can eliminate data duplication and perform efficient data management. The management department can adjust the frequency of data updates to always maintain the latest information. The management department can review the data classification method to enable efficient data retrieval. As a result, the management department can efficiently manage the collected information and quickly provide users with the information they need. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, when eliminating data duplication, the management department can use AI to automatically detect and delete duplicate data. As a result, the management department can manage data efficiently.

[0039] The reception desk can receive information about specific questions or tasks from users. For example, the reception desk can receive questions or tasks in text format entered by the user. The reception desk can also receive questions or tasks in multiple-choice format. The reception desk can also receive questions or tasks from users using voice input. The reception desk can estimate the user's emotions and adjust the way questions or tasks are received based on the estimated emotions. For example, if the user is feeling anxious, a simple and intuitive interface is provided. If the user is excited, detailed input options are provided. If the user is tired, voice input is prioritized to quickly receive questions or tasks. The reception desk can refer to the user's past question history and select the optimal reception method. For example, it may prioritize providing question formats that the user has frequently used in the past. It may analyze specific patterns from the user's past question history and suggest the optimal reception method. It may prioritize providing input methods (voice, text, etc.) that the user has used in the past. This allows the reception desk to provide information that meets the user's needs. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the reception desk to provide the most appropriate reception service based on the user's emotions.

[0040] The search unit can search for cases related to information received by the reception unit from information managed by the administration unit. The search unit can search for relevant cases using, for example, keyword searches. The search unit can also narrow down search results using filtering. The search unit can also prioritize displaying highly relevant cases using rankings. The search unit can estimate the user's emotions and adjust how search results are displayed based on the estimated user emotions. For example, if the user is feeling anxious, it will prioritize displaying cases that provide reassurance. If the user is excited, it will prioritize displaying challenging cases. If the user is tired, it will prioritize displaying cases that are easy to implement. The search unit can evaluate the relevance of cases and prioritize displaying highly relevant information. For example, it will prioritize displaying cases that are directly related to the current problem. It will prioritize displaying cases that are related to the same industry or market. It will prioritize displaying cases that are related to companies of similar size. This allows the search unit to provide appropriate cases for the user's questions and problems. Some or all of the above processing in the search unit may be performed using, for example, AI, or not using AI. For example, when performing a keyword search, the search unit can use AI to automatically extract relevant keywords and display the search results. This allows the search unit to efficiently find relevant cases.

[0041] The delivery unit can provide the user with information generated by the generation unit. For example, the delivery unit can provide the user with search results in report format. The delivery unit can also display search results in dashboard format. The delivery unit can also notify the user of search results in notification format. The delivery unit can estimate the user's emotions and adjust the format of the information provided based on the estimated emotions. For example, if the user is feeling anxious, the information can be provided in a reassuring format. If the user is excited, the information can be provided in a challenging format. If the user is tired, the information can be provided in a simple and visually easy-to-understand format. The delivery unit can refer to the user's past usage history and select the optimal method of information delivery. For example, it can prioritize providing information in formats that the user has frequently used in the past. It can analyze specific patterns from the user's past usage history and suggest the optimal method of information delivery. It can provide information in a format optimized for the devices and platforms the user has used in the past. This allows the delivery unit to quickly obtain the information the user needs. Some or all of the above processing in the delivery unit may be performed using AI, for example, or not using AI. For example, when the service provider estimates a user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the service provider to provide the most appropriate information based on the user's emotions.

[0042] The explanatory section can explain why the generated solutions and directions are effective, based on historical evidence. The explanatory section can provide explanations in, for example, text format. The explanatory section can also provide explanations in video format. The explanatory section can also provide explanations visually using infographics. The explanatory section can automate the explanation of solutions and directions using generative AI. For example, the explanatory section can use generative AI to explain why a strategy was effective based on past success stories. The explanatory section can use generative AI to explain the background of solutions and directions for user questions and problems. This allows the explanatory section to deepen the user's understanding. Some or all of the above processing in the explanatory section may be performed using, for example, AI, or not using AI. For example, the explanatory section can take the solutions and directions generated by the generative section as input and provide explanations using an AI model that explains their background and effectiveness. This allows the explanatory section to provide users with reliable explanations.

[0043] The data collection unit can evaluate the reliability of cases during collection and prioritize the collection of reliable information. For example, the unit will prioritize the collection of cases if the source of the case is a reliable academic paper or official report. The unit will prioritize the collection of cases if the case has been verified by multiple reliable sources. The unit will prioritize the collection of cases if the provider of the case is an expert or industry leader. The unit evaluates the reliability of cases and prioritizes the collection of reliable information. This allows the unit to improve the reliability of the information it provides. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when evaluating the reliability of cases, the unit can use AI to analyze the data source and verification method and calculate a reliability score. This allows the unit to efficiently collect reliable information.

[0044] The data collection unit can adjust its collection scope considering the timing and location of each incident. For example, it prioritizes collecting recent incidents. If an incident occurs in a specific region, it also collects other incidents related to that region. If incidents occur in a concentrated period, it also collects other incidents related to that period. The data collection unit adjusts its collection scope considering the timing and location of each incident. This allows the data collection unit to collect more relevant incidents. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when analyzing the timing and location of an incident, the data collection unit can use AI to analyze timestamps and geographic information systems (GIS) to adjust the collection scope. This allows the data collection unit to efficiently collect more relevant incidents.

[0045] The data collection unit can evaluate the relevance of cases during collection and prioritize the collection of highly relevant information. For example, the data collection unit will prioritize collecting cases that are directly related to current issues. The data collection unit will prioritize collecting cases that are related to the same industry or market. The data collection unit will prioritize collecting cases that are related to companies of similar size. The data collection unit evaluates the relevance of cases and prioritizes the collection of highly relevant information. This allows the data collection unit to improve the relevance of the information it provides. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, when evaluating the relevance of cases, the data collection unit can use AI to perform co-occurrence network and correlation analysis and calculate relevance scores. This allows the data collection unit to efficiently collect highly relevant information.

[0046] The data collection unit can adjust the content of its collections by considering the background and scope of impact of each case. For example, the collection unit prioritizes collecting cases where the background is similar to the current situation. The collection unit also prioritizes collecting cases where the scope of impact is widespread. If the background of a case is related to a specific policy or economic situation, the collection unit will also collect other cases related to that background. The collection unit adjusts the content of its collections by considering the background and scope of impact of each case. This allows the collection unit to collect more relevant cases. Some or all of the above processing in the collection unit may be performed using AI, for example, or not. For example, when analyzing the background and scope of impact of a case, the collection unit can use AI to conduct background research and impact analysis and adjust the content of its collections. This allows the collection unit to efficiently collect more relevant cases.

[0047] The management department can adjust the frequency of data updates during management to always maintain the latest information. For example, the management department can immediately update the database when a significant event occurs. The management department can periodically check the database and update outdated information. The management department can update the database as needed based on user feedback. The management department adjusts the frequency of data updates to always maintain the latest information. This allows the management department to always provide the latest information. Some or all of the above processes in the management department may be performed using AI, for example, or not. For example, when adjusting the frequency of data updates, the management department can use AI to analyze the importance and update frequency of the data and determine the optimal update schedule. This allows the management department to efficiently provide the latest information.

[0048] The management department can eliminate data duplication during management and perform efficient data management. For example, if the same case is collected from multiple sources, the management department will eliminate duplication and manage it as a single case. The management department will periodically check for and delete duplicate data in the database. The management department will perform duplicate checks during collection to prevent data duplication. The management department will eliminate data duplication and perform efficient data management. This will enable the management department to quickly search for and provide data. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, when eliminating data duplication, the management department can use AI to automatically detect and delete duplicate data. This will enable the management department to manage data efficiently.

[0049] The management department can ensure data security by regularly backing up data during management. For example, the management department can back up the database regularly on a daily basis. The management department can immediately back up data when important data is added. The management department can ensure data security by storing data backups in multiple locations. The management department can ensure data security by regularly backing up data. In this way, the management department can ensure data security. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, when backing up data, the management department can use AI to optimize the backup schedule and perform backups efficiently. In this way, the management department can ensure data security efficiently.

[0050] The management department can review data classification methods during management to enable efficient data retrieval. For example, the management department can periodically review data categories and classify them based on the latest information. The management department can improve data classification methods based on user feedback. The management department can utilize tagging and metadata to improve data retrieval efficiency. The management department can review data classification methods to enable efficient data retrieval. This allows the management department to efficiently search for data. Some or all of the above processes in the management department may be performed using AI, for example, or not. For example, when reviewing data classification methods, the management department can use AI to automatically generate and classify data categories and tags. This allows the management department to manage data efficiently.

[0051] The reception desk can refer to the user's past question history and select the most suitable reception method at the time of reception. For example, the reception desk may prioritize providing question formats that the user has frequently used in the past. The reception desk may analyze specific patterns from the user's past question history and propose the most suitable reception method. The reception desk may prioritize providing input methods (voice, text, etc.) that the user has used in the past. The reception desk refers to the user's past question history and selects the most suitable reception method at the time of reception. This enables the reception desk to provide information that meets the user's needs. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, when analyzing the user's past question history, the reception desk may use AI to perform database lookups and log analysis to select the most suitable reception method. This enables the reception desk to efficiently provide information that meets the user's needs.

[0052] The reception desk can prioritize questions based on the user's industry and job duties at the time of reception. For example, if the user belongs to a specific industry, the reception desk will prioritize questions related to that industry. The reception desk will also prioritize questions related to the user's job duties. Based on the user's industry and job duties, the reception desk will prioritize displaying specific question categories. The reception desk prioritizes questions based on the user's industry and job duties at the time of reception. This allows the reception desk to receive questions more appropriately. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, when analyzing the user's industry and job duties, the reception desk can use AI to generate industry codes and job classifications and determine question priorities. This allows the reception desk to efficiently receive questions that meet the user's needs.

[0053] The reception desk can select the optimal reception method at the time of reception, taking into account the user's geographical location information. For example, if the user is in a specific region, the reception desk will prioritize receiving questions related to that region. The reception desk will propose the optimal reception method based on the user's geographical location information. If the user is on the move, the reception desk will update the location information in real time and provide the optimal reception method. The reception desk selects the optimal reception method at the time of reception, taking into account the user's geographical location information. This allows the reception desk to select a more appropriate reception method. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, when analyzing the user's geographical location information, the reception desk can use AI to analyze GPS data and IP addresses to select the optimal reception method. This allows the reception desk to efficiently provide reception methods that meet the user's needs.

[0054] The reception desk can select the optimal reception method at the time of reception, taking into account the user's device information. For example, if the user is using a smartphone, the reception desk provides a mobile-friendly interface. If the user is using a tablet, the reception desk provides an interface optimized for a larger screen. If the user is using a desktop, the reception desk provides detailed input options. The reception desk selects the optimal reception method at the time of reception, taking into account the user's device information. This allows the reception desk to select a more appropriate reception method. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, when analyzing the user's device information, the reception desk can use AI to analyze the device ID and browser information and select the optimal reception method. This allows the reception desk to efficiently provide a reception method that meets the user's needs.

[0055] The search unit can evaluate the relevance of case studies during a search and prioritize displaying highly relevant information. For example, the search unit prioritizes displaying case studies that are directly related to the current issue. The search unit prioritizes displaying case studies that are related to the same industry or market. The search unit prioritizes displaying case studies that are related to companies of similar size. The search unit evaluates the relevance of case studies and prioritizes displaying highly relevant information. This allows the search unit to improve the relevance of the information it provides. Some or all of the above processing in the search unit may be performed using AI, for example, or not using AI. For example, when evaluating the relevance of case studies, the search unit can use AI to perform co-occurrence network and correlation analysis and calculate a relevance score. This allows the search unit to efficiently provide highly relevant information.

[0056] The search unit can adjust its search scope when performing a search, taking into account the timing and location of the incidents. For example, the search unit prioritizes displaying incidents that have occurred recently. If an incident occurred in a specific region, the search unit also displays other incidents related to that region. If incidents occurred in a concentrated period, the search unit also displays other incidents related to that period. The search unit adjusts its search scope considering the timing and location of the incidents. This allows the search unit to provide more relevant information. Some or all of the above processing in the search unit may be performed using AI, for example, or not. For example, when analyzing the timing and location of incidents, the search unit can use AI to analyze timestamps and geographic information systems (GIS) and adjust the search scope. This allows the search unit to efficiently provide more relevant information.

[0057] The search function can evaluate the reliability of cases during a search and prioritize displaying highly reliable information. For example, the search function prioritizes cases whose source is a reliable academic paper or official report. The search function prioritizes cases that have been verified by multiple reliable sources. The search function prioritizes cases where the provider is an expert or industry leader. The search function evaluates the reliability of cases and prioritizes displaying highly reliable information. This allows the search function to improve the reliability of the information it provides. Some or all of the above processing in the search function may be performed using AI, for example, or not using AI. For example, when evaluating the reliability of cases, the search function can use AI to analyze the data source and verification method and calculate a reliability score. This allows the search function to efficiently provide highly reliable information.

[0058] The search function can adjust the search results when a case occurs, taking into account its background and scope of impact. For example, the search function prioritizes displaying cases where the background is similar to the current situation. The search function also prioritizes displaying cases where the scope of impact is widespread. If the background of a case is related to a specific policy or economic situation, the search function also displays other cases related to that background. The search function adjusts the search results by considering the background and scope of impact of each case. This allows the search function to provide more relevant information. Some or all of the above processing in the search function may be performed using AI, for example, or not. For example, when analyzing the background and scope of impact of a case, the search function can use AI to conduct background research and impact analysis and adjust the search results. This allows the search function to efficiently provide more relevant information.

[0059] The information provider can refer to the user's past usage history when providing information and select the most suitable method of information delivery. For example, the information provider may prioritize providing information in formats that the user has frequently used in the past. The information provider may analyze specific patterns from the user's past usage history and propose the most suitable method of information delivery. The information provider may provide information in a format optimized for the devices and platforms the user has used in the past. The information provider refers to the user's past usage history when providing information and selects the most suitable method of information delivery. This enables the information provider to provide information that meets the user's needs. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, when analyzing the user's past usage history, the information provider may use AI to perform database referencing and log analysis to select the most suitable method of information delivery. This enables the information provider to efficiently provide information that meets the user's needs.

[0060] The information delivery unit can prioritize information based on the user's industry and job duties at the time of delivery. For example, if a user belongs to a specific industry, the information delivery unit will prioritize providing information related to that industry. The information delivery unit will prioritize providing information related to the user's job duties. The information delivery unit will prioritize displaying specific information categories based on the user's industry and job duties. The information delivery unit prioritizes information based on the user's industry and job duties at the time of delivery. This enables the information delivery unit to provide more appropriate information. Some or all of the above processing in the information delivery unit may be performed using AI, for example, or not using AI. For example, when analyzing a user's industry and job duties, the information delivery unit can use AI to perform industry codes and job classifications and determine information priorities. This enables the information delivery unit to efficiently provide information that meets the user's needs.

[0061] The information provider can select the optimal information delivery method by considering the user's geographical location information at the time of delivery. For example, if the user is in a specific region, the information provider will prioritize providing information related to that region. The information provider will propose the optimal information delivery method based on the user's geographical location information. If the user is on the move, the information provider will update the location information in real time and provide the optimal information delivery method. The information provider selects the optimal information delivery method by considering the user's geographical location information at the time of delivery. This allows the information provider to select a more appropriate information delivery method. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, when analyzing the user's geographical location information, the information provider can use AI to analyze GPS data and IP addresses and select the optimal information delivery method. This allows the information provider to efficiently provide information delivery methods that meet the user's needs.

[0062] The information provider can select the optimal information delivery method at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the information provider will provide information in a mobile-friendly format. If the user is using a tablet, the information provider will provide information in a format optimized for a larger screen. If the user is using a desktop, the information provider will provide detailed information. The information provider selects the optimal information delivery method at the time of delivery, taking into account the user's device information. This allows the information provider to select a more appropriate information delivery method. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, when analyzing the user's device information, the information provider can use AI to analyze the device ID and browser information and select the optimal information delivery method. This allows the information provider to efficiently provide information delivery methods that meet the user's needs.

[0063] The generation unit can evaluate the relevance of case studies during generation and prioritize the generation of highly relevant solutions. For example, the generation unit prioritizes generating solutions if a case study is directly related to the current problem. The generation unit prioritizes generating solutions if a case study is related to the same industry or market. The generation unit prioritizes generating solutions if a case study is related to companies of similar size. The generation unit evaluates the relevance of case studies and prioritizes the generation of highly relevant solutions. This allows the generation unit to improve the relevance of the solutions it provides. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, when evaluating the relevance of case studies, the generation unit can use AI to perform co-occurrence network and correlation analysis and calculate relevance scores. This allows the generation unit to efficiently provide highly relevant solutions.

[0064] The generation unit can adjust the generated content during generation, taking into account the timing and location of the incident. For example, if the incident is recent, the generation unit will prioritize generating solutions. If the incident occurred in a specific region, the generation unit will generate solutions while also considering other incidents related to that region. If the incidents occurred in a concentrated period, the generation unit will generate solutions while also considering other incidents related to that period. The generation unit adjusts the generated content, taking into account the timing and location of the incidents. This allows the generation unit to provide more relevant solutions. Some or all of the above processing in the generation unit may be performed using AI, for example, or not. For example, when analyzing the timing and location of an incident, the generation unit can use AI to analyze timestamps and geographic information systems (GIS) and adjust the generated content. This allows the generation unit to efficiently provide more relevant solutions.

[0065] The generation unit can evaluate the reliability of cases during generation and prioritize the generation of highly reliable solutions. For example, the generation unit will prioritize generating solutions if the source of a case is a reliable academic paper or official report. The generation unit will prioritize generating solutions if the case has been verified by multiple reliable sources. The generation unit will prioritize generating solutions if the provider of the case is an expert or industry leader. The generation unit evaluates the reliability of cases and prioritizes the generation of highly reliable solutions. This allows the generation unit to improve the reliability of the solutions it provides. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, when evaluating the reliability of a case, the generation unit can use AI to analyze the data source and verification method and calculate a reliability score. This allows the generation unit to efficiently provide highly reliable solutions.

[0066] The generation unit can adjust the generated content by considering the background and scope of impact of a case during the generation process. For example, the generation unit will prioritize generating solutions if the background of a case is similar to the current situation. The generation unit will also prioritize generating solutions if the scope of impact of a case is widespread. If the background of a case is related to a specific policy or economic situation, the generation unit will consider other cases related to that background when generating solutions. The generation unit adjusts the generated content by considering the background and scope of impact of a case. This allows the generation unit to provide more relevant solutions. Some or all of the above processing in the generation unit may be performed using AI, for example, or not. For example, when analyzing the background and scope of impact of a case, the generation unit can use AI to conduct background research and impact analysis and adjust the generated content. This allows the generation unit to efficiently provide more relevant solutions.

[0067] The commentary section can evaluate the relevance of case studies during commentary and prioritize providing commentaries that are highly relevant. For example, the commentary section will prioritize providing commentaries if the case study is directly related to current issues. The commentary section will prioritize providing commentaries if the case study is related to the same industry or market. The commentary section will prioritize providing commentaries if the case study is related to companies of similar size. The commentary section evaluates the relevance of case studies and prioritizes providing commentaries that are highly relevant. This allows the commentary section to improve the relevance of the commentaries it provides. Some or all of the above processing in the commentary section may be performed using AI, for example, or not using AI. For example, when evaluating the relevance of case studies, the commentary section may use AI to perform co-occurrence network and correlation analysis and calculate relevance scores. This allows the commentary section to efficiently provide highly relevant commentaries.

[0068] The commentary section can adjust its commentary content by considering the timing and location of the incident. For example, if the incident occurred recently, the commentary section will prioritize providing a commentary. If the incident occurred in a specific region, the commentary section will also consider other incidents related to that region when providing a commentary. If the incidents occurred in a concentrated period of time, the commentary section will also consider other incidents related to that period when providing a commentary. The commentary section adjusts its commentary content by considering the timing and location of the incident. This allows the commentary section to provide a more relevant commentary. Some or all of the above processing in the commentary section may be performed using AI, for example, or not using AI. For example, when analyzing the timing and location of an incident, the commentary section can use AI to analyze timestamps and geographic information systems (GIS) and adjust the commentary content. This allows the commentary section to efficiently provide a more relevant commentary.

[0069] The commentary section can evaluate the reliability of a case when providing commentary and prioritize providing reliable commentary. For example, the commentary section will prioritize providing commentary if the source of the case is a reliable academic paper or official report. The commentary section will prioritize providing commentary if the case has been verified from multiple reliable sources. The commentary section will prioritize providing commentary if the provider of the case is an expert or industry leader. The commentary section evaluates the reliability of a case and prioritizes providing reliable commentary. This allows the commentary section to improve the reliability of the commentary it provides. Some or all of the above processing in the commentary section may be performed using AI, for example, or not using AI. For example, when evaluating the reliability of a case, the commentary section may use AI to analyze the data source and verification method and calculate a reliability score. This allows the commentary section to efficiently provide reliable commentary.

[0070] The commentary section can adjust its commentary content when providing commentary, taking into account the background and scope of impact of a case. For example, the commentary section will prioritize providing commentary when the background of a case is similar to the current situation. The commentary section will prioritize providing commentary when the scope of impact of a case is wide-ranging. If the background of a case is related to a specific policy or economic situation, the commentary section will also consider other cases related to that background when providing commentary. The commentary section adjusts its commentary content by taking into account the background and scope of impact of a case. This allows the commentary section to provide more relevant commentary. Some or all of the above processing in the commentary section may be performed using AI, for example, or not. For example, when analyzing the background and scope of impact of a case, the commentary section can use AI to conduct background research and impact analysis and adjust the commentary content. This allows the commentary section to efficiently provide more relevant commentary.

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

[0072] Decision support systems can also include a predictive unit. This unit predicts future trends and risks based on collected data. For example, it can analyze past case data to predict future trends in a specific industry or market. It can also use AI to extract patterns from collected data and identify future risks and opportunities. The predictive unit can present future scenarios in response to user questions and challenges, providing information to aid in decision-making. This allows decision support systems to assist in decision-making not only based on past cases but also on future predictions.

[0073] The decision support system can also include a feedback unit. The feedback unit collects the results after the user implements the provided solutions or directions and feeds them back into the system. For example, the feedback unit can collect data on the success or failure of strategies implemented by the user and add it to the system's database. Based on user feedback, the feedback unit can improve the system's algorithms and provide more accurate solutions. The feedback unit can also collect user satisfaction and areas for improvement, enhancing the system's user experience. This allows the decision support system to continuously improve and provide more effective assistance.

[0074] The decision support system can also include a simulation unit. The simulation unit provides the ability for users to test proposed solutions in a virtual environment. For example, the simulation unit can allow users to test a new product launch strategy in a virtual market. The simulation unit can assist users in comparing different strategies and selecting the optimal one. The simulation unit can also use AI to generate scenarios in the virtual environment in real time and provide feedback to the user. This allows the decision support system to verify strategies before taking actual action, minimizing risk.

[0075] Decision support systems can also include a collaboration section. This section provides functions for multiple users to make decisions collaboratively. For example, the collaboration section can provide a chat function for users to exchange opinions in real time and jointly consider solutions. It can also provide a co-editing function for users to collaboratively edit documents and consolidate solutions. Furthermore, it can provide a video conferencing function for users to hold meetings and discuss solutions. This allows the decision support system to assist team-wide decision-making and lead to more effective solutions.

[0076] Decision support systems can also include a learning section. This section provides educational content for users to learn how to use the system and develop decision-making skills. For example, the learning section could provide tutorial videos explaining the system's functions and operation. It could also offer online courses for learning decision-making theory and practice. Furthermore, it could provide case studies for users to learn from past examples and apply that knowledge to real-world decision-making. This allows the decision support system to help users improve their skills and provide support for more effective decision-making.

[0077] The following briefly describes the processing flow for example form 1.

[0078] Step 1: The data collection department gathers information on past cases. For example, the department collects information on successful and unsuccessful cases of companies, and events with significant social impact. The data collection department can gather information from publicly available databases on the internet and internal company databases. They can also gather information through surveys and interviews. Step 2: The Management Department will create a database of the information collected by the Collection Department and manage it. The Management Department will save the collected information as digital data and register it in the database. The Management Department will optimize the database structure to enable quick information retrieval and provision. In addition, the Management Department will regularly back up the data to ensure data security. Step 3: The reception desk receives information about questions and tasks from users. The reception desk accepts questions and tasks in text format entered by users. It can also accept questions and tasks in multiple-choice format, as well as questions and tasks using voice input. Step 4: The search unit searches for cases related to the information received by the reception unit from the information managed by the administration unit. The search unit searches for related cases using keyword search. Search results can be narrowed down using filtering, and highly relevant cases can be displayed preferentially using ranking. Step 5: The service provider provides users with information based on the search results generated by the search unit. The service provider provides users with the search results in report format. The search results can also be displayed in dashboard format, or users can be notified of the search results.

[0079] (Example of form 2) The decision support system based on historical cases according to an embodiment of the present invention is a system that suggests the optimal direction based on past historical cases in response to challenges and events faced by companies. The decision support system based on historical cases first collects information on past cases and manages it in a database. Next, it receives information on questions and challenges from users and searches for cases related to that information. Based on the search results, it generates solutions and directions using generational AI and provides that information to the user. Furthermore, it explains why the generated solutions and directions are effective based on historical evidence. For example, the collection unit collects information such as success stories and failures of companies, and events with significant social impact. The management unit manages the collected information in a database. This enables the rapid provision of information that users need. When a user inputs information on a question or challenge, the reception unit receives that information. For example, a question such as "I want to know about successful cases regarding the market launch of a new product" may be entered. The information received by the reception unit is sent to the search unit to search for relevant cases from the database managed by the management unit. The search unit searches for cases related to the information received by the reception unit from the information managed by the management unit. For example, it searches for past successful cases regarding the market launch of a new product. Based on search results, the generation unit uses generational AI to generate solutions and directions. For example, it proposes successful strategies and methods for launching new products into the market. The delivery unit provides the information generated by the generation unit to the user. For example, it provides the user with successful case studies and strategies for launching new products into the market. Furthermore, the explanation unit explains why the generated solutions and directions are effective, based on historical evidence. For example, it explains why a particular strategy was effective based on past success stories. This system enables companies to make decisions with minimized risk based on evidence from historical cases. Consulting firms, educational institutions, and government agencies can also utilize this system to produce reliable proposals, educational materials, and policy formulations. In this way, a decision support system based on historical cases can suggest the optimal direction for addressing a company's challenges.

[0080] The decision support system according to this embodiment comprises a collection unit, a management unit, a reception unit, a search unit, and a provision unit. The collection unit collects information on past cases. For example, the collection unit collects information on successful and unsuccessful cases of companies, and events with significant social impact. For example, the collection unit can collect information from publicly available databases on the internet. The collection unit can also collect information from internal company databases. Furthermore, the collection unit can also collect information through surveys and interviews. The management unit databases and manages the information collected by the collection unit. For example, the management unit stores the collected information as digital data and registers it in the database. The management unit optimizes the database structure to enable quick information retrieval and provision. The management unit regularly backs up the data to ensure data security. The reception unit receives information on questions and issues from users. For example, the reception unit receives questions and issues in text format entered by users. The reception unit can also receive questions and issues in multiple-choice format. The reception unit can also receive questions and issues from users using voice input. The search unit searches for cases related to information received by the reception unit from the information managed by the management unit. The search unit can search for related cases using, for example, keyword search. The search unit can also narrow down the search results using filtering. The search unit can also prioritize displaying highly relevant cases using ranking. The provision unit provides information to the user based on the search results from the search unit. The provision unit can, for example, provide the search results to the user in report format. The provision unit can also display the search results in dashboard format. The provision unit can also notify the user of the search results in notification format. As a result, the decision support system according to the embodiment can suggest the optimal direction for a company's challenges based on past cases.

[0081] The data collection unit collects information on past cases. For example, it collects information on corporate successes and failures, and events with significant social impact. Specifically, the unit can collect information from publicly available databases on the internet, such as academic journal databases, industry reports, news articles, and government statistics. It can also collect information from internal corporate databases, including past project reports, customer feedback, sales data, and marketing campaign results. Furthermore, the unit can collect information through surveys and interviews. Surveys are conducted via online forms and email, while interviews are conducted in person or via video call. This allows the unit to gather a wide range of data from diverse sources, accumulating a rich foundation for decision support systems. To ensure the reliability and accuracy of the collected data, the unit implements a data verification process. For example, it verifies the source of data and cross-checks data from multiple sources. The unit also sets data collection and update frequencies to ensure that the latest information is always available. This allows the unit to efficiently collect reliable data and improve the overall accuracy and reliability of the system.

[0082] The management department manages the information collected by the collection department by creating a database. For example, the management department stores the collected information as digital data and registers it in the database. Specifically, the management department optimizes the database structure to enable quick information retrieval and provision. For example, the database is built using relational databases or NoSQL databases, and the appropriate data model is adopted depending on the type and use of the information. The management department ensures data security by regularly backing up the data. Backups are performed both on-site and off-site, enabling data recovery in the event of disasters or system failures. The management department also sets data access permissions to thoroughly protect confidential information. For example, different access levels are set for each user so that only necessary information can be viewed. Furthermore, the management department performs data quality control to maintain the consistency and accuracy of the collected information. For example, it implements processes to detect and correct data duplication and omissions. This allows the management department to manage the collected information efficiently and securely, improving the reliability and performance of the overall system.

[0083] The reception desk receives information about questions and issues from users. For example, the reception desk can receive questions and issues in text format entered by users. Specifically, the reception desk can receive input from users through web forms or chatbots. Users can freely enter questions and issues and attach detailed explanations and related information. The reception desk can also accept questions and issues in multiple-choice format. For example, users can easily submit questions and issues by selecting the appropriate item from predefined options. The reception desk can also receive questions and issues from users using voice input. Using speech recognition technology, the system converts the user's voice into text and inputs it. This improves user convenience and allows the reception desk to support diverse input methods. Furthermore, the reception desk has a function to automatically classify user input and distribute it to the appropriate department or person in charge. For example, using natural language processing technology, it analyzes the content of user questions and issues and extracts relevant keywords and categories. This allows the reception desk to efficiently process user input and enable a quick response.

[0084] The search unit searches for cases related to information received by the reception unit from information managed by the administration unit. For example, the search unit searches for related cases using keyword searches. Specifically, the search unit searches the database based on keywords entered by the user and extracts related cases. The search unit can also narrow down search results using filtering. For example, by narrowing down search results by a specific period, region, or industry, it can quickly provide the information the user is looking for. The search unit can also prioritize displaying highly relevant cases using rankings. For example, it can sort search results in order of relevance and prioritize displaying the information the user needs most. Furthermore, the search unit can improve the accuracy of search results using AI. For example, it can use machine learning algorithms to analyze the user's search history and behavior patterns and provide search results that are optimal for each individual user. In this way, the search unit can provide highly accurate search results that meet the user's needs and maximize the effectiveness of the decision support system.

[0085] The service provider provides users with information based on the search results generated by the search unit. For example, the service provider can provide users with search results in report format. Specifically, the service provider organizes the search results and creates reports in a visually easy-to-understand format. The reports include detailed information on related cases, statistical data, graphs, and charts. The service provider can also display search results in dashboard format. For example, it can provide an interactive dashboard so that users can view search results in real time. The dashboard displays an overview of the search results and key metrics, allowing users to quickly grasp the information they need. The service provider can also notify users of search results in notification format. For example, it can notify users of search results via email, SMS, or push notifications. This allows users to respond quickly without missing important information. Furthermore, the service provider can collect user feedback and continuously improve the quality of the information it provides. For example, when users leave ratings and comments on the information provided, the service provider can gain valuable insights to improve the accuracy and usefulness of the information. This allows the service provider to provide users with high-quality information and maximize the effectiveness of the decision support system.

[0086] The search unit includes a generation unit that generates information indicating solutions or directions based on the search results using a generation AI. The generation unit generates information based on the search results from the search unit using a generation AI. For example, the generation unit generates solutions and directions using natural language generation technology. The generation unit can also generate visual solutions using image generation technology. The generation unit can also generate solutions in audio format using speech generation technology. The generation unit generates specific solutions to the user's questions and problems using a generation AI. For example, in response to the user's question, "I want to know about successful cases regarding the market launch of a new product," the generation unit proposes a specific strategy based on past success stories. The generation unit automates the generation of solutions and directions using a generation AI. This allows the generation unit to generate solutions and directions quickly and efficiently. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate solutions and directions using an AI model that takes the search results from the search unit as input and outputs solutions and directions. This allows the generation unit to provide optimal solutions and directions to the user's questions and problems.

[0087] The generation unit includes an explanation unit that explains the generated solutions or directions. The explanation unit explains why the solutions or directions generated by the generation unit are effective. The explanation unit provides explanations in, for example, text format. The explanation unit can also provide explanations in video format. The explanation unit can also provide explanations visually using infographics. The explanation unit automates the explanation of solutions and directions using generation AI. For example, the explanation unit uses generation AI to explain why a strategy was effective based on past success stories. The explanation unit uses generation AI to explain the background of solutions and directions for user questions and problems. This allows the explanation unit to deepen the user's understanding. Some or all of the above processing in the explanation unit may be performed using, for example, AI, or not using AI. For example, the explanation unit can take the solutions or directions generated by the generation unit as input and provide explanations using an AI model that explains their background and effectiveness. This allows the explanation unit to provide reliable explanations to users.

[0088] The data collection unit can collect specific information on corporate success stories, failures, and events with significant social impact. For example, the unit can collect corporate success stories and failures. As success stories, the unit can collect examples such as increased sales and expanded market share. As failure stories, the unit can collect examples such as project failures and market withdrawals. As events with significant social impact, the unit can collect examples such as legal reforms, disasters, and social movements. The unit can collect information from publicly available databases on the internet, for example. The unit can also collect information from internal corporate databases. The unit can also collect information through surveys and interviews. This allows the unit to cover a wide range of cases. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when collecting information from publicly available databases on the internet, the unit can use AI to automatically extract relevant information. This allows the unit to collect information efficiently.

[0089] The management department can manage the collected information by creating a database. For example, the management department can store the collected information as digital data and register it in the database. The management department can optimize the database structure to enable quick retrieval and provision of information. The management department can regularly back up the data to ensure data security. The management department can eliminate data duplication and perform efficient data management. The management department can adjust the frequency of data updates to always maintain the latest information. The management department can review the data classification method to enable efficient data retrieval. As a result, the management department can efficiently manage the collected information and quickly provide users with the information they need. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, when eliminating data duplication, the management department can use AI to automatically detect and delete duplicate data. As a result, the management department can manage data efficiently.

[0090] The reception desk can receive information about specific questions or tasks from users. For example, the reception desk can receive questions or tasks in text format entered by the user. The reception desk can also receive questions or tasks in multiple-choice format. The reception desk can also receive questions or tasks from users using voice input. The reception desk can estimate the user's emotions and adjust the way questions or tasks are received based on the estimated emotions. For example, if the user is feeling anxious, a simple and intuitive interface is provided. If the user is excited, detailed input options are provided. If the user is tired, voice input is prioritized to quickly receive questions or tasks. The reception desk can refer to the user's past question history and select the optimal reception method. For example, it may prioritize providing question formats that the user has frequently used in the past. It may analyze specific patterns from the user's past question history and suggest the optimal reception method. It may prioritize providing input methods (voice, text, etc.) that the user has used in the past. This allows the reception desk to provide information that meets the user's needs. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the reception desk to provide the most appropriate reception service based on the user's emotions.

[0091] The search unit can search for cases related to information received by the reception unit from information managed by the administration unit. The search unit can search for relevant cases using, for example, keyword searches. The search unit can also narrow down search results using filtering. The search unit can also prioritize displaying highly relevant cases using rankings. The search unit can estimate the user's emotions and adjust how search results are displayed based on the estimated user emotions. For example, if the user is feeling anxious, it will prioritize displaying cases that provide reassurance. If the user is excited, it will prioritize displaying challenging cases. If the user is tired, it will prioritize displaying cases that are easy to implement. The search unit can evaluate the relevance of cases and prioritize displaying highly relevant information. For example, it will prioritize displaying cases that are directly related to the current problem. It will prioritize displaying cases that are related to the same industry or market. It will prioritize displaying cases that are related to companies of similar size. This allows the search unit to provide appropriate cases for the user's questions and problems. Some or all of the above processing in the search unit may be performed using, for example, AI, or not using AI. For example, when performing a keyword search, the search unit can use AI to automatically extract relevant keywords and display the search results. This allows the search unit to efficiently find relevant cases.

[0092] The delivery unit can provide the user with information generated by the generation unit. For example, the delivery unit can provide the user with search results in report format. The delivery unit can also display search results in dashboard format. The delivery unit can also notify the user of search results in notification format. The delivery unit can estimate the user's emotions and adjust the format of the information provided based on the estimated emotions. For example, if the user is feeling anxious, the information can be provided in a reassuring format. If the user is excited, the information can be provided in a challenging format. If the user is tired, the information can be provided in a simple and visually easy-to-understand format. The delivery unit can refer to the user's past usage history and select the optimal method of information delivery. For example, it can prioritize providing information in formats that the user has frequently used in the past. It can analyze specific patterns from the user's past usage history and suggest the optimal method of information delivery. It can provide information in a format optimized for the devices and platforms the user has used in the past. This allows the delivery unit to quickly obtain the information the user needs. Some or all of the above processing in the delivery unit may be performed using AI, for example, or not using AI. For example, when the service provider estimates a user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the service provider to provide the most appropriate information based on the user's emotions.

[0093] The explanatory section can explain why the generated solutions and directions are effective, based on historical evidence. The explanatory section can provide explanations in, for example, text format. The explanatory section can also provide explanations in video format. The explanatory section can also provide explanations visually using infographics. The explanatory section can automate the explanation of solutions and directions using generative AI. For example, the explanatory section can use generative AI to explain why a strategy was effective based on past success stories. The explanatory section can use generative AI to explain the background of solutions and directions for user questions and problems. This allows the explanatory section to deepen the user's understanding. Some or all of the above processing in the explanatory section may be performed using, for example, AI, or not using AI. For example, the explanatory section can take the solutions and directions generated by the generative section as input and provide explanations using an AI model that explains their background and effectiveness. This allows the explanatory section to provide users with reliable explanations.

[0094] The data collection unit can estimate the user's emotions and determine the priority of specific examples to collect based on the estimated user emotions. For example, if the user is feeling anxious, the data collection unit will prioritize collecting successful examples that provide a sense of security. If the user is excited, the data collection unit will prioritize collecting challenging examples. If the user is tired, the data collection unit will prioritize collecting easy and actionable examples. The data collection unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generative AI. For example, the data collection unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The data collection unit can also record the user's voice and estimate their emotions using voice analysis technology. The data collection unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the data collection unit to determine the priority of examples to collect based on the user's emotions. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, when the data collection unit estimates a user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the data collection unit to collect the most relevant examples based on the user's emotions.

[0095] The data collection unit can evaluate the reliability of cases during collection and prioritize the collection of reliable information. For example, the unit will prioritize the collection of cases if the source of the case is a reliable academic paper or official report. The unit will prioritize the collection of cases if the case has been verified by multiple reliable sources. The unit will prioritize the collection of cases if the provider of the case is an expert or industry leader. The unit evaluates the reliability of cases and prioritizes the collection of reliable information. This allows the unit to improve the reliability of the information it provides. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when evaluating the reliability of cases, the unit can use AI to analyze the data source and verification method and calculate a reliability score. This allows the unit to efficiently collect reliable information.

[0096] The data collection unit can adjust its collection scope considering the timing and location of each incident. For example, it prioritizes collecting recent incidents. If an incident occurs in a specific region, it also collects other incidents related to that region. If incidents occur in a concentrated period, it also collects other incidents related to that period. The data collection unit adjusts its collection scope considering the timing and location of each incident. This allows the data collection unit to collect more relevant incidents. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, when analyzing the timing and location of an incident, the data collection unit can use AI to analyze timestamps and geographic information systems (GIS) to adjust the collection scope. This allows the data collection unit to efficiently collect more relevant incidents.

[0097] The data collection unit can estimate the user's emotions and select categories of cases to collect based on the estimated user emotions. For example, if the user is feeling anxious, the data collection unit will select categories of successful cases that provide a sense of security. If the user is excited, the data collection unit will select categories of challenging cases. If the user is tired, the data collection unit will select categories of easy and actionable cases. The data collection unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generative AI. For example, the data collection unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The data collection unit can also record the user's voice and estimate their emotions using voice analysis technology. The data collection unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the data collection unit to select categories of cases to collect based on the user's emotions. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, when estimating a user's emotions, the data collection unit can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the data collection unit to select the most appropriate category of cases based on the user's emotions.

[0098] The data collection unit can evaluate the relevance of cases during collection and prioritize the collection of highly relevant information. For example, the data collection unit will prioritize collecting cases that are directly related to current issues. The data collection unit will prioritize collecting cases that are related to the same industry or market. The data collection unit will prioritize collecting cases that are related to companies of similar size. The data collection unit evaluates the relevance of cases and prioritizes the collection of highly relevant information. This allows the data collection unit to improve the relevance of the information it provides. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, when evaluating the relevance of cases, the data collection unit can use AI to perform co-occurrence network and correlation analysis and calculate relevance scores. This allows the data collection unit to efficiently collect highly relevant information.

[0099] The data collection unit can adjust the content of its collections by considering the background and scope of impact of each case. For example, the collection unit prioritizes collecting cases where the background is similar to the current situation. The collection unit also prioritizes collecting cases where the scope of impact is widespread. If the background of a case is related to a specific policy or economic situation, the collection unit will also collect other cases related to that background. The collection unit adjusts the content of its collections by considering the background and scope of impact of each case. This allows the collection unit to collect more relevant cases. Some or all of the above processing in the collection unit may be performed using AI, for example, or not. For example, when analyzing the background and scope of impact of a case, the collection unit can use AI to conduct background research and impact analysis and adjust the content of its collections. This allows the collection unit to efficiently collect more relevant cases.

[0100] The management unit can estimate the user's emotions and optimize the database structure based on the estimated user emotions. For example, if the user is feeling anxious, the management unit can optimize the structure to prioritize displaying reassuring examples. If the user is excited, the management unit can optimize the structure to prioritize displaying challenging examples. If the user is tired, the management unit can optimize the structure to prioritize displaying simple and easy-to-execute examples. The management unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generative AI. For example, the management unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The management unit can also record the user's voice and estimate their emotions using voice analysis technology. The management unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the management unit to optimize the database structure based on the user's emotions. Some or all of the above processing in the management unit may be performed using AI, for example, or without AI. For example, when the management department needs to estimate a user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the management department to provide an optimal database structure based on the user's emotions.

[0101] The management department can adjust the frequency of data updates during management to always maintain the latest information. For example, the management department can immediately update the database when a significant event occurs. The management department can periodically check the database and update outdated information. The management department can update the database as needed based on user feedback. The management department adjusts the frequency of data updates to always maintain the latest information. This allows the management department to always provide the latest information. Some or all of the above processes in the management department may be performed using AI, for example, or not. For example, when adjusting the frequency of data updates, the management department can use AI to analyze the importance and update frequency of the data and determine the optimal update schedule. This allows the management department to efficiently provide the latest information.

[0102] The management department can eliminate data duplication during management and perform efficient data management. For example, if the same case is collected from multiple sources, the management department will eliminate duplication and manage it as a single case. The management department will periodically check for and delete duplicate data in the database. The management department will perform duplicate checks during collection to prevent data duplication. The management department will eliminate data duplication and perform efficient data management. This will enable the management department to quickly search for and provide data. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, when eliminating data duplication, the management department can use AI to automatically detect and delete duplicate data. This will enable the management department to manage data efficiently.

[0103] The management unit can estimate the user's emotions and set data access permissions based on the estimated user emotions. For example, if the user is feeling anxious, the management unit will prioritize access to reassuring examples. If the user is excited, the management unit will prioritize access to challenging examples. If the user is tired, the management unit will prioritize access to simple and easy-to-execute examples. The management unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generative AI. For example, the management unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The management unit can also record the user's voice and estimate their emotions using voice analysis technology. The management unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the management unit to set data access permissions based on the user's emotions. Some or all of the above processing in the management unit may be performed using AI, for example, or without AI. For example, when the management department needs to estimate a user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the management department to provide optimal access permissions based on the user's emotions.

[0104] The management department can ensure data security by regularly backing up data during management. For example, the management department can back up the database regularly on a daily basis. The management department can immediately back up data when important data is added. The management department can ensure data security by storing data backups in multiple locations. The management department can ensure data security by regularly backing up data. In this way, the management department can ensure data security. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, when backing up data, the management department can use AI to optimize the backup schedule and perform backups efficiently. In this way, the management department can ensure data security efficiently.

[0105] The management department can review data classification methods during management to enable efficient data retrieval. For example, the management department can periodically review data categories and classify them based on the latest information. The management department can improve data classification methods based on user feedback. The management department can utilize tagging and metadata to improve data retrieval efficiency. The management department can review data classification methods to enable efficient data retrieval. This allows the management department to efficiently search for data. Some or all of the above processes in the management department may be performed using AI, for example, or not. For example, when reviewing data classification methods, the management department can use AI to automatically generate and classify data categories and tags. This allows the management department to manage data efficiently.

[0106] The reception desk can estimate the user's emotions and adjust how questions and tasks are handled based on the estimated emotions. For example, if the user is feeling anxious, the reception desk provides a simple and intuitive interface. If the user is excited, the reception desk provides detailed input options. If the user is tired, the reception desk prioritizes voice input and quickly handles questions and tasks. The reception desk estimates the user's emotions using emotion estimation capabilities, such as an emotion engine or generative AI. For example, the reception desk can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The reception desk can also record the user's voice and estimate their emotions using voice analysis technology. The reception desk can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the reception desk to adjust how questions and tasks are handled based on the user's emotions. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the reception desk to provide the most appropriate reception service based on the user's emotions.

[0107] The reception desk can refer to the user's past question history and select the most suitable reception method at the time of reception. For example, the reception desk may prioritize providing question formats that the user has frequently used in the past. The reception desk may analyze specific patterns from the user's past question history and propose the most suitable reception method. The reception desk may prioritize providing input methods (voice, text, etc.) that the user has used in the past. The reception desk refers to the user's past question history and selects the most suitable reception method at the time of reception. This enables the reception desk to provide information that meets the user's needs. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, when analyzing the user's past question history, the reception desk may use AI to perform database lookups and log analysis to select the most suitable reception method. This enables the reception desk to efficiently provide information that meets the user's needs.

[0108] The reception desk can prioritize questions based on the user's industry and job duties at the time of reception. For example, if the user belongs to a specific industry, the reception desk will prioritize questions related to that industry. The reception desk will also prioritize questions related to the user's job duties. Based on the user's industry and job duties, the reception desk will prioritize displaying specific question categories. The reception desk prioritizes questions based on the user's industry and job duties at the time of reception. This allows the reception desk to receive questions more appropriately. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, when analyzing the user's industry and job duties, the reception desk can use AI to generate industry codes and job classifications and determine question priorities. This allows the reception desk to efficiently receive questions that meet the user's needs.

[0109] The reception desk can estimate the user's emotions and adjust the time it takes to answer questions based on the estimated emotions. For example, if the user is feeling anxious, the reception desk will answer questions quickly. If the user is excited, the reception desk will extend the time it takes to answer detailed questions. If the user is tired, the reception desk will answer questions for a short time. The reception desk estimates the user's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the reception desk can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The reception desk can also record the user's voice and estimate the emotion using voice analysis technology. The reception desk can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. This allows the reception desk to adjust the time it takes to answer questions based on the user's emotions. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the reception desk to provide the optimal reception time based on the user's emotions.

[0110] The reception desk can select the optimal reception method at the time of reception, taking into account the user's geographical location information. For example, if the user is in a specific region, the reception desk will prioritize receiving questions related to that region. The reception desk will propose the optimal reception method based on the user's geographical location information. If the user is on the move, the reception desk will update the location information in real time and provide the optimal reception method. The reception desk selects the optimal reception method at the time of reception, taking into account the user's geographical location information. This allows the reception desk to select a more appropriate reception method. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, when analyzing the user's geographical location information, the reception desk can use AI to analyze GPS data and IP addresses to select the optimal reception method. This allows the reception desk to efficiently provide reception methods that meet the user's needs.

[0111] The reception desk can select the optimal reception method at the time of reception, taking into account the user's device information. For example, if the user is using a smartphone, the reception desk provides a mobile-friendly interface. If the user is using a tablet, the reception desk provides an interface optimized for a larger screen. If the user is using a desktop, the reception desk provides detailed input options. The reception desk selects the optimal reception method at the time of reception, taking into account the user's device information. This allows the reception desk to select a more appropriate reception method. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, when analyzing the user's device information, the reception desk can use AI to analyze the device ID and browser information and select the optimal reception method. This allows the reception desk to efficiently provide a reception method that meets the user's needs.

[0112] The search unit can estimate the user's emotions and adjust how search results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the search unit will prioritize displaying reassuring examples. If the user is excited, the search unit will prioritize displaying challenging examples. If the user is tired, the search unit will prioritize displaying easy and actionable examples. The search unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generative AI. For example, the search unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The search unit can also record the user's voice and estimate their emotions using voice analysis technology. The search unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the search unit to adjust how search results are displayed based on the user's emotions. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, when the search unit estimates a user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the search unit to provide the most appropriate display method for search results based on the user's emotions.

[0113] The search unit can evaluate the relevance of case studies during a search and prioritize displaying highly relevant information. For example, the search unit prioritizes displaying case studies that are directly related to the current issue. The search unit prioritizes displaying case studies that are related to the same industry or market. The search unit prioritizes displaying case studies that are related to companies of similar size. The search unit evaluates the relevance of case studies and prioritizes displaying highly relevant information. This allows the search unit to improve the relevance of the information it provides. Some or all of the above processing in the search unit may be performed using AI, for example, or not using AI. For example, when evaluating the relevance of case studies, the search unit can use AI to perform co-occurrence network and correlation analysis and calculate a relevance score. This allows the search unit to efficiently provide highly relevant information.

[0114] The search unit can adjust its search scope when performing a search, taking into account the timing and location of the incidents. For example, the search unit prioritizes displaying incidents that have occurred recently. If an incident occurred in a specific region, the search unit also displays other incidents related to that region. If incidents occurred in a concentrated period, the search unit also displays other incidents related to that period. The search unit adjusts its search scope considering the timing and location of the incidents. This allows the search unit to provide more relevant information. Some or all of the above processing in the search unit may be performed using AI, for example, or not. For example, when analyzing the timing and location of incidents, the search unit can use AI to analyze timestamps and geographic information systems (GIS) and adjust the search scope. This allows the search unit to efficiently provide more relevant information.

[0115] The search unit can estimate the user's emotions and prioritize search results based on the estimated emotions. For example, if the user is feeling anxious, the search unit will prioritize displaying reassuring results. If the user is excited, the search unit will prioritize displaying challenging results. If the user is tired, the search unit will prioritize displaying easy and actionable results. The search unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generative AI. For example, the search unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The search unit can also record the user's voice and estimate their emotions using voice analysis technology. The search unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the search unit to prioritize search results based on the user's emotions. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, when the search unit estimates a user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the search unit to provide the optimal priority of search results based on the user's emotions.

[0116] The search function can evaluate the reliability of cases during a search and prioritize displaying highly reliable information. For example, the search function prioritizes cases whose source is a reliable academic paper or official report. The search function prioritizes cases that have been verified by multiple reliable sources. The search function prioritizes cases where the provider is an expert or industry leader. The search function evaluates the reliability of cases and prioritizes displaying highly reliable information. This allows the search function to improve the reliability of the information it provides. Some or all of the above processing in the search function may be performed using AI, for example, or not using AI. For example, when evaluating the reliability of cases, the search function can use AI to analyze the data source and verification method and calculate a reliability score. This allows the search function to efficiently provide highly reliable information.

[0117] The search function can adjust the search results when a case occurs, taking into account its background and scope of impact. For example, the search function prioritizes displaying cases where the background is similar to the current situation. The search function also prioritizes displaying cases where the scope of impact is widespread. If the background of a case is related to a specific policy or economic situation, the search function also displays other cases related to that background. The search function adjusts the search results by considering the background and scope of impact of each case. This allows the search function to provide more relevant information. Some or all of the above processing in the search function may be performed using AI, for example, or not. For example, when analyzing the background and scope of impact of a case, the search function can use AI to conduct background research and impact analysis and adjust the search results. This allows the search function to efficiently provide more relevant information.

[0118] The service provider can estimate the user's emotions and adjust the format of the information it provides based on the estimated emotions. For example, if the user is feeling anxious, the service provider will provide information in a reassuring format. If the user is excited, the service provider will provide information in a challenging format. If the user is tired, the service provider will provide information in a simple and visually easy-to-understand format. The service provider estimates the user's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the service provider can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The service provider can also record the user's voice and estimate their emotions using voice analysis technology. The service provider can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the service provider to adjust the format of the information it provides based on the user's emotions. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, when the service provider estimates a user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the service provider to provide the most appropriate information format based on the user's emotions.

[0119] The information provider can refer to the user's past usage history when providing information and select the most suitable method of information delivery. For example, the information provider may prioritize providing information in formats that the user has frequently used in the past. The information provider may analyze specific patterns from the user's past usage history and propose the most suitable method of information delivery. The information provider may provide information in a format optimized for the devices and platforms the user has used in the past. The information provider refers to the user's past usage history when providing information and selects the most suitable method of information delivery. This enables the information provider to provide information that meets the user's needs. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, when analyzing the user's past usage history, the information provider may use AI to perform database referencing and log analysis to select the most suitable method of information delivery. This enables the information provider to efficiently provide information that meets the user's needs.

[0120] The information delivery unit can prioritize information based on the user's industry and job duties at the time of delivery. For example, if a user belongs to a specific industry, the information delivery unit will prioritize providing information related to that industry. The information delivery unit will prioritize providing information related to the user's job duties. The information delivery unit will prioritize displaying specific information categories based on the user's industry and job duties. The information delivery unit prioritizes information based on the user's industry and job duties at the time of delivery. This enables the information delivery unit to provide more appropriate information. Some or all of the above processing in the information delivery unit may be performed using AI, for example, or not using AI. For example, when analyzing a user's industry and job duties, the information delivery unit can use AI to perform industry codes and job classifications and determine information priorities. This enables the information delivery unit to efficiently provide information that meets the user's needs.

[0121] The information provider can estimate the user's emotions and adjust the timing of information delivery based on the estimated emotions. For example, if the user is feeling anxious, the information provider will provide information quickly. If the user is excited, the information provider will extend the time it takes to provide detailed information. If the user is tired, the information provider will provide information in a short amount of time. The information provider estimates the user's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the information provider can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The information provider can also record the user's voice and estimate their emotions using voice analysis technology. The information provider can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the information provider to adjust the timing of information delivery based on the user's emotions. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, when estimating the user's emotions, the information provider can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the service provider to deliver information at the optimal timing based on the user's emotions.

[0122] The information provider can select the optimal information delivery method by considering the user's geographical location information at the time of delivery. For example, if the user is in a specific region, the information provider will prioritize providing information related to that region. The information provider will propose the optimal information delivery method based on the user's geographical location information. If the user is on the move, the information provider will update the location information in real time and provide the optimal information delivery method. The information provider selects the optimal information delivery method by considering the user's geographical location information at the time of delivery. This allows the information provider to select a more appropriate information delivery method. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, when analyzing the user's geographical location information, the information provider can use AI to analyze GPS data and IP addresses and select the optimal information delivery method. This allows the information provider to efficiently provide information delivery methods that meet the user's needs.

[0123] The information provider can select the optimal information delivery method at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the information provider will provide information in a mobile-friendly format. If the user is using a tablet, the information provider will provide information in a format optimized for a larger screen. If the user is using a desktop, the information provider will provide detailed information. The information provider selects the optimal information delivery method at the time of delivery, taking into account the user's device information. This allows the information provider to select a more appropriate information delivery method. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, when analyzing the user's device information, the information provider can use AI to analyze the device ID and browser information and select the optimal information delivery method. This allows the information provider to efficiently provide information delivery methods that meet the user's needs.

[0124] The generation unit can estimate the user's emotions and determine the priority of the solutions to generate based on the estimated user emotions. For example, if the user is feeling anxious, the generation unit will prioritize generating solutions that provide a sense of security. If the user is excited, the generation unit will prioritize generating challenging solutions. If the user is tired, the generation unit will prioritize generating simple and easy-to-implement solutions. The generation unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generation AI. For example, the generation unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. The generation unit can also record the user's voice and estimate emotions using voice analysis technology. The generation unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. This allows the generation unit to determine the priority of the solutions to generate based on the user's emotions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, when estimating a user's emotions, the generation unit can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the generation unit to prioritize the optimal solution based on the user's emotions.

[0125] The generation unit can evaluate the relevance of case studies during generation and prioritize the generation of highly relevant solutions. For example, the generation unit prioritizes generating solutions if a case study is directly related to the current problem. The generation unit prioritizes generating solutions if a case study is related to the same industry or market. The generation unit prioritizes generating solutions if a case study is related to companies of similar size. The generation unit evaluates the relevance of case studies and prioritizes the generation of highly relevant solutions. This allows the generation unit to improve the relevance of the solutions it provides. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, when evaluating the relevance of case studies, the generation unit can use AI to perform co-occurrence network and correlation analysis and calculate relevance scores. This allows the generation unit to efficiently provide highly relevant solutions.

[0126] The generation unit can adjust the generated content during generation, taking into account the timing and location of the incident. For example, if the incident is recent, the generation unit will prioritize generating solutions. If the incident occurred in a specific region, the generation unit will generate solutions while also considering other incidents related to that region. If the incidents occurred in a concentrated period, the generation unit will generate solutions while also considering other incidents related to that period. The generation unit adjusts the generated content, taking into account the timing and location of the incidents. This allows the generation unit to provide more relevant solutions. Some or all of the above processing in the generation unit may be performed using AI, for example, or not. For example, when analyzing the timing and location of an incident, the generation unit can use AI to analyze timestamps and geographic information systems (GIS) and adjust the generated content. This allows the generation unit to efficiently provide more relevant solutions.

[0127] The generation unit can estimate the user's emotions and adjust the format of the solutions it generates based on the estimated user emotions. For example, if the user is feeling anxious, the generation unit will generate a solution in a reassuring format. If the user is excited, the generation unit will generate a solution in a challenging format. If the user is tired, the generation unit will generate a solution in a simple and visually easy-to-understand format. The generation unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generation AI. For example, the generation unit can capture the user's facial expressions with a camera and estimate emotions using an emotion estimation algorithm. The generation unit can also record the user's voice and estimate emotions using voice analysis technology. The generation unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. This allows the generation unit to adjust the format of the solutions it generates based on the user's emotions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, when estimating a user's emotions, the generation unit can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the generation unit to provide the optimal solution format based on the user's emotions.

[0128] The generation unit can evaluate the reliability of cases during generation and prioritize the generation of highly reliable solutions. For example, the generation unit will prioritize generating solutions if the source of a case is a reliable academic paper or official report. The generation unit will prioritize generating solutions if the case has been verified by multiple reliable sources. The generation unit will prioritize generating solutions if the provider of the case is an expert or industry leader. The generation unit evaluates the reliability of cases and prioritizes the generation of highly reliable solutions. This allows the generation unit to improve the reliability of the solutions it provides. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, when evaluating the reliability of a case, the generation unit can use AI to analyze the data source and verification method and calculate a reliability score. This allows the generation unit to efficiently provide highly reliable solutions.

[0129] The generation unit can adjust the generated content by considering the background and scope of impact of a case during the generation process. For example, the generation unit will prioritize generating solutions if the background of a case is similar to the current situation. The generation unit will also prioritize generating solutions if the scope of impact of a case is widespread. If the background of a case is related to a specific policy or economic situation, the generation unit will consider other cases related to that background when generating solutions. The generation unit adjusts the generated content by considering the background and scope of impact of a case. This allows the generation unit to provide more relevant solutions. Some or all of the above processing in the generation unit may be performed using AI, for example, or not. For example, when analyzing the background and scope of impact of a case, the generation unit can use AI to conduct background research and impact analysis and adjust the generated content. This allows the generation unit to efficiently provide more relevant solutions.

[0130] The commentary unit can estimate the user's emotions and adjust the way it presents its commentary based on those emotions. For example, if the user is feeling anxious, the commentary unit will present the commentary in a reassuring way. If the user is excited, the commentary unit will present the commentary in a challenging way. If the user is tired, the commentary unit will present the commentary in a simple and visually easy-to-understand way. The commentary unit estimates the user's emotions using an emotion estimation function, such as an emotion engine or generative AI. For example, the commentary unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The commentary unit can also record the user's voice and estimate their emotions using voice analysis technology. The commentary unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the commentary unit to adjust the way it presents its commentary based on the user's emotions. Some or all of the above-described processes in the commentary unit may be performed using AI, for example, or without AI. For example, when the commentary unit estimates the user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the commentary unit to provide the most appropriate commentary based on the user's emotions.

[0131] The commentary section can evaluate the relevance of case studies during commentary and prioritize providing commentaries that are highly relevant. For example, the commentary section will prioritize providing commentaries if the case study is directly related to current issues. The commentary section will prioritize providing commentaries if the case study is related to the same industry or market. The commentary section will prioritize providing commentaries if the case study is related to companies of similar size. The commentary section evaluates the relevance of case studies and prioritizes providing commentaries that are highly relevant. This allows the commentary section to improve the relevance of the commentaries it provides. Some or all of the above processing in the commentary section may be performed using AI, for example, or not using AI. For example, when evaluating the relevance of case studies, the commentary section may use AI to perform co-occurrence network and correlation analysis and calculate relevance scores. This allows the commentary section to efficiently provide highly relevant commentaries.

[0132] The commentary section can adjust its commentary content by considering the timing and location of the incident. For example, if the incident occurred recently, the commentary section will prioritize providing a commentary. If the incident occurred in a specific region, the commentary section will also consider other incidents related to that region when providing a commentary. If the incidents occurred in a concentrated period of time, the commentary section will also consider other incidents related to that period when providing a commentary. The commentary section adjusts its commentary content by considering the timing and location of the incident. This allows the commentary section to provide a more relevant commentary. Some or all of the above processing in the commentary section may be performed using AI, for example, or not using AI. For example, when analyzing the timing and location of an incident, the commentary section can use AI to analyze timestamps and geographic information systems (GIS) and adjust the commentary content. This allows the commentary section to efficiently provide a more relevant commentary.

[0133] The commentary unit can estimate the user's emotions and adjust the length of the commentary based on the estimated emotions. For example, if the user is feeling anxious, the commentary unit will provide a short, concise commentary. If the user is excited, the commentary unit will provide a detailed commentary. If the user is tired, the commentary unit will provide a concise, visually easy-to-understand commentary. The commentary unit estimates the user's emotions using emotion estimation functions, such as an emotion engine or generative AI. For example, the commentary unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The commentary unit can also record the user's voice and estimate their emotions using voice analysis technology. The commentary unit can also collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the commentary unit to adjust the length of the commentary based on the user's emotions. Some or all of the above processing in the commentary unit may be performed using AI, for example, or without AI. For example, when the commentary section estimates the user's emotions, it can use AI to analyze the user's facial expressions and voice data to estimate their emotions. This allows the commentary section to provide an optimal length of commentary based on the user's emotions.

[0134] The commentary section can evaluate the reliability of a case when providing commentary and prioritize providing reliable commentary. For example, the commentary section will prioritize providing commentary if the source of the case is a reliable academic paper or official report. The commentary section will prioritize providing commentary if the case has been verified from multiple reliable sources. The commentary section will prioritize providing commentary if the provider of the case is an expert or industry leader. The commentary section evaluates the reliability of a case and prioritizes providing reliable commentary. This allows the commentary section to improve the reliability of the commentary it provides. Some or all of the above processing in the commentary section may be performed using AI, for example, or not using AI. For example, when evaluating the reliability of a case, the commentary section may use AI to analyze the data source and verification method and calculate a reliability score. This allows the commentary section to efficiently provide reliable commentary.

[0135] The commentary section can adjust its commentary content when providing commentary, taking into account the background and scope of impact of a case. For example, the commentary section will prioritize providing commentary when the background of a case is similar to the current situation. The commentary section will prioritize providing commentary when the scope of impact of a case is wide-ranging. If the background of a case is related to a specific policy or economic situation, the commentary section will also consider other cases related to that background when providing commentary. The commentary section adjusts its commentary content by taking into account the background and scope of impact of a case. This allows the commentary section to provide more relevant commentary. Some or all of the above processing in the commentary section may be performed using AI, for example, or not. For example, when analyzing the background and scope of impact of a case, the commentary section can use AI to conduct background research and impact analysis and adjust the commentary content. This allows the commentary section to efficiently provide more relevant commentary.

[0136] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0137] Decision support systems can also include a predictive unit. This unit predicts future trends and risks based on collected data. For example, it can analyze past case data to predict future trends in a specific industry or market. It can also use AI to extract patterns from collected data and identify future risks and opportunities. The predictive unit can present future scenarios in response to user questions and challenges, providing information to aid in decision-making. This allows decision support systems to assist in decision-making not only based on past cases but also on future predictions.

[0138] The decision support system can also include a feedback unit. The feedback unit collects the results after the user implements the provided solutions or directions and feeds them back into the system. For example, the feedback unit can collect data on the success or failure of strategies implemented by the user and add it to the system's database. Based on user feedback, the feedback unit can improve the system's algorithms and provide more accurate solutions. The feedback unit can also collect user satisfaction and areas for improvement, enhancing the system's user experience. This allows the decision support system to continuously improve and provide more effective assistance.

[0139] The decision support system can also include a simulation unit. The simulation unit provides the ability for users to test proposed solutions in a virtual environment. For example, the simulation unit can allow users to test a new product launch strategy in a virtual market. The simulation unit can assist users in comparing different strategies and selecting the optimal one. The simulation unit can also use AI to generate scenarios in the virtual environment in real time and provide feedback to the user. This allows the decision support system to verify strategies before taking actual action, minimizing risk.

[0140] Decision support systems can also include a collaboration section. This section provides functions for multiple users to make decisions collaboratively. For example, the collaboration section can provide a chat function for users to exchange opinions in real time and jointly consider solutions. It can also provide a co-editing function for users to collaboratively edit documents and consolidate solutions. Furthermore, it can provide a video conferencing function for users to hold meetings and discuss solutions. This allows the decision support system to assist team-wide decision-making and lead to more effective solutions.

[0141] Decision support systems can also include a learning section. This section provides educational content for users to learn how to use the system and develop decision-making skills. For example, the learning section could provide tutorial videos explaining the system's functions and operation. It could also offer online courses for learning decision-making theory and practice. Furthermore, it could provide case studies for users to learn from past examples and apply that knowledge to real-world decision-making. This allows the decision support system to help users improve their skills and provide support for more effective decision-making.

[0142] The decision support system can further customize solutions based on the user's emotions using emotion estimation functionality. For example, if the user is feeling anxious, the generation unit can prioritize generating solutions that provide a sense of security. If the user is excited, the generation unit can prioritize generating challenging solutions. If the user is tired, the generation unit can prioritize generating simple and easy-to-implement solutions. The emotion estimation function can estimate emotions in real time by analyzing the user's facial expressions and voice data. This allows the decision support system to provide the optimal solution tailored to the user's emotions.

[0143] The decision support system can further adjust how information is delivered based on the user's emotions using an emotion estimation function. For example, if the user is feeling anxious, the system can deliver information in a reassuring format. If the user is excited, the system can deliver information in a challenging format. If the user is tired, the system can deliver information in a simple and visually easy-to-understand format. The emotion estimation function can analyze the user's facial expressions and voice data to estimate emotions in real time. This allows the decision support system to provide the most appropriate information delivery method according to the user's emotions.

[0144] The decision support system can further use emotion estimation to adjust how search results are displayed based on the user's emotions. For example, if the user is feeling anxious, the search unit can prioritize displaying reassuring examples. If the user is excited, the search unit can prioritize displaying challenging examples. If the user is tired, the search unit can prioritize displaying simple and easy-to-implement examples. The emotion estimation function can analyze the user's facial expressions and voice data to estimate emotions in real time. This allows the decision support system to provide optimal search results tailored to the user's emotions.

[0145] The decision support system can further adjust the way explanations are presented based on the user's emotions using an emotion estimation function. For example, if the user is feeling anxious, the explanation can be presented in a reassuring manner. If the user is excited, the explanation can be presented in a challenging manner. If the user is tired, the explanation can be presented in a simple and visually easy-to-understand manner. The emotion estimation function can estimate emotions in real time by analyzing the user's facial expressions and voice data. This allows the decision support system to provide optimal explanations tailored to the user's emotions.

[0146] The decision support system can further adjust the length of its explanations based on the user's emotions using its emotion estimation function. For example, if the user is feeling anxious, the explanation can provide a short, concise explanation. If the user is excited, the explanation can provide a detailed explanation. If the user is tired, the explanation can provide a simple, visually easy-to-understand explanation. The emotion estimation function can estimate emotions in real time by analyzing the user's facial expressions and voice data. This allows the decision support system to provide the optimal length of explanation according to the user's emotions.

[0147] The following briefly describes the processing flow for example form 2.

[0148] Step 1: The data collection department gathers information on past cases. For example, the department collects information on successful and unsuccessful cases of companies, and events with significant social impact. The data collection department can gather information from publicly available databases on the internet and internal company databases. They can also gather information through surveys and interviews. Step 2: The Management Department will create a database of the information collected by the Collection Department and manage it. The Management Department will save the collected information as digital data and register it in the database. The Management Department will optimize the database structure to enable quick information retrieval and provision. In addition, the Management Department will regularly back up the data to ensure data security. Step 3: The reception desk receives information about questions and tasks from users. The reception desk accepts questions and tasks in text format entered by users. It can also accept questions and tasks in multiple-choice format, as well as questions and tasks using voice input. Step 4: The search unit searches for cases related to the information received by the reception unit from the information managed by the administration unit. The search unit searches for related cases using keyword search. Search results can be narrowed down using filtering, and highly relevant cases can be displayed preferentially using ranking. Step 5: The service provider provides users with information based on the search results generated by the search unit. The service provider provides users with the search results in report format. The search results can also be displayed in dashboard format, or users can be notified of the search results.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0151] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] For example, the data collection unit is implemented by either the data processing unit 12 or the smart device 14. For instance, the data collection unit uses the camera 42 and microphone 38B of the smart device 14 to collect the user's facial expressions and voice, and estimates their emotions using an emotion estimation algorithm. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the collected information by creating a database. The reception unit is implemented by the control unit 46A of the smart device 14 and receives information about questions and issues from the user. The search unit is implemented by the specific processing unit 290 of the data processing unit 12 and searches for relevant cases from the information managed by the management unit. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the user with the information generated by the generation unit. The explanation unit is implemented by the specific processing unit 290 of the data processing unit 12 and explains why the generated solutions and directions are effective. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0153] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0154] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0156] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0160] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0161] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0162] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0163] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0165] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0167] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0168] For example, the data collection unit is implemented by either the data processing unit 12 or the smart glasses 214. For instance, the data collection unit uses the camera 42 and microphone 238 of the smart glasses 214 to collect the user's facial expressions and voice, and estimates their emotions using an emotion estimation algorithm. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the collected information by creating a database. The reception unit is implemented by the control unit 46A of the smart glasses 214 and receives information about questions and issues from the user. The search unit is implemented by the specific processing unit 290 of the data processing unit 12 and searches for relevant cases from the information managed by the management unit. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the user with the information generated by the generation unit. The explanation unit is implemented by the specific processing unit 290 of the data processing unit 12 and explains why the generated solutions and directions are effective. The correspondence between each unit and the devices and control units is not limited to the example described above, and various changes are possible.

[0169] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0170] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0171] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0172] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0173] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0175] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0176] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0177] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0178] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0179] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0180] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0181] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0182] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0183] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0184] For example, the data collection unit is implemented by either the data processing unit 12 or the headset terminal 314. For instance, the data collection unit uses the camera 42 and microphone 238 of the headset terminal 314 to collect the user's facial expressions and voice, and estimates their emotions using an emotion estimation algorithm. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the collected information by creating a database. The reception unit is implemented by the control unit 46A of the headset terminal 314 and receives information about questions and issues from the user. The search unit is implemented by the specific processing unit 290 of the data processing unit 12 and searches for relevant cases from the information managed by the management unit. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the information generated by the generation unit to the user. The explanation unit is implemented by the specific processing unit 290 of the data processing unit 12 and explains why the generated solutions and directions are effective. The correspondence between each unit and the devices and control units is not limited to the example described above, and various changes are possible.

[0185] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0186] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0187] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0188] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0189] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0191] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0192] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0193] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0194] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0195] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0196] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0197] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0198] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0199] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0200] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0201] For example, the data collection unit is implemented by either the data processing unit 12 or the robot 414. For instance, the data collection unit uses the camera 42 and microphone 238 of the robot 414 to collect the user's facial expressions and voice, and estimates their emotions using an emotion estimation algorithm. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the collected information by creating a database. The reception unit is implemented by the control unit 46A of the robot 414 and receives information about questions and issues from the user. The search unit is implemented by the specific processing unit 290 of the data processing unit 12 and searches for relevant cases from the information managed by the management unit. The provision unit is implemented by the control unit 46A of the robot 414 and provides the information generated by the generation unit to the user. The explanation unit is implemented by the specific processing unit 290 of the data processing unit 12 and explains why the generated solutions and directions are effective. The correspondence between each unit and the devices and control units is not limited to the example described above, and various changes are possible.

[0202] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0203] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0204] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0205] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0206] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0207] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0208] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0209] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0210] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0211] 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.

[0212] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0213] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0214] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0215] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0216] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0217] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0218] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0219] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0220] (Note 1) A collection unit that collects information on past cases, The management unit manages the information on cases collected by the aforementioned collection unit by creating a database. A reception desk that receives information on specific questions or issues from users, A search unit that searches for information on cases related to information received by the reception unit from the information managed by the management unit, The system includes a providing unit that provides information to the user based on the search results obtained by the search unit. A system characterized by the following features. (Note 2) The system includes a generation unit that uses AI to generate information indicating solutions or directions based on the search results from the search unit. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an explanatory section that explains the solutions or directions generated by the generation section. The system described in Appendix 2, characterized by the features described herein. (Note 4) The aforementioned collection unit is We collect specific information on corporate success stories, failures, and events with significant social impact. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned management department, The collected information is stored in a database and managed. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is We accept information about specific questions or issues from users. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned search unit, Search for cases related to information received by the reception department from information managed by the management department. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned supply unit is, The information generated by the generation unit is provided to the user. The system described in Appendix 2, characterized by the features described herein. (Note 9) The aforementioned explanatory section is, This section explains, based on historical evidence, why the generated solutions and directions are effective. The system described in Appendix 3, characterized by the features described herein. (Note 10) The aforementioned collection unit is We estimate the user's emotions and, based on those estimated emotions, determine the priority of specific examples to collect. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is During data collection, the reliability of the cases is evaluated, and the collection of highly reliable information is prioritized. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting data, adjust the scope of collection considering the timing and location of the incident. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is The system estimates user sentiment and selects categories of examples to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is During data collection, the relevance of the cases is evaluated, and the most relevant information is collected preferentially. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is When collecting data, adjust the content of the collection considering the background and scope of the incident. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned management department, It estimates user sentiment and optimizes the database structure based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned management department, During management, adjust the data update frequency to always maintain the latest information. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned management department, During management, eliminate data duplication and perform efficient data management. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned management department, The system estimates the user's emotions and sets data access permissions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned management department, During management, data backups are performed regularly to ensure data security. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned management department, During management, review the data classification method and enable efficient data retrieval. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned reception unit is The system estimates the user's emotions and adjusts how questions and tasks are submitted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned reception unit is During registration, the system will refer to the user's past question history to select the most appropriate registration method. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned reception unit is During registration, we prioritize questions based on the user's industry and job responsibilities. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned reception unit is The system estimates the user's emotions and adjusts the question acceptance time based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned reception unit is At the time of registration, the system will select the most suitable registration method, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned reception unit is At the time of registration, the optimal registration method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned search unit, It estimates the user's sentiment and adjusts how search results are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned search unit, When searching, the system evaluates the relevance of cases and prioritizes displaying the most relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned search unit, When searching, adjust the search scope considering the timing and location of the incident. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned search unit, It estimates the user's emotions and determines the priority of search results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned search unit, When searching, the reliability of the cases is evaluated, and reliable information is displayed preferentially. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned search unit, When searching, adjust your search criteria to take into account the background and scope of the incident. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned supply unit is, It estimates the user's emotions and adjusts the format of the information provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned supply unit is, When providing information, the system will refer to the user's past usage history to select the most appropriate method of information delivery. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned supply unit is, When providing information, we prioritize it according to the user's industry and job function. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned supply unit is, It estimates the user's emotions and adjusts the timing of information delivery based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned supply unit is, When providing information, the optimal method of information delivery will be selected, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned supply unit is, When providing information, the optimal method of information delivery is selected, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 40) The generating unit is It estimates the user's emotions and determines the priority of solutions to generate based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 41) The generating unit is During generation, the relevance of the cases is evaluated, and highly relevant solutions are generated preferentially. The system described in Appendix 2, characterized by the features described herein. (Appendix 42) The generation unit adjusts the generated content in consideration of the occurrence time and region of the case during generation. The system according to Appendix 2, characterized in that. (Appendix 43) The generation unit estimates the user's emotion and adjusts the form of the solution generated based on the estimated user's emotion. The system according to Appendix 2, characterized in that. (Appendix 44) The generation unit evaluates the reliability of the case during generation and preferentially generates a highly reliable solution. The system according to Appendix 2, characterized in that. (Appendix 45) The generation unit adjusts the generated content in consideration of the occurrence background and influence range of the case during generation. The system according to Appendix 2, characterized in that. (Appendix 46) The explanation unit estimates the user's emotion and adjusts the expression method of the explanation based on the estimated user's emotion. The system according to Appendix 3, characterized in that. (Appendix 47) The explanation unit evaluates the relevance of the case during explanation and preferentially provides a highly relevant explanation. The system according to Appendix 3, characterized in that. (Appendix 48) The explanation unit adjusts the explanation content in consideration of the occurrence time and region of the case during explanation. The system according to Appendix 3, characterized in that. (Appendix 49) The explanation unit estimates the user's emotion and adjusts the length of the explanation based on the estimated user's emotion. The system according to Appendix 3, characterized in that. (Appendix 50) The explanation unit During explanations, we evaluate the reliability of the examples and prioritize providing explanations that are highly reliable. The system described in Appendix 3, characterized by the features described herein. (Note 51) The aforementioned explanatory section is, When providing explanations, we adjust the content of the explanations to take into account the background and scope of impact of the cases. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0221] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection unit that collects information on past cases, The management unit manages the information on cases collected by the aforementioned collection unit by creating a database. A reception desk that receives information on specific questions or issues from users, A search unit that searches for information on cases related to information received by the reception unit from the information managed by the management unit, The system includes a providing unit that provides information to the user based on the search results obtained by the search unit. A system characterized by the following features.

2. The system includes a generation unit that generates information indicating solutions or directions using AI based on the search results from the aforementioned search unit. The system according to feature 1.

3. The system includes an explanatory section that explains the solutions or directions generated by the generation unit. The system according to feature 2.

4. The aforementioned collection unit is We collect specific information on corporate success stories, failures, and events with significant social impact. The system according to feature 1.

5. The aforementioned management department, The collected information is stored in a database and managed. The system according to feature 1.

6. The aforementioned reception unit is We accept information on specific questions or issues from the aforementioned users. The system according to feature 1.

7. The aforementioned search unit, Search for cases related to information received by the reception department from the information managed by the aforementioned management department. The system according to feature 1.

8. The aforementioned supply unit is, The information generated by the generation unit is provided to the user. The system according to feature 2.

Images