system

Abstract

The system according to this embodiment aims to quickly retrieve necessary information from an internal company database and provide highly accurate answers in real time. [Solution] The system according to the embodiment comprises an acquisition unit, an answering unit, a linking unit, a support unit, and a learning unit. The acquisition unit quickly retrieves necessary information from the company's internal database. The answering unit provides highly accurate answers in real time based on the information retrieved by the acquisition unit. The linking unit seamlessly links the answers provided by the answering unit with existing internal chat tools and portals. The support unit provides support for the answers provided by the answering unit in multiple languages. The learning unit continuously learns based on the answers provided by the answering unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to quickly extract necessary information from an in-house database and provide a highly accurate answer in real time, and there is room for efficiency improvement.

[0005] The system according to the embodiment aims to quickly extract necessary information from an in-house database and provide a highly accurate answer in real time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, an answering unit, an integration unit, a support unit, and a learning unit. The acquisition unit quickly retrieves necessary information from the company's internal database. The answering unit provides highly accurate answers in real time based on the information retrieved by the acquisition unit. The integration unit seamlessly integrates the answers provided by the answering unit with existing internal chat tools and portals. The support unit provides multilingual support for the answers provided by the answering unit. The learning unit continuously learns based on the answers provided by the answering unit. [Effects of the Invention]

[0007] The system according to this embodiment can quickly retrieve necessary information from an internal database and provide highly accurate answers in real time. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The interactive system according to an embodiment of the present invention is a system in which a generating AI responds immediately to internal accounting procedures. This interactive system uses RAG to quickly retrieve necessary information from the internal database and provides highly accurate answers in real time. Furthermore, it seamlessly integrates with existing internal chat tools and portals, allowing users to interact in a familiar environment. It utilizes text generation AI to provide multilingual support. By incorporating a continuous learning function based on the content of inquiries, the accuracy of the AI's answers is improved. This mechanism realizes the efficiency of accounting operations and the standardization of internal accounting, thereby improving the productivity of the entire company and reducing the burden on the accounting department. For example, if an employee asks the interactive system, "Please tell me the latest expense reimbursement procedure," RAG searches the internal database and retrieves information on the latest expense reimbursement procedure. This allows employees to quickly obtain the necessary information. Next, the interactive system seamlessly integrates with existing internal chat tools and portals. For example, employees can make accounting inquiries through the chat tool they normally use. This eliminates the need for employees to learn new tools and allows them to interact in a familiar environment. Furthermore, the interactive system utilizes text generation AI to provide multilingual support. For example, if a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the AI ​​will provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the AI ​​will provide an answer in English. This allows employees who speak different languages ​​to perform accounting procedures smoothly. Furthermore, the conversational system incorporates a continuous learning function based on the content of inquiries, improving the accuracy of the AI's answers. For example, if an employee asks, "Please tell me about the expense reimbursement procedure," and the answer provided by the AI ​​is insufficient, the AI ​​can learn from that feedback and improve the accuracy of future answers. In this way, the conversational system enables the streamlining of accounting operations and the standardization of internal accounting.Employees can quickly obtain the information they need, reducing the burden on the accounting department. This also contributes to increased productivity across the entire company. For example, by reducing the time employees spend on accounting procedures, they can focus on other tasks, thereby improving overall company productivity. Thus, interactive systems can streamline accounting operations and standardize internal accounting, leading to increased productivity across the company and a reduced burden on the accounting department.

[0029] The interactive system according to this embodiment comprises an acquisition unit, an answering unit, a collaboration unit, a support unit, and a learning unit. The acquisition unit quickly retrieves necessary information from the company's internal database. For example, the acquisition unit searches the internal database using RAG and retrieves the necessary information. RAG stands for Retrieval-Augmented Generation, a technology that combines information retrieval and generation AI. For example, if an employee asks, "Please tell me the latest expense reimbursement procedure," the acquisition unit searches the internal database using RAG and retrieves information regarding the latest expense reimbursement procedure. The answering unit provides highly accurate answers in real time based on the information retrieved by the acquisition unit. For example, the answering unit generates answers based on the information retrieved by the acquisition unit using generation AI. The generation AI generates answers in natural language using text generation AI (e.g., LLM). For example, if an employee asks, "Please tell me the latest expense reimbursement procedure," the answering unit generates an answer using generation AI based on the information retrieved by the acquisition unit. The collaboration unit seamlessly integrates the answers provided by the answering unit with existing internal chat tools and portals. The Integration Department, for example, uses APIs to send answers to internal chat tools and portals. This allows employees to interact in a familiar environment. For example, the Integration Department enables employees to make accounting inquiries through their usual chat tool. The Support Department provides multilingual support for the answers provided by the Answering Department. The Support Department generates answers in multiple languages, for example, using generative AI. The generative AI uses text generation AI (e.g., LLM) to generate answers in different languages. For example, if a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the Support Department uses the generative AI to provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the generative AI provides an answer in English. The Learning Department continuously learns based on the answers provided by the Answering Department. The Learning Department updates the generative AI's learning data, for example, based on employee feedback.This improves the accuracy of responses in subsequent instances. For example, if an employee asks, "Please tell me about the expense reimbursement procedure," and the response provided by the generating AI is insufficient, the learning unit updates the AI's learning data based on that feedback to improve the accuracy of responses in subsequent instances. As a result, the interactive system according to this embodiment can quickly retrieve necessary information from the company's internal database and provide highly accurate responses in real time, thereby achieving increased efficiency in accounting operations and standardization of internal accounting.

[0030] The retrieval unit quickly extracts necessary information from the company's internal database. For example, the retrieval unit uses RAG to search the internal database and extract the required information. RAG stands for Retrieval-Augmented Generation, a technology that combines information retrieval and generative AI. Specifically, RAG first analyzes the content of an employee's inquiry and extracts relevant keywords and phrases. Next, it searches the internal database using these keywords and retrieves relevant documents and data. The retrieved information is input into the generative AI, which generates an appropriate answer to the inquiry. For example, if an employee asks, "Please tell me the latest expense reimbursement procedure," RAG extracts keywords such as "expense reimbursement procedure" and "latest" and searches the internal database. The documents and data obtained as search results are input into the generative AI, which generates an answer in natural language. In this way, the retrieval unit can quickly and accurately extract the necessary information and pass it on to the next processing step. Furthermore, the retrieval unit can dynamically adjust the parameters of the search algorithm to improve the accuracy of the search results. For example, if the search results are not very relevant, the weighting of keywords and the search range can be adjusted to obtain more appropriate information. This allows the acquisition unit to always provide optimal information, improving the overall system performance.

[0031] The response unit provides highly accurate answers in real time based on the information extracted by the information acquisition unit. The response unit generates answers based on the information extracted by the information acquisition unit, for example, using a generation AI. The generation AI uses a text generation AI (e.g., LLM) to generate answers in natural language. Specifically, the generation AI analyzes the acquired information and generates the answer that is most appropriate to the inquiry. For example, if an employee asks, "Please tell me the latest expense reimbursement procedure," the generation AI will generate a detailed explanation of the latest expense reimbursement procedure based on the information extracted by the information acquisition unit. The generation AI can not only generate grammatically correct sentences but also accurately understand the intent of the inquiry and provide appropriate information. Furthermore, the response unit can evaluate the quality of the generated answers and make corrections as needed. For example, if the answer generated by the generation AI is insufficient, the response unit will acquire additional information and generate the answer again. In this way, the response unit can always provide high-quality answers and improve employee satisfaction.

[0032] The Integration Department seamlessly integrates the answers provided by the Response Department with existing internal chat tools and portals. For example, the Integration Department uses APIs to send answers to internal chat tools and portals. This allows employees to communicate in a familiar environment. Specifically, the Integration Department has the functionality to automatically send generated answers to the chat tools and portals that employees normally use. For example, if an employee asks "Please tell me the latest expense reimbursement procedure" via a chat tool, the Integration Department sends the answer generated by the Response Department to the chat tool and displays it to the employee. This eliminates the need for employees to learn new tools and allows them to obtain information while maintaining their existing workflows. Furthermore, because the Integration Department can integrate with multiple chat tools and portals, it can support tools used by different departments and teams. This allows the Integration Department to improve the overall flexibility and usability of the system.

[0033] The support department provides multilingual support for the answers provided by the response department. The support department generates answers in multiple languages, for example, using generative AI. The generative AI uses text generation AI (e.g., LLM) to generate answers in different languages. Specifically, the generative AI analyzes the inquiry and acquired information to generate answers in multiple languages. For example, if a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the generative AI will provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the generative AI will provide an answer in English. This allows the support department to provide consistent information to employees who speak different languages. Furthermore, the support department can evaluate the quality of the generated answers and make corrections as needed. For example, if the answer generated by the generative AI is insufficient, the support department will acquire additional information and generate the answer again. In this way, the support department can always provide high-quality multilingual answers and improve employee satisfaction.

[0034] The learning unit continuously learns based on the answers provided by the answering unit. For example, the learning unit updates the training data for the generative AI based on employee feedback. Specifically, the learning unit analyzes the feedback provided by employees and extracts data to improve the generative AI model. For example, if an employee asks, "Please tell me about the expense reimbursement procedure," and the answer provided by the generative AI is insufficient, the learning unit updates the training data for the generative AI based on that feedback to improve the accuracy of future answers. The learning unit categorizes the content of the feedback and identifies which parts need improvement. For example, if the content of the answer is unclear, it adjusts the model to add more specific information. The learning unit also periodically evaluates the performance of the generative AI and retrains the model as needed. This allows the learning unit to maintain the generative AI in a way that provides up-to-date information and highly accurate answers at all times. Furthermore, the learning unit can analyze employee inquiry patterns and trends to prepare for future needs. This allows the learning unit to continuously improve the overall system performance and user satisfaction.

[0035] The retrieval unit can extract information from the company's internal database using RAG. For example, the retrieval unit can search the internal database using RAG and extract the necessary information. RAG stands for Retrieval-Augmented Generation, a technology that combines information retrieval and generation AI. For example, if an employee asks the retrieval unit, "Please tell me the latest expense reimbursement procedure," the retrieval unit will use RAG to search the internal database and extract information about the latest expense reimbursement procedure. This allows for the rapid extraction of necessary information from the internal database using RAG. The specific technology and implementation method of RAG is realized, for example, using specific algorithms and protocols. Some or all of the above-described processes in the retrieval unit may be performed using AI, for example, or not using AI. For example, the retrieval unit can have AI perform the process of searching the internal database using RAG and extracting the necessary information.

[0036] The integration unit can seamlessly integrate with existing internal chat tools and portals. For example, the integration unit can use APIs to send responses to internal chat tools and portals. This allows employees to communicate in a familiar environment. For example, the integration unit can enable employees to make accounting inquiries through the chat tool they normally use. This allows users to communicate in a familiar environment by seamlessly integrating with existing internal chat tools and portals. The specific criteria and methods for seamless integration are evaluated based on factors such as latency and user experience. Some or all of the above-mentioned processes in the integration unit may be performed using AI, or not. For example, the integration unit can have AI perform the process of sending responses to internal chat tools and portals using APIs.

[0037] The support department can provide multilingual support by utilizing text generation AI. For example, the support department uses generation AI to generate answers in multiple languages. The generation AI uses text generation AI (e.g., LLM) to generate answers in different languages. For example, if a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the support department will use generation AI to provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the generation AI will provide an answer in English. In this way, by utilizing text generation AI, employees who speak different languages ​​can smoothly carry out accounting procedures. Some or all of the above processes in the support department are performed using generation AI. For example, the support department executes the process of generating answers in multiple languages ​​using generation AI.

[0038] The learning unit can continuously learn from inquiries and improve the accuracy of the AI's responses. For example, the learning unit can update the training data of the generating AI based on feedback from employees. This improves the accuracy of responses in the future. For example, if an employee asks, "Please tell me about the expense reimbursement procedure," and the answer provided by the generating AI is insufficient, the learning unit will update the training data of the generating AI based on that feedback to improve the accuracy of responses in the future. In this way, the accuracy of the AI's responses improves by continuously learning from inquiries. The specific frequency and duration of continuous learning can be set, for example, daily, weekly, or in real time. Some or all of the above processes in the learning unit are performed using AI. For example, the learning unit can have the AI ​​perform the process of updating the training data of the generating AI based on feedback from employees.

[0039] The data retrieval unit can analyze the user's past inquiry history and select the optimal retrieval method. For example, the retrieval unit can prioritize retrieving information that the user has frequently inquired about in the past. Furthermore, the retrieval unit can identify specific patterns from the user's past inquiry history and select the optimal retrieval method. In addition, the retrieval unit can prioritize retrieval methods (APIs, databases, etc.) that the user has used in the past. This allows the optimal retrieval method to be selected by analyzing the user's past inquiry history. Specific criteria and methods for determining the optimal retrieval method are implemented using, for example, search algorithms and filtering technologies. Some or all of the above-described processes in the retrieval unit are performed using AI. For example, the retrieval unit can have AI perform the process of analyzing the user's past inquiry history and selecting the optimal retrieval method.

[0040] The data acquisition unit can filter information based on the user's current work situation and areas of interest when acquiring it. For example, the data acquisition unit can prioritize acquiring information related to projects the user is currently working on. The data acquisition unit can also filter and acquire highly relevant information based on the user's areas of interest. Furthermore, the data acquisition unit can filter and acquire necessary information according to the user's work situation (busy, free time, etc.). This allows the system to provide highly relevant information by filtering information based on the user's current work situation and areas of interest. The specific types and criteria for work situation are evaluated based on, for example, project progress and task priority. The specific methods and criteria for identifying areas of interest are implemented using, for example, past search history and user profile information. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have AI perform the filtering process based on the user's current work situation and areas of interest when acquiring information.

[0041] The data acquisition unit can prioritize the acquisition of highly relevant information by considering the user's geographical location when acquiring information. For example, if the user is in a specific office, the data acquisition unit will prioritize the acquisition of information related to that office. Furthermore, if the user is on a business trip, the data acquisition unit can prioritize the acquisition of information related to the destination. Additionally, if the user is working remotely, the data acquisition unit can prioritize the acquisition of information related to their home. This allows for the provision of highly relevant information by considering the user's geographical location. Specific methods for acquiring and using geographical location information include, for example, GPS data and IP addresses. Some or all of the above-described processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have the AI ​​perform the process of prioritizing the acquisition of highly relevant information by considering the user's geographical location when acquiring information.

[0042] The data acquisition unit can analyze a user's social media activity and acquire relevant information when acquiring data. For example, the data acquisition unit can acquire relevant information based on information shared by the user on social media. It can also acquire information related to accounts that the user follows on social media. Furthermore, the data acquisition unit can acquire information that the user might be interested in based on their social media activity history. This allows the system to provide highly relevant information by analyzing the user's social media activity. The specific methods and criteria for analyzing social media activity are evaluated based on factors such as the content of posts and the number of likes. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have AI perform the process of analyzing a user's social media activity and acquiring relevant information when acquiring data.

[0043] The response unit can adjust the level of detail in the response based on the importance of the inquiry when generating the response. For example, the response unit will provide a detailed explanation for important inquiries. It can also provide a concise response for general inquiries. Furthermore, it can provide a concise response that can be addressed quickly for urgent inquiries. In this way, appropriate answers can be provided by adjusting the level of detail in the response based on the importance of the inquiry. Specific evaluation criteria and methods for importance are based on factors such as business impact and urgency. Some or all of the above processing in the response unit is performed using a generation AI. For example, the response unit can have the generation AI perform the process of adjusting the level of detail in the response based on the importance of the inquiry when generating the response.

[0044] The response unit can apply different response algorithms depending on the category of the inquiry when generating a response. For example, the response unit can apply a dedicated response algorithm for expense reimbursement inquiries. It can also apply a dedicated response algorithm for payroll inquiries. Furthermore, it can apply a dedicated response algorithm for invoice processing inquiries. By applying different response algorithms depending on the category of the inquiry, it is possible to provide more appropriate answers. The specific classification methods and criteria for categories are evaluated based on, for example, technology categories or business categories. The specific types and implementation methods of response algorithms are implemented using, for example, rule-based or machine learning-based algorithms. Some or all of the above processing in the response unit is performed using generative AI. For example, the response unit can have the generative AI execute the process of applying different response algorithms depending on the category of the inquiry when generating a response.

[0045] The response unit can determine the priority of responses based on when the inquiry was submitted when generating responses. For example, the response unit will provide responses to urgent inquiries with the highest priority. It can also provide responses to regular inquiries with normal priority. Furthermore, it can postpone responses to past inquiries. This allows for timely responses by determining the priority of responses based on when the inquiry was submitted. The specific criteria and evaluation methods for submission timing may be based on factors such as time of day or date. The specific criteria and methods for determining priority may be based on factors such as importance or urgency. Some or all of the above processing in the response unit is performed using a generation AI. For example, the response unit can have the generation AI perform the process of determining the priority of responses based on when the inquiry was submitted when generating responses.

[0046] The response unit can adjust the order of responses based on the relevance of the inquiry when generating answers. For example, the response unit can provide the most relevant information first. It can also postpone less relevant information. Furthermore, the response unit can prioritize displaying highly relevant information so that users can quickly find the information they need. This allows users to quickly find the information they need by adjusting the order of responses based on the relevance of the inquiry. Specific criteria and methods for evaluating relevance are, for example, based on keyword matching or topic similarity. Specific criteria and methods for adjusting the order are, for example, based on importance or relevance. Some or all of the above processing in the response unit is performed using a generation AI. For example, the response unit can have the generation AI perform the process of adjusting the order of responses based on the relevance of the inquiry when generating answers.

[0047] The integration unit can select the optimal integration method by referring to the user's past operation history during integration. For example, the integration unit can prioritize providing integration methods that the user has used in the past. The integration unit can also select the optimal integration method from the user's past operation history. Furthermore, the integration unit can automatically select integration methods that the user has frequently used in the past. This allows the optimal integration method to be selected by referring to the user's past operation history. The specific methods for acquiring and using operation history are evaluated based on, for example, click history and operation logs. The specific criteria and methods for the optimal integration method are evaluated based on, for example, notification methods and integration timing. Some or all of the above processes in the integration unit are performed using AI. For example, the integration unit can have AI execute the process of selecting the optimal integration method by referring to the user's past operation history during integration.

[0048] The integration unit can select the optimal integration method by considering the user's device information during integration. For example, if the user is using a smartphone, the integration unit will provide the optimal integration method for smartphones. Furthermore, if the user is using a tablet, the integration unit can provide the optimal integration method for tablets. In addition, if the user is using a desktop, the integration unit can provide the optimal integration method for desktops. This allows the system to provide the optimal integration method by considering the user's device information. The specific methods for acquiring and using device information are evaluated based on factors such as device type and OS information. The specific criteria and methods for the optimal integration method are evaluated based on factors such as notification methods and integration timing. Some or all of the above-described processes in the integration unit are performed using AI. For example, the integration unit can have AI perform the process of selecting the optimal integration method by considering the user's device information during integration.

[0049] The support unit can adjust the level of detail provided based on the user's language skills. For example, if the user is using their native language, the support unit will provide support that includes detailed explanations. If the user is using a second language, the support unit can also provide concise and clear support. Furthermore, if the user is using multiple languages, the support unit can provide a language switching function. This allows for more appropriate support to be provided by adjusting the level of detail based on the user's language skills. Specific evaluation criteria and methods for language skills include, for example, TOEIC scores and frequency of language use. Specific criteria and methods for adjusting the level of detail include, for example, the level of detail of the information and the depth of the explanation. Some or all of the above processing in the support unit is performed using generative AI. For example, the support unit can have the generative AI perform the process of adjusting the level of detail of support based on the user's language skills when providing support.

[0050] The support department can apply different support algorithms depending on the user's work content when providing support. For example, the support department can apply a support algorithm specifically for expense reimbursement to support related to expense reimbursement. It can also apply a support algorithm specifically for payroll to support related to payroll. Furthermore, it can apply a support algorithm specifically for invoice processing to support related to invoice processing. This allows for the provision of more appropriate support by applying different support algorithms according to the user's work content. The specific methods and criteria for identifying work content are evaluated based on factors such as project type and task content. The specific types and implementation methods of support algorithms are implemented using methods such as rule-based or machine learning-based algorithms. Some or all of the above-described processes in the support department are performed using generative AI. For example, the support department can have the generative AI execute the process of applying different support algorithms depending on the user's work content when providing support.

[0051] The support department can determine the priority of support based on the user's working hours when providing support. For example, the support department will respond to urgent support requests with the highest priority. The support department can also respond to regular support requests with normal priority. Furthermore, the support department can postpone responding to past support requests. This allows important support to be provided preferentially by determining the priority of support based on the user's working hours. The specific methods and criteria for determining working hours are evaluated based on, for example, working hours or project deadlines. The specific criteria and methods for determining priority are evaluated based on, for example, importance or urgency. Some or all of the above processes in the support department are performed using generative AI. For example, the support department can have the generative AI execute the process of determining the priority of support based on the user's working hours when providing support.

[0052] The support department can adjust the order of support by referring to the user's relevant business data when providing support. For example, the support department can prioritize support related to the user's current projects. It can also prioritize the most relevant support based on the user's relevant business data. Furthermore, the support department can analyze the user's business data to determine the optimal support order. This allows it to prioritize the provision of the most relevant support by referring to the user's relevant business data. The specific methods for acquiring and using relevant business data are evaluated based on, for example, project data and task data. The specific criteria and methods for adjusting the order are evaluated based on, for example, importance and relevance. Some or all of the above processes in the support department are performed using generative AI. For example, the support department can have the generative AI execute the process of adjusting the order of support by referring to the user's relevant business data when providing support.

[0053] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. It can also find effective learning patterns from past learning data and optimize the algorithm. Furthermore, the learning unit can analyze past learning data to improve the accuracy of the learning algorithm. This allows for the optimization of the learning algorithm and improvement of learning accuracy by referring to past learning data. The specific methods for acquiring and using past learning data are evaluated based on, for example, log data and historical data. The specific types and implementation methods of the learning algorithms are implemented using, for example, deep learning and reinforcement learning. Some or all of the above-described processes in the learning unit are performed using generative AI. For example, the learning unit can have the generative AI perform the process of optimizing the learning algorithm by referring to past learning data during the learning process.

[0054] The learning unit can weight training data based on the submission date of queries during training. For example, the learning unit can assign higher weights to recent query data during training. It can also assign lower weights to older query data during training. Furthermore, the learning unit can dynamically adjust the weights of the training data according to the submission date. This allows for more effective training by weighting the training data based on the submission date of queries. Specific criteria and evaluation methods for submission date may be based on factors such as time of day or date. Specific criteria and methods for weighting the training data may be based on factors such as data freshness and relevance. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit can have the generative AI perform the process of weighting training data based on the submission date of queries during training.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The data retrieval unit can analyze the user's past inquiry history and select the optimal retrieval method. For example, the retrieval unit can prioritize retrieving information that the user has frequently inquired about in the past. Furthermore, the retrieval unit can identify specific patterns from the user's past inquiry history and select the optimal retrieval method. In addition, the retrieval unit can prioritize retrieval methods (APIs, databases, etc.) that the user has used in the past. This allows the optimal retrieval method to be selected by analyzing the user's past inquiry history. Specific criteria and methods for determining the optimal retrieval method are implemented using, for example, search algorithms and filtering technologies. Some or all of the above-described processes in the retrieval unit are performed using AI. For example, the retrieval unit can have AI perform the process of analyzing the user's past inquiry history and selecting the optimal retrieval method.

[0057] The data acquisition unit can filter information based on the user's current work situation and areas of interest when acquiring it. For example, the data acquisition unit can prioritize acquiring information related to projects the user is currently working on. The data acquisition unit can also filter and acquire highly relevant information based on the user's areas of interest. Furthermore, the data acquisition unit can filter and acquire necessary information according to the user's work situation (busy, free time, etc.). This allows the system to provide highly relevant information by filtering information based on the user's current work situation and areas of interest. The specific types and criteria for work situation are evaluated based on, for example, project progress and task priority. The specific methods and criteria for identifying areas of interest are implemented using, for example, past search history and user profile information. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have AI perform the filtering process based on the user's current work situation and areas of interest when acquiring information.

[0058] The data acquisition unit can prioritize the acquisition of highly relevant information by considering the user's geographical location when acquiring information. For example, if the user is in a specific office, the data acquisition unit will prioritize the acquisition of information related to that office. Furthermore, if the user is on a business trip, the data acquisition unit can prioritize the acquisition of information related to the destination. Additionally, if the user is working remotely, the data acquisition unit can prioritize the acquisition of information related to their home. This allows for the provision of highly relevant information by considering the user's geographical location. Specific methods for acquiring and using geographical location information include, for example, GPS data and IP addresses. Some or all of the above-described processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have the AI ​​perform the process of prioritizing the acquisition of highly relevant information by considering the user's geographical location when acquiring information.

[0059] The data acquisition unit can analyze a user's social media activity and acquire relevant information when acquiring data. For example, the data acquisition unit can acquire relevant information based on information shared by the user on social media. It can also acquire information related to accounts that the user follows on social media. Furthermore, the data acquisition unit can acquire information that the user might be interested in based on their social media activity history. This allows the system to provide highly relevant information by analyzing the user's social media activity. The specific methods and criteria for analyzing social media activity are evaluated based on factors such as the content of posts and the number of likes. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have AI perform the process of analyzing a user's social media activity and acquiring relevant information when acquiring data.

[0060] The response unit can adjust the level of detail in the response based on the importance of the inquiry when generating the response. For example, the response unit will provide a detailed explanation for important inquiries. It can also provide a concise response for general inquiries. Furthermore, it can provide a concise response that can be addressed quickly for urgent inquiries. In this way, appropriate answers can be provided by adjusting the level of detail in the response based on the importance of the inquiry. Specific evaluation criteria and methods for importance are based on factors such as business impact and urgency. Some or all of the above processing in the response unit is performed using a generation AI. For example, the response unit can have the generation AI perform the process of adjusting the level of detail in the response based on the importance of the inquiry when generating the response.

[0061] The response unit can apply different response algorithms depending on the category of the inquiry when generating a response. For example, the response unit can apply a dedicated response algorithm for expense reimbursement inquiries. It can also apply a dedicated response algorithm for payroll inquiries. Furthermore, it can apply a dedicated response algorithm for invoice processing inquiries. By applying different response algorithms depending on the category of the inquiry, it is possible to provide more appropriate answers. The specific classification methods and criteria for categories are evaluated based on, for example, technology categories or business categories. The specific types and implementation methods of response algorithms are implemented using, for example, rule-based or machine learning-based algorithms. Some or all of the above processing in the response unit is performed using generative AI. For example, the response unit can have the generative AI execute the process of applying different response algorithms depending on the category of the inquiry when generating a response.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The retrieval unit quickly retrieves the necessary information from the company database. For example, it uses RAG (Retrieval-Augmented Generation) to search the company database and retrieve the necessary information. If an employee asks, "Please tell me the latest expense reimbursement procedure," RAG is used to retrieve information about the latest expense reimbursement procedure. Step 2: The response unit provides highly accurate answers in real time based on the information extracted by the acquisition unit. For example, it uses a generation AI (text generation AI, e.g., LLM) to generate answers in natural language based on the information extracted by the acquisition unit. If an employee asks, "Please tell me the latest expense reimbursement procedure," the generation AI is used to generate an answer. Step 3: The Integration Department seamlessly integrates the answers provided by the Response Department with existing internal chat tools and portals. For example, it sends answers to internal chat tools and portals using an API. This allows employees to communicate in a familiar environment. Employees can make accounting-related inquiries through the chat tools they normally use. Step 4: The support department provides multilingual support for the answers provided by the response department. For example, it uses generative AI to generate answers in multiple languages. If a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the generative AI will provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the generative AI will provide an answer in English. Step 5: The learning unit continuously learns based on the answers provided by the answering unit. For example, the learning data of the generating AI is updated based on feedback from employees. This improves the accuracy of answers in the future. If an employee asks, "Please tell me about the expense reimbursement procedure," and the answer provided by the generating AI is insufficient, the learning data of the generating AI is updated based on that feedback to improve the accuracy of answers in the future.

[0064] (Example of form 2) The interactive system according to an embodiment of the present invention is a system in which a generating AI responds immediately to internal accounting procedures. This interactive system uses RAG to quickly retrieve necessary information from the internal database and provides highly accurate answers in real time. Furthermore, it seamlessly integrates with existing internal chat tools and portals, allowing users to interact in a familiar environment. It utilizes text generation AI to provide multilingual support. By incorporating a continuous learning function based on the content of inquiries, the accuracy of the AI's answers is improved. This mechanism realizes the efficiency of accounting operations and the standardization of internal accounting, thereby improving the productivity of the entire company and reducing the burden on the accounting department. For example, if an employee asks the interactive system, "Please tell me the latest expense reimbursement procedure," RAG searches the internal database and retrieves information on the latest expense reimbursement procedure. This allows employees to quickly obtain the necessary information. Next, the interactive system seamlessly integrates with existing internal chat tools and portals. For example, employees can make accounting inquiries through the chat tool they normally use. This eliminates the need for employees to learn new tools and allows them to interact in a familiar environment. Furthermore, the interactive system utilizes text generation AI to provide multilingual support. For example, if a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the AI ​​will provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the AI ​​will provide an answer in English. This allows employees who speak different languages ​​to perform accounting procedures smoothly. Furthermore, the conversational system incorporates a continuous learning function based on the content of inquiries, improving the accuracy of the AI's answers. For example, if an employee asks, "Please tell me about the expense reimbursement procedure," and the answer provided by the AI ​​is insufficient, the AI ​​can learn from that feedback and improve the accuracy of future answers. In this way, the conversational system enables the streamlining of accounting operations and the standardization of internal accounting.Employees can quickly obtain the information they need, reducing the burden on the accounting department. This also contributes to increased productivity across the entire company. For example, by reducing the time employees spend on accounting procedures, they can focus on other tasks, thereby improving overall company productivity. Thus, interactive systems can streamline accounting operations and standardize internal accounting, leading to increased productivity across the company and a reduced burden on the accounting department.

[0065] The interactive system according to this embodiment comprises an acquisition unit, an answering unit, a collaboration unit, a support unit, and a learning unit. The acquisition unit quickly retrieves necessary information from the company's internal database. For example, the acquisition unit searches the internal database using RAG and retrieves the necessary information. RAG stands for Retrieval-Augmented Generation, a technology that combines information retrieval and generation AI. For example, if an employee asks, "Please tell me the latest expense reimbursement procedure," the acquisition unit searches the internal database using RAG and retrieves information regarding the latest expense reimbursement procedure. The answering unit provides highly accurate answers in real time based on the information retrieved by the acquisition unit. For example, the answering unit generates answers based on the information retrieved by the acquisition unit using generation AI. The generation AI generates answers in natural language using text generation AI (e.g., LLM). For example, if an employee asks, "Please tell me the latest expense reimbursement procedure," the answering unit generates an answer using generation AI based on the information retrieved by the acquisition unit. The collaboration unit seamlessly integrates the answers provided by the answering unit with existing internal chat tools and portals. The Integration Department, for example, uses APIs to send answers to internal chat tools and portals. This allows employees to interact in a familiar environment. For example, the Integration Department enables employees to make accounting inquiries through their usual chat tool. The Support Department provides multilingual support for the answers provided by the Answering Department. The Support Department generates answers in multiple languages, for example, using generative AI. The generative AI uses text generation AI (e.g., LLM) to generate answers in different languages. For example, if a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the Support Department uses the generative AI to provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the generative AI provides an answer in English. The Learning Department continuously learns based on the answers provided by the Answering Department. The Learning Department updates the generative AI's learning data, for example, based on employee feedback.This improves the accuracy of responses in subsequent instances. For example, if an employee asks, "Please tell me about the expense reimbursement procedure," and the response provided by the generating AI is insufficient, the learning unit updates the AI's learning data based on that feedback to improve the accuracy of responses in subsequent instances. As a result, the interactive system according to this embodiment can quickly retrieve necessary information from the company's internal database and provide highly accurate responses in real time, thereby achieving increased efficiency in accounting operations and standardization of internal accounting.

[0066] The retrieval unit quickly extracts necessary information from the company's internal database. For example, the retrieval unit uses RAG to search the internal database and extract the required information. RAG stands for Retrieval-Augmented Generation, a technology that combines information retrieval and generative AI. Specifically, RAG first analyzes the content of an employee's inquiry and extracts relevant keywords and phrases. Next, it searches the internal database using these keywords and retrieves relevant documents and data. The retrieved information is input into the generative AI, which generates an appropriate answer to the inquiry. For example, if an employee asks, "Please tell me the latest expense reimbursement procedure," RAG extracts keywords such as "expense reimbursement procedure" and "latest" and searches the internal database. The documents and data obtained as search results are input into the generative AI, which generates an answer in natural language. In this way, the retrieval unit can quickly and accurately extract the necessary information and pass it on to the next processing step. Furthermore, the retrieval unit can dynamically adjust the parameters of the search algorithm to improve the accuracy of the search results. For example, if the search results are not very relevant, the weighting of keywords and the search range can be adjusted to obtain more appropriate information. This allows the acquisition unit to always provide optimal information, improving the overall system performance.

[0067] The response unit provides highly accurate answers in real time based on the information extracted by the information acquisition unit. The response unit generates answers based on the information extracted by the information acquisition unit, for example, using a generation AI. The generation AI uses a text generation AI (e.g., LLM) to generate answers in natural language. Specifically, the generation AI analyzes the acquired information and generates the answer that is most appropriate to the inquiry. For example, if an employee asks, "Please tell me the latest expense reimbursement procedure," the generation AI will generate a detailed explanation of the latest expense reimbursement procedure based on the information extracted by the information acquisition unit. The generation AI can not only generate grammatically correct sentences but also accurately understand the intent of the inquiry and provide appropriate information. Furthermore, the response unit can evaluate the quality of the generated answers and make corrections as needed. For example, if the answer generated by the generation AI is insufficient, the response unit will acquire additional information and generate the answer again. In this way, the response unit can always provide high-quality answers and improve employee satisfaction.

[0068] The Integration Department seamlessly integrates the answers provided by the Response Department with existing internal chat tools and portals. For example, the Integration Department uses APIs to send answers to internal chat tools and portals. This allows employees to communicate in a familiar environment. Specifically, the Integration Department has the functionality to automatically send generated answers to the chat tools and portals that employees normally use. For example, if an employee asks "Please tell me the latest expense reimbursement procedure" via a chat tool, the Integration Department sends the answer generated by the Response Department to the chat tool and displays it to the employee. This eliminates the need for employees to learn new tools and allows them to obtain information while maintaining their existing workflows. Furthermore, because the Integration Department can integrate with multiple chat tools and portals, it can support tools used by different departments and teams. This allows the Integration Department to improve the overall flexibility and usability of the system.

[0069] The support department provides multilingual support for the answers provided by the response department. The support department generates answers in multiple languages, for example, using generative AI. The generative AI uses text generation AI (e.g., LLM) to generate answers in different languages. Specifically, the generative AI analyzes the inquiry and acquired information to generate answers in multiple languages. For example, if a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the generative AI will provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the generative AI will provide an answer in English. This allows the support department to provide consistent information to employees who speak different languages. Furthermore, the support department can evaluate the quality of the generated answers and make corrections as needed. For example, if the answer generated by the generative AI is insufficient, the support department will acquire additional information and generate the answer again. In this way, the support department can always provide high-quality multilingual answers and improve employee satisfaction.

[0070] The learning unit continuously learns based on the answers provided by the answering unit. For example, the learning unit updates the training data for the generative AI based on employee feedback. Specifically, the learning unit analyzes the feedback provided by employees and extracts data to improve the generative AI model. For example, if an employee asks, "Please tell me about the expense reimbursement procedure," and the answer provided by the generative AI is insufficient, the learning unit updates the training data for the generative AI based on that feedback to improve the accuracy of future answers. The learning unit categorizes the content of the feedback and identifies which parts need improvement. For example, if the content of the answer is unclear, it adjusts the model to add more specific information. The learning unit also periodically evaluates the performance of the generative AI and retrains the model as needed. This allows the learning unit to maintain the generative AI in a way that provides up-to-date information and highly accurate answers at all times. Furthermore, the learning unit can analyze employee inquiry patterns and trends to prepare for future needs. This allows the learning unit to continuously improve the overall system performance and user satisfaction.

[0071] The retrieval unit can extract information from the company's internal database using RAG. For example, the retrieval unit can search the internal database using RAG and extract the necessary information. RAG stands for Retrieval-Augmented Generation, a technology that combines information retrieval and generation AI. For example, if an employee asks the retrieval unit, "Please tell me the latest expense reimbursement procedure," the retrieval unit will use RAG to search the internal database and extract information about the latest expense reimbursement procedure. This allows for the rapid extraction of necessary information from the internal database using RAG. The specific technology and implementation method of RAG is realized, for example, using specific algorithms and protocols. Some or all of the above-described processes in the retrieval unit may be performed using AI, for example, or not using AI. For example, the retrieval unit can have AI perform the process of searching the internal database using RAG and extracting the necessary information.

[0072] The integration unit can seamlessly integrate with existing internal chat tools and portals. For example, the integration unit can use APIs to send responses to internal chat tools and portals. This allows employees to communicate in a familiar environment. For example, the integration unit can enable employees to make accounting inquiries through the chat tool they normally use. This allows users to communicate in a familiar environment by seamlessly integrating with existing internal chat tools and portals. The specific criteria and methods for seamless integration are evaluated based on factors such as latency and user experience. Some or all of the above-mentioned processes in the integration unit may be performed using AI, or not. For example, the integration unit can have AI perform the process of sending responses to internal chat tools and portals using APIs.

[0073] The support department can provide multilingual support by utilizing text generation AI. For example, the support department uses generation AI to generate answers in multiple languages. The generation AI uses text generation AI (e.g., LLM) to generate answers in different languages. For example, if a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the support department will use generation AI to provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the generation AI will provide an answer in English. In this way, by utilizing text generation AI, employees who speak different languages ​​can smoothly carry out accounting procedures. Some or all of the above processes in the support department are performed using generation AI. For example, the support department executes the process of generating answers in multiple languages ​​using generation AI.

[0074] The learning unit can continuously learn from inquiries and improve the accuracy of the AI's responses. For example, the learning unit can update the training data of the generating AI based on feedback from employees. This improves the accuracy of responses in the future. For example, if an employee asks, "Please tell me about the expense reimbursement procedure," and the answer provided by the generating AI is insufficient, the learning unit will update the training data of the generating AI based on that feedback to improve the accuracy of responses in the future. In this way, the accuracy of the AI's responses improves by continuously learning from inquiries. The specific frequency and duration of continuous learning can be set, for example, daily, weekly, or in real time. Some or all of the above processes in the learning unit are performed using AI. For example, the learning unit can have the AI ​​perform the process of updating the training data of the generating AI based on feedback from employees.

[0075] The information acquisition unit can estimate the user's emotions and adjust the timing of information acquisition based on the estimated emotions. For example, if the user is feeling stressed, the acquisition unit can acquire and provide information immediately. Conversely, if the user is relaxed, the acquisition unit can postpone information that can be delayed slightly. Furthermore, if the user is in a hurry, the acquisition unit can prioritize the information that can be acquired most quickly. This allows for the provision of information at a more appropriate time by adjusting the timing of information acquisition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the acquisition unit are performed using AI. For example, the acquisition unit can have the AI ​​perform the process of estimating the user's emotions and adjusting the timing of information acquisition based on the estimated emotions.

[0076] The data retrieval unit can analyze the user's past inquiry history and select the optimal retrieval method. For example, the retrieval unit can prioritize retrieving information that the user has frequently inquired about in the past. Furthermore, the retrieval unit can identify specific patterns from the user's past inquiry history and select the optimal retrieval method. In addition, the retrieval unit can prioritize retrieval methods (APIs, databases, etc.) that the user has used in the past. This allows the optimal retrieval method to be selected by analyzing the user's past inquiry history. Specific criteria and methods for determining the optimal retrieval method are implemented using, for example, search algorithms and filtering technologies. Some or all of the above-described processes in the retrieval unit are performed using AI. For example, the retrieval unit can have AI perform the process of analyzing the user's past inquiry history and selecting the optimal retrieval method.

[0077] The data acquisition unit can filter information based on the user's current work situation and areas of interest when acquiring it. For example, the data acquisition unit can prioritize acquiring information related to projects the user is currently working on. The data acquisition unit can also filter and acquire highly relevant information based on the user's areas of interest. Furthermore, the data acquisition unit can filter and acquire necessary information according to the user's work situation (busy, free time, etc.). This allows the system to provide highly relevant information by filtering information based on the user's current work situation and areas of interest. The specific types and criteria for work situation are evaluated based on, for example, project progress and task priority. The specific methods and criteria for identifying areas of interest are implemented using, for example, past search history and user profile information. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have AI perform the filtering process based on the user's current work situation and areas of interest when acquiring information.

[0078] The data acquisition unit can estimate the user's emotions and determine the priority of information to acquire based on the estimated emotions. For example, if the user is stressed, the data acquisition unit will prioritize acquiring the most important information. If the user is relaxed, the data acquisition unit can also prioritize acquiring detailed information. Furthermore, if the user is in a hurry, the data acquisition unit can prioritize information that can be acquired quickly. This allows for the priority provision of important information by prioritizing information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have the AI ​​perform the process of estimating the user's emotions and determining the priority of information to acquire based on the estimated emotions.

[0079] The data acquisition unit can prioritize the acquisition of highly relevant information by considering the user's geographical location when acquiring information. For example, if the user is in a specific office, the data acquisition unit will prioritize the acquisition of information related to that office. Furthermore, if the user is on a business trip, the data acquisition unit can prioritize the acquisition of information related to the destination. Additionally, if the user is working remotely, the data acquisition unit can prioritize the acquisition of information related to their home. This allows for the provision of highly relevant information by considering the user's geographical location. Specific methods for acquiring and using geographical location information include, for example, GPS data and IP addresses. Some or all of the above-described processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have the AI ​​perform the process of prioritizing the acquisition of highly relevant information by considering the user's geographical location when acquiring information.

[0080] The data acquisition unit can analyze a user's social media activity and acquire relevant information when acquiring data. For example, the data acquisition unit can acquire relevant information based on information shared by the user on social media. It can also acquire information related to accounts that the user follows on social media. Furthermore, the data acquisition unit can acquire information that the user might be interested in based on their social media activity history. This allows the system to provide highly relevant information by analyzing the user's social media activity. The specific methods and criteria for analyzing social media activity are evaluated based on factors such as the content of posts and the number of likes. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have AI perform the process of analyzing a user's social media activity and acquiring relevant information when acquiring data.

[0081] The response unit can estimate the user's emotions and adjust the way it expresses its response based on those emotions. For example, if the user is stressed, the response unit can provide a concise and clear response. If the user is relaxed, it can also provide a response that includes detailed explanations. Furthermore, if the user is in a hurry, it can provide a concise and quick response. This allows for the provision of more appropriate responses by adjusting the way the response is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the response unit are performed using generative AI. For example, the response unit can have the generative AI perform the process of estimating the user's emotions and adjusting the way the response is expressed based on those estimated emotions.

[0082] The response unit can adjust the level of detail in the response based on the importance of the inquiry when generating the response. For example, the response unit will provide a detailed explanation for important inquiries. It can also provide a concise response for general inquiries. Furthermore, it can provide a concise response that can be addressed quickly for urgent inquiries. In this way, appropriate answers can be provided by adjusting the level of detail in the response based on the importance of the inquiry. Specific evaluation criteria and methods for importance are based on factors such as business impact and urgency. Some or all of the above processing in the response unit is performed using a generation AI. For example, the response unit can have the generation AI perform the process of adjusting the level of detail in the response based on the importance of the inquiry when generating the response.

[0083] The response unit can apply different response algorithms depending on the category of the inquiry when generating a response. For example, the response unit can apply a dedicated response algorithm for expense reimbursement inquiries. It can also apply a dedicated response algorithm for payroll inquiries. Furthermore, it can apply a dedicated response algorithm for invoice processing inquiries. By applying different response algorithms depending on the category of the inquiry, it is possible to provide more appropriate answers. The specific classification methods and criteria for categories are evaluated based on, for example, technology categories or business categories. The specific types and implementation methods of response algorithms are implemented using, for example, rule-based or machine learning-based algorithms. Some or all of the above processing in the response unit is performed using generative AI. For example, the response unit can have the generative AI execute the process of applying different response algorithms depending on the category of the inquiry when generating a response.

[0084] The response unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is stressed, the response unit can provide a short, to-the-point response. If the user is relaxed, the response unit can provide a longer response with more detailed explanations. Furthermore, if the user is in a hurry, the response unit can provide a short, quick-to-read response. By adjusting the length of the response based on the user's emotions, a more appropriate response can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit is performed using generative AI. For example, the response unit can have the generative AI perform the process of estimating the user's emotions and adjusting the length of the response based on the estimated emotions.

[0085] The response unit can determine the priority of responses based on when the inquiry was submitted when generating responses. For example, the response unit will provide responses to urgent inquiries with the highest priority. It can also provide responses to regular inquiries with normal priority. Furthermore, it can postpone responses to past inquiries. This allows for timely responses by determining the priority of responses based on when the inquiry was submitted. The specific criteria and evaluation methods for submission timing may be based on factors such as time of day or date. The specific criteria and methods for determining priority may be based on factors such as importance or urgency. Some or all of the above processing in the response unit is performed using a generation AI. For example, the response unit can have the generation AI perform the process of determining the priority of responses based on when the inquiry was submitted when generating responses.

[0086] The response unit can adjust the order of responses based on the relevance of the inquiry when generating answers. For example, the response unit can provide the most relevant information first. It can also postpone less relevant information. Furthermore, the response unit can prioritize displaying highly relevant information so that users can quickly find the information they need. This allows users to quickly find the information they need by adjusting the order of responses based on the relevance of the inquiry. Specific criteria and methods for evaluating relevance are, for example, based on keyword matching or topic similarity. Specific criteria and methods for adjusting the order are, for example, based on importance or relevance. Some or all of the above processing in the response unit is performed using a generation AI. For example, the response unit can have the generation AI perform the process of adjusting the order of responses based on the relevance of the inquiry when generating answers.

[0087] The interaction unit can estimate the user's emotions and adjust the interaction method based on the estimated emotions. For example, if the user is stressed, the interaction unit can provide a simple interaction method. It can also provide a more detailed interaction method if the user is relaxed. Furthermore, if the user is in a hurry, the interaction unit can provide a method for quick interaction. This allows for the provision of more appropriate interaction methods by adjusting the interaction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the interaction unit are performed using AI. For example, the interaction unit can have the AI ​​perform the process of estimating the user's emotions and adjusting the interaction method based on the estimated emotions.

[0088] The integration unit can select the optimal integration method by referring to the user's past operation history during integration. For example, the integration unit can prioritize providing integration methods that the user has used in the past. The integration unit can also select the optimal integration method from the user's past operation history. Furthermore, the integration unit can automatically select integration methods that the user has frequently used in the past. This allows the optimal integration method to be selected by referring to the user's past operation history. The specific methods for acquiring and using operation history are evaluated based on, for example, click history and operation logs. The specific criteria and methods for the optimal integration method are evaluated based on, for example, notification methods and integration timing. Some or all of the above processes in the integration unit are performed using AI. For example, the integration unit can have AI execute the process of selecting the optimal integration method by referring to the user's past operation history during integration.

[0089] The collaboration unit can estimate the user's emotions and determine the priority of collaborations based on those emotions. For example, if the user is stressed, the collaboration unit will prioritize the most important collaborations. It can also prioritize detailed collaborations if the user is relaxed. Furthermore, if the user is in a hurry, the collaboration unit can prioritize methods that allow for quick collaboration. This allows for the priority provision of important collaborations by determining the priority of collaborations based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collaboration unit is performed using AI. For example, the collaboration unit can have AI perform the process of estimating the user's emotions and determining the priority of collaborations based on those estimated emotions.

[0090] The integration unit can select the optimal integration method by considering the user's device information during integration. For example, if the user is using a smartphone, the integration unit will provide the optimal integration method for smartphones. Furthermore, if the user is using a tablet, the integration unit can provide the optimal integration method for tablets. In addition, if the user is using a desktop, the integration unit can provide the optimal integration method for desktops. This allows the system to provide the optimal integration method by considering the user's device information. The specific methods for acquiring and using device information are evaluated based on factors such as device type and OS information. The specific criteria and methods for the optimal integration method are evaluated based on factors such as notification methods and integration timing. Some or all of the above-described processes in the integration unit are performed using AI. For example, the integration unit can have AI perform the process of selecting the optimal integration method by considering the user's device information during integration.

[0091] The support unit can estimate the user's emotions and adjust the way it expresses support based on those emotions. For example, if the user is stressed, the support unit can provide concise and clear support. If the user is relaxed, the support unit can also provide support that includes detailed explanations. Furthermore, if the user is in a hurry, the support unit can provide concise and rapid support. This allows for more appropriate support to be provided by adjusting the way support is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the support unit are performed using generative AI. For example, the support unit can have the generative AI perform the process of estimating the user's emotions and adjusting the way support is expressed based on those estimated emotions.

[0092] The support unit can adjust the level of detail provided based on the user's language skills. For example, if the user is using their native language, the support unit will provide support that includes detailed explanations. If the user is using a second language, the support unit can also provide concise and clear support. Furthermore, if the user is using multiple languages, the support unit can provide a language switching function. This allows for more appropriate support to be provided by adjusting the level of detail based on the user's language skills. Specific evaluation criteria and methods for language skills include, for example, TOEIC scores and frequency of language use. Specific criteria and methods for adjusting the level of detail include, for example, the level of detail of the information and the depth of the explanation. Some or all of the above processing in the support unit is performed using generative AI. For example, the support unit can have the generative AI perform the process of adjusting the level of detail of support based on the user's language skills when providing support.

[0093] The support department can apply different support algorithms depending on the user's work content when providing support. For example, the support department can apply a support algorithm specifically for expense reimbursement to support related to expense reimbursement. It can also apply a support algorithm specifically for payroll to support related to payroll. Furthermore, it can apply a support algorithm specifically for invoice processing to support related to invoice processing. This allows for the provision of more appropriate support by applying different support algorithms according to the user's work content. The specific methods and criteria for identifying work content are evaluated based on factors such as project type and task content. The specific types and implementation methods of support algorithms are implemented using methods such as rule-based or machine learning-based algorithms. Some or all of the above-described processes in the support department are performed using generative AI. For example, the support department can have the generative AI execute the process of applying different support algorithms depending on the user's work content when providing support.

[0094] The support unit can estimate the user's emotions and adjust the length of the support based on those emotions. For example, if the user is stressed, the support unit can provide short, concise support. If the user is relaxed, the support unit can provide longer support with more detailed explanations. Furthermore, if the user is in a hurry, the support unit can provide short, quick-to-read support. By adjusting the length of support based on the user's emotions, more appropriate support can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the support unit is performed using generative AI. For example, the support unit can have the generative AI perform the process of estimating the user's emotions and adjusting the length of the support based on those emotions.

[0095] The support department can determine the priority of support based on the user's working hours when providing support. For example, the support department will respond to urgent support requests with the highest priority. The support department can also respond to regular support requests with normal priority. Furthermore, the support department can postpone responding to past support requests. This allows important support to be provided preferentially by determining the priority of support based on the user's working hours. The specific methods and criteria for determining working hours are evaluated based on, for example, working hours or project deadlines. The specific criteria and methods for determining priority are evaluated based on, for example, importance or urgency. Some or all of the above processes in the support department are performed using generative AI. For example, the support department can have the generative AI execute the process of determining the priority of support based on the user's working hours when providing support.

[0096] The support department can adjust the order of support by referring to the user's relevant business data when providing support. For example, the support department can prioritize support related to the user's current projects. It can also prioritize the most relevant support based on the user's relevant business data. Furthermore, the support department can analyze the user's business data to determine the optimal support order. This allows it to prioritize the provision of the most relevant support by referring to the user's relevant business data. The specific methods for acquiring and using relevant business data are evaluated based on, for example, project data and task data. The specific criteria and methods for adjusting the order are evaluated based on, for example, importance and relevance. Some or all of the above processes in the support department are performed using generative AI. For example, the support department can have the generative AI execute the process of adjusting the order of support by referring to the user's relevant business data when providing support.

[0097] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is stressed, the learning unit will select concise and clear training data. If the user is relaxed, the learning unit can also select training data that includes detailed explanations. Furthermore, if the user is in a hurry, the learning unit can select data that allows for rapid learning. This enables more effective learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The criteria and specific methods for selecting training data are evaluated based on, for example, the type and quality of the data. Some or all of the above-described processes in the learning unit are performed using generative AI. For example, the learning unit can have the generative AI perform the process of estimating the user's emotions and selecting training data based on those estimated emotions.

[0098] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. It can also find effective learning patterns from past learning data and optimize the algorithm. Furthermore, the learning unit can analyze past learning data to improve the accuracy of the learning algorithm. This allows for the optimization of the learning algorithm and improvement of learning accuracy by referring to past learning data. The specific methods for acquiring and using past learning data are evaluated based on, for example, log data and historical data. The specific types and implementation methods of the learning algorithms are implemented using, for example, deep learning and reinforcement learning. Some or all of the above-described processes in the learning unit are performed using generative AI. For example, the learning unit can have the generative AI perform the process of optimizing the learning algorithm by referring to past learning data during the learning process.

[0099] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency. Conversely, if the user is relaxed, the learning unit can increase the learning frequency. Furthermore, if the user is in a hurry, the learning unit can adjust the learning frequency to learn more efficiently. This allows for more effective learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Specific criteria and methods for adjusting the learning frequency are evaluated based on, for example, the learning interval and learning timing. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit can have the generative AI perform the process of estimating the user's emotions and adjusting the learning frequency based on the estimated emotions.

[0100] The learning unit can weight training data based on the submission date of queries during training. For example, the learning unit can assign higher weights to recent query data during training. It can also assign lower weights to older query data during training. Furthermore, the learning unit can dynamically adjust the weights of the training data according to the submission date. This allows for more effective training by weighting the training data based on the submission date of queries. Specific criteria and evaluation methods for submission date may be based on factors such as time of day or date. Specific criteria and methods for weighting the training data may be based on factors such as data freshness and relevance. Some or all of the above processing in the learning unit is performed using generative AI. For example, the learning unit can have the generative AI perform the process of weighting training data based on the submission date of queries during training.

[0101] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0102] The information acquisition unit can estimate the user's emotions and adjust the timing of information acquisition based on the estimated emotions. For example, if the user is feeling stressed, the acquisition unit can acquire and provide information immediately. Conversely, if the user is relaxed, the acquisition unit can postpone information that can be delayed slightly. Furthermore, if the user is in a hurry, the acquisition unit can prioritize the information that can be acquired most quickly. This allows for the provision of information at a more appropriate time by adjusting the timing of information acquisition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the acquisition unit are performed using AI. For example, the acquisition unit can have the AI ​​perform the process of estimating the user's emotions and adjusting the timing of information acquisition based on the estimated emotions.

[0103] The data retrieval unit can analyze the user's past inquiry history and select the optimal retrieval method. For example, the retrieval unit can prioritize retrieving information that the user has frequently inquired about in the past. Furthermore, the retrieval unit can identify specific patterns from the user's past inquiry history and select the optimal retrieval method. In addition, the retrieval unit can prioritize retrieval methods (APIs, databases, etc.) that the user has used in the past. This allows the optimal retrieval method to be selected by analyzing the user's past inquiry history. Specific criteria and methods for determining the optimal retrieval method are implemented using, for example, search algorithms and filtering technologies. Some or all of the above-described processes in the retrieval unit are performed using AI. For example, the retrieval unit can have AI perform the process of analyzing the user's past inquiry history and selecting the optimal retrieval method.

[0104] The data acquisition unit can filter information based on the user's current work situation and areas of interest when acquiring it. For example, the data acquisition unit can prioritize acquiring information related to projects the user is currently working on. The data acquisition unit can also filter and acquire highly relevant information based on the user's areas of interest. Furthermore, the data acquisition unit can filter and acquire necessary information according to the user's work situation (busy, free time, etc.). This allows the system to provide highly relevant information by filtering information based on the user's current work situation and areas of interest. The specific types and criteria for work situation are evaluated based on, for example, project progress and task priority. The specific methods and criteria for identifying areas of interest are implemented using, for example, past search history and user profile information. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have AI perform the filtering process based on the user's current work situation and areas of interest when acquiring information.

[0105] The data acquisition unit can estimate the user's emotions and determine the priority of information to acquire based on the estimated emotions. For example, if the user is stressed, the data acquisition unit will prioritize acquiring the most important information. If the user is relaxed, the data acquisition unit can also prioritize acquiring detailed information. Furthermore, if the user is in a hurry, the data acquisition unit can prioritize information that can be acquired quickly. This allows for the priority provision of important information by prioritizing information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have the AI ​​perform the process of estimating the user's emotions and determining the priority of information to acquire based on the estimated emotions.

[0106] The data acquisition unit can prioritize the acquisition of highly relevant information by considering the user's geographical location when acquiring information. For example, if the user is in a specific office, the data acquisition unit will prioritize the acquisition of information related to that office. Furthermore, if the user is on a business trip, the data acquisition unit can prioritize the acquisition of information related to the destination. Additionally, if the user is working remotely, the data acquisition unit can prioritize the acquisition of information related to their home. This allows for the provision of highly relevant information by considering the user's geographical location. Specific methods for acquiring and using geographical location information include, for example, GPS data and IP addresses. Some or all of the above-described processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have the AI ​​perform the process of prioritizing the acquisition of highly relevant information by considering the user's geographical location when acquiring information.

[0107] The data acquisition unit can analyze a user's social media activity and acquire relevant information when acquiring data. For example, the data acquisition unit can acquire relevant information based on information shared by the user on social media. It can also acquire information related to accounts that the user follows on social media. Furthermore, the data acquisition unit can acquire information that the user might be interested in based on their social media activity history. This allows the system to provide highly relevant information by analyzing the user's social media activity. The specific methods and criteria for analyzing social media activity are evaluated based on factors such as the content of posts and the number of likes. Some or all of the above processing in the data acquisition unit is performed using AI. For example, the data acquisition unit can have AI perform the process of analyzing a user's social media activity and acquiring relevant information when acquiring data.

[0108] The response unit can estimate the user's emotions and adjust the way it expresses its response based on those emotions. For example, if the user is stressed, the response unit can provide a concise and clear response. If the user is relaxed, it can also provide a response that includes detailed explanations. Furthermore, if the user is in a hurry, it can provide a concise and quick response. This allows for the provision of more appropriate responses by adjusting the way the response is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the response unit are performed using generative AI. For example, the response unit can have the generative AI perform the process of estimating the user's emotions and adjusting the way the response is expressed based on those estimated emotions.

[0109] The response unit can adjust the level of detail in the response based on the importance of the inquiry when generating the response. For example, the response unit will provide a detailed explanation for important inquiries. It can also provide a concise response for general inquiries. Furthermore, it can provide a concise response that can be addressed quickly for urgent inquiries. In this way, appropriate answers can be provided by adjusting the level of detail in the response based on the importance of the inquiry. Specific evaluation criteria and methods for importance are based on factors such as business impact and urgency. Some or all of the above processing in the response unit is performed using a generation AI. For example, the response unit can have the generation AI perform the process of adjusting the level of detail in the response based on the importance of the inquiry when generating the response.

[0110] The response unit can apply different response algorithms depending on the category of the inquiry when generating a response. For example, the response unit can apply a dedicated response algorithm for expense reimbursement inquiries. It can also apply a dedicated response algorithm for payroll inquiries. Furthermore, it can apply a dedicated response algorithm for invoice processing inquiries. By applying different response algorithms depending on the category of the inquiry, it is possible to provide more appropriate answers. The specific classification methods and criteria for categories are evaluated based on, for example, technology categories or business categories. The specific types and implementation methods of response algorithms are implemented using, for example, rule-based or machine learning-based algorithms. Some or all of the above processing in the response unit is performed using generative AI. For example, the response unit can have the generative AI execute the process of applying different response algorithms depending on the category of the inquiry when generating a response.

[0111] The response unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is stressed, the response unit can provide a short, to-the-point response. If the user is relaxed, the response unit can provide a longer response with more detailed explanations. Furthermore, if the user is in a hurry, the response unit can provide a short, quick-to-read response. By adjusting the length of the response based on the user's emotions, a more appropriate response can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit is performed using generative AI. For example, the response unit can have the generative AI perform the process of estimating the user's emotions and adjusting the length of the response based on the estimated emotions.

[0112] The following briefly describes the processing flow for example form 2.

[0113] Step 1: The retrieval unit quickly retrieves the necessary information from the company database. For example, it uses RAG (Retrieval-Augmented Generation) to search the company database and retrieve the necessary information. If an employee asks, "Please tell me the latest expense reimbursement procedure," RAG is used to retrieve information about the latest expense reimbursement procedure. Step 2: The response unit provides highly accurate answers in real time based on the information extracted by the acquisition unit. For example, it uses a generation AI (text generation AI, e.g., LLM) to generate answers in natural language based on the information extracted by the acquisition unit. If an employee asks, "Please tell me the latest expense reimbursement procedure," the generation AI is used to generate an answer. Step 3: The Integration Department seamlessly integrates the answers provided by the Response Department with existing internal chat tools and portals. For example, it sends answers to internal chat tools and portals using an API. This allows employees to communicate in a familiar environment. Employees can make accounting-related inquiries through the chat tools they normally use. Step 4: The support department provides multilingual support for the answers provided by the response department. For example, it uses generative AI to generate answers in multiple languages. If a Japanese-speaking employee asks, "Please tell me about the expense reimbursement procedure," the generative AI will provide an answer in Japanese. Similarly, if an English-speaking employee asks, "Tell me about the expense reimbursement process," the generative AI will provide an answer in English. Step 5: The learning unit continuously learns based on the answers provided by the answering unit. For example, the learning data of the generating AI is updated based on feedback from employees. This improves the accuracy of answers in the future. If an employee asks, "Please tell me about the expense reimbursement procedure," and the answer provided by the generating AI is insufficient, the learning data of the generating AI is updated based on that feedback to improve the accuracy of answers in the future.

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0115] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0116] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0117] Each of the multiple elements described above, including the acquisition unit, response unit, collaboration unit, support unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the acquisition unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The response unit is implemented by the specific processing unit 290 of the data processing unit 12. The collaboration unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The support unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0118] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0122] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0124] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0125] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0126] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0127] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0128] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0130] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0132] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements described above, including the acquisition unit, response unit, collaboration unit, support unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The response unit is implemented by the specific processing unit 290 of the data processing unit 12. The collaboration unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The support unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0134] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0135] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0136] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0137] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0138] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0140] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0141] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0142] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0143] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0144] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0146] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0148] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements described above, including the acquisition unit, response unit, cooperation unit, support unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The response unit is implemented by the specific processing unit 290 of the data processing unit 12. The cooperation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The support unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0150] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0151] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0152] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0153] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0154] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0156] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0157] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0158] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0159] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0160] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0161] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0163] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0165] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0166] Each of the multiple elements described above, including the acquisition unit, response unit, cooperation unit, support unit, and learning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The response unit is implemented by the specific processing unit 290 of the data processing unit 12. The cooperation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The support unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0167] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0168] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0169] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0170] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0171] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0172] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0173] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0174] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0175] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0176] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0177] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0178] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0179] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0180] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0181] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0182] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0183] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0184] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0185] (Note 1) The retrieval unit quickly extracts necessary information from the company's internal database, A response unit that provides a highly accurate response in real time based on the information extracted by the acquisition unit, The response provided by the aforementioned response unit is integrated with an integration unit that seamlessly connects with existing internal chat tools and portals. A support unit that provides multilingual support for the answers provided by the aforementioned answer unit, The system comprises a learning unit that continuously learns based on the answers provided by the answering unit. A system characterized by the following features. (Note 2) The acquisition unit is, Retrieve information from the company's internal database using RAG. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned linkage unit is, Seamless integration with existing internal chat tools and portals. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned support unit is We provide multilingual support using text generation AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, The AI ​​continuously learns from the content of inquiries and improves the accuracy of its responses. The system described in Appendix 1, characterized by the features described herein. (Note 6) The acquisition unit is, It estimates the user's emotions and adjusts the timing of information acquisition based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, Analyze the user's past inquiry history and select the optimal method for obtaining the information. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, When retrieving information, filtering is performed based on the user's current work situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, It estimates the user's emotions and determines the priority of information to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, When retrieving information, the system prioritizes retrieving highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, When acquiring information, the system analyzes the user's social media activity and retrieves relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned response section is, It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned response section is, When generating an answer, adjust the level of detail in the answer based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned response section is, When generating responses, different response algorithms are applied depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned response section is, It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned response section is, When generating responses, the priority of responses is determined based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned response section is, When generating responses, the order of responses is adjusted based on the relevance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned linkage unit is, It estimates the user's emotions and adjusts the interaction method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned linkage unit is, During integration, the system selects the optimal integration method by referring to the user's past operation history. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned linkage unit is, It estimates the user's emotions and determines the priority of collaborations based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned linkage unit is, During integration, the optimal integration method is selected by considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned support unit is It estimates the user's emotions and adjusts the way support is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned support unit is When providing support, we adjust the level of detail based on the user's language skills. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned support unit is When providing support, different support algorithms are applied depending on the user's work content. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned support unit is It estimates the user's emotions and adjusts the length of support based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned support unit is When providing support, we prioritize support based on the user's working hours. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned support unit is When providing support, we adjust the order of support by referring to the user's relevant business data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned learning unit, During training, the training data is weighted based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The retrieval unit quickly extracts necessary information from the company's internal database, A response unit that provides a highly accurate response in real time based on the information extracted by the acquisition unit, The response provided by the aforementioned response unit is integrated with an integration unit that seamlessly connects with existing internal chat tools and portals. A support unit that provides multilingual support for the answers provided by the aforementioned answer unit, The system comprises a learning unit that continuously learns based on the answers provided by the answering unit. A system characterized by the following features.

2. The acquisition unit is, Retrieve information from the company's internal database using RAG. The system according to feature 1.

3. The aforementioned linkage unit is, Seamless integration with existing internal chat tools and portals. The system according to feature 1.

4. The aforementioned support unit is We utilize text generation AI to provide multilingual support. The system according to feature 1.

5. The aforementioned learning unit, The AI ​​continuously learns from the content of inquiries and improves the accuracy of its responses. The system according to feature 1.

6. The acquisition unit is, It estimates the user's emotions and adjusts the timing of information acquisition based on the estimated user emotions. The system according to feature 1.

7. The acquisition unit is, Analyze the user's past inquiry history and select the optimal method for obtaining the information. The system according to feature 1.

8. The acquisition unit is, When retrieving information, filtering is performed based on the user's current work situation and areas of interest. The system according to feature 1.

9. The acquisition unit is, It estimates the user's emotions and determines the priority of information to acquire based on the estimated user emotions. The system according to feature 1.

10. The acquisition unit is, When retrieving information, the system prioritizes retrieving highly relevant information by considering the user's geographical location. The system according to feature 1.

Images