system

Abstract

The system according to this embodiment aims to enable employees to quickly and appropriately obtain internal company information. [Solution] The system according to this embodiment comprises a reception unit, an analysis unit, and a provision unit. The reception unit receives questions from employees. The analysis unit analyzes the questions received by the reception unit and searches internal company documents. The provision unit provides the information retrieved by the analysis unit to the employees.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult for newly hired employees or transferees to quickly obtain in-house information, and there is a risk of stress and anxiety.

[0005] The system according to the embodiment aims to enable employees to quickly and appropriately obtain in-house information.

Means for Solving the Problems

[0006] The system according to the embodiment includes a reception unit, an analysis unit, and a provision unit. The reception unit receives questions from employees. The analysis unit analyzes the questions received by the reception unit and searches for in-house documents. The provision unit provides the information searched by the analysis unit to the employees.

Effects of the Invention

[0007] The system according to this embodiment can enable employees to quickly and appropriately obtain company information. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The internal assistant tool according to an embodiment of the present invention is a system that utilizes generating AI to alleviate the lack of information and anxiety experienced by new employees and those transferring departments, thereby improving work efficiency and psychological safety. In this system, employees input questions, the generating AI analyzes the questions, searches internal documents, and provides relevant information. Furthermore, the information input by employees is accumulated as knowledge, improving the accuracy of answers to subsequent questions. In addition, the system considers the security of output by linking the input information with the information category, using the employee's department as an information category. This allows employees to proceed with their work with peace of mind, without feeling a lack of information or anxiety. This allows internal assistant tools to alleviate employee information deficiencies and anxieties, thereby improving work efficiency and psychological safety.

[0029] The internal assistant tool according to this embodiment comprises a reception unit, an analysis unit, and a provision unit. The reception unit receives questions from employees. Employee questions include, but are not limited to, questions in text format, voice format, or on specific topics. The reception unit can, for example, receive questions in text format. The reception unit can also receive questions in voice format. Furthermore, the reception unit can also receive questions on specific topics. For example, the reception unit receives questions in text format and analyzes them using natural language processing technology. Questions in voice format are converted to text using speech recognition technology and then analyzed. Questions on specific topics are analyzed using keyword matching technology. The analysis unit analyzes the questions received by the reception unit and searches internal company documents. The analysis is performed using, but is not limited to, methods such as natural language processing technology, keyword matching, and machine learning algorithms. For example, the analysis unit analyzes questions using natural language processing technology and searches related internal company documents. The analysis unit can also analyze questions using keyword matching technology and identify relevant information. Furthermore, the analysis department can also analyze questions using machine learning algorithms and provide optimal information. For example, the analysis department can analyze questions using natural language processing technology and search for relevant internal documents. Keyword matching technology compares keywords in the question with keywords in internal documents to identify information with a high degree of match. Machine learning algorithms learn from past question and answer data to generate optimal answers for new questions. The delivery department provides the information retrieved by the analysis department to employees. Delivery may be, but is not limited to, email, dashboard display, or real-time notification. For example, the delivery department can provide information via email. The delivery department can also display information on a dashboard. Furthermore, the delivery department can provide information via real-time notification. For example, the delivery department can provide information via email so that employees can quickly obtain the information they need. The dashboard displays information in an easily accessible format for employees, allowing them to see the necessary information at a glance.Real-time notifications allow employees to be immediately informed of important information, enabling a quick response. This allows the internal assistant tool according to the embodiment to efficiently receive, analyze, and provide information to employees regarding their questions.

[0030] The reception desk receives questions from employees. These questions may include, but are not limited to, text-based, audio-based, or questions on specific topics. For example, the reception desk can accept text-based questions, audio-based questions, and questions on specific topics. For instance, the reception desk can accept text-based questions and analyze them using natural language processing techniques. Audio-based questions are converted to text and analyzed using speech recognition techniques. Questions on specific topics are analyzed using keyword matching techniques. The reception desk can provide web or mobile applications as interfaces for employees to use, allowing them to easily submit questions from their devices. Text-based questions are accepted via chatbots or form input, while audio-based questions are recorded using microphones. Speech recognition uses speech models to convert audio data to text, also removing background noise and identifying the speaker. Questions on specific topics are categorized using predefined categories and tags, and keyword matching techniques analyze the content of the questions to identify relevant topics. This allows the reception department to handle diverse question formats from employees and efficiently receive inquiries. Furthermore, the reception department can have a function to evaluate the priority and urgency of questions upon receipt. For example, by responding immediately to high-urgency questions and postponing lower-priority questions, it can achieve optimal resource allocation. In addition, the reception department can save the history of received questions and refer to it later, thereby building a database of past questions and answers. This allows the reception department to efficiently receive employee questions and prepare them for handover to the analysis department.

[0031] The analysis department analyzes questions received by the reception department and searches internal documents. Analysis is performed using methods such as, but is not limited to, natural language processing, keyword matching, and machine learning algorithms. For example, the analysis department can use natural language processing to analyze questions and search related internal documents. It can also use keyword matching to analyze questions and identify relevant information. Furthermore, it can use machine learning algorithms to analyze questions and provide optimal information. For example, the analysis department can use natural language processing to analyze questions and search related internal documents. Keyword matching compares keywords in the question with keywords in internal documents to identify information with a high degree of match. Machine learning algorithms learn from past question and answer data to generate the best answer for new questions. To understand the content of a question, the analysis department uses natural language processing to analyze the context and identify the intent of the question. For example, even if a question is ambiguous, it can find the most appropriate answer by considering the context. Keyword matching extracts keywords from the question and compares them with keywords in internal documents to identify highly relevant information. This allows the analysis unit to quickly and accurately search for relevant information. The machine learning algorithm learns from past question and answer data and generates the optimal answer to new questions. For example, it can learn patterns from past questions and answers and provide the best answer to similar questions. Furthermore, the analysis unit can prioritize and provide relevant information based on the analysis results of the questions. This allows the analysis unit to provide quick and accurate answers to employee questions, improving work efficiency.

[0032] The information delivery department provides employees with information retrieved by the analysis department. This delivery can be, but is not limited to, email, dashboard display, or real-time notifications. For example, the information delivery department can provide information via email. It can also display information on a dashboard. Furthermore, it can provide information via real-time notifications. For example, the information delivery department can provide information via email, allowing employees to quickly obtain the information they need. Dashboards display information in an easily accessible format, allowing employees to see the necessary information at a glance. Real-time notifications instantly inform employees of important information, enabling quick responses. The information delivery department is designed to offer flexible options for information delivery, allowing it to select the most suitable method based on employee needs. For example, high-priority information can be provided immediately via real-time notifications, while detailed information can be provided via email or dashboards. The information delivery department can also save a history of information delivery for later reference, enabling tracing of past information provision. Furthermore, the information delivery department can collect feedback from employees to continuously improve the accuracy and effectiveness of information delivery. For example, it can evaluate whether the provided information was useful and revise the delivery method and content based on the feedback. Furthermore, the information delivery department can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, and email. This allows the information delivery department to provide information to employees quickly and reliably, improving operational efficiency.

[0033] The reception desk can accept employees' department affiliations as information categories. For example, the reception desk can accept employees' department affiliations as input and manage them as information categories. For example, the reception desk can input the department to which an employee belongs and set an information category based on that information. The reception desk can also set information categories for each project. For example, the reception desk can categorize information related to a specific project and provide appropriate information. Furthermore, the reception desk can also set information categories for each job title. For example, the reception desk can set information categories for managers and general employees and provide appropriate information. This makes it possible to provide appropriate information by categorizing information based on the employee's department affiliation. Information categories include, but are not limited to, categories by department, category by project, category by job title, etc. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can manage information categories using an AI model that accepts employees' department affiliations as input and sets information categories based on that information.

[0034] The analysis unit can search internal documents and identify relevant information. For example, the analysis unit can perform a full-text search of internal documents to identify relevant information. For example, the analysis unit can search the full text of internal documents to identify information related to a question. The analysis unit can also perform metadata searches. For example, the analysis unit can search the metadata of internal documents to identify relevant information. Furthermore, the analysis unit can perform searches with filtering conditions set. For example, the analysis unit can set filtering conditions such as specific keywords or date ranges to identify relevant information. This allows for the provision of appropriate information to employees by searching internal documents and identifying relevant information. Relevant information includes, but is not limited to, highly relevant information, the latest information, and frequently occurring information. Some or all of the above processing in the analysis unit may be performed using generative AI, or not. For example, the analysis unit can identify information using a generative AI model that performs a full-text search of internal documents and identifies relevant information.

[0035] The information delivery unit can provide identified information to employees. For example, the information delivery unit can provide identified information via email. For example, the information delivery unit can send identified information to employees via email to provide information quickly. The information delivery unit can also display the information on a dashboard. For example, the information delivery unit can display identified information on a dashboard and provide it in a format that is easy for employees to access. Furthermore, the information delivery unit can also provide information via real-time notifications. For example, the information delivery unit can notify employees of identified information in real time, immediately conveying important information to employees. This alleviates employee information deficiencies and anxieties by providing employees with identified information. Identified information includes, but is not limited to, information of high importance and information of high relevance. Some or all of the above processes in the information delivery unit may be performed using AI or not. For example, the information delivery unit can provide information using an AI model that provides identified information via email.

[0036] The storage unit can store knowledge. For example, the storage unit can store FAQs. For example, the storage unit stores questions from employees and their answers as FAQs to improve the accuracy of answers to future questions. The storage unit can also store past questions and answers. For example, the storage unit stores questions and answers from employees in the past in a database to use as a reference for future questions. Furthermore, the storage unit can also store technical documents. For example, the storage unit stores internal technical documents in a database so that employees can quickly obtain the information they need. By accumulating knowledge in this way, the accuracy of answers to future questions is improved. Knowledge includes, but is not limited to, FAQs, past questions and answers, and technical documents. Some or all of the above processes in the storage unit may be performed using AI or not. For example, the storage unit can store knowledge using an AI model that stores questions from employees and their answers.

[0037] The Management Department can manage information classification. For example, the Management Department can manage information classification by setting access permissions. For example, the Management Department can set access permissions based on the department and position of employees to ensure information security. The Management Department can also manage information classification by setting methods for classifying information. For example, the Management Department can classify information by department, project, and position to provide appropriate information. Furthermore, the Management Department can manage information classification by setting the frequency of information updates. For example, the Management Department can frequently update important information to provide the latest information. In this way, by managing information classification, consideration can be given to the security of the output. Information classification includes, but is not limited to, setting access permissions, methods for classifying information, and information update frequency. Some or all of the above processes in the Management Department may be performed using AI or not. For example, the Management Department can manage information classification using an AI model that sets access permissions based on the department and position of employees.

[0038] The reception department can analyze an employee's past question history and select the optimal reception method. For example, the reception department can automatically suggest relevant questions based on the content of questions the employee has frequently asked in the past. For example, the reception department can store past question history in a database and analyze frequently asked questions. The reception department can also prioritize suggesting question formats (text, voice, etc.) that the employee has used in the past. For example, the reception department can analyze past question formats and suggest the most suitable format. Furthermore, the reception department can select a reception method suitable for a specific time of day based on the employee's past question history. For example, the reception department selects a reception method suitable for a specific time of day based on past question history. This allows the reception department to select the optimal reception method by analyzing the employee's past question history. The question history includes, but is not limited to, a database of past questions and answers and an analysis of frequently asked questions. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department can use an AI model that analyzes an employee's past question history and selects the optimal reception method to handle question reception.

[0039] The reception desk can filter questions based on the employee's current projects and areas of interest. For example, the reception desk can prioritize questions related to the employee's current projects. For example, the reception desk can accept the employee's project information as input and filter out relevant questions. The reception desk can also filter and accept questions based on the employee's areas of interest. For example, the reception desk can accept the employee's areas of interest as input and filter out relevant questions. Furthermore, the reception desk can accept appropriate questions according to the employee's project progress. For example, the reception desk can accept the project progress as input and filter out appropriate questions. This ensures that appropriate questions are received by filtering questions based on the employee's current projects and areas of interest. Filtering includes, but is not limited to, project names, areas of interest, and keywords. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can receive questions using an AI model that filters questions based on the employee's current projects and areas of interest.

[0040] The reception desk can prioritize receiving questions that are highly relevant, taking into account the employee's geographical location. For example, if an employee is in a specific office, the reception desk will prioritize questions related to that office. For instance, the reception desk can accept the employee's geographical location as input and filter out relevant questions. Furthermore, if an employee is on a business trip, the reception desk can prioritize questions related to their destination. For example, the reception desk can accept the employee's business trip destination as input and filter out relevant questions. Additionally, if an employee is working remotely, the reception desk can prioritize questions related to their home or remote work environment. For example, the reception desk can accept the employee's remote work environment as input and filter out relevant questions. This allows for prioritizing the reception of highly relevant questions by considering the employee's geographical location. Geographical location information includes, but is not limited to, GPS data, IP addresses, and beacons. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can use an AI model that filters questions based on the employee's geographical location to handle inquiries.

[0041] The reception desk can analyze an employee's social media activity when receiving a question and receive relevant questions. For example, the reception desk can receive relevant questions based on information shared by the employee on social media. For example, the reception desk can receive an employee's social media activity as input and filter for relevant questions. The reception desk can also receive questions related to topics of interest from an employee's social media activity. For example, the reception desk can analyze an employee's social media activity and filter for questions related to topics of interest. Furthermore, the reception desk can receive questions related to accounts that an employee follows on social media. For example, the reception desk can receive information about accounts that an employee follows as input and filter for relevant questions. In this way, relevant questions can be received by analyzing an employee's social media activity. Social media activity includes, but is not limited to, posts, the number of likes, and the number of followers. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can receive questions using an AI model that analyzes an employee's social media activity and receives relevant questions.

[0042] The analysis unit can adjust the level of detail of the analysis based on the importance of the questions during the analysis. For example, the analysis unit can perform a detailed analysis for questions of high importance. For example, the analysis unit can evaluate the importance of the questions and perform a detailed analysis for those of high importance. The analysis unit can also perform a concise analysis for questions of low importance. For example, the analysis unit can evaluate the importance of the questions and perform a concise analysis for those of low importance. Furthermore, the analysis unit can select an appropriate level of detail of analysis according to the importance of the questions. For example, the analysis unit can evaluate the importance of the questions and select an appropriate level of detail of analysis. This makes it possible to provide appropriate information by adjusting the level of detail of the analysis according to the importance of the questions. The importance of a question includes, but is not limited to, the degree of impact on business, urgency, and frequency. Some or all of the above processing in the analysis unit may be performed using generative AI, or it may be performed without using generative AI. For example, the analysis unit can perform the analysis using a generative AI model that evaluates the importance of questions and adjusts the level of detail of the analysis.

[0043] The analysis unit can apply different analysis algorithms depending on the category of the question during analysis. For example, for technical questions, the analysis unit can apply a specialized technical analysis algorithm. For example, the analysis unit can accept a technical question as input and apply a specialized technical analysis algorithm. The analysis unit can also apply a specialized business process analysis algorithm to questions about business processes. For example, the analysis unit can accept a question about business processes as input and apply a specialized business process analysis algorithm. Furthermore, the analysis unit can apply a specialized corporate culture analysis algorithm to questions about corporate culture. For example, the analysis unit can accept a question about corporate culture as input and apply a specialized corporate culture analysis algorithm. This allows for more accurate analysis by applying the appropriate analysis algorithm according to the category of the question. The categories of questions include, but are not limited to, technical questions, questions about business processes, and general questions. Some or all of the above processing in the analysis unit may be performed using generative AI, or not. For example, the analysis unit can perform analysis using a generative AI model that applies an analysis algorithm according to the category of the question.

[0044] The analysis unit can determine the priority of analysis based on when the questions were submitted. For example, the analysis unit may prioritize the analysis of recently submitted questions. For example, the analysis unit may accept the submission date of the questions as input and prioritize the analysis of recently submitted questions. The analysis unit can also set appropriate priorities according to the submission date of the questions. For example, the analysis unit may evaluate the submission date of the questions and set appropriate priorities. Furthermore, the analysis unit may set a lower priority for questions that were submitted a long time ago. For example, the analysis unit may evaluate the submission date of the questions and set a lower priority for older questions. This makes it possible to provide appropriate information by determining the priority of analysis based on the submission date of the questions. The submission date includes, but is not limited to, timestamps and records of the submission date. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis using a generative AI model that evaluates the submission date of questions and determines the priority of analysis.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the questions during analysis. For example, the analysis unit can prioritize the analysis of questions that are highly relevant. For example, the analysis unit can evaluate the relevance of the questions and prioritize the analysis of highly relevant questions. The analysis unit can also postpone the analysis of questions that are less relevant. For example, the analysis unit can evaluate the relevance of the questions and postpone the analysis of less relevant questions. Furthermore, the analysis unit can perform the analysis in an appropriate order according to the relevance of the questions. For example, the analysis unit can evaluate the relevance of the questions and perform the analysis in an appropriate order. By adjusting the order of analysis based on the relevance of the questions, it becomes possible to provide appropriate information. The relevance of questions includes, but is not limited to, keyword matching and topic similarity. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis using a generative AI model that evaluates the relevance of questions and adjusts the order of analysis.

[0046] The information delivery unit can adjust the level of detail provided based on the importance of the information at the time of delivery. For example, the delivery unit can provide detailed information for highly important information. For example, the delivery unit can evaluate the importance of the information and provide detailed information for highly important information. The delivery unit can also provide concise information for less important information. For example, the delivery unit can evaluate the importance of the information and provide concise information for less important information. Furthermore, the delivery unit can select an appropriate level of detail for the information according to its importance. For example, the delivery unit can evaluate the importance of the information and select an appropriate level of detail. This makes it possible to provide appropriate information by adjusting the level of detail according to the importance of the information. The importance of information includes, but is not limited to, the degree of impact on business, urgency, and frequency. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can provide information using an AI model that evaluates the importance of information and adjusts the level of detail for the information provided.

[0047] The information delivery unit can apply different delivery algorithms depending on the category of information at the time of delivery. For example, the delivery unit can apply a specialized technical delivery algorithm to technical information. For example, the delivery unit can accept technical information as input and apply a specialized technical delivery algorithm. The delivery unit can also apply a specialized business process delivery algorithm to information related to business processes. For example, the delivery unit can accept information related to business processes as input and apply a specialized business process delivery algorithm. Furthermore, the delivery unit can apply a specialized corporate culture delivery algorithm to information related to corporate culture. For example, the delivery unit can accept information related to corporate culture as input and apply a specialized corporate culture delivery algorithm. This makes it possible to provide more accurate information by applying the appropriate delivery algorithm according to the category of information. Information categories include, but are not limited to, technical information, information related to business processes, and general information. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can provide information using an AI model that applies a delivery algorithm according to the category of information.

[0048] The information provider can determine the priority of information provision based on the submission date at the time of provision. For example, the provider may prioritize the provision of recently submitted information. For example, the provider may accept the submission date as input and prioritize the provision of recently submitted information. The provider can also set appropriate priorities according to the submission date of the information. For example, the provider may evaluate the submission date of the information and set appropriate priorities. Furthermore, the provider may set a lower priority for older information. For example, the provider may evaluate the submission date of the information and set a lower priority for older information. This makes it possible to provide appropriate information by determining the priority of provision based on the submission date of the information. The submission date includes, but is not limited to, timestamps and records of the submission date. Some or all of the above processing in the provider may be performed using AI or not. For example, the provider can provide information using an AI model that evaluates the submission date of information and determines the priority of provision.

[0049] The information provider can adjust the order of information delivery based on its relevance. For example, the provider can prioritize the delivery of highly relevant information. For instance, the provider can evaluate the relevance of information and prioritize the delivery of highly relevant information. The provider can also postpone the delivery of less relevant information. For example, the provider can evaluate the relevance of information and postpone the delivery of less relevant information. Furthermore, the provider can deliver information in an appropriate order according to its relevance. For example, the provider can evaluate the relevance of information and deliver it in an appropriate order. This allows for appropriate information delivery by adjusting the order of delivery based on the relevance of information. Information relevance includes, but is not limited to, keyword matching and topic similarity. Some or all of the above processing in the information provider may be performed using AI or not. For example, the information provider can provide information using an AI model that evaluates the relevance of information and adjusts the order of delivery.

[0050] The storage unit can optimize the storage algorithm by referring to past stored data during storage. For example, the storage unit can select the optimal storage algorithm based on past stored data. For example, the storage unit can analyze past stored data and select the optimal storage algorithm. The storage unit can also derive an efficient storage method from past stored data. For example, the storage unit can analyze past stored data and derive an efficient storage method. Furthermore, the storage unit can analyze past stored data and optimize the storage algorithm. For example, the storage unit analyzes past stored data and optimizes the storage algorithm. This allows the storage algorithm to be optimized by referring to past stored data. Stored data includes, but is not limited to, past questions and answers, technical documents, and FAQs. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can store data using an AI model that analyzes past stored data and optimizes the storage algorithm.

[0051] The storage unit can weight the stored data based on when the questions were submitted. For example, the storage unit can prioritize storing data related to recently submitted questions. For example, the storage unit can accept the submission date of a question as input and prioritize storing data related to recently submitted questions. The storage unit can also perform appropriate weighting according to the submission date of the question. For example, the storage unit can evaluate the submission date of the question and perform appropriate weighting. Furthermore, the storage unit can set a lower weight for older questions. For example, the storage unit can evaluate the submission date of the question and set a lower weight for older questions. This enables appropriate data storage by weighting the stored data based on the submission date of the question. The submission date includes, but is not limited to, timestamps and records of the submission date. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can store data using an AI model that evaluates the submission date of a question and weights the stored data.

[0052] The management department can optimize management algorithms by referring to past management data during management. For example, the management department can select the optimal management algorithm based on past management data. For example, the management department can analyze past management data and select the optimal management algorithm. The management department can also derive efficient management methods from past management data. For example, the management department can analyze past management data and derive efficient management methods. Furthermore, the management department can analyze past management data and optimize management algorithms. For example, the management department can analyze past management data and optimize management algorithms. This allows for the optimization of management algorithms by referring to past management data. Management data includes, but is not limited to, past management records, access logs, and security settings. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can manage information using an AI model that analyzes past management data and optimizes management algorithms.

[0053] The management department can weight management data based on the submission date of the information during management. For example, the management department can prioritize the management of recently submitted information. For example, the management department can accept the submission date of the information as input and prioritize the management of recently submitted information. The management department can also perform appropriate weighting according to the submission date of the information. For example, the management department can evaluate the submission date of the information and perform appropriate weighting. Furthermore, the management department can set a lower weight for information that is older. For example, the management department can evaluate the submission date of the information and set a lower weight for older information. This enables appropriate information management by weighting management data based on the submission date of the information. The submission date includes, but is not limited to, timestamps and records of the submission date. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can manage information using an AI model that evaluates the submission date of information and weights management data.

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

[0055] The reception department can assess the urgency of employee inquiries and prioritize processing those with higher urgency. For example, the reception department can analyze the content of the inquiries and use an algorithm to quickly send high-urgency inquiries to the analysis department. The reception department can also set appropriate response times according to the urgency of the inquiries. For example, high-urgency inquiries can be answered immediately, while lower-urgency inquiries can be handled within the normal response time. Furthermore, the reception department can dynamically adjust the priority of inquiries based on their urgency. This enables appropriate responses to employee inquiries according to their urgency.

[0056] The analysis department can search relevant external resources and identify the appropriate information based on the content of the question. For example, it can search publicly available databases and specialized websites on the internet to identify information related to the question. It can also forward the question to external experts or consultants to obtain expert answers. Furthermore, the analysis department can integrate the information obtained from external resources with internal documents to provide a comprehensive answer. This enables the provision of more accurate information by utilizing both internal and external resources.

[0057] The information provision department can evaluate the reliability of answers to employee questions and prioritize providing highly reliable information. For example, the department can evaluate the source and information sources of answers and select highly reliable information. The department can also refer to past answer history and prioritize providing highly reliable answers. Furthermore, the department can adjust the level of detail in answers based on their reliability. This ensures that employees can perform their work with confidence by receiving reliable information.

[0058] The data storage unit can evaluate the quality of the stored data when accumulating knowledge, and prioritize the storage of high-quality data. For example, the storage unit can evaluate the accuracy and reliability of the data and select high-quality data. It can also evaluate the update frequency and usage frequency of the data and prioritize the storage of important data. Furthermore, the storage unit can dynamically adjust the storage priority based on the data quality. This ensures the quality of the stored data and improves the accuracy of answers to future questions.

[0059] The management department can evaluate the confidentiality of information when managing information classifications and strictly manage highly confidential information. For example, the management department can use an algorithm to evaluate the confidentiality of information and set strict access restrictions for highly confidential information. Furthermore, the management department can strengthen information encryption and security measures based on the confidentiality of the information. In addition, the management department can dynamically adjust information management methods according to the confidentiality of the information. This allows for the proper management of highly confidential information and ensures information security.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The reception desk receives questions from employees. These questions can be in text format, audio format, or on specific topics. For example, text questions are accepted as is, audio questions are converted to text using speech recognition technology, and questions on specific topics are analyzed using keyword matching technology. Step 2: The analysis department analyzes the questions received by the reception department and searches internal documents. The analysis is performed using methods such as natural language processing, keyword matching, and machine learning algorithms. For example, natural language processing is used to analyze the questions and search for relevant internal documents. Keyword matching compares the keywords in the questions with the keywords in the internal documents to identify information with a high degree of match. Machine learning algorithms learn from past question and answer data to generate the best answer for new questions. Step 3: The provisioning department provides employees with the information retrieved by the analysis department. This provision can be done via email, dashboard display, or real-time notifications. For example, information can be provided via email to allow employees to quickly obtain the information they need. Dashboards display information in an easily accessible format, allowing employees to see the necessary information at a glance. Real-time notifications instantly inform employees of important information, enabling quick responses.

[0062] (Example of form 2) The internal assistant tool according to an embodiment of the present invention is a system that utilizes generating AI to alleviate the lack of information and anxiety experienced by new employees and those transferring departments, thereby improving work efficiency and psychological safety. In this system, employees input questions, the generating AI analyzes the questions, searches internal documents, and provides relevant information. Furthermore, the information input by employees is accumulated as knowledge, improving the accuracy of answers to subsequent questions. In addition, the system considers the security of output by linking the input information with the information category, using the employee's department as an information category. This allows employees to proceed with their work with peace of mind, without feeling a lack of information or anxiety. This allows internal assistant tools to alleviate employee information deficiencies and anxieties, thereby improving work efficiency and psychological safety.

[0063] The internal assistant tool according to this embodiment comprises a reception unit, an analysis unit, and a provision unit. The reception unit receives questions from employees. Employee questions include, but are not limited to, questions in text format, voice format, or on specific topics. The reception unit can, for example, receive questions in text format. The reception unit can also receive questions in voice format. Furthermore, the reception unit can also receive questions on specific topics. For example, the reception unit receives questions in text format and analyzes them using natural language processing technology. Questions in voice format are converted to text using speech recognition technology and then analyzed. Questions on specific topics are analyzed using keyword matching technology. The analysis unit analyzes the questions received by the reception unit and searches internal company documents. The analysis is performed using, but is not limited to, methods such as natural language processing technology, keyword matching, and machine learning algorithms. For example, the analysis unit analyzes questions using natural language processing technology and searches related internal company documents. The analysis unit can also analyze questions using keyword matching technology and identify relevant information. Furthermore, the analysis department can also analyze questions using machine learning algorithms and provide optimal information. For example, the analysis department can analyze questions using natural language processing technology and search for relevant internal documents. Keyword matching technology compares keywords in the question with keywords in internal documents to identify information with a high degree of match. Machine learning algorithms learn from past question and answer data to generate optimal answers for new questions. The delivery department provides the information retrieved by the analysis department to employees. Delivery may be, but is not limited to, email, dashboard display, or real-time notification. For example, the delivery department can provide information via email. The delivery department can also display information on a dashboard. Furthermore, the delivery department can provide information via real-time notification. For example, the delivery department can provide information via email so that employees can quickly obtain the information they need. The dashboard displays information in an easily accessible format for employees, allowing them to see the necessary information at a glance.Real-time notifications allow employees to be immediately informed of important information, enabling a quick response. This allows the internal assistant tool according to the embodiment to efficiently receive, analyze, and provide information to employees regarding their questions.

[0064] The reception desk receives questions from employees. These questions may include, but are not limited to, text-based, audio-based, or questions on specific topics. For example, the reception desk can accept text-based questions, audio-based questions, and questions on specific topics. For instance, the reception desk can accept text-based questions and analyze them using natural language processing techniques. Audio-based questions are converted to text and analyzed using speech recognition techniques. Questions on specific topics are analyzed using keyword matching techniques. The reception desk can provide web or mobile applications as interfaces for employees to use, allowing them to easily submit questions from their devices. Text-based questions are accepted via chatbots or form input, while audio-based questions are recorded using microphones. Speech recognition uses speech models to convert audio data to text, also removing background noise and identifying the speaker. Questions on specific topics are categorized using predefined categories and tags, and keyword matching techniques analyze the content of the questions to identify relevant topics. This allows the reception department to handle diverse question formats from employees and efficiently receive inquiries. Furthermore, the reception department can have a function to evaluate the priority and urgency of questions upon receipt. For example, by responding immediately to high-urgency questions and postponing lower-priority questions, it can achieve optimal resource allocation. In addition, the reception department can save the history of received questions and refer to it later, thereby building a database of past questions and answers. This allows the reception department to efficiently receive employee questions and prepare them for handover to the analysis department.

[0065] The analysis department analyzes questions received by the reception department and searches internal documents. Analysis is performed using methods such as, but is not limited to, natural language processing, keyword matching, and machine learning algorithms. For example, the analysis department can use natural language processing to analyze questions and search related internal documents. It can also use keyword matching to analyze questions and identify relevant information. Furthermore, it can use machine learning algorithms to analyze questions and provide optimal information. For example, the analysis department can use natural language processing to analyze questions and search related internal documents. Keyword matching compares keywords in the question with keywords in internal documents to identify information with a high degree of match. Machine learning algorithms learn from past question and answer data to generate the best answer for new questions. To understand the content of a question, the analysis department uses natural language processing to analyze the context and identify the intent of the question. For example, even if a question is ambiguous, it can find the most appropriate answer by considering the context. Keyword matching extracts keywords from the question and compares them with keywords in internal documents to identify highly relevant information. This allows the analysis unit to quickly and accurately search for relevant information. The machine learning algorithm learns from past question and answer data and generates the optimal answer to new questions. For example, it can learn patterns from past questions and answers and provide the best answer to similar questions. Furthermore, the analysis unit can prioritize and provide relevant information based on the analysis results of the questions. This allows the analysis unit to provide quick and accurate answers to employee questions, improving work efficiency.

[0066] The information delivery department provides employees with information retrieved by the analysis department. This delivery can be, but is not limited to, email, dashboard display, or real-time notifications. For example, the information delivery department can provide information via email. It can also display information on a dashboard. Furthermore, it can provide information via real-time notifications. For example, the information delivery department can provide information via email, allowing employees to quickly obtain the information they need. Dashboards display information in an easily accessible format, allowing employees to see the necessary information at a glance. Real-time notifications instantly inform employees of important information, enabling quick responses. The information delivery department is designed to offer flexible options for information delivery, allowing it to select the most suitable method based on employee needs. For example, high-priority information can be provided immediately via real-time notifications, while detailed information can be provided via email or dashboards. The information delivery department can also save a history of information delivery for later reference, enabling tracing of past information provision. Furthermore, the information delivery department can collect feedback from employees to continuously improve the accuracy and effectiveness of information delivery. For example, it can evaluate whether the provided information was useful and revise the delivery method and content based on the feedback. Furthermore, the information delivery department can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, and email. This allows the information delivery department to provide information to employees quickly and reliably, improving operational efficiency.

[0067] The reception desk can accept employees' department affiliations as information categories. For example, the reception desk can accept employees' department affiliations as input and manage them as information categories. For example, the reception desk can input the department to which an employee belongs and set an information category based on that information. The reception desk can also set information categories for each project. For example, the reception desk can categorize information related to a specific project and provide appropriate information. Furthermore, the reception desk can also set information categories for each job title. For example, the reception desk can set information categories for managers and general employees and provide appropriate information. This makes it possible to provide appropriate information by categorizing information based on the employee's department affiliation. Information categories include, but are not limited to, categories by department, category by project, category by job title, etc. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can manage information categories using an AI model that accepts employees' department affiliations as input and sets information categories based on that information.

[0068] The analysis unit can search internal documents and identify relevant information. For example, the analysis unit can perform a full-text search of internal documents to identify relevant information. For example, the analysis unit can search the full text of internal documents to identify information related to a question. The analysis unit can also perform metadata searches. For example, the analysis unit can search the metadata of internal documents to identify relevant information. Furthermore, the analysis unit can perform searches with filtering conditions set. For example, the analysis unit can set filtering conditions such as specific keywords or date ranges to identify relevant information. This allows for the provision of appropriate information to employees by searching internal documents and identifying relevant information. Relevant information includes, but is not limited to, highly relevant information, the latest information, and frequently occurring information. Some or all of the above processing in the analysis unit may be performed using generative AI, or not. For example, the analysis unit can identify information using a generative AI model that performs a full-text search of internal documents and identifies relevant information.

[0069] The information delivery unit can provide identified information to employees. For example, the information delivery unit can provide identified information via email. For example, the information delivery unit can send identified information to employees via email to provide information quickly. The information delivery unit can also display the information on a dashboard. For example, the information delivery unit can display identified information on a dashboard and provide it in a format that is easy for employees to access. Furthermore, the information delivery unit can also provide information via real-time notifications. For example, the information delivery unit can notify employees of identified information in real time, immediately conveying important information to employees. This alleviates employee information deficiencies and anxieties by providing employees with identified information. Identified information includes, but is not limited to, information of high importance and information of high relevance. Some or all of the above processes in the information delivery unit may be performed using AI or not. For example, the information delivery unit can provide information using an AI model that provides identified information via email.

[0070] The storage unit can store knowledge. For example, the storage unit can store FAQs. For example, the storage unit stores questions from employees and their answers as FAQs to improve the accuracy of answers to future questions. The storage unit can also store past questions and answers. For example, the storage unit stores questions and answers from employees in the past in a database to use as a reference for future questions. Furthermore, the storage unit can also store technical documents. For example, the storage unit stores internal technical documents in a database so that employees can quickly obtain the information they need. By accumulating knowledge in this way, the accuracy of answers to future questions is improved. Knowledge includes, but is not limited to, FAQs, past questions and answers, and technical documents. Some or all of the above processes in the storage unit may be performed using AI or not. For example, the storage unit can store knowledge using an AI model that stores questions from employees and their answers.

[0071] The Management Department can manage information classification. For example, the Management Department can manage information classification by setting access permissions. For example, the Management Department can set access permissions based on the department and position of employees to ensure information security. The Management Department can also manage information classification by setting methods for classifying information. For example, the Management Department can classify information by department, project, and position to provide appropriate information. Furthermore, the Management Department can manage information classification by setting the frequency of information updates. For example, the Management Department can frequently update important information to provide the latest information. In this way, by managing information classification, consideration can be given to the security of the output. Information classification includes, but is not limited to, setting access permissions, methods for classifying information, and information update frequency. Some or all of the above processes in the Management Department may be performed using AI or not. For example, the Management Department can manage information classification using an AI model that sets access permissions based on the department and position of employees.

[0072] The reception desk can estimate an employee's emotions and adjust the timing of question reception based on the estimated emotions. For example, if an employee is stressed, the reception desk will quickly receive questions and respond immediately. For instance, the reception desk may capture the employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the employee is stressed, questions will be received quickly. Conversely, if the employee is relaxed, the reception desk can receive questions at a normal pace and collect detailed information. For example, the reception desk may record the employee's voice and estimate their emotions using voice analysis technology. If the employee is relaxed, questions will be received at a normal pace. Furthermore, if an employee is in a hurry, the reception desk can receive concise questions and quickly send the information to the analysis department. For example, the reception desk may collect the employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If the employee is in a hurry, questions will be received concisely. This allows for more appropriate responses by adjusting the timing of question reception according to the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reception area may be performed using AI or not. For example, the reception area can receive questions using an AI model that estimates the emotions of employees and adjusts the timing of question reception.

[0073] The reception department can analyze an employee's past question history and select the optimal reception method. For example, the reception department can automatically suggest relevant questions based on the content of questions the employee has frequently asked in the past. For example, the reception department can store past question history in a database and analyze frequently asked questions. The reception department can also prioritize suggesting question formats (text, voice, etc.) that the employee has used in the past. For example, the reception department can analyze past question formats and suggest the most suitable format. Furthermore, the reception department can select a reception method suitable for a specific time of day based on the employee's past question history. For example, the reception department selects a reception method suitable for a specific time of day based on past question history. This allows the reception department to select the optimal reception method by analyzing the employee's past question history. The question history includes, but is not limited to, a database of past questions and answers and an analysis of frequently asked questions. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department can use an AI model that analyzes an employee's past question history and selects the optimal reception method to handle question reception.

[0074] The reception desk can filter questions based on the employee's current projects and areas of interest. For example, the reception desk can prioritize questions related to the employee's current projects. For example, the reception desk can accept the employee's project information as input and filter out relevant questions. The reception desk can also filter and accept questions based on the employee's areas of interest. For example, the reception desk can accept the employee's areas of interest as input and filter out relevant questions. Furthermore, the reception desk can accept appropriate questions according to the employee's project progress. For example, the reception desk can accept the project progress as input and filter out appropriate questions. This ensures that appropriate questions are received by filtering questions based on the employee's current projects and areas of interest. Filtering includes, but is not limited to, project names, areas of interest, and keywords. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can receive questions using an AI model that filters questions based on the employee's current projects and areas of interest.

[0075] The reception desk can estimate an employee's emotions and prioritize questions based on that estimation. For example, if an employee is stressed, the reception desk will prioritize urgent questions. For instance, the reception desk could capture the employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the employee is stressed, urgent questions will be prioritized. The reception desk can also prioritize questions according to normal priority if the employee is relaxed. For example, the reception desk could record the employee's voice and estimate their emotions using voice analysis technology. If the employee is relaxed, questions will be prioritized. Furthermore, if an employee is in a hurry, the reception desk can prioritize questions requiring a quick response. For example, the reception desk could collect the employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If the employee is in a hurry, questions requiring a quick response will be prioritized. This allows for more appropriate responses by prioritizing questions according to the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reception area may be performed using AI or not. For example, the reception area can receive questions using an AI model that estimates the emotions of employees and determines the priority of questions.

[0076] The reception desk can prioritize receiving questions that are highly relevant, taking into account the employee's geographical location. For example, if an employee is in a specific office, the reception desk will prioritize questions related to that office. For instance, the reception desk can accept the employee's geographical location as input and filter out relevant questions. Furthermore, if an employee is on a business trip, the reception desk can prioritize questions related to their destination. For example, the reception desk can accept the employee's business trip destination as input and filter out relevant questions. Additionally, if an employee is working remotely, the reception desk can prioritize questions related to their home or remote work environment. For example, the reception desk can accept the employee's remote work environment as input and filter out relevant questions. This allows for prioritizing the reception of highly relevant questions by considering the employee's geographical location. Geographical location information includes, but is not limited to, GPS data, IP addresses, and beacons. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can use an AI model that filters questions based on the employee's geographical location to handle inquiries.

[0077] The reception desk can analyze an employee's social media activity when receiving a question and receive relevant questions. For example, the reception desk can receive relevant questions based on information shared by the employee on social media. For example, the reception desk can receive an employee's social media activity as input and filter for relevant questions. The reception desk can also receive questions related to topics of interest from an employee's social media activity. For example, the reception desk can analyze an employee's social media activity and filter for questions related to topics of interest. Furthermore, the reception desk can receive questions related to accounts that an employee follows on social media. For example, the reception desk can receive information about accounts that an employee follows as input and filter for relevant questions. In this way, relevant questions can be received by analyzing an employee's social media activity. Social media activity includes, but is not limited to, posts, the number of likes, and the number of followers. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can receive questions using an AI model that analyzes an employee's social media activity and receives relevant questions.

[0078] The analysis unit can estimate an employee's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if an employee is stressed, the analysis unit uses a concise and easy-to-understand presentation. For instance, the analysis unit captures an employee's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. If the employee is stressed, a concise and easy-to-understand presentation is used. The analysis unit can also use a presentation that includes detailed information if the employee is relaxed. For example, the analysis unit records an employee's voice and estimates their emotions using voice analysis technology. If the employee is relaxed, a presentation that includes detailed information is used. Furthermore, if an employee is in a hurry, the analysis unit can use a presentation that gets straight to the point. For example, the analysis unit collects an employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. If the employee is in a hurry, a presentation that gets straight to the point is used. This allows for the provision of more appropriate information by adjusting the presentation of the analysis according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the analysis unit may be performed using the generative AI, or not. For example, the analysis unit may perform the analysis using a generative AI model that estimates the emotions of employees and adjusts the way the analysis is expressed.

[0079] The analysis unit can adjust the level of detail of the analysis based on the importance of the questions during the analysis. For example, the analysis unit can perform a detailed analysis for questions of high importance. For example, the analysis unit can evaluate the importance of the questions and perform a detailed analysis for those of high importance. The analysis unit can also perform a concise analysis for questions of low importance. For example, the analysis unit can evaluate the importance of the questions and perform a concise analysis for those of low importance. Furthermore, the analysis unit can select an appropriate level of detail of analysis according to the importance of the questions. For example, the analysis unit can evaluate the importance of the questions and select an appropriate level of detail of analysis. This makes it possible to provide appropriate information by adjusting the level of detail of the analysis according to the importance of the questions. The importance of a question includes, but is not limited to, the degree of impact on business, urgency, and frequency. Some or all of the above processing in the analysis unit may be performed using generative AI, or it may be performed without using generative AI. For example, the analysis unit can perform the analysis using a generative AI model that evaluates the importance of questions and adjusts the level of detail of the analysis.

[0080] The analysis unit can apply different analysis algorithms depending on the category of the question during analysis. For example, for technical questions, the analysis unit can apply a specialized technical analysis algorithm. For example, the analysis unit can accept a technical question as input and apply a specialized technical analysis algorithm. The analysis unit can also apply a specialized business process analysis algorithm to questions about business processes. For example, the analysis unit can accept a question about business processes as input and apply a specialized business process analysis algorithm. Furthermore, the analysis unit can apply a specialized corporate culture analysis algorithm to questions about corporate culture. For example, the analysis unit can accept a question about corporate culture as input and apply a specialized corporate culture analysis algorithm. This allows for more accurate analysis by applying the appropriate analysis algorithm according to the category of the question. The categories of questions include, but are not limited to, technical questions, questions about business processes, and general questions. Some or all of the above processing in the analysis unit may be performed using generative AI, or not. For example, the analysis unit can perform analysis using a generative AI model that applies an analysis algorithm according to the category of the question.

[0081] The analysis unit can estimate an employee's emotions and adjust the length of the analysis based on the estimated emotions. For example, if an employee is stressed, the analysis unit will perform a short, concise analysis. For instance, the analysis unit can capture an employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the employee is stressed, it will perform a short, concise analysis. The analysis unit can also perform a detailed analysis if the employee is relaxed. For example, the analysis unit can record an employee's voice and estimate their emotions using voice analysis technology. If the employee is relaxed, it will perform a detailed analysis. Furthermore, if an employee is in a hurry, the analysis unit can perform a short analysis for quick understanding. For example, the analysis unit can collect an employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If the employee is in a hurry, it will perform a short analysis for quick understanding. By adjusting the length of the analysis according to the employee's emotions, it becomes possible to provide more appropriate information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the analysis unit may be performed using the generative AI, or not. For example, the analysis unit may perform the analysis using a generative AI model that estimates the emotions of employees and adjusts the length of the analysis.

[0082] The analysis unit can determine the priority of analysis based on when the questions were submitted. For example, the analysis unit may prioritize the analysis of recently submitted questions. For example, the analysis unit may accept the submission date of the questions as input and prioritize the analysis of recently submitted questions. The analysis unit can also set appropriate priorities according to the submission date of the questions. For example, the analysis unit may evaluate the submission date of the questions and set appropriate priorities. Furthermore, the analysis unit may set a lower priority for questions that were submitted a long time ago. For example, the analysis unit may evaluate the submission date of the questions and set a lower priority for older questions. This makes it possible to provide appropriate information by determining the priority of analysis based on the submission date of the questions. The submission date includes, but is not limited to, timestamps and records of the submission date. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis using a generative AI model that evaluates the submission date of questions and determines the priority of analysis.

[0083] The analysis unit can adjust the order of analysis based on the relevance of the questions during analysis. For example, the analysis unit can prioritize the analysis of questions that are highly relevant. For example, the analysis unit can evaluate the relevance of the questions and prioritize the analysis of highly relevant questions. The analysis unit can also postpone the analysis of questions that are less relevant. For example, the analysis unit can evaluate the relevance of the questions and postpone the analysis of less relevant questions. Furthermore, the analysis unit can perform the analysis in an appropriate order according to the relevance of the questions. For example, the analysis unit can evaluate the relevance of the questions and perform the analysis in an appropriate order. By adjusting the order of analysis based on the relevance of the questions, it becomes possible to provide appropriate information. The relevance of questions includes, but is not limited to, keyword matching and topic similarity. Some or all of the above processing in the analysis unit may be performed using generative AI or not. For example, the analysis unit can perform analysis using a generative AI model that evaluates the relevance of questions and adjusts the order of analysis.

[0084] The information provider can estimate employees' emotions and adjust the way information is presented based on those estimated emotions. For example, if an employee is stressed, the provider will use a concise and easy-to-understand presentation. For instance, the provider can capture an employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the employee is stressed, a concise and easy-to-understand presentation is used. The provider can also use a presentation that includes detailed information if the employee is relaxed. For example, the provider can record an employee's voice and estimate their emotions using voice analysis technology. If the employee is relaxed, a presentation that includes detailed information is used. Furthermore, if an employee is in a hurry, the provider can use a presentation that gets straight to the point. For example, the provider can collect an employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If the employee is in a hurry, a presentation that gets straight to the point is used. This allows for more appropriate information to be provided by adjusting the presentation of information according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text-generating AI (e.g., LLM) and multimodal-generating AI. Some or all of the processing described above in the delivery unit may be performed using or without generative AI. For example, the delivery unit may provide information using a generative AI model that estimates employees' emotions and adjusts how the information is presented.

[0085] The information delivery unit can adjust the level of detail provided based on the importance of the information at the time of delivery. For example, the delivery unit can provide detailed information for highly important information. For example, the delivery unit can evaluate the importance of the information and provide detailed information for highly important information. The delivery unit can also provide concise information for less important information. For example, the delivery unit can evaluate the importance of the information and provide concise information for less important information. Furthermore, the delivery unit can select an appropriate level of detail for the information according to its importance. For example, the delivery unit can evaluate the importance of the information and select an appropriate level of detail. This makes it possible to provide appropriate information by adjusting the level of detail according to the importance of the information. The importance of information includes, but is not limited to, the degree of impact on business, urgency, and frequency. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can provide information using an AI model that evaluates the importance of information and adjusts the level of detail for the information provided.

[0086] The information delivery unit can apply different delivery algorithms depending on the category of information at the time of delivery. For example, the delivery unit can apply a specialized technical delivery algorithm to technical information. For example, the delivery unit can accept technical information as input and apply a specialized technical delivery algorithm. The delivery unit can also apply a specialized business process delivery algorithm to information related to business processes. For example, the delivery unit can accept information related to business processes as input and apply a specialized business process delivery algorithm. Furthermore, the delivery unit can apply a specialized corporate culture delivery algorithm to information related to corporate culture. For example, the delivery unit can accept information related to corporate culture as input and apply a specialized corporate culture delivery algorithm. This makes it possible to provide more accurate information by applying the appropriate delivery algorithm according to the category of information. Information categories include, but are not limited to, technical information, information related to business processes, and general information. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can provide information using an AI model that applies a delivery algorithm according to the category of information.

[0087] The information delivery system can estimate an employee's emotions and adjust the length of the information provided based on the estimated emotions. For example, if an employee is stressed, the system can provide short, concise information. For instance, the system can capture an employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the employee is stressed, it provides short, concise information. The system can also provide detailed information if the employee is relaxed. For example, the system can record an employee's voice and estimate their emotions using voice analysis technology. If the employee is relaxed, it provides detailed information. Furthermore, if an employee is in a hurry, the system can provide short information that can be quickly understood. For example, the system can collect an employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If the employee is in a hurry, it provides short information that can be quickly understood. By adjusting the length of information according to the employee's emotions, more appropriate information can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the processing described above in the delivery unit may be performed using or without generative AI. For example, the delivery unit may provide information using a generative AI model that estimates employees' emotions and adjusts the length of the information.

[0088] The information provider can determine the priority of information provision based on the submission date at the time of provision. For example, the provider may prioritize the provision of recently submitted information. For example, the provider may accept the submission date as input and prioritize the provision of recently submitted information. The provider can also set appropriate priorities according to the submission date of the information. For example, the provider may evaluate the submission date of the information and set appropriate priorities. Furthermore, the provider may set a lower priority for older information. For example, the provider may evaluate the submission date of the information and set a lower priority for older information. This makes it possible to provide appropriate information by determining the priority of provision based on the submission date of the information. The submission date includes, but is not limited to, timestamps and records of the submission date. Some or all of the above processing in the provider may be performed using AI or not. For example, the provider can provide information using an AI model that evaluates the submission date of information and determines the priority of provision.

[0089] The information provider can adjust the order of information delivery based on its relevance. For example, the provider can prioritize the delivery of highly relevant information. For instance, the provider can evaluate the relevance of information and prioritize the delivery of highly relevant information. The provider can also postpone the delivery of less relevant information. For example, the provider can evaluate the relevance of information and postpone the delivery of less relevant information. Furthermore, the provider can deliver information in an appropriate order according to its relevance. For example, the provider can evaluate the relevance of information and deliver it in an appropriate order. This allows for appropriate information delivery by adjusting the order of delivery based on the relevance of information. Information relevance includes, but is not limited to, keyword matching and topic similarity. Some or all of the above processing in the information provider may be performed using AI or not. For example, the information provider can provide information using an AI model that evaluates the relevance of information and adjusts the order of delivery.

[0090] The data storage unit can estimate employees' emotions and select data to store based on the estimated emotions. For example, if an employee is stressed, the storage unit prioritizes storing important data. For instance, it can capture an employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the employee is stressed, it prioritizes storing important data. The storage unit can also store detailed data if the employee is relaxed. For example, it can record an employee's voice and estimate their emotions using voice analysis technology. If the employee is relaxed, it stores detailed data. Furthermore, if an employee is in a hurry, the storage unit can select data that can be stored quickly. For example, it can collect an employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If the employee is in a hurry, it selects data that can be stored quickly. This allows for more appropriate data storage by selecting data according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the storage unit may be performed using a generative AI, or not. For example, the storage unit can store data using a generative AI model that estimates employees' emotions and selects data to be stored.

[0091] The storage unit can optimize the storage algorithm by referring to past stored data during storage. For example, the storage unit can select the optimal storage algorithm based on past stored data. For example, the storage unit can analyze past stored data and select the optimal storage algorithm. The storage unit can also derive an efficient storage method from past stored data. For example, the storage unit can analyze past stored data and derive an efficient storage method. Furthermore, the storage unit can analyze past stored data and optimize the storage algorithm. For example, the storage unit analyzes past stored data and optimizes the storage algorithm. This allows the storage algorithm to be optimized by referring to past stored data. Stored data includes, but is not limited to, past questions and answers, technical documents, and FAQs. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can store data using an AI model that analyzes past stored data and optimizes the storage algorithm.

[0092] The data storage unit can estimate employees' emotions and adjust the storage frequency based on the estimated emotions. For example, if an employee is stressed, the storage unit will frequently store important data. For instance, the storage unit might capture the employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. If the employee is stressed, important data will be stored frequently. The storage unit can also store data at a normal frequency if the employee is relaxed. For example, the storage unit might record the employee's voice and estimate their emotions using voice analysis technology. If the employee is relaxed, data will be stored at a normal frequency. Furthermore, if an employee is in a hurry, the storage unit can prioritize storing data that can be stored quickly. For example, the storage unit might collect the employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If the employee is in a hurry, data that can be stored quickly will be prioritized. This allows for more appropriate data storage by adjusting the storage frequency according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the storage unit may be performed using the generative AI or not. For example, the storage unit may store data using a generative AI model that estimates employees' emotions and adjusts the frequency of storage.

[0093] The storage unit can weight the stored data based on when the questions were submitted. For example, the storage unit can prioritize storing data related to recently submitted questions. For example, the storage unit can accept the submission date of a question as input and prioritize storing data related to recently submitted questions. The storage unit can also perform appropriate weighting according to the submission date of the question. For example, the storage unit can evaluate the submission date of the question and perform appropriate weighting. Furthermore, the storage unit can set a lower weight for older questions. For example, the storage unit can evaluate the submission date of the question and set a lower weight for older questions. This enables appropriate data storage by weighting the stored data based on the submission date of the question. The submission date includes, but is not limited to, timestamps and records of the submission date. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can store data using an AI model that evaluates the submission date of a question and weights the stored data.

[0094] The management department can estimate employees' emotions and adjust information categorized management methods based on those estimated emotions. For example, if an employee is stressed, the management department can use a concise and easy-to-understand information categorized management method. For instance, the management department could capture an employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If an employee is stressed, a concise and easy-to-understand information categorized management method is used. The management department can also use a detailed information categorized management method if an employee is relaxed. For example, the management department could record an employee's voice and estimate their emotions using voice analysis technology. If an employee is relaxed, a detailed information categorized management method is used. Furthermore, if an employee is in a hurry, the management department can use a concise information categorized management method that can be quickly understood. For example, the management department could collect an employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If an employee is in a hurry, a concise information categorized management method is used for quick understanding. By adjusting information categorized management methods according to employees' emotions, more appropriate information management becomes possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the management department may be performed using generative AI or not. For example, the management department can manage information using a generative AI model that estimates employees' emotions and adjusts the information classification management method.

[0095] The management department can optimize management algorithms by referring to past management data during management. For example, the management department can select the optimal management algorithm based on past management data. For example, the management department can analyze past management data and select the optimal management algorithm. The management department can also derive efficient management methods from past management data. For example, the management department can analyze past management data and derive efficient management methods. Furthermore, the management department can analyze past management data and optimize management algorithms. For example, the management department can analyze past management data and optimize management algorithms. This allows for the optimization of management algorithms by referring to past management data. Management data includes, but is not limited to, past management records, access logs, and security settings. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can manage information using an AI model that analyzes past management data and optimizes management algorithms.

[0096] The management department can estimate employees' emotions and prioritize information categories based on those estimated emotions. For example, if an employee is stressed, the management department will prioritize managing important information categories. For instance, the management department could capture an employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the employee is stressed, important information categories will be prioritized. The management department can also manage information categories with normal priorities if the employee is relaxed. For example, the management department could record an employee's voice and estimate their emotions using voice analysis technology. If the employee is relaxed, information categories will be prioritized. Furthermore, if an employee is in a hurry, the management department can prioritize managing information categories that require a quick response. For example, the management department could collect an employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. If the employee is in a hurry, information categories that require a quick response will be prioritized. This allows for more appropriate information management by prioritizing information categories according to the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the management department may be performed using generative AI or not. For example, the management department can manage information using a generative AI model that estimates employees' emotions and determines the priority of information categories.

[0097] The management department can weight management data based on the submission date of the information during management. For example, the management department can prioritize the management of recently submitted information. For example, the management department can accept the submission date of the information as input and prioritize the management of recently submitted information. The management department can also perform appropriate weighting according to the submission date of the information. For example, the management department can evaluate the submission date of the information and perform appropriate weighting. Furthermore, the management department can set a lower weight for information that is older. For example, the management department can evaluate the submission date of the information and set a lower weight for older information. This enables appropriate information management by weighting management data based on the submission date of the information. The submission date includes, but is not limited to, timestamps and records of the submission date. Some or all of the above processes in the management department may be performed using AI or not. For example, the management department can manage information using an AI model that evaluates the submission date of information and weights management data.

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

[0099] The reception department can assess the urgency of employee inquiries and prioritize processing those with higher urgency. For example, the reception department can analyze the content of the inquiries and use an algorithm to quickly send high-urgency inquiries to the analysis department. The reception department can also set appropriate response times according to the urgency of the inquiries. For example, high-urgency inquiries can be answered immediately, while lower-urgency inquiries can be handled within the normal response time. Furthermore, the reception department can dynamically adjust the priority of inquiries based on their urgency. This enables appropriate responses to employee inquiries according to their urgency.

[0100] The analysis department can search relevant external resources and identify the appropriate information based on the content of the question. For example, it can search publicly available databases and specialized websites on the internet to identify information related to the question. It can also forward the question to external experts or consultants to obtain expert answers. Furthermore, the analysis department can integrate the information obtained from external resources with internal documents to provide a comprehensive answer. This enables the provision of more accurate information by utilizing both internal and external resources.

[0101] The information provision department can evaluate the reliability of answers to employee questions and prioritize providing highly reliable information. For example, the department can evaluate the source and information sources of answers and select highly reliable information. The department can also refer to past answer history and prioritize providing highly reliable answers. Furthermore, the department can adjust the level of detail in answers based on their reliability. This ensures that employees can perform their work with confidence by receiving reliable information.

[0102] The data storage unit can evaluate the quality of the stored data when accumulating knowledge, and prioritize the storage of high-quality data. For example, the storage unit can evaluate the accuracy and reliability of the data and select high-quality data. It can also evaluate the update frequency and usage frequency of the data and prioritize the storage of important data. Furthermore, the storage unit can dynamically adjust the storage priority based on the data quality. This ensures the quality of the stored data and improves the accuracy of answers to future questions.

[0103] The management department can evaluate the confidentiality of information when managing information classifications and strictly manage highly confidential information. For example, the management department can use an algorithm to evaluate the confidentiality of information and set strict access restrictions for highly confidential information. Furthermore, the management department can strengthen information encryption and security measures based on the confidentiality of the information. In addition, the management department can dynamically adjust information management methods according to the confidentiality of the information. This allows for the proper management of highly confidential information and ensures information security.

[0104] The reception desk can estimate an employee's emotions and customize how questions are handled based on that estimation. For example, if an employee is stressed, the reception desk can provide a concise and easy-to-understand question form. If the employee is relaxed, it can provide a more detailed question form. Furthermore, if an employee is in a hurry, the reception desk can provide a shortcut for quickly submitting their question. This enables flexible question handling that is tailored to the employee's emotions.

[0105] The analysis unit can estimate employees' emotions and adjust the accuracy of the analysis based on those estimates. For example, if an employee is stressed, the analysis unit can perform a quick analysis and provide a concise response. If an employee is relaxed, the analysis unit can perform a detailed analysis and provide a comprehensive response. Furthermore, if an employee is in a hurry, the analysis unit can perform a concise analysis and provide a quick response. This enables appropriate analysis tailored to each employee's emotions.

[0106] The information delivery system can estimate employees' emotions and adjust the format of the information provided based on those estimates. For example, if an employee is stressed, the system can provide information using visually easy-to-understand graphs and charts. If an employee is relaxed, the system can provide detailed text information. Furthermore, if an employee is in a hurry, the system can provide information summarized in bullet points. This enables the provision of appropriate information tailored to each employee's emotions.

[0107] The data storage unit can estimate employees' emotions and adjust how it organizes the stored data based on those estimated emotions. For example, if an employee is stressed, the unit organizes the data in a concise and easy-to-understand format. If an employee is relaxed, the unit can organize the data in a more detailed format. Furthermore, if an employee is in a hurry, the unit can organize the data for quick access. This enables appropriate data organization tailored to each employee's emotions.

[0108] The management department can estimate employees' emotions and adjust the frequency of information category updates based on those estimates. For example, if an employee is stressed, the management department will update important information categories more frequently. Conversely, if an employee is relaxed, the management department can manage information categories at a normal update frequency. Furthermore, if an employee is in a hurry, the management department can prioritize managing information categories that require quick updates. This enables appropriate information category management in accordance with employees' emotions.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The reception desk receives questions from employees. These questions can be in text format, audio format, or on specific topics. For example, text questions are accepted as is, audio questions are converted to text using speech recognition technology, and questions on specific topics are analyzed using keyword matching technology. Step 2: The analysis department analyzes the questions received by the reception department and searches internal documents. The analysis is performed using methods such as natural language processing, keyword matching, and machine learning algorithms. For example, natural language processing is used to analyze the questions and search for relevant internal documents. Keyword matching compares the keywords in the questions with the keywords in the internal documents to identify information with a high degree of match. Machine learning algorithms learn from past question and answer data to generate the best answer for new questions. Step 3: The provisioning department provides employees with the information retrieved by the analysis department. This provision can be done via email, dashboard display, or real-time notifications. For example, information can be provided via email to allow employees to quickly obtain the information they need. Dashboards display information in an easily accessible format, allowing employees to see the necessary information at a glance. Real-time notifications instantly inform employees of important information, enabling quick responses.

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

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

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

[0114] Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, storage unit, and management unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives questions from employees. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the questions and searches internal documents. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the retrieved information to employees. The storage unit is implemented by the specific processing unit 290 of the data processing unit 12 and stores knowledge. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages information classification. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, storage unit, and management unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives questions from employees. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the questions and searches internal documents. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the retrieved information to employees. The storage unit is implemented by the specific processing unit 290 of the data processing unit 12 and stores knowledge. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages information classification. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0135] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, storage unit, and management unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives questions from employees. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the questions and searches internal documents. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the retrieved information to employees. The storage unit is implemented by the specific processing unit 290 of the data processing unit 12 and stores knowledge. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages information classifications. The correspondence between each unit and the devices and control units is not limited to the example described above and can be changed in various ways.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0151] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the reception unit, analysis unit, provision unit, storage unit, and management unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives questions from employees. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the questions and searches internal documents. The provision unit is implemented by the control unit 46A of the robot 414 and provides the retrieved information to employees. The storage unit is implemented by the specific processing unit 290 of the data processing unit 12 and stores knowledge. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages information classification. The correspondence between each unit and the devices and control units is not limited to the example described above and can be changed in various ways.

[0164] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] 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.

[0174] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) A reception desk to answer employee questions, The analysis unit analyzes the questions received by the aforementioned reception unit and searches internal company documents, The system includes a provisioning unit that provides the information retrieved by the analysis unit to employees. A system characterized by the following features. (Note 2) The aforementioned reception unit is We accept information based on the employee's department. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Search internal documents and identify the relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, Provide identified information to employees The system described in Appendix 1, characterized by the features described herein. (Note 5) It is equipped with a storage unit for accumulating knowledge. The system described in Appendix 1, characterized by the features described herein. (Note 6) It has a management unit for managing information classifications. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is We estimate the emotions of our employees and adjust the timing of question submissions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze employees' past question history to select the most suitable method of handling inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving questions, filtering is performed based on the employee's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the employee's emotions and prioritizes the questions to be asked based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving questions, we will prioritize questions that are highly relevant to the employee's location, taking into account their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving questions, we analyze employees' social media activity and select relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate the emotions of our employees and adjust the representation of the analysis based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the question. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates the emotions of employees and adjusts the length of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During the analysis, the priority of the analysis will be determined based on when the questions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, We estimate employees' emotions and adjust the way information is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When providing information, adjust the level of detail based on its importance. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing information, different delivery algorithms are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, The system estimates employees' emotions and adjusts the length of information provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing information, we will determine the priority of provision based on when the information was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing information, the order of provision will be adjusted based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The storage unit is The system estimates the emotions of employees and selects accumulated data based on the estimated emotions of the employees. The system described in Appendix 1, characterized by the features described herein. (Note 26) The storage unit is During data storage, the storage algorithm is optimized by referring to past stored data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The storage unit is The system estimates employees' emotions and adjusts the frequency of data accumulation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The storage unit is During data accumulation, the accumulated data is weighted based on when the questions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned management department, We estimate employees' emotions and adjust the information classification management method based on the estimated emotions of the employees. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned management department, During management, the management algorithm is optimized by referring to past management data. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned management department, The system estimates employees' emotions and determines the priority of information categories based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned management department, During management, weight the management data based on when the information was submitted. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that takes questions from employees, The analysis unit analyzes the questions received by the aforementioned reception unit and searches internal company documents, The system includes a provisioning unit that provides the information retrieved by the analysis unit to employees. A system characterized by the following features.

2. The aforementioned reception unit is We accept information based on the employee's department. The system according to feature 1.

3. The aforementioned analysis unit, Search internal documents and identify the relevant information. The system according to feature 1.

4. The aforementioned supply unit is, Provide identified information to employees The system according to feature 1.

5. It is equipped with a knowledge storage unit. The system according to feature 1.

6. It has a management unit for managing information classifications. The system according to feature 1.

7. The aforementioned reception unit is We estimate the emotions of our employees and adjust the timing of question submissions based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is Analyze employees' past question history to select the most suitable method of handling inquiries. The system according to feature 1.

9. The aforementioned reception unit is When receiving questions, filtering is performed based on the employee's current projects and areas of interest. The system according to feature 1.

10. The aforementioned reception unit is The system estimates the employee's emotions and prioritizes the questions to be asked based on those estimated emotions. The system according to feature 1.

Images