System

Abstract

To provide a system that efficiently automates internal counter services and appropriately performs escalations.SOLUTION: A system according to an embodiment comprises: a collection unit; a generation unit; a coordination unit; and a notification unit. The collection unit collects information. The generation unit generates responses on the basis of the information collected by the collection unit. The coordination unit performs escalations on the basis of the responses generated by the generation unit. The notification unit notifies a person in charge of system of the content escalated by the coordination unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, there was a problem in that it was difficult to efficiently automate internal office operations and properly escalate issues.

[0005] The system according to the embodiment aims to efficiently automate internal office operations and appropriately carry out escalation. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a generation unit, a coordination unit, and a notification unit. The collection unit collects information. The generation unit generates a response based on the information collected by the collection unit. The coordination unit performs escalation based on the response generated by the generation unit. The notification unit notifies the system administrator of the content of the escalation by the coordination unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently automate internal office operations and appropriately handle escalation. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The in-house help desk system according to the embodiment of the present invention is a system that replaces the work of employees and contracted employees who work as an in-house help desk for employees with a generation AI. This system uses an AI service such as Azure (registered trademark) OpenAI Service, sets access restrictions within the vNet, and builds a mechanism for loading information without opting in. As a result, the generation AI performs all primary responses, and when escalation is required, it cooperates with the reception desk in charge of the system using a method specialized for the reception desk in charge of the system. In addition, the employee who is the user changes the business flow to one that allows the SLA (service level agreement) based on this mechanism. First, when an employee makes a question or inquiry, the generation AI accepts the content. Next, the generation AI generates an appropriate answer based on the information that was previously loaded. For example, the generation AI immediately provides an answer to a question about the company's regulations and procedures. In this case, by using the Azure OpenAI Service, it is possible to provide a quick answer while ensuring security. Furthermore, when a complex inquiry that the generation AI cannot handle or escalation is required, it is automatically linked to the reception desk in charge of the system. For example, for matters that the generation AI cannot handle, such as technical issues or detailed inquiries about a specific department, the system staff will handle them. This collaboration is carried out smoothly using specialized methods. In addition, the employees who are the users will change their work flow to one that allows for the SLA based on this new mechanism. Specifically, a work flow will be introduced that takes into account the speed of the generation AI's first response and the efficiency of escalation. This allows employees to work efficiently. This mechanism will streamline internal employee support operations, providing quick and appropriate responses. In addition, it will be possible to respond smoothly even when escalation is necessary, improving overall work efficiency. As a result, the internal support system will be able to provide quick and appropriate responses to employee inquiries, improving work efficiency.

[0029] The in-house window system according to the embodiment includes a collection unit, a generation unit, a linking unit, and a notification unit. The collection unit collects information from an in-house database or document. For example, the collection unit can collect information on in-house regulations and procedures. The collection unit can also restrict access and encrypt data. For example, the collection unit performs user authentication and allows access only from a specific IP address. Furthermore, the collection unit can protect data using AES encryption. The generation unit uses a generation AI to generate an appropriate answer based on the collected information. For example, the generation unit uses a text generation AI (e.g., LLM) to generate an answer to an employee's question. The generation unit can also use a multimodal generation AI to generate an answer including an image or audio. For example, the generation unit provides an answer including a related image or audio to an employee's question. The linking unit escalates when the generated answer cannot be satisfied. For example, the linking unit escalates a technical problem or a detailed inquiry about a specific department to a system manager. The linking unit can also set escalation rules. For example, the coordination unit performs escalation based on priority and assignment of personnel. The notification unit notifies the system staff of the escalated content. For example, the notification unit can send email notifications or alert notifications. The notification unit can also display a dashboard. For example, the notification unit can display the escalated content on a dashboard so that the system staff can respond quickly. As a result, the internal customer service system according to the embodiment can provide quick and appropriate responses to employee inquiries, improving business efficiency.

[0030] The collection unit collects information from in-house databases and documents. Specifically, it can collect information on in-house regulations and procedures. For example, the collection unit periodically collects information from documents such as in-house policies, procedures, FAQs, and manuals, and keeps the latest information. The collection unit can also restrict access and encrypt data. For example, the collection unit performs user authentication and allows access only from a specific IP address. This can reduce the risk of in-house confidential information leaking to the outside. Furthermore, the collection unit can protect data using AES encryption. AES encryption is a powerful encryption method for increasing the confidentiality of data, and prevents the collected data from being accessed illegally. By implementing these security measures, the collection unit can safely collect and protect in-house information. In addition, the collection unit can flexibly set the frequency of data collection and the scope of the data. For example, by preferentially collecting information related to a specific department or project, it is possible to quickly provide the necessary information. This allows the collection unit to efficiently collect in-house information and improve the performance of the entire system.

[0031] The generation unit uses a generation AI to generate an appropriate answer based on the collected information. Specifically, a text generation AI (e.g., LLM) is used to generate answers to employees' questions. LLM has the ability to learn large amounts of text data and generate answers in natural language. For example, if an employee asks, "How do I apply for vacation?", the generation unit can provide a detailed answer on the specific procedure and necessary documents based on the collected information. The generation unit can also use a multimodal generation AI to generate answers that include images and voice. For example, if an employee asks, "Where is the logo for the new project?", the generation unit can search for related image files and attach them to the answer. In addition, the generation unit can also respond to questions by voice using voice recognition technology. For example, if an employee inputs a question by voice, the generation unit converts the voice into text and generates an appropriate answer. This allows the generation unit to integrate information in various formats, such as text, images, and voice, to meet the diverse needs of employees. In addition, the generation unit can evaluate the quality of the generated answer and make corrections and improvements as necessary. For example, if the generated answer is inaccurate, the generator will revise the answer based on the feedback and improve the accuracy of the answer from the next time onwards. This allows the generator to consistently provide high-quality answers and increase employee satisfaction.

[0032] The coordination department escalates when the generated answer is insufficient. Specifically, it escalates technical issues or detailed inquiries about a specific department to the system manager. For example, if an employee asks "I don't know how to install a new system," and the generation department cannot generate an appropriate answer, the coordination department escalates the inquiry to the system manager. The coordination department can also set escalation rules. For example, the coordination department escalates based on priority and assignment of personnel. High-priority inquiries are quickly responded to and assigned to specific personnel, enabling efficient response. Furthermore, the coordination department can manage escalation history and refer to past response status. This allows a quick response if a similar inquiry occurs again. The coordination department can automate the escalation process to speed up and streamline response. For example, it can be set so that inquiries containing specific keywords or phrases are automatically escalated. This allows the coordination department to quickly respond to complex inquiries that the generation department cannot handle, and support employees in solving problems.

[0033] The notification unit notifies the system manager of the escalated content. Specifically, it can perform email notification and alert notification. For example, when an escalated inquiry occurs, the notification unit immediately sends an email to the system manager to notify him / her that a response is required. The notification unit can also display a dashboard. For example, the escalated content can be displayed on the dashboard so that the system manager can respond quickly. The dashboard displays detailed information about the escalation and the response status in real time, so that the system manager can grasp the priority and progress at a glance. Furthermore, the notification unit can combine multiple notification means to reliably convey information. For example, by using SMS or push notification in addition to email notification, important information can be prevented from being overlooked. The notification unit can also manage the history of notifications and refer to the contents of past notifications. This makes it possible to track the response status of the escalation and follow up as necessary. Through these functions, the notification unit can support a prompt and appropriate response to the escalated inquiry and improve the efficiency of the entire system.

[0034] The collection unit can collect information from an in-house database or document. In-house databases and documents include, but are not limited to, for example, a customer database, technical documents, and project reports. The collection unit can collect, for example, customer information from a customer database. The collection unit can also collect technical information from technical documents. Furthermore, the collection unit can collect project progress from project reports. This allows the collection unit to efficiently collect necessary information from in-house databases and documents. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, when collecting information from an in-house database, the collection unit can search and extract data using AI.

[0035] The generation unit can generate an answer based on the collected information. The collected information includes, for example, text data, numerical data, image data, and the like, but is not limited to such examples. The generation unit can generate an answer based on, for example, text data. The generation unit can also generate an answer based on numerical data. Furthermore, the generation unit can also generate an answer based on image data. This allows the generation unit to generate a prompt and appropriate answer based on the collected information. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the collected text data to an AI, which can generate an answer.

[0036] The coordination unit can perform escalation when the generated answer cannot be used. Examples of cases where the answer cannot be used include, but are not limited to, cases where a specific keyword is included or where an answer is not generated within a certain time. The coordination unit can perform escalation for technical issues, for example. The coordination unit can also perform escalation for detailed inquiries about a specific department. Furthermore, the coordination unit can also perform escalation for complex inquiries. This allows the coordination unit to appropriately perform escalation when the generated answer cannot be used. A part or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can use AI to determine the criteria for escalation and perform escalation when the generated answer cannot be used.

[0037] The notification unit can notify the system person of the escalated content. The escalated content includes, for example, an error message, an unresolved inquiry, and the like, but is not limited to such examples. The notification unit can, for example, notify the system person of an error message. The notification unit can also notify the system person of the unresolved inquiry. Furthermore, the notification unit can also notify the system person of a technical problem. This allows the notification unit to quickly notify the system person of the escalated content. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input the escalated content into AI, and the AI ​​can notify the system person.

[0038] The collection unit can perform access restriction or data encryption. The access restriction includes, for example, user authentication, IP address restriction, etc., but is not limited to such examples. The collection unit can, for example, perform user authentication to allow only a specific user to access. The collection unit can also perform IP address restriction to allow access only from a specific IP address. Furthermore, the collection unit can encrypt data. The data encryption includes, for example, AES encryption, RSA encryption, etc., but is not limited to such examples. The collection unit can protect data using, for example, AES encryption. The collection unit can also protect data using RSA encryption. This allows the collection unit to efficiently collect information while ensuring the security of the information. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can automatically perform access restriction and data encryption using AI.

[0039] The coordination unit can set escalation rules. Escalation rules include, for example, setting a priority and assigning a person in charge, but are not limited to such examples. The coordination unit can, for example, set a priority and escalate important inquiries preferentially. The coordination unit can also assign a person in charge and escalate to a specific person in charge. Furthermore, the coordination unit can set an escalation procedure. For example, the coordination unit can set an escalation procedure and perform escalation efficiently. This allows the coordination unit to clarify the criteria for escalation and perform escalation efficiently. A part or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can automatically set the escalation rule using AI.

[0040] The in-house help desk system includes a support department, and can provide a training program or guidelines for employees to adapt to the new work flow. The support department provides training programs and guidelines for employees to quickly adapt to the new work flow. For example, the support department can provide online courses to allow employees to learn at their own pace. The support department can also hold workshops to allow employees to actually experience the new work flow. Furthermore, the support department can provide manuals and procedures to allow employees to refer to necessary information at any time. This allows employees to quickly adapt to the new work flow. Some or all of the above-mentioned processing in the support department can be performed, for example, using AI, or can be performed without using AI. For example, the support department can automatically generate the contents of the training program using AI and provide it to employees.

[0041] When collecting information from an internal database or document, the collection unit can determine the priority of collection based on the importance of the information. For example, the collection unit prioritizes collection of information related to important regulations and procedures. The collection unit can also prioritize collection of the latest internal policies and guidelines. Furthermore, the collection unit can prioritize collection of frequently asked information based on past inquiry history. This allows the collection unit to efficiently collect important information by determining the priority of collection based on the importance of information. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can evaluate the importance of information using AI and determine the priority of collection.

[0042] The collection unit can select a collection method by referring to past collection history when collecting information. For example, the collection unit reuses a collection method that was effective in the past. The collection unit can also select the most efficient database from the past collection history. Furthermore, the collection unit can analyze the past collection history and determine the optimal collection timing. In this way, the collection unit can select the optimal collection method by referring to the past collection history and efficiently collect information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the past collection history into AI, which can select the optimal collection method.

[0043] When collecting information, the collection unit can adjust the collected content based on feedback from multiple departments within the company. The collection unit, for example, collects necessary information based on feedback from each department. The collection unit can also adjust the content of the information to be collected, taking into account the priorities of each department. Furthermore, the collection unit can expand or reduce the range of information to be collected based on feedback. This allows the collection unit to adjust the collected content based on feedback from different departments within the company, thereby enabling more appropriate information collection. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input feedback from each department into AI, which can adjust the collected content.

[0044] The collection unit may also collect information from external public databases or literature when collecting information. The collection unit, for example, collects the latest industry information from external public databases. The collection unit may also refer to external literature and compare it with in-house information. Furthermore, the collection unit may also collect related research results and statistical data from external databases. This allows the collection unit to collect information from external public databases and literature, enabling more extensive information collection. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit may use AI to search and extract data when collecting information from external public databases.

[0045] The generation unit can apply different answer generation algorithms according to the category of the question based on the collected information. For example, the generation unit applies a technical algorithm to a technical question. The generation unit can also apply a legal algorithm to a question about regulations and procedures. Furthermore, the generation unit can apply a general-purpose algorithm to a general inquiry. In this way, the generation unit can provide a more appropriate answer by applying an optimal answer generation algorithm according to the category of the question. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can classify the category of the question using AI and apply an optimal answer generation algorithm.

[0046] The generation unit can generate an answer by referring to a past answer history when generating an answer. The generation unit generates an optimal answer based on answers provided in the past, for example. The generation unit can also generate answers to frequently asked questions from the past answer history. Furthermore, the generation unit can analyze the past answer history and generate the most effective answer. As a result, the generation unit can generate an optimal answer by referring to the past answer history and efficiently provide the answer. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the past answer history to AI, which can generate an optimal answer.

[0047] The generation unit can determine the order of answers based on the submission time of the questions when generating answers. For example, the generation unit generates answers preferentially for urgent questions. The generation unit can also generate answers quickly for questions submitted earlier. Furthermore, the generation unit can generate answers sequentially for questions submitted more recently. In this way, the generation unit can provide answers efficiently by determining the priority order of answers based on the submission time of the questions. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the submission time of the questions to an AI, which can determine the order of the answers.

[0048] The generation unit can adjust the order of answers based on the relevance of the questions when generating answers. For example, when the relevance of the questions is high, the generation unit generates answers with priority. Also, when the relevance of the questions is low, the generation unit can generate answers later. Furthermore, the generation unit can analyze the relevance of the questions and generate answers in an optimal order. In this way, the generation unit can provide answers efficiently by adjusting the order of answers based on the relevance of the questions. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can evaluate the relevance of the questions using AI and adjust the order of the answers.

[0049] The coordination unit can determine the order of escalation when the generated answer is not applicable. For example, the coordination unit prioritizes escalation for important inquiries. The coordination unit can also quickly escalate technical issues. Furthermore, the coordination unit can also sequentially escalate general inquiries. This allows the coordination unit to appropriately determine the priority order of escalation when the generated answer is not applicable. A part or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can determine the order of escalation by AI.

[0050] At the time of escalation, the coordination unit can select a coordination method by referring to past escalation history. For example, the coordination unit reuses a coordination method that was effective in the past. The coordination unit can also select the most efficient coordination method from the past escalation history. Furthermore, the coordination unit can analyze the past escalation history and determine the optimal coordination method. In this way, the coordination unit can select the optimal coordination method by referring to the past escalation history and perform escalation efficiently. A part or all of the above-mentioned processing in the coordination unit may be performed, for example, using AI or may be performed without using AI. For example, the coordination unit can input the past escalation history into AI, which can select the optimal coordination method.

[0051] The coordination department can adjust the escalation content in consideration of coordination with multiple departments within the company at the time of escalation. The coordination department adjusts the escalation content, for example, in consideration of the expertise of each department. The coordination department can also adjust the escalation content in consideration of the priority of each department. Furthermore, the coordination department can adjust the escalation content based on feedback from each department. This allows the coordination department to adjust the escalation content in consideration of coordination with different departments within the company, thereby enabling more appropriate escalation. A part or all of the above-mentioned processing in the coordination department may be performed, for example, using AI, or may be performed without using AI. For example, the coordination department can input feedback from each department into AI, which can adjust the escalation content.

[0052] The collaboration unit can collaborate with external experts and consultants at the time of escalation. For example, the collaboration unit escalates technical issues to external experts. The collaboration unit can also escalate business process improvements to external consultants. Furthermore, the collaboration unit can provide optimal solutions through collaboration with external experts and consultants. This allows the collaboration unit to provide more appropriate solutions by collaborating with external experts and consultants. Some or all of the above-mentioned processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can automatically collaborate with external experts and consultants using AI.

[0053] The notification unit can determine the order of notifications when notifying the system personnel of the escalated contents. For example, the notification unit gives priority to notifications for important escalation contents. The notification unit can also quickly notify technical issues. Furthermore, the notification unit can also give notifications sequentially for general escalation contents. In this way, the notification unit can efficiently notify by determining the priority order of notifications according to the importance of the escalated contents. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can determine the order of notifications by AI.

[0054] The notification unit can select a notification method by referring to past notification history at the time of notification. The notification unit, for example, reuses a notification method that was effective in the past. The notification unit can also select the most efficient notification method from the past notification history. Furthermore, the notification unit can analyze the past notification history and determine the optimal notification method. As a result, the notification unit can select the optimal notification method by referring to the past notification history and efficiently perform notification. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input the past notification history into AI, which can select the optimal notification method.

[0055] The notification unit can adjust the notification content based on feedback from multiple departments in the company at the time of notification. The notification unit notifies necessary information based on feedback from each department, for example. The notification unit can also adjust the notification content taking into account the priorities of each department. Furthermore, the notification unit can expand or reduce the range of information to be notified based on feedback. This allows the notification unit to adjust the notification content based on feedback from different departments in the company, making it possible to provide more appropriate notification. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input feedback from each department into AI, which can adjust the notification content.

[0056] The notification unit may also notify external experts and consultants at the time of notification. The notification unit, for example, notifies external experts of technical problems. The notification unit may also notify external consultants of improvements to business processes. Furthermore, the notification unit may provide an optimal solution through collaboration with external experts and consultants. As a result, the notification unit can provide a more appropriate solution by notifying external experts and consultants. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit may automatically notify external experts and consultants using AI.

[0057] When providing a training program for employees to adapt to a new work flow, the support department can select the program by referring to past training history. For example, the support department reuses a training program that was effective in the past. The support department can also select the most efficient program from the past training history. Furthermore, the support department can analyze the past training history and determine the optimal program. As a result, the support department can select the optimal training program by referring to the past training history and efficiently provide it. A part or all of the above-mentioned processing in the support department may be performed using, for example, AI, or may be performed without using AI. For example, the support department can input the past training history into AI, which can select the optimal training program.

[0058] When providing a training program or guideline, the support department can adjust the content based on feedback from different departments within the company. For example, the support department provides necessary information based on feedback from each department. The support department can also adjust the content of the training program or guideline taking into account the priorities of each department. Furthermore, the support department can expand or reduce the range of information provided based on feedback. This allows the support department to provide more appropriate training programs and guidelines by adjusting the content based on feedback from different departments within the company. Some or all of the above-mentioned processing in the support department may be performed using, for example, AI, or may be performed without using AI. For example, the support department can input feedback from each department into AI, which then adjusts the content.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The in-house customer support system further includes an analysis unit that can analyze the collected data to identify trends and patterns. For example, the analysis unit can analyze past inquiry data to identify frequently asked topics. The analysis unit can also identify trends in inquiries that increase at certain times. The analysis unit can also track changes in the content of inquiries to detect new trends at an early stage. In this way, the analysis unit can identify trends and patterns based on the collected data and use the results to improve and optimize the system.

[0061] The generation unit can apply different answer generation algorithms depending on the category of the question based on the collected information. For example, a technical algorithm can be applied to technical questions. A legal algorithm can be applied to questions about regulations and procedures. Furthermore, a general-purpose algorithm can be applied to general inquiries. In this way, the generation unit can provide a more appropriate answer by applying the optimal answer generation algorithm depending on the category of the question.

[0062] The notification unit can determine the order of notifications when notifying the system personnel of escalated content. For example, important escalated content can be notified with priority. Also, technical problems can be notified quickly. Furthermore, general escalated content can be notified sequentially. In this way, the notification unit can efficiently notify personnel by determining the priority of notifications according to the importance of the escalated content.

[0063] When collecting information, the collection department may also collect information from external public databases or literature. For example, the latest industry information may be collected from external public databases. External literature may also be referenced to compare with in-house information. Furthermore, related research results and statistical data may also be collected from external databases. This allows the collection department to collect a wider range of information by collecting information from external public databases and literature.

[0064] At the time of escalation, the coordination department can adjust the escalation content taking into account coordination with multiple departments within the company. For example, the escalation content can be adjusted taking into account the expertise of each department. The escalation content can also be adjusted taking into account the priorities of each department. Furthermore, the escalation content can be adjusted based on feedback from each department. This allows the coordination department to adjust the escalation content taking into account coordination with different departments within the company, enabling more appropriate escalation.

[0065] When providing a training program for employees to adapt to a new work flow, the support department can select the program by referring to past training history. For example, training programs that were effective in the past can be reused. The most efficient program can also be selected from the past training history. Furthermore, the past training history can be analyzed to determine the optimal program. This allows the support department to select the optimal training program by referring to the past training history and provide it efficiently.

[0066] The process flow of the first embodiment will be briefly described below.

[0067] Step 1: The collection unit collects information from company databases and documents. For example, the collection unit may collect information about company policies and procedures. The collection unit may also restrict access and encrypt the data. For example, the collection unit may authenticate users and allow access only from specific IP addresses. The collection unit may also protect the data using AES encryption. Step 2: The generation unit uses a generation AI to generate an appropriate answer based on the collected information. For example, the generation unit uses a text generation AI (e.g., LLM) to generate an answer to the employee's question. The generation unit can also use a multimodal generation AI to generate an answer that includes images and audio. For example, the generation unit provides an answer to the employee's question that includes relevant images and audio. Step 3: The Collaboration Team escalates the case if the generated answer is not sufficient. For example, the Collaboration Team escalates technical issues or detailed inquiries related to a specific department to the system manager. The Collaboration Team can also set escalation rules. For example, the Collaboration Team can escalate based on priority or assignment of personnel. Step 4: The notification unit notifies the system administrator of the escalated content. For example, the notification unit can send an email notification or an alert notification. The notification unit can also display a dashboard. For example, the notification unit can display the escalated content on a dashboard, allowing the system administrator to respond quickly.

[0068] (Example 2) The in-house help desk system according to the embodiment of the present invention is a system that replaces the work of employees and contracted employees who work as an in-house help desk for employees with a generation AI. This system uses a generation AI service such as Azure OpenAI Service, sets access restrictions within the vNet, and builds a mechanism that allows information to be read without opting in. As a result, the generation AI performs all primary responses, and when escalation is required, it cooperates with the system's reception desk using a method specialized for the system's reception desk. In addition, the employee, who is the user, changes the business flow to one that allows the SLA (service level agreement) based on this mechanism. First, when an employee makes a question or inquiry, the generation AI accepts the content. Next, the generation AI generates an appropriate answer based on the information that was previously loaded. For example, the generation AI provides an immediate answer to a question about internal regulations and procedures. At this time, by using Azure OpenAI Service, it is possible to provide a quick answer while ensuring security. Furthermore, when a complex inquiry that the generation AI cannot handle or an escalation is required, it is automatically linked to the system's reception desk. For example, the system staff will handle content that the generation AI cannot handle, such as technical issues or detailed inquiries about a specific department. This collaboration is carried out smoothly using specialized methods. In addition, the employees who are the users will change their work flows to ones that allow for the SLA based on this new mechanism. Specifically, a work flow will be introduced that takes into account the speed of the first response by the generative AI and the efficiency of escalation. This will allow employees to carry out their work efficiently. This mechanism will streamline internal customer service operations for employees, providing quick and appropriate responses. In addition, it will enable smooth handling in cases where escalation is necessary, improving overall work efficiency. This will enable the internal customer service system to provide quick and appropriate responses to employee inquiries, improving work efficiency.

[0069] The in-house window system according to the embodiment includes a collection unit, a generation unit, a linking unit, and a notification unit. The collection unit collects information from an in-house database or document. For example, the collection unit can collect information on in-house regulations and procedures. The collection unit can also restrict access and encrypt data. For example, the collection unit performs user authentication and allows access only from a specific IP address. Furthermore, the collection unit can protect data using AES encryption. The generation unit uses a generation AI to generate an appropriate answer based on the collected information. For example, the generation unit uses a text generation AI (e.g., LLM) to generate an answer to an employee's question. The generation unit can also use a multimodal generation AI to generate an answer including an image or audio. For example, the generation unit provides an answer including a related image or audio to an employee's question. The linking unit escalates when the generated answer cannot be satisfied. For example, the linking unit escalates a technical problem or a detailed inquiry about a specific department to a system manager. The linking unit can also set escalation rules. For example, the coordination unit performs escalation based on priority and assignment of personnel. The notification unit notifies the system staff of the escalated content. For example, the notification unit can send email notifications or alert notifications. The notification unit can also display a dashboard. For example, the notification unit can display the escalated content on a dashboard so that the system staff can respond quickly. As a result, the internal customer service system according to the embodiment can provide quick and appropriate responses to employee inquiries, improving business efficiency.

[0070] The collection unit collects information from in-house databases and documents. Specifically, it can collect information on in-house regulations and procedures. For example, the collection unit periodically collects information from documents such as in-house policies, procedures, FAQs, and manuals, and keeps the latest information. The collection unit can also restrict access and encrypt data. For example, the collection unit performs user authentication and allows access only from a specific IP address. This can reduce the risk of in-house confidential information leaking to the outside. Furthermore, the collection unit can protect data using AES encryption. AES encryption is a powerful encryption method for increasing the confidentiality of data, and prevents the collected data from being accessed illegally. By implementing these security measures, the collection unit can safely collect and protect in-house information. In addition, the collection unit can flexibly set the frequency of data collection and the scope of the data. For example, by preferentially collecting information related to a specific department or project, it is possible to quickly provide the necessary information. This allows the collection unit to efficiently collect in-house information and improve the performance of the entire system.

[0071] The generation unit uses a generation AI to generate an appropriate answer based on the collected information. Specifically, a text generation AI (e.g., LLM) is used to generate answers to employees' questions. LLM has the ability to learn large amounts of text data and generate answers in natural language. For example, if an employee asks, "How do I apply for vacation?", the generation unit can provide a detailed answer on the specific procedure and necessary documents based on the collected information. The generation unit can also use a multimodal generation AI to generate answers that include images and voice. For example, if an employee asks, "Where is the logo for the new project?", the generation unit can search for related image files and attach them to the answer. In addition, the generation unit can also respond to questions by voice using voice recognition technology. For example, if an employee inputs a question by voice, the generation unit converts the voice into text and generates an appropriate answer. This allows the generation unit to integrate information in various formats, such as text, images, and voice, to meet the diverse needs of employees. In addition, the generation unit can evaluate the quality of the generated answer and make corrections and improvements as necessary. For example, if the generated answer is inaccurate, the generator will revise the answer based on the feedback and improve the accuracy of the answer from the next time onwards. This allows the generator to consistently provide high-quality answers and increase employee satisfaction.

[0072] The coordination department escalates when the generated answer is insufficient. Specifically, it escalates technical issues or detailed inquiries about a specific department to the system manager. For example, if an employee asks "I don't know how to install a new system," and the generation department cannot generate an appropriate answer, the coordination department escalates the inquiry to the system manager. The coordination department can also set escalation rules. For example, the coordination department escalates based on priority and assignment of personnel. High-priority inquiries are quickly responded to and assigned to specific personnel, enabling efficient response. Furthermore, the coordination department can manage escalation history and refer to past response status. This allows a quick response if a similar inquiry occurs again. The coordination department can automate the escalation process to speed up and streamline response. For example, it can be set so that inquiries containing specific keywords or phrases are automatically escalated. This allows the coordination department to quickly respond to complex inquiries that the generation department cannot handle, and support employees in solving problems.

[0073] The notification unit notifies the system manager of the escalated content. Specifically, it can perform email notification and alert notification. For example, when an escalated inquiry occurs, the notification unit immediately sends an email to the system manager to notify him / her that a response is required. The notification unit can also display a dashboard. For example, the escalated content can be displayed on the dashboard so that the system manager can respond quickly. The dashboard displays detailed information about the escalation and the response status in real time, so that the system manager can grasp the priority and progress at a glance. Furthermore, the notification unit can combine multiple notification means to reliably convey information. For example, by using SMS or push notification in addition to email notification, important information can be prevented from being overlooked. The notification unit can also manage the history of notifications and refer to the contents of past notifications. This makes it possible to track the response status of the escalation and follow up as necessary. Through these functions, the notification unit can support a prompt and appropriate response to the escalated inquiry and improve the efficiency of the entire system.

[0074] The collection unit can collect information from an in-house database or document. In-house databases and documents include, but are not limited to, for example, a customer database, technical documents, and project reports. The collection unit can collect, for example, customer information from a customer database. The collection unit can also collect technical information from technical documents. Furthermore, the collection unit can collect project progress from project reports. This allows the collection unit to efficiently collect necessary information from in-house databases and documents. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, when collecting information from an in-house database, the collection unit can search and extract data using AI.

[0075] The generation unit can generate an answer based on the collected information. The collected information includes, for example, text data, numerical data, image data, and the like, but is not limited to such examples. The generation unit can generate an answer based on, for example, text data. The generation unit can also generate an answer based on numerical data. Furthermore, the generation unit can also generate an answer based on image data. This allows the generation unit to generate a prompt and appropriate answer based on the collected information. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the collected text data to an AI, which can generate an answer.

[0076] The coordination unit can perform escalation when the generated answer cannot be used. Examples of cases where the answer cannot be used include, but are not limited to, cases where a specific keyword is included or where an answer is not generated within a certain time. The coordination unit can perform escalation for technical issues, for example. The coordination unit can also perform escalation for detailed inquiries about a specific department. Furthermore, the coordination unit can also perform escalation for complex inquiries. This allows the coordination unit to appropriately perform escalation when the generated answer cannot be used. A part or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can use AI to determine the criteria for escalation and perform escalation when the generated answer cannot be used.

[0077] The notification unit can notify the system person of the escalated content. The escalated content includes, for example, an error message, an unresolved inquiry, and the like, but is not limited to such examples. The notification unit can, for example, notify the system person of an error message. The notification unit can also notify the system person of the unresolved inquiry. Furthermore, the notification unit can also notify the system person of a technical problem. This allows the notification unit to quickly notify the system person of the escalated content. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input the escalated content into AI, and the AI ​​can notify the system person.

[0078] The collection unit can perform access restriction or data encryption. The access restriction includes, for example, user authentication, IP address restriction, etc., but is not limited to such examples. The collection unit can, for example, perform user authentication to allow only a specific user to access. The collection unit can also perform IP address restriction to allow access only from a specific IP address. Furthermore, the collection unit can encrypt data. The data encryption includes, for example, AES encryption, RSA encryption, etc., but is not limited to such examples. The collection unit can protect data using, for example, AES encryption. The collection unit can also protect data using RSA encryption. This allows the collection unit to efficiently collect information while ensuring the security of the information. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can automatically perform access restriction and data encryption using AI.

[0079] The coordination unit can set escalation rules. Escalation rules include, for example, setting a priority and assigning a person in charge, but are not limited to such examples. The coordination unit can, for example, set a priority and escalate important inquiries preferentially. The coordination unit can also assign a person in charge and escalate to a specific person in charge. Furthermore, the coordination unit can set an escalation procedure. For example, the coordination unit can set an escalation procedure and perform escalation efficiently. This allows the coordination unit to clarify the criteria for escalation and perform escalation efficiently. A part or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can automatically set the escalation rule using AI.

[0080] The in-house help desk system includes a support department, and can provide a training program or guidelines for employees to adapt to the new work flow. The support department provides training programs and guidelines for employees to quickly adapt to the new work flow. For example, the support department can provide online courses to allow employees to learn at their own pace. The support department can also hold workshops to allow employees to actually experience the new work flow. Furthermore, the support department can provide manuals and procedures to allow employees to refer to necessary information at any time. This allows employees to quickly adapt to the new work flow. Some or all of the above-mentioned processing in the support department can be performed, for example, using AI, or can be performed without using AI. For example, the support department can automatically generate the contents of the training program using AI and provide it to employees.

[0081] The collection unit can estimate the user's emotion and adjust the timing of information collection based on the estimated user's emotion. For example, when the user is feeling stressed, the collection unit reduces the frequency of information collection and collects only important information. In addition, when the user is relaxed, the collection unit can also collect detailed information and provide a comprehensive answer. Furthermore, when the user is in a hurry, the collection unit can quickly collect necessary information and generate an answer immediately. This allows the collection unit to adjust the timing of information collection according to the user's emotion, thereby enabling more appropriate information collection. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI, and the generation AI can adjust the timing of information collection.

[0082] When collecting information from an internal database or document, the collection unit can determine the priority of collection based on the importance of the information. For example, the collection unit prioritizes collection of information related to important regulations and procedures. The collection unit can also prioritize collection of the latest internal policies and guidelines. Furthermore, the collection unit can prioritize collection of frequently asked information based on past inquiry history. This allows the collection unit to efficiently collect important information by determining the priority of collection based on the importance of information. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can evaluate the importance of information using AI and determine the priority of collection.

[0083] The collection unit can select a collection method by referring to past collection history when collecting information. For example, the collection unit reuses a collection method that was effective in the past. The collection unit can also select the most efficient database from the past collection history. Furthermore, the collection unit can analyze the past collection history and determine the optimal collection timing. In this way, the collection unit can select the optimal collection method by referring to the past collection history and efficiently collect information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the past collection history into AI, which can select the optimal collection method.

[0084] The collection unit can estimate the user's emotion and determine the priority of information to be collected based on the estimated user's emotion. For example, when the user is feeling stressed, the collection unit preferentially collects only important information. In addition, when the user is relaxed, the collection unit can also preferentially collect detailed information. Furthermore, when the user is in a hurry, the collection unit can also preferentially collect information that is quickly required. This allows the collection unit to determine the priority of information to be collected according to the user's emotion, thereby enabling more appropriate information collection. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and determine the priority of information to be collected by the generation AI.

[0085] When collecting information, the collection unit can adjust the collected content based on feedback from multiple departments within the company. The collection unit, for example, collects necessary information based on feedback from each department. The collection unit can also adjust the content of the information to be collected, taking into account the priorities of each department. Furthermore, the collection unit can expand or reduce the range of information to be collected based on feedback. This allows the collection unit to adjust the collected content based on feedback from different departments within the company, thereby enabling more appropriate information collection. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input feedback from each department into AI, which can adjust the collected content.

[0086] The collection unit may also collect information from external public databases or literature when collecting information. The collection unit, for example, collects the latest industry information from external public databases. The collection unit may also refer to external literature and compare it with in-house information. Furthermore, the collection unit may also collect related research results and statistical data from external databases. This allows the collection unit to collect information from external public databases and literature, enabling more extensive information collection. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit may use AI to search and extract data when collecting information from external public databases.

[0087] The generation unit can estimate the user's emotion and adjust the way of expressing the answer based on the estimated user's emotion. For example, when the user is stressed, the generation unit generates a concise and clear answer. In addition, when the user is relaxed, the generation unit can also generate an answer that includes a detailed explanation. Furthermore, when the user is in a hurry, the generation unit can also generate an answer that can be quickly understood. In this way, the generation unit can provide a more appropriate answer by adjusting the way of expressing the answer according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI, and the generation AI can adjust the way of expressing the answer.

[0088] The generation unit can apply different answer generation algorithms according to the category of the question based on the collected information. For example, the generation unit applies a technical algorithm to a technical question. The generation unit can also apply a legal algorithm to a question about regulations and procedures. Furthermore, the generation unit can apply a general-purpose algorithm to a general inquiry. In this way, the generation unit can provide a more appropriate answer by applying an optimal answer generation algorithm according to the category of the question. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can classify the category of the question using AI and apply an optimal answer generation algorithm.

[0089] The generation unit can generate an answer by referring to a past answer history when generating an answer. The generation unit generates an optimal answer based on answers provided in the past, for example. The generation unit can also generate answers to frequently asked questions from the past answer history. Furthermore, the generation unit can analyze the past answer history and generate the most effective answer. As a result, the generation unit can generate an optimal answer by referring to the past answer history and efficiently provide the answer. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the past answer history to AI, which can generate an optimal answer.

[0090] The generation unit can estimate the user's emotion and adjust the level of detail of the answer based on the estimated user's emotion. For example, when the user is stressed, the generation unit generates a concise answer that is to the point. In addition, when the user is relaxed, the generation unit can also generate an answer that includes a detailed explanation. Furthermore, when the user is in a hurry, the generation unit can also generate an answer that can be quickly understood. In this way, the generation unit can provide a more appropriate answer by adjusting the level of detail of the answer according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI, and the generation AI can adjust the level of detail of the answer.

[0091] The generation unit can determine the order of answers based on the submission time of the questions when generating answers. For example, the generation unit generates answers preferentially for urgent questions. The generation unit can also generate answers quickly for questions submitted earlier. Furthermore, the generation unit can generate answers sequentially for questions submitted more recently. In this way, the generation unit can provide answers efficiently by determining the priority order of answers based on the submission time of the questions. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the submission time of the questions to an AI, which can determine the order of the answers.

[0092] The generation unit can adjust the order of answers based on the relevance of the questions when generating answers. For example, when the relevance of the questions is high, the generation unit generates answers with priority. Also, when the relevance of the questions is low, the generation unit can generate answers later. Furthermore, the generation unit can analyze the relevance of the questions and generate answers in an optimal order. In this way, the generation unit can provide answers efficiently by adjusting the order of answers based on the relevance of the questions. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can evaluate the relevance of the questions using AI and adjust the order of the answers.

[0093] The linking unit can estimate the user's emotion and adjust the escalation criteria based on the estimated user's emotion. For example, when the user is feeling stressed, the linking unit quickly escalates. Also, when the user is relaxed, the linking unit can collect detailed information before escalating. Furthermore, when the user is in a hurry, the linking unit can immediately escalate. This allows the linking unit to adjust the escalation criteria according to the user's emotion, thereby enabling more appropriate escalation. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the linking unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the linking unit can input the user's emotion data to the generation AI, and the generation AI can adjust the escalation criteria.

[0094] The coordination unit can determine the order of escalation when the generated answer is not applicable. For example, the coordination unit prioritizes escalation for important inquiries. The coordination unit can also quickly escalate technical issues. Furthermore, the coordination unit can also sequentially escalate general inquiries. This allows the coordination unit to appropriately determine the priority order of escalation when the generated answer is not applicable. A part or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can determine the order of escalation by AI.

[0095] At the time of escalation, the coordination unit can select a coordination method by referring to past escalation history. For example, the coordination unit reuses a coordination method that was effective in the past. The coordination unit can also select the most efficient coordination method from the past escalation history. Furthermore, the coordination unit can analyze the past escalation history and determine the optimal coordination method. In this way, the coordination unit can select the optimal coordination method by referring to the past escalation history and perform escalation efficiently. A part or all of the above-mentioned processing in the coordination unit may be performed, for example, using AI or may be performed without using AI. For example, the coordination unit can input the past escalation history into AI, which can select the optimal coordination method.

[0096] The linking unit can estimate the user's emotion and adjust the timing of escalation based on the estimated user's emotion. For example, when the user is stressed, the linking unit quickly performs escalation. Also, when the user is relaxed, the linking unit can collect detailed information before performing escalation. Furthermore, when the user is in a hurry, the linking unit can immediately perform escalation. As a result, the linking unit can perform escalation at a more appropriate timing by adjusting the timing of escalation according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the linking unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the linking unit can input the user's emotion data to the generation AI, and the generation AI can adjust the timing of escalation.

[0097] The coordination department can adjust the escalation content in consideration of coordination with multiple departments within the company at the time of escalation. The coordination department adjusts the escalation content, for example, in consideration of the expertise of each department. The coordination department can also adjust the escalation content in consideration of the priority of each department. Furthermore, the coordination department can adjust the escalation content based on feedback from each department. This allows the coordination department to adjust the escalation content in consideration of coordination with different departments within the company, thereby enabling more appropriate escalation. A part or all of the above-mentioned processing in the coordination department may be performed, for example, using AI, or may be performed without using AI. For example, the coordination department can input feedback from each department into AI, which can adjust the escalation content.

[0098] The collaboration unit can collaborate with external experts and consultants at the time of escalation. For example, the collaboration unit escalates technical issues to external experts. The collaboration unit can also escalate business process improvements to external consultants. Furthermore, the collaboration unit can provide optimal solutions through collaboration with external experts and consultants. This allows the collaboration unit to provide more appropriate solutions by collaborating with external experts and consultants. Some or all of the above-mentioned processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can automatically collaborate with external experts and consultants using AI.

[0099] The notification unit can estimate the user's emotion and adjust the notification expression method based on the estimated user's emotion. For example, when the user is feeling stressed, the notification unit provides a concise and clear notification. In addition, when the user is relaxed, the notification unit can also provide a notification including a detailed explanation. Furthermore, when the user is in a hurry, the notification unit can also provide a notification that can be quickly understood. In this way, the notification unit can adjust the notification expression method according to the user's emotion and provide a more appropriate notification. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the user's emotion data to the generation AI, and the generation AI can adjust the notification expression method.

[0100] The notification unit can determine the order of notifications when notifying the system personnel of the escalated contents. For example, the notification unit gives priority to notifications for important escalation contents. The notification unit can also quickly notify technical issues. Furthermore, the notification unit can also give notifications sequentially for general escalation contents. In this way, the notification unit can efficiently notify by determining the priority order of notifications according to the importance of the escalated contents. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can determine the order of notifications by AI.

[0101] The notification unit can select a notification method by referring to past notification history at the time of notification. The notification unit, for example, reuses a notification method that was effective in the past. The notification unit can also select the most efficient notification method from the past notification history. Furthermore, the notification unit can analyze the past notification history and determine the optimal notification method. As a result, the notification unit can select the optimal notification method by referring to the past notification history and efficiently perform notification. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input the past notification history into AI, which can select the optimal notification method.

[0102] The notification unit can estimate the user's emotion and adjust the timing of the notification based on the estimated user's emotion. For example, when the user is feeling stressed, the notification unit quickly notifies the user. Also, when the user is relaxed, the notification unit can collect detailed information before notifying the user. Furthermore, when the user is in a hurry, the notification unit can immediately notify the user. As a result, the notification unit can adjust the timing of the notification according to the user's emotion, thereby making it possible to notify at a more appropriate timing. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the user's emotion data to the generation AI, and the generation AI can adjust the timing of the notification.

[0103] The notification unit can adjust the notification content based on feedback from multiple departments in the company at the time of notification. The notification unit notifies necessary information based on feedback from each department, for example. The notification unit can also adjust the notification content taking into account the priorities of each department. Furthermore, the notification unit can expand or reduce the range of information to be notified based on feedback. This allows the notification unit to adjust the notification content based on feedback from different departments in the company, making it possible to provide more appropriate notification. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input feedback from each department into AI, which can adjust the notification content.

[0104] The notification unit may also notify external experts and consultants at the time of notification. The notification unit, for example, notifies external experts of technical problems. The notification unit may also notify external consultants of improvements to business processes. Furthermore, the notification unit may provide an optimal solution through collaboration with external experts and consultants. As a result, the notification unit can provide a more appropriate solution by notifying external experts and consultants. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit may automatically notify external experts and consultants using AI.

[0105] The support unit can estimate the user's emotions and adjust the contents of the training program or guideline based on the estimated user's emotions. For example, when the user is feeling stressed, the support unit provides a concise and clear training program. In addition, when the user is relaxed, the support unit can also provide a training program that includes detailed explanations. Furthermore, when the user is in a hurry, the support unit can also provide a training program that can be quickly understood. This allows the support unit to provide more appropriate support by adjusting the contents of the training program or guideline according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the support unit can input the user's emotion data into the generation AI, and the generation AI can adjust the contents of the training program or guideline.

[0106] When providing a training program for employees to adapt to a new work flow, the support department can select the program by referring to past training history. For example, the support department reuses a training program that was effective in the past. The support department can also select the most efficient program from the past training history. Furthermore, the support department can analyze the past training history and determine the optimal program. As a result, the support department can select the optimal training program by referring to the past training history and efficiently provide it. A part or all of the above-mentioned processing in the support department may be performed using, for example, AI, or may be performed without using AI. For example, the support department can input the past training history into AI, which can select the optimal training program.

[0107] The support unit can estimate the user's emotions and determine the priority of the training programs based on the estimated user's emotions. For example, when the user is feeling stressed, the support unit provides important training programs with priority. In addition, the support unit can also provide detailed training programs when the user is relaxed. Furthermore, when the user is in a hurry, the support unit can provide training programs that can be quickly understood. In this way, the support unit can provide more appropriate training by determining the priority of the training programs according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the support unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the support unit can input the user's emotion data into the generation AI, and the generation AI can determine the priority of the training programs.

[0108] When providing a training program or guideline, the support department can adjust the content based on feedback from different departments within the company. For example, the support department provides necessary information based on feedback from each department. The support department can also adjust the content of the training program or guideline taking into account the priorities of each department. Furthermore, the support department can expand or reduce the range of information provided based on feedback. This allows the support department to provide more appropriate training programs and guidelines by adjusting the content based on feedback from different departments within the company. Some or all of the above-mentioned processing in the support department may be performed using, for example, AI, or may be performed without using AI. For example, the support department can input feedback from each department into AI, which then adjusts the content.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The in-house customer support system further includes an analysis unit that can analyze the collected data to identify trends and patterns. For example, the analysis unit can analyze past inquiry data to identify frequently asked topics. The analysis unit can also identify trends in inquiries that increase at certain times. The analysis unit can also track changes in the content of inquiries to detect new trends at an early stage. In this way, the analysis unit can identify trends and patterns based on the collected data and use the results to improve and optimize the system.

[0111] The collection unit can estimate the user's emotions and adjust the timing of information collection based on the estimated user's emotions. For example, when the user is stressed, the frequency of information collection is reduced and only important information is collected. When the user is relaxed, detailed information can be collected and a comprehensive answer can be provided. Furthermore, when the user is in a hurry, necessary information can be quickly collected and an answer can be generated immediately. This allows the collection unit to adjust the timing of information collection according to the user's emotions, thereby enabling more appropriate information collection.

[0112] The generation unit can apply different answer generation algorithms depending on the category of the question based on the collected information. For example, a technical algorithm can be applied to technical questions. A legal algorithm can be applied to questions about regulations and procedures. Furthermore, a general-purpose algorithm can be applied to general inquiries. In this way, the generation unit can provide a more appropriate answer by applying the optimal answer generation algorithm depending on the category of the question.

[0113] The linking unit can estimate the user's emotions and adjust the escalation criteria based on the estimated user's emotions. For example, if the user is feeling stressed, escalation can be performed quickly. If the user is relaxed, escalation can be performed after collecting detailed information. Furthermore, if the user is in a hurry, escalation can be performed immediately. In this way, the linking unit can adjust the escalation criteria according to the user's emotions, enabling more appropriate escalation.

[0114] The notification unit can determine the order of notifications when notifying the system personnel of escalated content. For example, important escalated content can be notified with priority. Also, technical problems can be notified quickly. Furthermore, general escalated content can be notified sequentially. In this way, the notification unit can efficiently notify personnel by determining the priority of notifications according to the importance of the escalated content.

[0115] When collecting information, the collection department may also collect information from external public databases or literature. For example, the latest industry information may be collected from external public databases. External literature may also be referenced to compare with in-house information. Furthermore, related research results and statistical data may also be collected from external databases. This allows the collection department to collect a wider range of information by collecting information from external public databases and literature.

[0116] The generation unit can estimate the user's emotion and adjust the way the answer is expressed based on the estimated user's emotion. For example, if the user is stressed, a concise and clear answer can be generated. Also, if the user is relaxed, an answer including a detailed explanation can be generated. Furthermore, if the user is in a hurry, an answer that can be quickly understood can be generated. In this way, the generation unit can provide a more appropriate answer by adjusting the way the answer is expressed according to the user's emotion.

[0117] At the time of escalation, the coordination department can adjust the escalation content taking into account coordination with multiple departments within the company. For example, the escalation content can be adjusted taking into account the expertise of each department. The escalation content can also be adjusted taking into account the priorities of each department. Furthermore, the escalation content can be adjusted based on feedback from each department. This allows the coordination department to adjust the escalation content taking into account coordination with different departments within the company, enabling more appropriate escalation.

[0118] The notification unit can estimate the user's emotion and adjust the notification expression method based on the estimated user's emotion. For example, if the user is stressed, a concise and clear notification can be provided. If the user is relaxed, a notification including a detailed explanation can be provided. Furthermore, if the user is in a hurry, a notification that can be quickly understood can be provided. In this way, the notification unit can provide more appropriate notifications by adjusting the notification expression method according to the user's emotion.

[0119] When providing a training program for employees to adapt to a new work flow, the support department can select the program by referring to past training history. For example, training programs that were effective in the past can be reused. The most efficient program can also be selected from the past training history. Furthermore, the past training history can be analyzed to determine the optimal program. This allows the support department to select the optimal training program by referring to the past training history and provide it efficiently.

[0120] The process flow of the second embodiment will be briefly described below.

[0121] Step 1: The collection unit collects information from company databases and documents. For example, the collection unit may collect information about company policies and procedures. The collection unit may also restrict access and encrypt the data. For example, the collection unit may authenticate users and allow access only from specific IP addresses. The collection unit may also protect the data using AES encryption. Step 2: The generation unit uses a generation AI to generate an appropriate answer based on the collected information. For example, the generation unit uses a text generation AI (e.g., LLM) to generate an answer to the employee's question. The generation unit can also use a multimodal generation AI to generate an answer that includes images and audio. For example, the generation unit provides an answer to the employee's question that includes relevant images and audio. Step 3: The Collaboration Team escalates the case if the generated answer is not sufficient. For example, the Collaboration Team escalates technical issues or detailed inquiries related to a specific department to the system manager. The Collaboration Team can also set escalation rules. For example, the Collaboration Team can escalate based on priority or assignment of personnel. Step 4: The notification unit notifies the system administrator of the escalated content. For example, the notification unit can send an email notification or an alert notification. The notification unit can also display a dashboard. For example, the notification unit can display the escalated content on a dashboard, allowing the system administrator to respond quickly.

[0122] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0123] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0124] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0125] Each of the multiple elements including the above-mentioned collection unit, generation unit, linkage unit, notification unit, and support unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects information from an in-house database or document by the control unit 46A of the smart device 14. The generation unit generates an appropriate answer using a generation AI by the specific processing unit 290 of the data processing device 12, for example. The linkage unit performs escalation by the control unit 46A of the smart device 14, for example. The notification unit notifies the system person by the specific processing unit 290 of the data processing device 12, for example. The support unit provides a training program or guidelines by the control unit 46A of the smart device 14, for example. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0128] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0133] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0136] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0138] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements including the above-mentioned collection unit, generation unit, linkage unit, notification unit, and support unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects information from an in-house database or document by the control unit 46A of the smart glasses 214. The generation unit generates an appropriate answer using a generation AI by, for example, the specific processing unit 290 of the data processing device 12. The linkage unit performs escalation by, for example, the control unit 46A of the smart glasses 214. The notification unit notifies the system person by, for example, the specific processing unit 290 of the data processing device 12. The support unit provides a training program or guidelines by, for example, the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0144] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0149] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0152] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0156] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements including the above-mentioned collection unit, generation unit, linkage unit, notification unit, and support unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects information from an in-house database or document by the control unit 46A of the headset type terminal 314. The generation unit generates an appropriate answer using a generation AI by the specific processing unit 290 of the data processing device 12, for example. The linkage unit performs escalation by the control unit 46A of the headset type terminal 314, for example. The notification unit notifies the system person by the specific processing unit 290 of the data processing device 12, for example. The support unit provides a training program or guidelines by the control unit 46A of the headset type terminal 314, for example. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0158] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0159] 7, a 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.

[0160] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0165] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0166] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0167] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0168] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0169] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0170] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0172] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0173] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0174] Each of the multiple elements including the above-mentioned collection unit, generation unit, collaboration unit, notification unit, and support unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects information from an in-house database or document by the control unit 46A of the robot 414. The generation unit generates an appropriate answer using a generation AI by the specific processing unit 290 of the data processing device 12, for example. The collaboration unit performs escalation by the control unit 46A of the robot 414, for example. The notification unit notifies the system person by the specific processing unit 290 of the data processing device 12, for example. The support unit provides a training program or guidelines by the control unit 46A of the robot 414, for example. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0175] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0176] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0177] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0178] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0179] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0180] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0182] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0183] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0184] In addition, 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 upon request from the data processing device 12.

[0185] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0186] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0187] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0188] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0189] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0190] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0191] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0192] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0193] (Appendix 1) A collection unit that collects information; A generator that generates an answer based on the information collected by the collector; a coordination unit that performs escalation based on the answer generated by the generation unit; a notification unit that notifies a system manager of the content escalated by the coordination unit; Equipped A system characterized by: (Appendix 2) The collecting unit includes: Collect information from internal databases or documents 2. The system of claim 1, (Appendix 3) The generation unit is Generate answers based on collected information 2. The system of claim 1, (Appendix 4) The linking portion is Escalation if the generated answer is not sufficient 2. The system of claim 1, (Appendix 5) The notification unit is Notify the system administrator of the escalated matter 2. The system of claim 1, (Appendix 6) The collecting unit includes: Restrict access or encrypt data 2. The system of claim 1, (Appendix 7) The linking portion is Setting Escalation Rules 2. The system of claim 1, (Appendix 8) Equipped with a support section, The support portion is Provide training programs or guidelines to help employees adapt to new work flows 2. The system of claim 1, (Appendix 9) The collecting unit includes: To estimate a user's emotions and adjust the timing of information collection based on the estimated user's emotions. 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting information from company databases and documents, prioritize collection based on the importance of the information 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting information, select the collection method by referring to past collection history. 2. The system of claim 1, (Appendix 12) The collecting unit includes: Estimate user emotions and prioritize information to be collected based on the estimated user emotions. 2. The system of claim 1, (Appendix 13) The collecting unit includes: When gathering information, tailor it based on feedback from multiple departments across the company 2. The system of claim 1, (Appendix 14) The collecting unit includes: When collecting information, we also collect information from external public databases or literature. 2. The system of claim 1, (Appendix 15) The generation unit is Infer user sentiment and adjust answer expression based on the inferred sentiment 2. The system of claim 1, (Appendix 16) The generation unit is Based on the collected information, different answer generation algorithms are applied depending on the question category. 2. The system of claim 1, (Appendix 17) The generation unit is When generating an answer, generate an answer by referring to past answer history 2. The system of claim 1, (Appendix 18) The generation unit is Infer user sentiment and adjust the detail of answers based on the inferred user sentiment 2. The system of claim 1, (Appendix 19) The generation unit is When generating answers, order answers based on when the question was submitted 2. The system of claim 1, (Appendix 20) The generation unit is When generating answers, adjust the order of answers based on the relevance of the question 2. The system of claim 1, (Appendix 21) The linking portion is Infer user sentiment and adjust escalation criteria based on the inferred user sentiment 2. The system of claim 1, (Appendix 22) The linking portion is Determine the order of escalation if the generated answers are not sufficient 2. The system of claim 1, (Appendix 23) The linking portion is When escalating, refer to past escalation history to determine the method of collaboration 2. The system of claim 1, (Appendix 24) The linking portion is Infer user emotions and adjust the timing of escalation based on the inferred user emotions 2. The system of claim 1, (Appendix 25) The linking portion is When escalating, coordinate the content of the escalation taking into account collaboration with multiple departments within the company. 2. The system of claim 1, (Appendix 26) The linking portion is Liaise with external experts and consultants during escalations 2. The system of claim 1, (Appendix 27) The notification unit is Infer user emotions and adjust notification presentation based on the inferred user emotions 2. The system of claim 1, (Appendix 28) The notification unit is Determine the notification order when notifying system personnel of escalated matters 2. The system of claim 1, (Appendix 29) The notification unit is When notifying, select the notification method by referring to past notification history 2. The system of claim 1, (Appendix 30) The notification unit is Infer user emotions and adjust notification timing based on the estimated user emotions 2. The system of claim 1, (Appendix 31) The notification unit is When sending notifications, tailor the content based on feedback from multiple departments within the company 2. The system of claim 1, (Appendix 32) The notification unit is At the time of notification, external experts and consultants will also be notified. 2. The system of claim 1, (Appendix 33) The support portion is Estimate user emotions and adjust the content of training programs and guidelines based on the estimated user emotions 2. The system of claim 1, (Appendix 34) The support portion is When providing training programs to help employees adapt to new work flows, select the programs by referring to past training history. 2. The system of claim 1, (Appendix 35) The support portion is To estimate a user's emotion and prioritize training programs based on the estimated user's emotion. 2. The system of claim 1, (Appendix 36) The support portion is When delivering training programs and guidelines, tailor content based on feedback from different departments within the company 2. The system of claim 1, [Explanation of symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects information; A generator that generates an answer based on the information collected by the collector; a coordination unit that performs escalation based on the answer generated by the generation unit; a notification unit that notifies a system manager of the content escalated by the coordination unit; Equipped A system characterized by:

2. The collecting unit includes: Collect information from internal databases or documents 2. The system of claim 1 .

3. The linking portion is Escalating when the answer generated by the generating unit is not sufficient 2. The system of claim 1 .

4. The notification unit is Notify the system administrator of the escalated matter 2. The system of claim 1 .

5. The collecting unit includes: Restrict access or encrypt data 2. The system of claim 1 .

6. The linking portion is Setting Escalation Rules 2. The system of claim 1 .

7. Equipped with a support section, The support portion is Provide training programs or guidelines to help employees adapt to new work flows 2. The system of claim 1 .

Images