System

Abstract

An object of the system according to the embodiment is to provide an answer to a consultation from an employee immediately and notify the employee of useful information in a timely manner.SOLUTION: A system according to an embodiment includes a collection unit, a generation unit, and a notification unit. The collection unit collects information in the company. The generation unit generates a response to the consultation from the employee based on the information collected by the collection unit. The notification unit push-notifies the employee of the answer or the useful information generated by the generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that it is difficult to provide immediate responses to inquiries from employees, and useful information is not provided to employees in a timely manner.

[0005] The system according to the embodiment aims to provide immediate answers to inquiries from employees and notify employees of useful information in a timely manner. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a generation unit, and a notification unit. The collection unit collects information within the company. The generation unit generates answers to inquiries from employees based on the information collected by the collection unit. The notification unit pushes the answers or useful information generated by the generation unit to the employees. [Effects of the Invention]

[0007] The system according to the embodiment can provide immediate answers to inquiries from employees and notify employees of useful information in a timely manner. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An inquiry response efficiency system according to an embodiment of the present invention collects information within a company, generates responses to inquiries from employees using a generation AI, and provides useful information via push notifications. The inquiry response efficiency system inputs various internal company information into the generation AI, providing immediate responses to inquiries from employees. Employee information is also input into the generation AI, allowing the generation AI to provide useful information via push notifications. For example, the inquiry response efficiency system collects detailed information such as a company's business processes, know-how, and past inquiry history, and inputs it into the generation AI. Next, when an employee inputs a question to the generation AI, the generation AI generates an optimal answer based on the input information. Furthermore, by inputting information such as employee titles, responsibilities, and past inquiry history into the generation AI, the generation AI provides useful information to each employee at the appropriate time. This improves the efficiency of inquiry response and utilizes useful information that employees may not otherwise be aware of. The inquiry response efficiency system thus improves the efficiency of inquiry response within a company and utilizes useful information that employees may not otherwise be aware of. For example, the generation AI can quickly respond to rare inquiries, eliminating the need for timely responses. In addition, the AI ​​can provide useful information that employees may not be aware of via push notifications, improving employee work efficiency and increasing productivity across the company.

[0029] An inquiry response efficiency improvement system according to an embodiment includes a collection unit, a generation unit, and a notification unit. The collection unit collects information within a company. The information within the company includes, but is not limited to, business processes, know-how, and inquiry history. For example, the collection unit collects detailed information about the company's business processes. The collection unit can also collect the company's know-how. The collection unit can also collect past inquiry history. For example, the collection unit collects business manuals, FAQs, and past inquiry response records. The generation unit uses a generation AI to generate answers to inquiries from employees based on the information collected by the collection unit. The generation unit quickly responds to various inquiries, such as questions about business procedures and solutions to specific problems. The generation unit can also generate optimal answers using the generation AI. For example, the generation AI generates answers to questions from employees using a text generation AI (e.g., LLM). The notification unit pushes the answers and useful information generated by the generation unit to employees. The notification unit provides useful information at appropriate times based on information such as the employee's job title, responsibilities, and past inquiry history. The notification unit can also use the generation AI to send push notifications to employees. For example, the generation AI can send push notifications of relevant information based on the employee's job title or job responsibilities. This allows the inquiry response efficiency improvement system according to the embodiment to improve the efficiency of inquiry responses within a company and utilize useful information that employees may not be aware of. For example, the generation unit generates quick and appropriate responses based on the information collected by the collection unit. This significantly improves the efficiency of inquiry responses. Furthermore, the notification unit can provide employees with useful information at the appropriate time, thereby improving the work efficiency of employees and improving the productivity of the entire company.

[0030] The collection unit can collect information on the company's business processes or know-how, and past inquiry history. For example, the collection unit collects detailed information on the company's business processes. For example, it collects business processes such as daily operations, project management, and customer support. The collection unit can also collect the company's know-how. For example, it collects technical know-how, business know-how, etc. Furthermore, the collection unit can also collect past inquiry history. For example, it collects past questions and answers, inquiry frequency, etc. This allows comprehensive collection of information within the company and improves the response accuracy of the generation AI. Some or all of the above-mentioned processing in the collection unit can be performed using, or without, the generation AI. For example, the collection unit can input information on the company's business processes, know-how, and past inquiry history into the generation AI and have the generation AI collect information.

[0031] The generation unit can generate appropriate answers based on the collected information. The generation unit, for example, quickly responds to various inquiries, such as questions about business procedures and solutions to specific problems, based on the collected information. For example, the generation unit generates answers including detailed procedures in response to questions about business procedures. The generation unit can also generate answers including solutions to specific problems. Furthermore, the generation unit can use a generation AI to generate optimal answers. For example, the generation AI uses a text generation AI (e.g., LLM) to generate answers to questions from employees. This makes it possible to quickly generate appropriate answers based on the collected information. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit may input the collected information into the generation AI and cause the generation AI to generate an answer.

[0032] The notification unit can send push notifications of useful information based on information such as an employee's job title, job responsibilities, and past inquiry history. The notification unit provides useful information at appropriate times based on information such as an employee's job title, job responsibilities, and past inquiry history. For example, the notification unit sends push notifications of relevant information based on an employee's job title. The notification unit can also send push notifications of relevant information based on an employee's job responsibilities. The notification unit can also send push notifications of relevant information based on an employee's past inquiry history. For example, the notification unit sends push notifications of new work procedures, related training materials, etc., based on the employee's job title. This allows useful information to be provided to employees at appropriate times. Some or all of the above-described processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input information such as an employee's job title, job responsibilities, and past inquiry history into the generation AI and have the generation AI execute the push notification.

[0033] The collection unit includes a unit that performs quality control of information. The collection unit includes a unit that performs quality control of information. The quality control unit, for example, evaluates the accuracy, reliability, and recency of the collected information and manages the quality. For example, the quality control unit confirms the accuracy of the collected information and checks for errors. The quality control unit can also evaluate the reliability of the collected information and prioritize managing highly reliable information. Furthermore, the quality control unit can confirm the recency of the collected information and update old information. For example, the quality control unit confirms the source of the information and prioritizes managing highly reliable information. This makes it possible to manage the quality of the collected information and provide highly reliable information. Some or all of the above-mentioned processing in the quality control unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the quality control unit can input the collected information into a generation AI and have the generation AI perform quality control.

[0034] The collection unit manages employee information and improves the accuracy of responses by the generation AI. The collection unit manages employee information and improves the accuracy of responses by the generation AI. The employee information management unit manages information such as employee job titles, responsibilities, and past inquiry histories. For example, the employee information management unit manages related information based on employee job titles. The employee information management unit can also manage related information based on employee job titles. Furthermore, the employee information management unit can manage related information based on employee job titles. For example, the employee information management unit manages related information according to employee job titles. This allows for appropriate management of employee information and improves the accuracy of responses by the generation AI. Some or all of the above-described processing by the employee information management unit may be performed using, or without, the generation AI. For example, the employee information management unit can input information such as employee job titles, responsibilities, and past inquiry histories into the generation AI and have the generation AI manage employee information.

[0035] The generation unit includes a customization unit that customizes services for other companies. The generation unit includes a customization unit that customizes services for other companies. The customization unit customizes the service by, for example, referring to the business processes, know-how, and past inquiry history of other companies. For example, the customization unit refers to the business processes of other companies and applies an optimal customization method. The customization unit can also refer to the know-how of other companies and apply an efficient customization method. Furthermore, the customization unit can refer to the past inquiry history of other companies and apply an optimal customization method. For example, the customization unit improves the accuracy of the customization based on success stories of other companies. This enables services to be customized for other companies and applied widely. Some or all of the above-described processing in the customization unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the customization unit may input information about the business processes, know-how, and past inquiry history of other companies into the generation AI and have the generation AI perform the customization.

[0036] The collection unit can determine the priority of collection based on the importance of the information to be collected. For example, the collection unit prioritizes collection of information with high importance and processes it quickly. For example, the collection unit prioritizes collection of information with high importance based on the impact on business operations and urgency. The collection unit can also postpone collection of information with low importance, thereby efficiently utilizing resources. Furthermore, when there is multiple pieces of information with high importance, the collection unit can set more detailed priorities. For example, the collection unit prioritizes collection of information with high importance and processes it quickly. This enables priority collection of information with high importance and efficient information collection. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the importance of the information to be collected into the generation AI and cause the generation AI to determine the collection priority based on the importance.

[0037] The collection unit can evaluate the reliability of information at the time of collection and prioritize collecting highly reliable information. The collection unit, for example, checks the source of the information and prioritizes collecting highly reliable information. For example, the collection unit can evaluate the reliability of the information source and prioritize collecting highly reliable information. The collection unit can also identify highly reliable information sources based on past performance. Furthermore, the collection unit can separately verify low-reliability information and collect it as needed. For example, the collection unit checks the source of the information and prioritizes collecting highly reliable information. This allows highly reliable information to be collected preferentially and the quality of the information to be improved. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit can input the reliability of the information to the generation AI at the time of collection and cause the generation AI to collect information based on the reliability.

[0038] The collection unit can apply different collection algorithms depending on the category of information when collecting the information. For example, for information related to business processes, the collection unit applies an algorithm that collects detailed procedures. For example, when collecting information related to business processes, the collection unit applies an algorithm that collects detailed procedures. The collection unit can also apply an algorithm that collects personal experiences and case studies to information related to know-how. Furthermore, the collection unit can apply an algorithm that collects past response records to information related to inquiry history. For example, when collecting information related to know-how, the collection unit applies an algorithm that collects personal experiences and case studies. This allows for the application of an appropriate collection algorithm depending on the category of information, thereby improving the collection accuracy. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit can input the category of information to the generation AI when collecting the information, and cause the generation AI to apply a collection algorithm depending on the category.

[0039] The collection unit can collect information while taking into consideration the attribute information of the person submitting the information. The collection unit collects relevant information, for example, based on the submitter's job title and job responsibilities. For example, the collection unit collects relevant information based on the submitter's job title and job responsibilities. The collection unit can also preferentially collect reliable information based on the submitter's past performance. Furthermore, the collection unit can collect detailed information according to the submitter's level of expertise. For example, the collection unit preferentially collects reliable information based on the submitter's past performance. This allows collection to be performed while taking into consideration the submitter's attribute information, and highly relevant information to be provided. Some or all of the above-described processing by the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the submitter's attribute information into the generation AI and cause the generation AI to collect information based on the attribute information.

[0040] The collection unit can collect information taking into account the geographical distribution of the information when collecting it. For example, the collection unit prioritizes collecting geographically close information and responds quickly. For example, the collection unit prioritizes collecting geographically close information and responds quickly. The collection unit can also separately verify geographically distant information and collect it as needed. Furthermore, the collection unit can apply different collection methods depending on geographical characteristics. For example, the collection unit prioritizes collecting geographically close information and responds quickly. This makes it possible to collect information taking into account the geographical distribution and achieve a quick response. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the collection unit can input the geographical distribution of the information into the generation AI when collecting it and cause the generation AI to collect information based on the geographical distribution.

[0041] The collection unit can improve the accuracy of the collection by referring to literature related to the information at the time of collection. For example, the collection unit can refer to related literature to confirm the accuracy of the information. For example, the collection unit can refer to related literature to confirm the accuracy of the information. The collection unit can also expand the range of information to be collected based on the literature. Furthermore, the collection unit can supplement the collected information based on the content of the literature. For example, the collection unit can expand the range of information to be collected based on the literature. This can improve the accuracy of the collection by referring to related literature and provide accurate information. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using or without the generation AI. For example, the collection unit can input literature related to the information into the generation AI at the time of collection and cause the generation AI to collect information based on the related literature.

[0042] The generation unit can adjust the level of detail of the answer based on the importance of the question during generation. For example, the generation unit generates a detailed answer for a question of high importance. For example, the generation unit generates a detailed answer for a question of high importance. The generation unit can also generate a concise answer for a question of low importance. Furthermore, when there are multiple questions of high importance, the generation unit can adjust the level of detail even more finely. For example, the generation unit generates a concise answer for a question of low importance. This makes it possible to adjust the level of detail of the answer based on the importance of the question and provide an appropriate answer. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the importance of the question to the generation AI and cause the generation AI to adjust the level of detail of the answer based on the importance.

[0043] The generation unit can apply different generation algorithms depending on the category of the question during generation. For example, the generation unit applies an algorithm that generates an answer including detailed procedures to a question about a business procedure. For example, the generation unit applies an algorithm that generates an answer including detailed procedures to a question about a business procedure. The generation unit can also apply an algorithm that generates an answer including technical terms to a technical question. Furthermore, the generation unit can apply an algorithm that generates a concise and easy-to-understand answer to a general question. For example, the generation unit applies an algorithm that generates an answer including technical terms to a technical question. This allows an appropriate generation algorithm to be applied depending on the category of the question, thereby improving the accuracy of the answer. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the category of the question into the generation AI and cause the generation AI to apply a generation algorithm depending on the category.

[0044] The generation unit can improve the accuracy of the answer by referring to past answer results during generation. The generation unit, for example, analyzes past answer results and generates an optimal answer for a similar question. For example, the generation unit analyzes past answer results and generates an optimal answer for a similar question. The generation unit can also apply an algorithm that improves the accuracy of the answer based on the past answer results. Furthermore, the generation unit can maintain the consistency of the answer by referring to the past answer results. For example, the generation unit applies an algorithm that improves the accuracy of the answer based on the past answer results. This makes it possible to improve the accuracy of the answer by referring to the past answer results and provide a consistent answer. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input past answer results into the generation AI and cause the generation AI to improve the accuracy of the answer based on the past answer results.

[0045] The generation unit can determine the priority of answers based on the submission time of the question at the time of generation. For example, the generation unit prioritizes answers to questions submitted earlier. For example, the generation unit prioritizes answers to questions submitted earlier. The generation unit can also postpone questions submitted later to efficiently utilize resources. Furthermore, the generation unit can set more detailed priorities when questions are submitted at the same time. For example, the generation unit postpones questions submitted later to efficiently utilize resources. This makes it possible to determine the priority of answers based on the submission time of the question and provide efficient answers. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the submission time of the question into the generation AI and cause the generation AI to determine the priority of answers based on the submission time.

[0046] The generation unit can adjust the order of answers based on the relevance of the questions when generating the answers. For example, the generation unit prioritizes answers to highly relevant questions. For example, the generation unit prioritizes answers to highly relevant questions. The generation unit can also postpone questions with low relevance to efficiently utilize resources. Furthermore, when there are multiple highly relevant questions, the generation unit can adjust the order in more detail. For example, the generation unit postpones questions with low relevance to efficiently utilize resources. This allows the order of answers to be adjusted based on the relevance of the questions, and efficient answers to be provided. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the relevance of questions to the generation AI and cause the generation AI to adjust the order of answers based on the relevance.

[0047] The generation unit can adjust the use of technical terminology in the answer depending on the employee's level of expertise during generation. For example, the generation unit generates an answer that uses a lot of technical terminology for an employee with a high level of expertise. For example, the generation unit generates an answer that uses a lot of technical terminology for an employee with a high level of expertise. The generation unit can also generate a concise and easy-to-understand answer for an employee with a low level of expertise. Furthermore, the generation unit can adjust the level of detail of the answer depending on the level of expertise. For example, the generation unit generates a concise and easy-to-understand answer for an employee with a low level of expertise. This makes it possible to adjust the use of technical terminology in the answer depending on the employee's level of expertise and provide an appropriate answer. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the employee's level of expertise into the generation AI and cause the generation AI to adjust the technical terminology of the answer based on the level of expertise.

[0048] The notification unit can determine the priority of notifications based on the importance of the information at the time of notification. For example, the notification unit can prioritize notification of information with high importance and respond quickly. For example, the notification unit can prioritize notification of information with high importance and respond quickly. The notification unit can also postpone information with low importance to efficiently utilize resources. Furthermore, when there is multiple information with high importance, the notification unit can set the priority even more finely. For example, the notification unit postpones information with low importance to efficiently utilize resources. In this way, the priority of notifications can be determined based on the importance of the information, and efficient notifications can be achieved. Some or all of the above-mentioned processing in the notification unit may be performed using, or without, the generation AI. For example, the notification unit can input the importance of information to the generation AI at the time of notification and cause the generation AI to determine the priority of notifications based on the importance.

[0049] The notification unit can apply different notification methods depending on the category of information when notifying. For example, the notification unit applies a notification method including detailed procedures to information related to business processes. For example, the notification unit applies a notification method including detailed procedures when notifying information related to business processes. The notification unit can also apply a notification method including personal experiences and case studies to information related to know-how. Furthermore, the notification unit can apply a notification method including past response records to information related to inquiry history. For example, the notification unit applies a notification method including personal experiences and case studies when notifying information related to know-how. This allows an appropriate notification method to be applied depending on the category of information, thereby improving the accuracy of notifications. Some or all of the above-mentioned processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the category of information to the generation AI when notifying and cause the generation AI to apply a notification method depending on the category.

[0050] The notification unit can improve the accuracy of notifications by referring to past notification results when providing notifications. For example, the notification unit analyzes past notification results and applies an optimal notification method for similar information. For example, the notification unit analyzes past notification results and applies an optimal notification method for similar information. The notification unit can also apply an algorithm that improves the accuracy of notifications based on past notification results. Furthermore, the notification unit can maintain the consistency of notifications by referring to past notification results. For example, the notification unit applies an algorithm that improves the accuracy of notifications based on past notification results. This makes it possible to improve the accuracy of notifications by referring to past notification results and provide consistent notifications. Some or all of the above-described processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input past notification results into the generation AI and cause the generation AI to improve the accuracy of notifications based on the past notification results.

[0051] The notification unit can customize the content of notifications based on the employee's job title and job responsibilities. For example, the notification unit can provide managers with notifications regarding the overall progress of work and important decisions. For example, the notification unit can provide managers with notifications regarding the overall progress of work and important decisions. The notification unit can also provide general employees with notifications regarding specific procedures and tasks related to their daily work. Furthermore, the notification unit can provide notifications including relevant information and resources based on the employee's job responsibilities. For example, the notification unit can provide general employees with notifications regarding specific procedures and tasks related to their daily work. This allows the content of notifications to be customized based on the employee's job title and job responsibilities, and appropriate information to be provided. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input the employee's job title and job responsibilities into the generation AI and have the generation AI customize the notification content based on the job title and job responsibilities.

[0052] The notification unit can provide notifications taking into account the employee's geographic location information. For example, if the employee is in the office, the notification unit provides notifications regarding resources and support within the office. For example, if the employee is in the office, the notification unit provides notifications regarding resources and support within the office. Furthermore, if the employee is on a business trip, the notification unit can provide notifications regarding information about the business trip destination and support. Furthermore, if the employee is working remotely, the notification unit can provide notifications regarding resources and support related to the remote work. For example, if the employee is on a business trip, the notification unit provides notifications regarding information about the business trip destination and support. This makes it possible to provide appropriate information by providing notifications taking into account the employee's geographic location information. Some or all of the above-described processing by the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the employee's geographic location information into the generation AI and cause the generation AI to execute notifications based on the geographic location information.

[0053] The notification unit can analyze the employee's social media activity and notify the employee of relevant information at the time of notification. The notification unit, for example, notifies the employee of work-related information shared by the employee on social media. For example, the notification unit notifies the employee of work-related information shared by the employee on social media. The notification unit can also analyze the employee's social media activity and provide relevant work information. Furthermore, the notification unit can notify the employee of relevant work information by referring to the activity of the employee's friends on social media. For example, the notification unit analyzes the employee's social media activity and provides relevant work information. This makes it possible to analyze the employee's social media activity to notify the employee of relevant information and provide appropriate information. Some or all of the above-mentioned processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the employee's social media activity into the generation AI and cause the generation AI to execute a notification based on the social media activity.

[0054] The management unit can evaluate the reliability of information during management and prioritize management of highly reliable information. The management unit, for example, verifies the source of the information and prioritizes management of highly reliable information. For example, the management unit can verify the source of the information and prioritize management of highly reliable information. The management unit can also identify highly reliable information sources based on past performance. Furthermore, the management unit can separately verify low-reliability information and manage it as needed. For example, the management unit can identify highly reliable information sources based on past performance. This allows the reliability of information to be evaluated and highly reliable information to be prioritized, thereby improving the quality of information. Some or all of the above-mentioned processing in the management unit may be performed using, or without, the generation AI. For example, the management unit can input the reliability of information into the generation AI during management and cause the generation AI to perform information management based on reliability.

[0055] The management unit can apply different management methods depending on the category of information during management. For example, the management unit applies a management method including detailed procedures to information related to business processes. For example, the management unit applies a management method including detailed procedures when managing information related to business processes. The management unit can also apply a management method including personal experiences and case studies to information related to know-how. Furthermore, the management unit can apply a management method including past response records to information related to inquiry history. For example, the management unit applies a management method including personal experiences and case studies when managing information related to know-how. This allows an appropriate management method to be applied depending on the category of information, thereby improving the accuracy of management. Some or all of the above-mentioned processing in the management unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the management unit can input the category of information into the generation AI during management and have the generation AI apply a management method depending on the category.

[0056] The management unit can determine management priorities based on the time of information submission during management. For example, the management unit prioritizes management of information submitted early. For example, the management unit prioritizes management of information submitted early. The management unit can also postpone information submitted late to efficiently utilize resources. Furthermore, the management unit can set more detailed priorities when submission times overlap. For example, the management unit postpones information submitted late to efficiently utilize resources. In this way, management priorities can be determined based on the time of information submission, and efficient management can be achieved. Some or all of the above-mentioned processing in the management unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the management unit can input the time of information submission into the generation AI during management and have the generation AI determine management priorities based on the time of submission.

[0057] The management unit can improve the accuracy of management by referring to literature related to the information during management. For example, the management unit can refer to related literature to confirm the accuracy of the information. The management unit can also expand the scope of information to be managed based on the literature. Furthermore, the management unit can supplement the managed information based on the content of the literature. For example, the management unit can expand the scope of information to be managed based on the literature. This makes it possible to improve the accuracy of management by referring to related literature and provide accurate information. Some or all of the above-mentioned processing in the management unit can be performed using, or without, the generation AI. For example, the management unit can input literature related to the information into the generation AI during management and have the generation AI perform information management based on the related literature.

[0058] The employee information management unit can manage information based on employees' job titles and responsibilities during management. For example, for managers, the employee information management unit manages information regarding the overall progress of work and important decisions. For example, for managers, the employee information management unit manages information regarding the overall progress of work and important decisions. The employee information management unit can also manage information regarding specific procedures and tasks related to daily work for general employees. Furthermore, the employee information management unit can manage related information and resources according to the responsibilities. For example, the employee information management unit manages information regarding specific procedures and tasks related to daily work for general employees. This allows information to be managed based on employees' job titles and responsibilities and appropriate information to be provided. Some or all of the above-described processing in the employee information management unit may be performed using, or without, a generation AI. For example, the employee information management unit can input employees' job titles and responsibilities into a generation AI and have the generation AI perform information management based on the job titles and responsibilities.

[0059] The employee information management unit can manage information by referring to the employee's past inquiry history during management. The employee information management unit, for example, manages information for similar inquiries based on the past inquiry history. For example, the employee information management unit manages information for similar inquiries based on the past inquiry history. The employee information management unit can also maintain consistency of information by referring to the past inquiry history. Furthermore, the employee information management unit can analyze the past inquiry history and apply an optimal management method. For example, the employee information management unit can maintain consistency of information by referring to the past inquiry history. This makes it possible to manage information by referring to the employee's past inquiry history and provide consistent information. Some or all of the above-mentioned processing in the employee information management unit may be performed using, or without, a generation AI. For example, the employee information management unit can input the employee's past inquiry history into the generation AI and have the generation AI perform information management based on the past inquiry history.

[0060] The employee information management unit can manage information taking into account the employee's geographic location information when managing information. For example, when an employee is in the office, the employee information management unit manages information about resources and support within the office. For example, when an employee is in the office, the employee information management unit manages information about resources and support within the office. Furthermore, when an employee is on a business trip, the employee information management unit can also manage information about the business trip destination and support. Furthermore, when an employee is working remotely, the employee information management unit can also manage information about resources and support related to the remote work. For example, when an employee is on a business trip, the employee information management unit manages information about the business trip destination and support. This makes it possible to manage information taking into account the employee's geographic location information and provide appropriate information. Some or all of the above-mentioned processing in the employee information management unit may be performed using, or without, a generation AI. For example, the employee information management unit can input the employee's geographic location information into the generation AI and have the generation AI perform information management based on the geographic location information.

[0061] The employee information management unit can analyze employees' social media activities during management and manage information. The employee information management unit, for example, manages work-related information shared by employees on social media. For example, the employee information management unit manages work-related information shared by employees on social media. The employee information management unit can also analyze employees' social media activities and manage related work information. Furthermore, the employee information management unit can manage related work information by referring to the activities of the employees' friends on social media. For example, the employee information management unit analyzes employees' social media activities and manages related work information. This makes it possible to analyze employees' social media activities to manage information and provide appropriate information. Some or all of the above-mentioned processing in the employee information management unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the employee information management unit can input employees' social media activities into a generation AI and have the generation AI perform information management based on the social media activities.

[0062] The customization unit can perform customization based on the business processes or know-how of other companies. For example, the customization unit refers to the business processes of other companies and applies the optimal customization method. For example, the customization unit refers to the business processes of other companies and applies the optimal customization method. The customization unit can also refer to the know-how of other companies and apply an efficient customization method. Furthermore, the customization unit can improve the accuracy of customization based on successful cases of other companies. For example, the customization unit refers to the know-how of other companies and applies an efficient customization method. This makes it possible to perform customization by referring to the business processes and know-how of other companies and provide appropriate customization. Some or all of the above-described processing in the customization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the customization unit can input the business processes and know-how of other companies into the generation AI and cause the generation AI to perform customization based on the business processes and know-how.

[0063] The customization unit can perform customization by referring to the past inquiry history of other companies. For example, the customization unit can refer to the past inquiry history of other companies and apply the optimal customization method. For example, the customization unit can refer to the past inquiry history of other companies and apply the optimal customization method. The customization unit can also improve the accuracy of customization based on the past inquiry history of other companies. Furthermore, the customization unit can analyze the past inquiry history of other companies and apply an efficient customization method. For example, the customization unit can improve the accuracy of customization based on the past inquiry history of other companies. This makes it possible to perform customization by referring to the past inquiry history of other companies and provide appropriate customization. Some or all of the above-described processing in the customization unit may be performed using, or without, a generation AI. For example, the customization unit can input the past inquiry history of other companies into the generation AI and cause the generation AI to perform customization based on the past inquiry history.

[0064] The customization unit can perform customization taking into account the geographic location information of other companies. For example, when the other company is in an office, the customization unit performs customization related to resources and support within the office. For example, when the other company is in an office, the customization unit performs customization related to resources and support within the office. Furthermore, when the other company is on a business trip, the customization unit can also perform customization related to business trip destination information and support. Furthermore, when the other company is working remotely, the customization unit can also perform customization related to resources and support related to remote work. For example, when the other company is on a business trip, the customization unit performs customization related to business trip destination information and support. This makes it possible to perform customization taking into account the geographic location information of other companies and provide appropriate customization. Some or all of the above-described processing in the customization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the customization unit can input the geographic location information of other companies into the generation AI and cause the generation AI to perform customization based on the geographic location information.

[0065] The customization unit can analyze the social media activities of other companies and perform customization during customization. The customization unit can perform customization based on, for example, business-related information shared by other companies on social media. For example, the customization unit can perform customization based on business-related information shared by other companies on social media. The customization unit can also analyze the social media activities of other companies and perform customization based on related business information. Furthermore, the customization unit can perform customization based on related business information, taking into account the activities of friends of other companies on social media. For example, the customization unit can analyze the social media activities of other companies and perform customization based on related business information. This makes it possible to analyze the social media activities of other companies and perform customization based on the related business information, thereby providing appropriate customization. Some or all of the above-described processing in the customization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the customization unit can input the social media activities of other companies into the generation AI and cause the generation AI to perform customization based on the social media activities.

[0066] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0067] The collection unit may include a reliability evaluation unit for evaluating the reliability of information when collecting information within a company. The reliability evaluation unit evaluates the reliability of the collected information, for example, based on the source of the information and past performance. For example, the reliability evaluation unit may check the source of the information and prioritize the collection of highly reliable information. The reliability evaluation unit may also identify highly reliable information sources based on past performance. Furthermore, the reliability evaluation unit may separately verify less reliable information and collect it as necessary. This ensures the reliability of the collected information and improves the accuracy of the generation AI's responses.

[0068] When collecting information on a company's business processes or know-how, or past inquiry history, the collection department can determine the priority of collection based on the importance of the information. For example, the collection department prioritizes the collection of information with high importance and processes it quickly. For example, the collection department prioritizes the collection of information with high importance based on the impact on business operations and urgency. It is also possible to postpone the collection of information with low importance, thereby making efficient use of resources. Furthermore, when there is multiple pieces of information with high importance, it is possible to set the priority even more finely. This allows the collection of information with high importance to be prioritized, thereby achieving efficient information collection.

[0069] The generation unit may include a reliability evaluation unit for evaluating the reliability of an answer when generating an appropriate answer based on collected information. The reliability evaluation unit evaluates the reliability of the generated answer, for example, based on past answer results and the source of the information. For example, the reliability evaluation unit analyzes past answer results and generates an optimal answer to a similar question. The reliability evaluation unit can also check the source of the information and generate an answer based on highly reliable information. Furthermore, the reliability evaluation unit can separately verify information with low reliability and generate an answer as necessary. This ensures the reliability of the generated answer and provides appropriate information to employees.

[0070] The notification department can customize the content of push notifications that deliver useful information based on an employee's job title, job responsibilities, and past inquiry history. For example, the notification department can provide managers with notifications about the overall progress of work and important decisions. It can also provide general employees with notifications about specific procedures and tasks related to their daily work. Furthermore, the notification department can provide notifications that include relevant information and resources according to the employee's job responsibilities. This allows the content of notifications to be customized based on an employee's job title and job responsibilities, providing them with appropriate information.

[0071] When the collection unit includes a unit that performs information quality control, it can apply different quality control methods depending on the category of information. For example, for information related to business processes, a quality control method including detailed procedures can be applied. For information related to know-how, a quality control method including personal experiences and case studies can be applied. Furthermore, for information related to inquiry history, a quality control method including past response records can be applied. This allows the application of an appropriate quality control method depending on the category of information, thereby improving the quality of the information.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The collection department collects information within the company. This information includes business processes, know-how, and inquiry history. For example, the collection department collects business manuals, FAQs, and records of past inquiries. Step 2: The generation unit generates answers to employee inquiries based on the information collected by the collection unit. The generation unit uses generative AI to quickly respond to various inquiries, such as questions about business procedures and solutions to specific problems. Step 3: The notification unit pushes the answers and useful information generated by the generation unit to employees. The notification unit provides useful information at the appropriate time based on information such as the employee's position, job responsibilities, and past inquiry history.

[0074] (Example 2) An inquiry response efficiency system according to an embodiment of the present invention collects information within a company, generates responses to inquiries from employees using a generation AI, and provides useful information via push notifications. The inquiry response efficiency system inputs various internal company information into the generation AI, providing immediate responses to inquiries from employees. Employee information is also input into the generation AI, allowing the generation AI to provide useful information via push notifications. For example, the inquiry response efficiency system collects detailed information such as a company's business processes, know-how, and past inquiry history, and inputs it into the generation AI. Next, when an employee inputs a question to the generation AI, the generation AI generates an optimal answer based on the input information. Furthermore, by inputting information such as employee titles, responsibilities, and past inquiry history into the generation AI, the generation AI provides useful information to each employee at the appropriate time. This improves the efficiency of inquiry response and utilizes useful information that employees may not otherwise be aware of. The inquiry response efficiency system thus improves the efficiency of inquiry response within a company and utilizes useful information that employees may not otherwise be aware of. For example, the generation AI can quickly respond to rare inquiries, eliminating the need for timely responses. In addition, the AI ​​can provide useful information that employees may not be aware of via push notifications, improving employee work efficiency and increasing productivity across the company.

[0075] An inquiry response efficiency improvement system according to an embodiment includes a collection unit, a generation unit, and a notification unit. The collection unit collects information within a company. The information within the company includes, but is not limited to, business processes, know-how, and inquiry history. For example, the collection unit collects detailed information about the company's business processes. The collection unit can also collect the company's know-how. The collection unit can also collect past inquiry history. For example, the collection unit collects business manuals, FAQs, and past inquiry response records. The generation unit uses a generation AI to generate answers to inquiries from employees based on the information collected by the collection unit. The generation unit quickly responds to various inquiries, such as questions about business procedures and solutions to specific problems. The generation unit can also generate optimal answers using the generation AI. For example, the generation AI generates answers to questions from employees using a text generation AI (e.g., LLM). The notification unit pushes the answers and useful information generated by the generation unit to employees. The notification unit provides useful information at appropriate times based on information such as the employee's job title, responsibilities, and past inquiry history. The notification unit can also use the generation AI to send push notifications to employees. For example, the generation AI can send push notifications of relevant information based on the employee's job title or job responsibilities. This allows the inquiry response efficiency improvement system according to the embodiment to improve the efficiency of inquiry responses within a company and utilize useful information that employees may not be aware of. For example, the generation unit generates quick and appropriate responses based on the information collected by the collection unit. This significantly improves the efficiency of inquiry responses. Furthermore, the notification unit can provide employees with useful information at the appropriate time, thereby improving the work efficiency of employees and improving the productivity of the entire company.

[0076] The collection unit can collect information on the company's business processes or know-how, and past inquiry history. For example, the collection unit collects detailed information on the company's business processes. For example, it collects business processes such as daily operations, project management, and customer support. The collection unit can also collect the company's know-how. For example, it collects technical know-how, business know-how, etc. Furthermore, the collection unit can also collect past inquiry history. For example, it collects past questions and answers, inquiry frequency, etc. This allows comprehensive collection of information within the company and improves the response accuracy of the generation AI. Some or all of the above-mentioned processing in the collection unit can be performed using, or without, the generation AI. For example, the collection unit can input information on the company's business processes, know-how, and past inquiry history into the generation AI and have the generation AI collect information.

[0077] The generation unit can generate appropriate answers based on the collected information. The generation unit, for example, quickly responds to various inquiries, such as questions about business procedures and solutions to specific problems, based on the collected information. For example, the generation unit generates answers including detailed procedures in response to questions about business procedures. The generation unit can also generate answers including solutions to specific problems. Furthermore, the generation unit can use a generation AI to generate optimal answers. For example, the generation AI uses a text generation AI (e.g., LLM) to generate answers to questions from employees. This makes it possible to quickly generate appropriate answers based on the collected information. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit may input the collected information into the generation AI and cause the generation AI to generate an answer.

[0078] The notification unit can send push notifications of useful information based on information such as an employee's job title, job responsibilities, and past inquiry history. The notification unit provides useful information at appropriate times based on information such as an employee's job title, job responsibilities, and past inquiry history. For example, the notification unit sends push notifications of relevant information based on an employee's job title. The notification unit can also send push notifications of relevant information based on an employee's job responsibilities. The notification unit can also send push notifications of relevant information based on an employee's past inquiry history. For example, the notification unit sends push notifications of new work procedures, related training materials, etc., based on the employee's job title. This allows useful information to be provided to employees at appropriate times. Some or all of the above-described processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input information such as an employee's job title, job responsibilities, and past inquiry history into the generation AI and have the generation AI execute the push notification.

[0079] The collection unit includes a unit that performs quality control of information. The collection unit includes a unit that performs quality control of information. The quality control unit, for example, evaluates the accuracy, reliability, and recency of the collected information and manages the quality. For example, the quality control unit confirms the accuracy of the collected information and checks for errors. The quality control unit can also evaluate the reliability of the collected information and prioritize managing highly reliable information. Furthermore, the quality control unit can confirm the recency of the collected information and update old information. For example, the quality control unit confirms the source of the information and prioritizes managing highly reliable information. This makes it possible to manage the quality of the collected information and provide highly reliable information. Some or all of the above-mentioned processing in the quality control unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the quality control unit can input the collected information into a generation AI and have the generation AI perform quality control.

[0080] The collection unit manages employee information and improves the accuracy of responses by the generation AI. The collection unit manages employee information and improves the accuracy of responses by the generation AI. The employee information management unit manages information such as employee job titles, responsibilities, and past inquiry histories. For example, the employee information management unit manages related information based on employee job titles. The employee information management unit can also manage related information based on employee job titles. Furthermore, the employee information management unit can manage related information based on employee job titles. For example, the employee information management unit manages related information according to employee job titles. This allows for appropriate management of employee information and improves the accuracy of responses by the generation AI. Some or all of the above-described processing by the employee information management unit may be performed using, or without, the generation AI. For example, the employee information management unit can input information such as employee job titles, responsibilities, and past inquiry histories into the generation AI and have the generation AI manage employee information.

[0081] The generation unit includes a customization unit that customizes services for other companies. The generation unit includes a customization unit that customizes services for other companies. The customization unit customizes the service by, for example, referring to the business processes, know-how, and past inquiry history of other companies. For example, the customization unit refers to the business processes of other companies and applies an optimal customization method. The customization unit can also refer to the know-how of other companies and apply an efficient customization method. Furthermore, the customization unit can refer to the past inquiry history of other companies and apply an optimal customization method. For example, the customization unit improves the accuracy of the customization based on success stories of other companies. This enables services to be customized for other companies and applied widely. Some or all of the above-described processing in the customization unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the customization unit may input information about the business processes, know-how, and past inquiry history of other companies into the generation AI and have the generation AI perform the customization.

[0082] The collection unit estimates the employee's emotions and adjusts the timing of information collection based on the estimated employee emotions. The collection unit estimates the employee's emotions and adjusts the timing of information collection based on the estimated employee emotions. For example, if the employee is feeling stressed, the collection unit reduces the frequency of information collection to reduce the employee's burden. Also, if the employee is relaxed, the collection unit can increase the frequency of information collection to collect more detailed information. Furthermore, if the employee is busy, the collection unit can adjust the timing of information collection to between work tasks. For example, the collection unit estimates the employee's emotions and adjusts the timing of information collection based on the estimated emotions. This allows the timing of information collection to be adjusted according to the employee's emotions and reduce the employee's burden. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection department can input employee emotional data into the generation AI and have the generation AI adjust the timing of information collection based on emotions.

[0083] The collection unit can determine the priority of collection based on the importance of the information to be collected. For example, the collection unit prioritizes collection of information with high importance and processes it quickly. For example, the collection unit prioritizes collection of information with high importance based on the impact on business operations and urgency. The collection unit can also postpone collection of information with low importance, thereby efficiently utilizing resources. Furthermore, when there is multiple pieces of information with high importance, the collection unit can set more detailed priorities. For example, the collection unit prioritizes collection of information with high importance and processes it quickly. This enables priority collection of information with high importance and efficient information collection. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the importance of the information to be collected into the generation AI and cause the generation AI to determine the collection priority based on the importance.

[0084] The collection unit can evaluate the reliability of information at the time of collection and prioritize collecting highly reliable information. The collection unit, for example, checks the source of the information and prioritizes collecting highly reliable information. For example, the collection unit can evaluate the reliability of the information source and prioritize collecting highly reliable information. The collection unit can also identify highly reliable information sources based on past performance. Furthermore, the collection unit can separately verify low-reliability information and collect it as needed. For example, the collection unit checks the source of the information and prioritizes collecting highly reliable information. This allows highly reliable information to be collected preferentially and the quality of the information to be improved. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit can input the reliability of the information to the generation AI at the time of collection and cause the generation AI to collect information based on the reliability.

[0085] The collection unit can apply different collection algorithms depending on the category of information when collecting the information. For example, for information related to business processes, the collection unit applies an algorithm that collects detailed procedures. For example, when collecting information related to business processes, the collection unit applies an algorithm that collects detailed procedures. The collection unit can also apply an algorithm that collects personal experiences and case studies to information related to know-how. Furthermore, the collection unit can apply an algorithm that collects past response records to information related to inquiry history. For example, when collecting information related to know-how, the collection unit applies an algorithm that collects personal experiences and case studies. This allows for the application of an appropriate collection algorithm depending on the category of information, thereby improving the collection accuracy. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit can input the category of information to the generation AI when collecting the information, and cause the generation AI to apply a collection algorithm depending on the category.

[0086] The collection unit can estimate the employee's emotions and select the type of information to collect based on the estimated employee's emotions. For example, if the employee is feeling stressed, the collection unit prioritizes collecting information that helps the employee relax. For example, if the employee is feeling stressed, the collection unit prioritizes collecting information that helps the employee relax. Furthermore, if the employee is relaxed, the collection unit can collect detailed information that is useful for work. Furthermore, if the employee is busy, the collection unit can collect concise but important information. For example, if the employee is relaxed, the collection unit collects detailed information that is useful for work. This allows the type of information to be selected based on the employee's emotions and provides appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, the generation AI. For example, the collection unit can input the employee's emotion data into the generation AI and cause the generation AI to select the type of information based on the emotion.

[0087] The collection unit can collect information while taking into consideration the attribute information of the person submitting the information. The collection unit collects relevant information, for example, based on the submitter's job title and job responsibilities. For example, the collection unit collects relevant information based on the submitter's job title and job responsibilities. The collection unit can also preferentially collect reliable information based on the submitter's past performance. Furthermore, the collection unit can collect detailed information according to the submitter's level of expertise. For example, the collection unit preferentially collects reliable information based on the submitter's past performance. This allows collection to be performed while taking into consideration the submitter's attribute information, and highly relevant information to be provided. Some or all of the above-described processing by the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the submitter's attribute information into the generation AI and cause the generation AI to collect information based on the attribute information.

[0088] The collection unit can collect information taking into account the geographical distribution of the information when collecting it. For example, the collection unit prioritizes collecting geographically close information and responds quickly. For example, the collection unit prioritizes collecting geographically close information and responds quickly. The collection unit can also separately verify geographically distant information and collect it as needed. Furthermore, the collection unit can apply different collection methods depending on geographical characteristics. For example, the collection unit prioritizes collecting geographically close information and responds quickly. This makes it possible to collect information taking into account the geographical distribution and achieve a quick response. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the collection unit can input the geographical distribution of the information into the generation AI when collecting it and cause the generation AI to collect information based on the geographical distribution.

[0089] The collection unit can improve the accuracy of the collection by referring to literature related to the information at the time of collection. For example, the collection unit can refer to related literature to confirm the accuracy of the information. For example, the collection unit can refer to related literature to confirm the accuracy of the information. The collection unit can also expand the range of information to be collected based on the literature. Furthermore, the collection unit can supplement the collected information based on the content of the literature. For example, the collection unit can expand the range of information to be collected based on the literature. This can improve the accuracy of the collection by referring to related literature and provide accurate information. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using or without the generation AI. For example, the collection unit can input literature related to the information into the generation AI at the time of collection and cause the generation AI to collect information based on the related literature.

[0090] The generation unit can estimate the employee's emotions and adjust the way the answer is expressed based on the estimated employee's emotions. For example, if the employee is feeling stressed, the generation unit generates a concise and easy-to-understand answer. For example, if the employee is feeling stressed, the generation unit generates a concise and easy-to-understand answer. The generation unit can also generate an answer including a detailed explanation if the employee is relaxed. Furthermore, the generation unit can generate a quick answer that focuses on the main points if the employee is in a hurry. For example, if the employee is relaxed, the generation unit generates an answer including a detailed explanation. This allows the way the answer is expressed to be adjusted according to the employee's emotions and an appropriate answer to be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, the generation AI. For example, the generation unit can input the employee's emotion data into the generation AI and cause the generation AI to adjust the way the answer is expressed based on the emotion.

[0091] The generation unit can adjust the level of detail of the answer based on the importance of the question during generation. For example, the generation unit generates a detailed answer for a question of high importance. For example, the generation unit generates a detailed answer for a question of high importance. The generation unit can also generate a concise answer for a question of low importance. Furthermore, when there are multiple questions of high importance, the generation unit can adjust the level of detail even more finely. For example, the generation unit generates a concise answer for a question of low importance. This makes it possible to adjust the level of detail of the answer based on the importance of the question and provide an appropriate answer. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the importance of the question to the generation AI and cause the generation AI to adjust the level of detail of the answer based on the importance.

[0092] The generation unit can apply different generation algorithms depending on the category of the question during generation. For example, the generation unit applies an algorithm that generates an answer including detailed procedures to a question about a business procedure. For example, the generation unit applies an algorithm that generates an answer including detailed procedures to a question about a business procedure. The generation unit can also apply an algorithm that generates an answer including technical terms to a technical question. Furthermore, the generation unit can apply an algorithm that generates a concise and easy-to-understand answer to a general question. For example, the generation unit applies an algorithm that generates an answer including technical terms to a technical question. This allows an appropriate generation algorithm to be applied depending on the category of the question, thereby improving the accuracy of the answer. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the category of the question into the generation AI and cause the generation AI to apply a generation algorithm depending on the category.

[0093] The generation unit can improve the accuracy of the answer by referring to past answer results during generation. The generation unit, for example, analyzes past answer results and generates an optimal answer for a similar question. For example, the generation unit analyzes past answer results and generates an optimal answer for a similar question. The generation unit can also apply an algorithm that improves the accuracy of the answer based on the past answer results. Furthermore, the generation unit can maintain the consistency of the answer by referring to the past answer results. For example, the generation unit applies an algorithm that improves the accuracy of the answer based on the past answer results. This makes it possible to improve the accuracy of the answer by referring to the past answer results and provide a consistent answer. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input past answer results into the generation AI and cause the generation AI to improve the accuracy of the answer based on the past answer results.

[0094] The generation unit can estimate the employee's emotions and adjust the length of the answer based on the estimated employee emotions. For example, if the employee is stressed, the generation unit generates a short, to-the-point answer. For example, if the employee is stressed, the generation unit generates a short, to-the-point answer. Furthermore, if the employee is relaxed, the generation unit can generate a longer answer with detailed explanations. Furthermore, if the employee is in a hurry, the generation unit can generate a concise, quick answer. For example, if the employee is relaxed, the generation unit generates a longer answer with detailed explanations. This allows the length of the answer to be adjusted according to the employee's emotions and provide an appropriate answer. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using the generation AI, or without using the generation AI. For example, the generation unit can input employee emotional data into the generation AI and have the generation AI adjust the length of the response based on the emotion.

[0095] The generation unit can determine the priority of answers based on the submission time of the question at the time of generation. For example, the generation unit prioritizes answers to questions submitted earlier. For example, the generation unit prioritizes answers to questions submitted earlier. The generation unit can also postpone questions submitted later to efficiently utilize resources. Furthermore, the generation unit can set more detailed priorities when questions are submitted at the same time. For example, the generation unit postpones questions submitted later to efficiently utilize resources. This makes it possible to determine the priority of answers based on the submission time of the question and provide efficient answers. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the submission time of the question into the generation AI and cause the generation AI to determine the priority of answers based on the submission time.

[0096] The generation unit can adjust the order of answers based on the relevance of the questions when generating the answers. For example, the generation unit prioritizes answers to highly relevant questions. For example, the generation unit prioritizes answers to highly relevant questions. The generation unit can also postpone questions with low relevance to efficiently utilize resources. Furthermore, when there are multiple highly relevant questions, the generation unit can adjust the order in more detail. For example, the generation unit postpones questions with low relevance to efficiently utilize resources. This allows the order of answers to be adjusted based on the relevance of the questions, and efficient answers to be provided. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the relevance of questions to the generation AI and cause the generation AI to adjust the order of answers based on the relevance.

[0097] The generation unit can adjust the use of technical terminology in the answer depending on the employee's level of expertise during generation. For example, the generation unit generates an answer that uses a lot of technical terminology for an employee with a high level of expertise. For example, the generation unit generates an answer that uses a lot of technical terminology for an employee with a high level of expertise. The generation unit can also generate a concise and easy-to-understand answer for an employee with a low level of expertise. Furthermore, the generation unit can adjust the level of detail of the answer depending on the level of expertise. For example, the generation unit generates a concise and easy-to-understand answer for an employee with a low level of expertise. This makes it possible to adjust the use of technical terminology in the answer depending on the employee's level of expertise and provide an appropriate answer. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the employee's level of expertise into the generation AI and cause the generation AI to adjust the technical terminology of the answer based on the level of expertise.

[0098] The notification unit can estimate the employee's emotions and adjust the timing of notifications based on the estimated employee emotions. For example, if the employee is feeling stressed, the notification unit reduces the frequency of notifications to reduce the employee's burden. For example, if the employee is feeling stressed, the notification unit reduces the frequency of notifications to reduce the employee's burden. The notification unit can also increase the frequency of notifications and provide more detailed information when the employee is relaxed. Furthermore, if the employee is busy, the notification unit can adjust the timing of notifications between work tasks. For example, if the employee is relaxed, the notification unit increases the frequency of notifications and provides more detailed information. This allows the timing of notifications to be adjusted according to the employee's emotions and reduce the employee's burden. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the notification unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the notification unit can input employee emotional data into the generation AI and have the generation AI adjust the timing of notifications based on the emotions.

[0099] The notification unit can determine the priority of notifications based on the importance of the information at the time of notification. For example, the notification unit can prioritize notification of information with high importance and respond quickly. For example, the notification unit can prioritize notification of information with high importance and respond quickly. The notification unit can also postpone information with low importance to efficiently utilize resources. Furthermore, when there is multiple information with high importance, the notification unit can set the priority even more finely. For example, the notification unit postpones information with low importance to efficiently utilize resources. In this way, the priority of notifications can be determined based on the importance of the information, and efficient notifications can be achieved. Some or all of the above-mentioned processing in the notification unit may be performed using, or without, the generation AI. For example, the notification unit can input the importance of information to the generation AI at the time of notification and cause the generation AI to determine the priority of notifications based on the importance.

[0100] The notification unit can apply different notification methods depending on the category of information when notifying. For example, the notification unit applies a notification method including detailed procedures to information related to business processes. For example, the notification unit applies a notification method including detailed procedures when notifying information related to business processes. The notification unit can also apply a notification method including personal experiences and case studies to information related to know-how. Furthermore, the notification unit can apply a notification method including past response records to information related to inquiry history. For example, the notification unit applies a notification method including personal experiences and case studies when notifying information related to know-how. This allows an appropriate notification method to be applied depending on the category of information, thereby improving the accuracy of notifications. Some or all of the above-mentioned processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the category of information to the generation AI when notifying and cause the generation AI to apply a notification method depending on the category.

[0101] The notification unit can improve the accuracy of notifications by referring to past notification results when providing notifications. For example, the notification unit analyzes past notification results and applies an optimal notification method for similar information. For example, the notification unit analyzes past notification results and applies an optimal notification method for similar information. The notification unit can also apply an algorithm that improves the accuracy of notifications based on past notification results. Furthermore, the notification unit can maintain the consistency of notifications by referring to past notification results. For example, the notification unit applies an algorithm that improves the accuracy of notifications based on past notification results. This makes it possible to improve the accuracy of notifications by referring to past notification results and provide consistent notifications. Some or all of the above-described processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input past notification results into the generation AI and cause the generation AI to improve the accuracy of notifications based on the past notification results.

[0102] The notification unit can estimate the employee's emotions and adjust the content of the notification based on the estimated employee's emotions. For example, if the employee is feeling stressed, the notification unit can provide concise and easy-to-understand notification content. For example, if the employee is feeling stressed, the notification unit can provide concise and easy-to-understand notification content. Furthermore, if the employee is relaxed, the notification unit can provide notification content including a detailed explanation. Furthermore, if the employee is in a hurry, the notification unit can provide quick notification content that focuses on the main points. For example, if the employee is relaxed, the notification unit provides notification content including a detailed explanation. This makes it possible to adjust the notification content according to the employee's emotions and provide appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the notification unit can be performed using, for example, the generation AI. For example, the notification unit can input the employee's emotion data into the generation AI and have the generation AI adjust the notification content based on the emotion.

[0103] The notification unit can customize the content of notifications based on the employee's job title and job responsibilities. For example, the notification unit can provide managers with notifications regarding the overall progress of work and important decisions. For example, the notification unit can provide managers with notifications regarding the overall progress of work and important decisions. The notification unit can also provide general employees with notifications regarding specific procedures and tasks related to their daily work. Furthermore, the notification unit can provide notifications including relevant information and resources based on the employee's job responsibilities. For example, the notification unit can provide general employees with notifications regarding specific procedures and tasks related to their daily work. This allows the content of notifications to be customized based on the employee's job title and job responsibilities, and appropriate information to be provided. Some or all of the above-described processing in the notification unit can be performed using, or without, a generation AI. For example, the notification unit can input the employee's job title and job responsibilities into the generation AI and have the generation AI customize the notification content based on the job title and job responsibilities.

[0104] The notification unit can provide notifications taking into account the employee's geographic location information. For example, if the employee is in the office, the notification unit provides notifications regarding resources and support within the office. For example, if the employee is in the office, the notification unit provides notifications regarding resources and support within the office. Furthermore, if the employee is on a business trip, the notification unit can provide notifications regarding information about the business trip destination and support. Furthermore, if the employee is working remotely, the notification unit can provide notifications regarding resources and support related to the remote work. For example, if the employee is on a business trip, the notification unit provides notifications regarding information about the business trip destination and support. This makes it possible to provide appropriate information by providing notifications taking into account the employee's geographic location information. Some or all of the above-described processing by the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the employee's geographic location information into the generation AI and cause the generation AI to execute notifications based on the geographic location information.

[0105] The notification unit can analyze the employee's social media activity and notify the employee of relevant information at the time of notification. The notification unit, for example, notifies the employee of work-related information shared by the employee on social media. For example, the notification unit notifies the employee of work-related information shared by the employee on social media. The notification unit can also analyze the employee's social media activity and provide relevant work information. Furthermore, the notification unit can notify the employee of relevant work information by referring to the activity of the employee's friends on social media. For example, the notification unit analyzes the employee's social media activity and provides relevant work information. This makes it possible to analyze the employee's social media activity to notify the employee of relevant information and provide appropriate information. Some or all of the above-mentioned processing in the notification unit may be performed using, or without, a generation AI. For example, the notification unit can input the employee's social media activity into the generation AI and cause the generation AI to execute a notification based on the social media activity.

[0106] The management unit can estimate the employee's emotions and perform information quality control based on the estimated employee's emotions. For example, when an employee is stressed, the management unit performs strict information quality control and provides reliable information. For example, when an employee is stressed, the management unit performs strict information quality control and provides reliable information. Furthermore, when an employee is relaxed, the management unit can perform information quality control flexibly and provide detailed information. Furthermore, when an employee is busy, the management unit can quickly perform information quality control and provide necessary information quickly. For example, when an employee is relaxed, the management unit performs information quality control flexibly and provides detailed information. This allows information quality control to be performed according to the employee's emotions and provide reliable information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the management unit can be performed using, for example, a generative AI, or can be performed without using a generative AI. For example, the management department can input employees' emotional data into a generation AI and have the generation AI perform quality control of information based on emotions.

[0107] The management unit can evaluate the reliability of information during management and prioritize management of highly reliable information. The management unit, for example, verifies the source of the information and prioritizes management of highly reliable information. For example, the management unit can verify the source of the information and prioritize management of highly reliable information. The management unit can also identify highly reliable information sources based on past performance. Furthermore, the management unit can separately verify low-reliability information and manage it as needed. For example, the management unit can identify highly reliable information sources based on past performance. This allows the reliability of information to be evaluated and highly reliable information to be prioritized, thereby improving the quality of information. Some or all of the above-mentioned processing in the management unit may be performed using, or without, the generation AI. For example, the management unit can input the reliability of information into the generation AI during management and cause the generation AI to perform information management based on reliability.

[0108] The management unit can apply different management methods depending on the category of information during management. For example, the management unit applies a management method including detailed procedures to information related to business processes. For example, the management unit applies a management method including detailed procedures when managing information related to business processes. The management unit can also apply a management method including personal experiences and case studies to information related to know-how. Furthermore, the management unit can apply a management method including past response records to information related to inquiry history. For example, the management unit applies a management method including personal experiences and case studies when managing information related to know-how. This allows an appropriate management method to be applied depending on the category of information, thereby improving the accuracy of management. Some or all of the above-mentioned processing in the management unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the management unit can input the category of information into the generation AI during management and have the generation AI apply a management method depending on the category.

[0109] The management unit can estimate the employee's emotions and adjust the frequency of management based on the estimated employee emotions. For example, if the employee is feeling stressed, the management unit can reduce the frequency of management to reduce the employee's burden. For example, if the employee is feeling stressed, the management unit can reduce the frequency of management to reduce the employee's burden. Furthermore, if the employee is relaxed, the management unit can increase the frequency of management and manage detailed information. Furthermore, if the employee is busy, the management unit can adjust the frequency of management between work tasks. For example, if the employee is relaxed, the management unit can increase the frequency of management and manage detailed information. In this way, the frequency of management can be adjusted according to the employee's emotions and reduce the employee's burden. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the management unit can be performed, for example, using a generative AI, or can be performed without a generative AI. For example, the management department can input employee emotional data into the generation AI and have the generation AI adjust the frequency of management based on emotions.

[0110] The management unit can determine management priorities based on the time of information submission during management. For example, the management unit prioritizes management of information submitted early. For example, the management unit prioritizes management of information submitted early. The management unit can also postpone information submitted late to efficiently utilize resources. Furthermore, the management unit can set more detailed priorities when submission times overlap. For example, the management unit postpones information submitted late to efficiently utilize resources. In this way, management priorities can be determined based on the time of information submission, and efficient management can be achieved. Some or all of the above-mentioned processing in the management unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the management unit can input the time of information submission into the generation AI during management and have the generation AI determine management priorities based on the time of submission.

[0111] The management unit can improve the accuracy of management by referring to literature related to the information during management. For example, the management unit can refer to related literature to confirm the accuracy of the information. The management unit can also expand the scope of information to be managed based on the literature. Furthermore, the management unit can supplement the managed information based on the content of the literature. For example, the management unit can expand the scope of information to be managed based on the literature. This makes it possible to improve the accuracy of management by referring to related literature and provide accurate information. Some or all of the above-mentioned processing in the management unit can be performed using, or without, the generation AI. For example, the management unit can input literature related to the information into the generation AI during management and have the generation AI perform information management based on the related literature.

[0112] The employee information management unit can estimate an employee's emotions and adjust the employee information management method based on the estimated employee emotions. For example, if an employee is feeling stressed, the employee information management unit applies a simple and easy-to-understand management method. For example, if an employee is feeling stressed, the employee information management unit applies a simple and easy-to-understand management method. Furthermore, if an employee is feeling relaxed, the employee information management unit can apply a management method that includes detailed information. Furthermore, if an employee is in a hurry, the employee information management unit can apply a quick and simple management method. For example, if an employee is relaxed, the employee information management unit applies a management method that includes detailed information. This allows the employee information management method to be adjusted according to the employee's emotions and provide appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the employee information management unit can be performed, for example, using the generation AI, or without the generation AI. For example, the employee information management department can input employee emotional data into the generation AI and have the generation AI adjust management methods based on emotions.

[0113] The employee information management unit can manage information based on employees' job titles and responsibilities during management. For example, for managers, the employee information management unit manages information regarding the overall progress of work and important decisions. For example, for managers, the employee information management unit manages information regarding the overall progress of work and important decisions. The employee information management unit can also manage information regarding specific procedures and tasks related to daily work for general employees. Furthermore, the employee information management unit can manage related information and resources according to the responsibilities. For example, the employee information management unit manages information regarding specific procedures and tasks related to daily work for general employees. This allows information to be managed based on employees' job titles and responsibilities and appropriate information to be provided. Some or all of the above-described processing in the employee information management unit may be performed using, or without, a generation AI. For example, the employee information management unit can input employees' job titles and responsibilities into a generation AI and have the generation AI perform information management based on the job titles and responsibilities.

[0114] The employee information management unit can manage information by referring to the employee's past inquiry history during management. The employee information management unit, for example, manages information for similar inquiries based on the past inquiry history. For example, the employee information management unit manages information for similar inquiries based on the past inquiry history. The employee information management unit can also maintain consistency of information by referring to the past inquiry history. Furthermore, the employee information management unit can analyze the past inquiry history and apply an optimal management method. For example, the employee information management unit can maintain consistency of information by referring to the past inquiry history. This makes it possible to manage information by referring to the employee's past inquiry history and provide consistent information. Some or all of the above-mentioned processing in the employee information management unit may be performed using, or without, a generation AI. For example, the employee information management unit can input the employee's past inquiry history into the generation AI and have the generation AI perform information management based on the past inquiry history.

[0115] The employee information management unit can estimate the employee's emotions and determine management priorities based on the estimated employee emotions. For example, if an employee is feeling stressed, the employee information management unit prioritizes management of information of high importance. For example, if an employee is feeling stressed, the employee information management unit prioritizes management of information of high importance. Furthermore, if an employee is relaxed, the employee information management unit can prioritize management of detailed information. Furthermore, if an employee is busy, the employee information management unit can prioritize management of concise but important information. For example, if an employee is relaxed, the employee information management unit prioritizes management of detailed information. This allows management priorities to be determined based on the employee's emotions and appropriate information to be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the employee information management unit can be performed, for example, using a generation AI, or without a generation AI. For example, the employee information management department can input employee emotional data into the generation AI and have the generation AI determine management priorities based on emotions.

[0116] The employee information management unit can manage information taking into account the employee's geographic location information when managing information. For example, when an employee is in the office, the employee information management unit manages information about resources and support within the office. For example, when an employee is in the office, the employee information management unit manages information about resources and support within the office. Furthermore, when an employee is on a business trip, the employee information management unit can also manage information about the business trip destination and support. Furthermore, when an employee is working remotely, the employee information management unit can also manage information about resources and support related to the remote work. For example, when an employee is on a business trip, the employee information management unit manages information about the business trip destination and support. This makes it possible to manage information taking into account the employee's geographic location information and provide appropriate information. Some or all of the above-mentioned processing in the employee information management unit may be performed using, or without, a generation AI. For example, the employee information management unit can input the employee's geographic location information into the generation AI and have the generation AI perform information management based on the geographic location information.

[0117] The employee information management unit can analyze employees' social media activities during management and manage information. The employee information management unit, for example, manages work-related information shared by employees on social media. For example, the employee information management unit manages work-related information shared by employees on social media. The employee information management unit can also analyze employees' social media activities and manage related work information. Furthermore, the employee information management unit can manage related work information by referring to the activities of the employees' friends on social media. For example, the employee information management unit analyzes employees' social media activities and manages related work information. This makes it possible to analyze employees' social media activities to manage information and provide appropriate information. Some or all of the above-mentioned processing in the employee information management unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the employee information management unit can input employees' social media activities into a generation AI and have the generation AI perform information management based on the social media activities.

[0118] The customization unit can estimate the employee's emotions and adjust the customization method based on the estimated employee's emotions. For example, if the employee is feeling stressed, the customization unit applies a simple and easy-to-understand customization method. For example, if the employee is feeling stressed, the customization unit applies a simple and easy-to-understand customization method. The customization unit can also apply a customization method including detailed information if the employee is relaxed. The customization unit can also apply a quick and simple customization method if the employee is in a hurry. For example, if the employee is relaxed, the customization unit applies a customization method including detailed information. This allows the customization method to be adjusted according to the employee's emotions and provide appropriate customization. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the customization unit can be performed using, for example, the generation AI. For example, the customization unit can input the employee's emotion data into the generation AI and cause the generation AI to adjust the customization method based on the emotion.

[0119] The customization unit can perform customization based on the business processes or know-how of other companies. For example, the customization unit refers to the business processes of other companies and applies the optimal customization method. For example, the customization unit refers to the business processes of other companies and applies the optimal customization method. The customization unit can also refer to the know-how of other companies and apply an efficient customization method. Furthermore, the customization unit can improve the accuracy of customization based on successful cases of other companies. For example, the customization unit refers to the know-how of other companies and applies an efficient customization method. This makes it possible to perform customization by referring to the business processes and know-how of other companies and provide appropriate customization. Some or all of the above-described processing in the customization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the customization unit can input the business processes and know-how of other companies into the generation AI and cause the generation AI to perform customization based on the business processes and know-how.

[0120] The customization unit can perform customization by referring to the past inquiry history of other companies. For example, the customization unit can refer to the past inquiry history of other companies and apply the optimal customization method. For example, the customization unit can refer to the past inquiry history of other companies and apply the optimal customization method. The customization unit can also improve the accuracy of customization based on the past inquiry history of other companies. Furthermore, the customization unit can analyze the past inquiry history of other companies and apply an efficient customization method. For example, the customization unit can improve the accuracy of customization based on the past inquiry history of other companies. This makes it possible to perform customization by referring to the past inquiry history of other companies and provide appropriate customization. Some or all of the above-described processing in the customization unit may be performed using, or without, a generation AI. For example, the customization unit can input the past inquiry history of other companies into the generation AI and cause the generation AI to perform customization based on the past inquiry history.

[0121] The customization unit can estimate the employee's emotions and determine customization priorities based on the estimated employee emotions. For example, if the employee is feeling stressed, the customization unit prioritizes customizations of higher importance. For example, if the employee is feeling stressed, the customization unit prioritizes customizations of higher importance. The customization unit can also prioritize detailed customizations if the employee is relaxed. Furthermore, if the employee is busy, the customization unit can prioritize simple but important customizations. For example, if the employee is relaxed, the customization unit prioritizes detailed customizations. This allows customization priorities to be determined based on the employee's emotions and appropriate customizations to be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the customization unit can be performed using, for example, the generation AI, or without the generation AI. For example, the customization department can input employee emotional data into the generation AI and have the generation AI determine priorities for customization based on emotions.

[0122] The customization unit can perform customization taking into account the geographic location information of other companies. For example, when the other company is in an office, the customization unit performs customization related to resources and support within the office. For example, when the other company is in an office, the customization unit performs customization related to resources and support within the office. Furthermore, when the other company is on a business trip, the customization unit can also perform customization related to business trip destination information and support. Furthermore, when the other company is working remotely, the customization unit can also perform customization related to resources and support related to remote work. For example, when the other company is on a business trip, the customization unit performs customization related to business trip destination information and support. This makes it possible to perform customization taking into account the geographic location information of other companies and provide appropriate customization. Some or all of the above-described processing in the customization unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the customization unit can input the geographic location information of other companies into the generation AI and cause the generation AI to perform customization based on the geographic location information.

[0123] The customization unit can analyze the social media activities of other companies and perform customization during customization. The customization unit can perform customization based on, for example, business-related information shared by other companies on social media. For example, the customization unit can perform customization based on business-related information shared by other companies on social media. The customization unit can also analyze the social media activities of other companies and perform customization based on related business information. Furthermore, the customization unit can perform customization based on related business information, taking into account the activities of friends of other companies on social media. For example, the customization unit can analyze the social media activities of other companies and perform customization based on related business information. This makes it possible to analyze the social media activities of other companies and perform customization based on the related business information, thereby providing appropriate customization. Some or all of the above-described processing in the customization unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the customization unit can input the social media activities of other companies into the generation AI and cause the generation AI to perform customization based on the social media activities. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, generation unit, notification unit, quality control unit, employee information management unit, customization unit, and emotion estimation unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects information within the company using the camera 42 and microphone 38B of the smart device 14 and manages the information using the control unit 46A. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and generates answers using a generation AI based on the collected information. The notification unit is implemented, for example, by the control unit 46A of the smart device 14 and pushes the generated answers and useful information to employees. The quality control unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and manages the quality of the collected information. The employee information management unit is implemented, for example, by the control unit 46A of the smart device 14 and manages information such as employee titles, responsibilities, and past inquiry history. The customization unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and customizes services for other companies. The emotion estimation unit estimates the employee's emotion using, for example, the camera 42 or microphone 38B of the smart device 14, and adjusts the timing of information collection using the control unit 46A. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, generation unit, notification unit, quality control unit, employee information management unit, customization unit, and emotion estimation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects information within the company using the camera 42 and microphone 238 of the smart glasses 214 and manages the information using the control unit 46A. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates answers using a generation AI based on the collected information. The notification unit is realized, for example, by the control unit 46A of the smart glasses 214 and pushes the generated answers and useful information to employees. The quality control unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and manages the quality of the collected information. The employee information management unit is realized, for example, by the control unit 46A of the smart glasses 214 and manages information such as employee titles, responsibilities, and past inquiry history. The customization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and customizes services for other companies. The emotion estimation unit estimates the employee's emotion using, for example, the camera 42 and microphone 238 of the smart glasses 214, and adjusts the timing of information collection using the control unit 46A. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, generation unit, notification unit, quality control unit, employee information management unit, customization unit, and emotion estimation unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit collects information within the company using the camera 42 and microphone 238 of the headset terminal 314 and manages the information using the control unit 46A. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and generates answers using a generation AI based on the collected information. The notification unit is implemented, for example, by the control unit 46A of the headset terminal 314 and pushes the generated answers and useful information to employees. The quality control unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and manages the quality of the collected information. The employee information management unit is implemented, for example, by the control unit 46A of the headset terminal 314 and manages information such as employees' job titles, responsibilities, and past inquiry history. The customization unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and customizes services for other companies. The emotion estimation unit estimates the emotions of employees using, for example, the camera 42 and microphone 238 of the headset-type terminal 314, and adjusts the timing of information collection using the control unit 46A. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, generation unit, notification unit, quality control unit, employee information management unit, customization unit, and emotion estimation unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects information within the company using the camera 42 and microphone 238 of the robot 414 and manages the information using the control unit 46A. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates answers using a generation AI based on the collected information. The notification unit is realized, for example, by the control unit 46A of the robot 414 and pushes the generated answers and useful information to employees. The quality control unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and manages the quality of the collected information. The employee information management unit is realized, for example, by the control unit 46A of the robot 414 and manages information such as employee titles, responsibilities, and past inquiry history. The customization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and customizes services for other companies. The emotion estimation unit estimates the emotion of the employee using, for example, the camera 42 and microphone 238 of the robot 414, and adjusts the timing of information collection by the control unit 46A.

[0124] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0125] The collection unit may include a reliability evaluation unit for evaluating the reliability of information when collecting information within a company. The reliability evaluation unit evaluates the reliability of the collected information, for example, based on the source of the information and past performance. For example, the reliability evaluation unit may check the source of the information and prioritize the collection of highly reliable information. The reliability evaluation unit may also identify highly reliable information sources based on past performance. Furthermore, the reliability evaluation unit may separately verify less reliable information and collect it as necessary. This ensures the reliability of the collected information and improves the accuracy of the generation AI's responses.

[0126] When collecting information on a company's business processes or know-how, or past inquiry history, the collection department can determine the priority of collection based on the importance of the information. For example, the collection department prioritizes the collection of information with high importance and processes it quickly. For example, the collection department prioritizes the collection of information with high importance based on the impact on business operations and urgency. It is also possible to postpone the collection of information with low importance, thereby making efficient use of resources. Furthermore, when there is multiple pieces of information with high importance, it is possible to set the priority even more finely. This allows the collection of information with high importance to be prioritized, thereby achieving efficient information collection.

[0127] The generation unit may include a reliability evaluation unit for evaluating the reliability of an answer when generating an appropriate answer based on collected information. The reliability evaluation unit evaluates the reliability of the generated answer, for example, based on past answer results and the source of the information. For example, the reliability evaluation unit analyzes past answer results and generates an optimal answer to a similar question. The reliability evaluation unit can also check the source of the information and generate an answer based on highly reliable information. Furthermore, the reliability evaluation unit can separately verify information with low reliability and generate an answer as necessary. This ensures the reliability of the generated answer and provides appropriate information to employees.

[0128] The notification department can customize the content of push notifications that deliver useful information based on an employee's job title, job responsibilities, and past inquiry history. For example, the notification department can provide managers with notifications about the overall progress of work and important decisions. It can also provide general employees with notifications about specific procedures and tasks related to their daily work. Furthermore, the notification department can provide notifications that include relevant information and resources according to the employee's job responsibilities. This allows the content of notifications to be customized based on an employee's job title and job responsibilities, providing them with appropriate information.

[0129] When the collection unit includes a unit that performs information quality control, it can apply different quality control methods depending on the category of information. For example, for information related to business processes, a quality control method including detailed procedures can be applied. For information related to know-how, a quality control method including personal experiences and case studies can be applied. Furthermore, for information related to inquiry history, a quality control method including past response records can be applied. This allows the application of an appropriate quality control method depending on the category of information, thereby improving the quality of the information.

[0130] The collection unit manages employee information and, when improving the response accuracy of the generation AI, can estimate employee emotions and adjust the timing of information collection based on the estimated employee emotions. For example, if an employee is feeling stressed, the frequency of information collection can be reduced to reduce the burden. Also, if an employee is relaxed, the frequency of information collection can be increased to collect more detailed information. Furthermore, if an employee is busy, the timing of information collection can be adjusted to between work hours. This makes it possible to adjust the timing of information collection according to the employee's emotions and reduce the burden.

[0131] When the generation unit is provided with a customization unit that customizes services for other companies, the generation unit can adjust the customization method based on the employee's emotions. For example, if the employee is feeling stressed, a simple and easy-to-understand customization method can be applied. If the employee is feeling relaxed, a customization method including detailed information can be applied. Furthermore, if the employee is in a hurry, a quick and simple customization method can be applied. In this way, the customization method can be adjusted according to the employee's emotions, and appropriate customization can be provided.

[0132] The collection unit can estimate the employee's emotions and select the type of information to collect based on the estimated employee emotions. For example, if the employee is feeling stressed, it can prioritize collecting information that will help them relax. Also, if the employee is relaxed, it can collect detailed information that is useful for work. Furthermore, if the employee is busy, it can collect concise but important information. In this way, it is possible to select the type of information to collect according to the employee's emotions and provide appropriate information.

[0133] The generation unit can estimate the employee's emotions and adjust the way the answer is expressed based on the estimated employee's emotions. For example, if the employee is feeling stressed, a concise and easy-to-understand answer can be generated. If the employee is relaxed, an answer including detailed explanations can be generated. Furthermore, if the employee is in a hurry, a quick answer that gets to the point can be generated. This allows the way the answer is expressed to be adjusted according to the employee's emotions, and an appropriate answer can be provided.

[0134] The notification unit can estimate the employee's emotions and adjust the timing of notifications based on the estimated employee emotions. For example, if an employee is feeling stressed, the frequency of notifications can be reduced to reduce the burden on the employee. Also, if the employee is relaxed, the frequency of notifications can be increased and more detailed information can be provided. Furthermore, if the employee is busy, the timing of notifications can be adjusted to between work tasks. In this way, the timing of notifications can be adjusted according to the employee's emotions, reducing the burden on the employee.

[0135] The processing flow of the second embodiment will be briefly explained below.

[0136] Step 1: The collection department collects information within the company. This information includes business processes, know-how, and inquiry history. For example, the collection department collects business manuals, FAQs, and records of past inquiries. Step 2: The generation unit generates answers to employee inquiries based on the information collected by the collection unit. The generation unit uses generative AI to quickly respond to various inquiries, such as questions about business procedures and solutions to specific problems. Step 3: The notification unit pushes the answers and useful information generated by the generation unit to employees. The notification unit provides useful information at the appropriate time based on information such as the employee's position, job responsibilities, and past inquiry history.

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0142] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0149] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0151] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0153] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0158] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0159] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0161] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0164] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0165] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0166] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0167] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0176] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0177] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0179] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0180] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0181] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0182] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0183] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0184] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0185] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0186] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0187] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0189] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0190] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0191] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0192] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0193] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0194] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0195] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0196] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0197] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0198] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0199] 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.

[0200] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0201] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0202] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0203] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0204] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0205] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0206] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0207] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0208] [Explanation of symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection department that collects information within the company; a generating unit that generates an answer to the inquiry from the employee based on the information collected by the collecting unit; a notification unit that pushes the answer or useful information generated by the generation unit to employees; Equipped with A system characterized by:

2. The collecting unit Collect information on the company's business processes or know-how, and past inquiry history 2. The system of claim 1.

3. The generation unit Generate appropriate answers based on collected information 2. The system of claim 1.

4. The notification unit Send useful information based on employee job title, job responsibilities, and past inquiry history 2. The system of claim 1.

5. The collecting unit Equipping a department to manage information quality 2. The system of claim 1.

6. The collecting unit Manage employee information and improve the accuracy of generated AI responses 2. The system of claim 1.

7. The generation unit Has a customization department that customizes services for other companies 2. The system of claim 1.

8. The collecting unit Estimate employee emotions and adjust the timing of information gathering based on the estimated employee emotions 2. The system of claim 1.

9. The collecting unit Prioritize collection based on the importance of the information to be collected 2. The system of claim 1.

10. The collecting unit Evaluate the reliability of information when collecting it and prioritize collection of reliable information 2. The system of claim 1.

Images