system

Abstract

The system according to this embodiment aims to efficiently create reports based on the history and interactions with customers. [Solution] The system according to the embodiment comprises a reading unit, a reference unit, a generation unit, and a creation unit. The reading unit reads emails containing the history and correspondence with customers. The reference unit refers to past internal reports based on the content of the emails read by the reading unit. The generation unit generates future countermeasures based on the information referred by the reference unit. The creation unit creates a report based on the countermeasures generated by the generation 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that creating a report based on the background and interactions with customers requires time and effort and is difficult to perform efficiently.

[0005] The system according to the embodiment aims to efficiently create a report based on the background and interactions with customers.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reading unit, a reference unit, a generation unit, and a creation unit. The reading unit reads emails containing the history and correspondence with customers. The reference unit references past internal reports based on the content of the emails read by the reading unit. The generation unit generates future countermeasures based on the information referenced by the reference unit. The creation unit creates a report based on the countermeasures generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently create reports based on the history and interactions with customers. [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 report generation system according to an embodiment of the present invention is a system that reads emails detailing the history of an incident and interactions with customers, generates future countermeasures based on past internal reports, and creates a report. The report generation system reads emails detailing the history of an incident and interactions with customers, refers to past internal reports, generates future countermeasures, and creates a report. This system is expected to support the generation of apology reports and contribute to improving operational efficiency and building trust. For example, the report generation system reads emails detailing the history of an incident and interactions with customers. At this time, it analyzes the content of the emails in detail and extracts important information. For example, it extracts the content of customer complaints and response history. This makes it possible to understand the history of customer service. Next, the report generation system refers to past internal reports and generates future countermeasures. Past reports often contain similar complaints and countermeasures. Based on this information, it generates future countermeasures. For example, it can propose an apology letter and countermeasures to the customer by referring to the countermeasures described in past reports. Next, the report generation system creates a report based on the generated countermeasures. The report contains the history of customer service and future countermeasures. For example, it includes an apology letter to the customer, countermeasures, and points for future improvement. This report will enable prompt and appropriate customer service. This system is expected to support the generation of apology reports, contributing to improved operational efficiency and the building of trust. For example, it will enable faster customer service and the creation of appropriate apology letters, which is expected to improve the company's image and help avoid legal risks. Furthermore, utilizing past reports will standardize and streamline operations. This will improve the quality of customer service and contribute to building trust. The report generation system will read the history and email correspondence with the customer, generate future countermeasures based on past internal reports, and create the report.

[0029] The report generation system according to the embodiment comprises a reading unit, a reference unit, a generation unit, and a creation unit. The reading unit reads emails containing the history and interactions with customers. The reading unit, for example, retrieves emails from a mail server and analyzes the content of the emails. The reading unit can also analyze the content of the emails in detail and extract important information. For example, the reading unit can extract customer complaint details and response history. The reference unit refers to past internal reports based on the content of the emails read by the reading unit. The reference unit searches past reports using, for example, keyword search or full-text search. The reference unit can also identify similar complaints and countermeasures from past reports. For example, the reference unit identifies countermeasures described in past reports. The generation unit generates future countermeasures based on the information identified by the reference unit. The generation unit generates future countermeasures using, for example, a generation AI. The generation unit inputs a prompt to the generation AI instructing it to generate countermeasures based on past reports, and the generation AI generates the countermeasures. The creation unit creates a report based on the countermeasures generated by the generation unit. The creation unit creates a report according to the report format based on the generated countermeasures. The creation unit can also create reports using a generation AI. For example, the creation unit can input prompts to the generation AI to create a report based on the generated countermeasures, and the generation AI will create the report. As a result, the report generation system according to this embodiment can read the history and emails of communication with customers, generate future countermeasures based on past internal reports, and create a report.

[0030] The reading unit reads emails containing the history and interactions with customers. Specifically, the reading unit retrieves emails from the mail server and analyzes their content. Email retrieval from the mail server is performed using protocols such as IMAP and POP3, and SSL / TLS encryption is applied to ensure security. The retrieved emails are analyzed by a text analysis engine, and metadata such as the email body, subject, sender, recipient, and date and time are extracted. Furthermore, the reading unit uses natural language processing (NLP) techniques to analyze the email content in detail and extract important information. For example, techniques such as keyword extraction, sentiment analysis, and entity recognition are used to extract customer complaint details and response history. This allows the reading unit to efficiently analyze email content and accurately extract necessary information. In addition, the reading unit stores the extracted information as structured data so that it can be used for subsequent processing. For example, customer complaint details and response history are stored in a database, making it accessible to the retrieval and generation units. This allows the reading unit to analyze email content in detail and extract important information, thereby improving the overall efficiency and accuracy of the system.

[0031] The reference unit accesses past internal reports based on the content of emails read by the input unit. Specifically, the reference unit searches past reports using keyword search and full-text search. Keyword search quickly searches past reports using important keywords extracted from the email content. Full-text search searches the entire text of the report, allowing for the acquisition of more detailed information. Furthermore, the reference unit can also identify similar claims and countermeasures from past reports. For example, it uses natural language processing technology to compare the content of emails with the content of past reports and calculates the similarity. This allows the reference unit to identify countermeasures described in past reports and use them as a reference for future countermeasures. The reference unit displays search results in a ranking format, prioritizing the display of the most relevant reports. The reference unit can also filter search results, limiting searches to specific periods or personnel. This allows the reference unit to efficiently access past reports and quickly acquire necessary information. In addition, the reference unit saves search results to a database for use in subsequent processing. This allows the reference unit to effectively utilize past reports and improve the overall efficiency and accuracy of the system.

[0032] The generation unit generates future countermeasures based on the information identified by the reference unit. Specifically, the generation unit uses a generation AI to generate future countermeasures. The generation AI is input with prompts instructing it to generate countermeasures based on past reports. These prompts include information such as customer complaints, past countermeasures, and the current situation. Based on this information, the generation AI generates the optimal countermeasures. The generation AI uses natural language generation (NLG) technology to generate specific countermeasure proposals as text. For example, the generation AI proposes countermeasures suitable for the new situation, while referring to countermeasures described in past reports. The generated countermeasures are verified by the generation unit and modified as necessary. The generation unit saves the generated countermeasures to a database so that they can be used for subsequent processing. This allows the generation unit to efficiently generate future countermeasures and improve the overall efficiency and accuracy of the system. Furthermore, the generation unit regularly updates the generation AI's training data so that it can generate countermeasures based on the latest information. This allows the generation unit to always provide the optimal countermeasures and improve the reliability and effectiveness of the overall system.

[0033] The creation department prepares reports based on the countermeasures generated by the generation department. Specifically, the creation department prepares reports according to the report format based on the generated countermeasures. The report format includes sections such as title, summary, details, and conclusion. The creation department can also create reports using a generation AI. The generation AI is given prompts to create a report based on the generated countermeasures. These prompts include the report format and necessary information. Based on this information, the generation AI automatically generates each section of the report. For example, the generation AI explains the generated countermeasures in detail, including specific procedures and points to note. The generation AI can also propose future prospects and additional countermeasures in the conclusion section of the report. The creation department reviews the generated reports and makes corrections as needed. The creation department can save the generated reports to a database and share them with other departments and stakeholders as needed. This allows the creation department to efficiently create reports and improve the overall efficiency and accuracy of the system. Furthermore, the creation department regularly updates the generation AI's training data to ensure that reports are based on the latest information. This allows the creation department to consistently provide high-quality reports and improve the reliability and effectiveness of the overall system.

[0034] The reading unit can analyze the content of emails in detail and extract important information. For example, the reading unit can analyze the content of emails using natural language processing techniques. For example, the reading unit can tokenize the content of emails and evaluate the importance of each token. The reading unit can also extract specific keywords or phrases from the content of emails. For example, the reading unit can extract keywords related to customer complaints. Furthermore, the reading unit can use algorithms to analyze the content of emails and extract important information. For example, the reading unit can use algorithms to analyze the content of emails and extract frequently occurring phrases and important information. This allows for a detailed analysis of the content of emails and the extraction of important information, enabling an understanding of the history of customer interactions. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input the content of emails into AI and have the AI ​​perform the extraction of important information.

[0035] The reference unit can refer to past reports and identify similar claims and countermeasures. For example, the reference unit can search past reports using keyword searches. For instance, it can extract specific keywords based on the content of an email and use those keywords to search past reports. The reference unit can also search past reports using full-text searches. For example, it can use the entire content of an email as a search query to search past reports. Furthermore, the reference unit can use algorithms to identify similar claims and countermeasures within past reports. For example, it can analyze the content of past reports and use algorithms to identify similar claims and countermeasures. This allows the reference unit to obtain information for generating future countermeasures by referring to past reports and identifying similar claims and countermeasures. Some or all of the above processing in the reference unit may be performed using AI, or not. For example, the reference unit can input past reports into an AI and have the AI ​​identify similar claims and countermeasures.

[0036] The generation unit can generate future countermeasures based on the information identified by the reference unit. For example, the generation unit can generate future countermeasures using a generation AI. The generation unit inputs a prompt to the generation AI instructing it to generate countermeasures based on past reports, and the generation AI generates the countermeasures. For example, the generation unit inputs the prompt "Generate an apology letter to the customer based on past reports" to the generation AI, and the generation AI generates the apology letter. The generation unit can also use the generation AI to generate countermeasures based on past reports. For example, the generation unit inputs the prompt "Generate improvement measures for customer service based on past reports" to the generation AI, and the generation AI generates improvement measures. In this way, by generating future countermeasures based on the information identified by the reference unit, it is possible to propose appropriate countermeasures. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the generation unit can input information identified by the reference unit into the generation AI and cause the generation AI to execute the generation of future countermeasures.

[0037] The creation unit can create a report based on the countermeasures generated by the generation unit. For example, the creation unit can create a report according to a report format based on the generated countermeasures. The creation unit can also create a report using a generation AI. For example, the creation unit can input a prompt to the generation AI to create a report based on the generated countermeasures, and the generation AI will create the report. The creation unit can also automatically generate the content of the report based on the generated countermeasures. For example, the creation unit can use an algorithm that automatically generates each item of the report based on the generated countermeasures. This enables quick and appropriate customer response by creating a report based on the countermeasures generated by the generation unit. Some or all of the above processes in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input the countermeasures generated by the generation unit into the AI ​​and have the AI ​​create the report.

[0038] The reading unit can prioritize the extraction of specific keywords and phrases when analyzing the content of an email. For example, the reading unit can prioritize the extraction of keywords related to customer complaints. For example, it can extract keywords such as "dissatisfaction," "problem," and "complaint." The reading unit can also prioritize the extraction of phrases related to important dates and deadlines. For example, it can extract phrases such as "deadline," "due date," and "delivery date." Furthermore, the reading unit can also prioritize the extraction of keywords related to customer gratitude and satisfaction. For example, it can extract keywords such as "thank you," "satisfied," and "grateful." By prioritizing the extraction of specific keywords and phrases, important information can be grasped quickly. Some or all of the above processing in the reading unit may be performed using AI, for example, or not. For example, the reading unit can input the content of an email into an AI and have the AI ​​perform the extraction of specific keywords and phrases.

[0039] The reading unit can analyze emails while considering the attribute information of the email sender and recipient. For example, if the sender is an important customer, the reading unit will prioritize the analysis of that email. For example, the reading unit will prioritize the analysis of emails from important customers to ensure a quick response. The reading unit can also analyze emails based on the attribute information of recipients who belong to a specific department or position. For example, the reading unit will prioritize the analysis of emails from recipients belonging to a specific department or position. Furthermore, the reading unit can determine the priority of analysis by considering the past communication history of the sender and recipient. For example, the reading unit will prioritize the analysis of important emails based on past communication history. This allows for the prioritization of important emails by considering the attribute information of the email sender and recipient. Some or all of the above processing in the reading unit may be performed using AI, or not. For example, the reading unit can input the attribute information of the email sender and recipient into AI and have AI determine the priority of analysis.

[0040] The reading unit can analyze emails while considering the geographical location information of the email sender. For example, the reading unit can prioritize analyzing emails from different regions to identify region-specific problems. For example, the reading unit can prioritize analyzing emails from a specific region to identify region-specific problems. The reading unit can also propose region-specific countermeasures based on the sender's geographical location information. For example, the reading unit can analyze emails from a specific region and propose countermeasures appropriate for that region. Furthermore, the reading unit can forward emails to the appropriate department, taking the sender's geographical location information into consideration. For example, the reading unit analyzes emails from a specific region and forwards them to the appropriate department for that region. This allows for the identification of region-specific problems by analyzing emails while considering the sender's geographical location information. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input the email sender's geographical location information into AI and have the AI ​​perform the analysis.

[0041] The reading unit can analyze emails while considering the time they were sent. For example, if an email was sent outside of business hours, the reading unit will prioritize its analysis to encourage a quick response. For example, the reading unit will prioritize the analysis of emails sent outside of business hours to ensure a quick response. The reading unit can also analyze emails sent during business hours with the usual priority. For example, the reading unit will analyze emails sent during business hours with the usual priority. Furthermore, if an email was sent during a specific event or campaign period, the reading unit can prioritize its analysis of that email. For example, the reading unit will prioritize the analysis of emails sent during a specific event or campaign period. This allows for a quicker response by considering the time the email was sent during the analysis. Some or all of the above processing in the reading unit may be performed using AI, or not. For example, the reading unit can input the email's sending time into AI and have the AI ​​perform the analysis.

[0042] The reference unit can prioritize referencing past reports, taking into account the report's creation date and the author's attribute information. For example, the reference unit can prioritize referencing reports with more recent creation dates and generate countermeasures based on the latest information. For example, the reference unit can prioritize referencing the most recent report and generate countermeasures based on the latest countermeasures. The reference unit can also prioritize referencing reports from individuals with specialized knowledge. For example, the reference unit can prioritize referencing reports from authors with specialized knowledge and generate countermeasures based on highly reliable information. Furthermore, the reference unit can prioritize referencing highly reliable reports based on the creation date and the author's attribute information. For example, the reference unit can prioritize referencing highly reliable reports and generate countermeasures based on accurate information. In this way, by considering the report's creation date and the author's attribute information when referencing, highly reliable reports can be prioritized. Some or all of the above processing in the reference unit may be performed using AI, for example, or not. For example, the reference unit can input the report's creation date and the author's attribute information into AI and have the AI ​​perform the referencing.

[0043] The reference unit can determine the priority of references based on the reliability and evaluation of the report content when referencing. For example, the reference unit can prioritize referencing highly reliable reports to generate accurate countermeasures. For example, the reference unit can prioritize referencing highly reliable reports to generate countermeasures based on accurate information. The reference unit can also prioritize referencing highly rated reports to generate effective countermeasures. For example, the reference unit can prioritize referencing highly rated reports to generate countermeasures based on effective information. Furthermore, the reference unit can select and reference the most suitable report based on reliability and evaluation. For example, the reference unit can select the most suitable report based on reliability and evaluation and generate countermeasures based on the most suitable information. In this way, by determining the priority of references based on the reliability and evaluation of the report content, accurate countermeasures can be generated. Some or all of the above processing in the reference unit may be performed using AI, for example, or not using AI. For example, the reference unit can input the reliability and evaluation of reports into AI and have the AI ​​perform the determination of the reference priority.

[0044] The reference unit can simultaneously refer to related literature and reference materials in the report when performing a reference. For example, the reference unit can automatically refer to literature related to the report and provide additional information. For example, the reference unit can automatically search for literature related to the report and provide additional information. The reference unit can also simultaneously refer to reference materials listed in the report and provide detailed information. For example, the reference unit can automatically search for reference materials listed in the report and provide detailed information. Furthermore, the reference unit can refer to related literature that complements the content of the report and provide comprehensive information. For example, the reference unit can automatically search for related literature that complements the content of the report and provide comprehensive information. In this way, comprehensive information can be provided by simultaneously referencing related literature and reference materials in the report. Some or all of the above processing in the reference unit may be performed using AI, for example, or not using AI. For example, the reference unit can input the related literature and reference materials of the report into AI and have the AI ​​perform the reference.

[0045] The reference section can be enhanced with a function to summarize and display the contents of a report when it is referenced. For example, the reference section can automatically extract the key points of a report and display them concisely. The reference section can also summarize the contents of a report and highlight important information. Furthermore, the reference section can summarize lengthy sections of a report and display them in a way that can be understood quickly. This allows users to grasp important information quickly by summarizing and displaying the contents of the report. Some or all of the above processing in the reference section may be performed using AI, for example, or without AI. For example, the reference section can input the contents of the report into an AI and have the AI ​​perform the summarization.

[0046] The generation unit can generate the optimal countermeasure by considering the effects and results of past countermeasures during the generation process. For example, the generation unit can analyze the effects of past countermeasures and generate the most effective countermeasure. The generation unit can also generate countermeasures that reflect improvements based on the results of past countermeasures. Furthermore, the generation unit can generate the optimal countermeasure by referring to successful examples of past countermeasures. In this way, by generating the optimal countermeasure by considering the effects and results of past countermeasures, it is possible to propose effective countermeasures. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the generation unit can input the effects and results of past countermeasures into a generation AI and have the generation AI execute the generation of the optimal countermeasure.

[0047] The generation unit can generate solutions while considering their feasibility and cost. For example, the generation unit can prioritize generating solutions with high feasibility. The generation unit can also consider costs and generate cost-effective solutions. Furthermore, the generation unit can generate optimal solutions based on feasibility and cost. By considering the feasibility and cost of solutions during generation, it is possible to propose cost-effective solutions. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input the feasibility and cost of solutions into the generation AI and have the generation AI generate the optimal solution.

[0048] The generation unit can perform generation while considering the resources and time required to implement the countermeasures. For example, the generation unit can prioritize generating countermeasures that require fewer resources to implement. The generation unit can also prioritize generating countermeasures that require less time to implement. Furthermore, the generation unit can consider resources and time to generate the optimal countermeasure. By considering the resources and time required to implement the countermeasures during generation, it is possible to propose efficient countermeasures. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the resources and time required to implement the countermeasures into the generation AI and have the generation AI generate the optimal countermeasures.

[0049] The generation unit can evaluate the risks and impacts associated with implementing countermeasures during the generation process. For example, the generation unit can prioritize generating countermeasures with low risk. The generation unit can also prioritize generating countermeasures with minimal impact. Furthermore, the generation unit can evaluate risks and impacts and generate the optimal countermeasure. By evaluating the risks and impacts associated with implementing countermeasures during the generation process, it is possible to propose safe and effective countermeasures. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input the risks and impacts of countermeasures into a generation AI and have the generation AI generate the optimal countermeasure.

[0050] The report creation department can create reports by referring to the format and style of past reports. For example, the report creation department can create reports with a consistent look and feel based on the format of past reports. The report creation department can also create reports that are easy to read by referring to the style of past reports. Furthermore, the report creation department can create reports efficiently by referring to the format and style of past reports. In this way, reports with a consistent look and feel can be created by referring to the format and style of past reports. Some or all of the above processes in the report creation department may be performed using AI, or not. For example, the report creation department can input the format and style of past reports into AI and have AI create the reports.

[0051] The report creation unit can create reports while considering the attribute information of the report recipient. For example, if the recipient is management, the creation unit can create a concise report that gets straight to the point. For example, if the recipient is management, the creation unit can create a concise report that gets straight to the point. The creation unit can also create reports that include detailed technical information if the recipient is a technical department. For example, if the recipient is a technical department, the creation unit can create reports that include detailed technical information. Furthermore, the creation unit can create reports tailored to the recipient's preferences by referring to the recipient's past feedback. For example, the creation unit can create reports tailored to the recipient's preferences by referring to the recipient's past feedback. In this way, by creating reports while considering the attribute information of the report recipient, it is possible to create reports that are suitable for the recipient. Some or all of the above processes in the creation unit may be performed using AI, for example, or not using AI. For example, the creation unit can input the recipient's attribute information into AI and have AI create the report.

[0052] The creation unit can add a function to summarize and display the contents of a report when it is being created. For example, the creation unit can automatically extract the key points of the report and display them concisely. For example, the creation unit can automatically extract the key points of the report and display them concisely. The creation unit can also summarize the contents of the report and highlight important information. For example, the creation unit can summarize the contents of the report and highlight important information. Furthermore, the creation unit can summarize long sections of the report and display them in a way that can be understood in a short amount of time. For example, the creation unit can summarize long sections of the report and display them in a way that can be understood in a short amount of time. This allows users to grasp important information in a short amount of time by summarizing and displaying the contents of the report. Some or all of the above processes in the creation unit may be performed using AI, for example, or not. For example, the creation unit can input the contents of the report into AI and have AI perform the summarization.

[0053] The creation unit can add a function to create reports in multiple languages ​​when generating reports. For example, the creation unit can automatically translate the report content and display it in multiple languages. The creation unit can also create reports in a language selected by the user. Furthermore, the creation unit can make the report content multilingual to accommodate international customers. For example, the creation unit can make the report content multilingual to accommodate international customers. This allows the creation of reports in multiple languages ​​to accommodate international customers. Some or all of the above processes in the creation unit may be performed using AI, or not. For example, the creation unit can input the report content into AI and have the AI ​​perform the translation.

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

[0055] The report generation system can also include a function to evaluate the trustworthiness of email senders when analyzing email content. For example, if the sender is a trustworthy customer, the email can be prioritized for analysis and a prompt response can be taken. If the sender is a new customer, a detailed analysis can be performed and appropriate countermeasures can be proposed. Furthermore, the trustworthiness can be evaluated by considering the sender's past communication history. By evaluating the trustworthiness of email senders, important emails can be prioritized for analysis, enabling a quick and appropriate response.

[0056] The report generation system can also include a function to analyze the content of past reports and evaluate their quality. For example, it can analyze the content of past reports to identify high-quality reports. Furthermore, it can generate future countermeasures based on these high-quality reports. It can also suggest areas for improvement in reports based on the quality evaluation. This allows for the generation of more effective countermeasures and overall improvement of report quality by evaluating the quality of past reports.

[0057] The report generation system can also incorporate a function that considers the time of email transmission when analyzing email content. For example, if an email is sent outside of business hours, it can be prioritized for analysis to encourage a quick response. If the email is sent during business hours, it can be analyzed with the usual priority. Furthermore, if the email is sent during a specific event or campaign period, it can be prioritized for analysis. This allows for a quicker response by considering the time of email transmission during analysis.

[0058] The report generation system can also include a function to analyze the content of past reports and suggest improvements. For example, it can analyze the content of past reports and identify areas for improvement. Furthermore, it can generate future countermeasures based on these improvements. It can also make suggestions to improve the quality of reports based on these improvements. In this way, by analyzing the content of past reports and suggesting improvements, the quality of reports can be improved.

[0059] The report generation system can also incorporate a function that considers the geographical location of the email sender when analyzing email content. For example, it can prioritize the analysis of emails from different regions to identify region-specific problems. It can also propose region-specific countermeasures based on the sender's geographical location. Furthermore, it can forward emails to the appropriate department, taking the sender's geographical location into consideration. In this way, by analyzing emails while considering the sender's geographical location, region-specific problems can be identified and appropriate responses can be taken.

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

[0061] Step 1: The reading unit reads emails containing the history and communication with the customer. For example, it retrieves emails from the mail server and analyzes their content. The reading unit can also analyze the email content in detail and extract important information. For example, it can extract customer complaint details and response history. Step 2: The reference unit references past internal reports based on the content of the emails read by the reading unit. For example, it searches past reports using keyword search or full-text search. The reference unit can also identify similar claims or countermeasures from past reports. For example, it can identify countermeasures described in past reports. Step 3: The generation unit generates future countermeasures based on the information identified by the reference unit. For example, it uses a generation AI to generate future countermeasures. The generation unit prompts the generation AI to generate countermeasures based on past reports, and the generation AI generates the countermeasures. Step 4: The creation unit creates a report based on the countermeasures generated by the generation unit. For example, it creates a report according to the report format based on the generated countermeasures. The creation unit can also create reports using the generation AI. For example, it can input a prompt to the generation AI to create a report based on the generated countermeasures, and the generation AI will create the report.

[0062] (Example of form 2) The report generation system according to an embodiment of the present invention is a system that reads emails detailing the history of an incident and interactions with customers, generates future countermeasures based on past internal reports, and creates a report. The report generation system reads emails detailing the history of an incident and interactions with customers, refers to past internal reports, generates future countermeasures, and creates a report. This system is expected to support the generation of apology reports and contribute to improving operational efficiency and building trust. For example, the report generation system reads emails detailing the history of an incident and interactions with customers. At this time, it analyzes the content of the emails in detail and extracts important information. For example, it extracts the content of customer complaints and response history. This makes it possible to understand the history of customer service. Next, the report generation system refers to past internal reports and generates future countermeasures. Past reports often contain similar complaints and countermeasures. Based on this information, it generates future countermeasures. For example, it can propose an apology letter and countermeasures to the customer by referring to the countermeasures described in past reports. Next, the report generation system creates a report based on the generated countermeasures. The report contains the history of customer service and future countermeasures. For example, it includes an apology letter to the customer, countermeasures, and points for future improvement. This report will enable prompt and appropriate customer service. This system is expected to support the generation of apology reports, contributing to improved operational efficiency and the building of trust. For example, it will enable faster customer service and the creation of appropriate apology letters, which is expected to improve the company's image and help avoid legal risks. Furthermore, utilizing past reports will standardize and streamline operations. This will improve the quality of customer service and contribute to building trust. The report generation system will read the history and email correspondence with the customer, generate future countermeasures based on past internal reports, and create the report.

[0063] The report generation system according to the embodiment comprises a reading unit, a reference unit, a generation unit, and a creation unit. The reading unit reads emails containing the history and interactions with customers. The reading unit, for example, retrieves emails from a mail server and analyzes the content of the emails. The reading unit can also analyze the content of the emails in detail and extract important information. For example, the reading unit can extract customer complaint details and response history. The reference unit refers to past internal reports based on the content of the emails read by the reading unit. The reference unit searches past reports using, for example, keyword search or full-text search. The reference unit can also identify similar complaints and countermeasures from past reports. For example, the reference unit identifies countermeasures described in past reports. The generation unit generates future countermeasures based on the information identified by the reference unit. The generation unit generates future countermeasures using, for example, a generation AI. The generation unit inputs a prompt to the generation AI instructing it to generate countermeasures based on past reports, and the generation AI generates the countermeasures. The creation unit creates a report based on the countermeasures generated by the generation unit. The creation unit creates a report according to the report format based on the generated countermeasures. The creation unit can also create reports using a generation AI. For example, the creation unit can input prompts to the generation AI to create a report based on the generated countermeasures, and the generation AI will create the report. As a result, the report generation system according to this embodiment can read the history and emails of communication with customers, generate future countermeasures based on past internal reports, and create a report.

[0064] The reading unit reads emails containing the history and interactions with customers. Specifically, the reading unit retrieves emails from the mail server and analyzes their content. Email retrieval from the mail server is performed using protocols such as IMAP and POP3, and SSL / TLS encryption is applied to ensure security. The retrieved emails are analyzed by a text analysis engine, and metadata such as the email body, subject, sender, recipient, and date and time are extracted. Furthermore, the reading unit uses natural language processing (NLP) techniques to analyze the email content in detail and extract important information. For example, techniques such as keyword extraction, sentiment analysis, and entity recognition are used to extract customer complaint details and response history. This allows the reading unit to efficiently analyze email content and accurately extract necessary information. In addition, the reading unit stores the extracted information as structured data so that it can be used for subsequent processing. For example, customer complaint details and response history are stored in a database, making it accessible to the retrieval and generation units. This allows the reading unit to analyze email content in detail and extract important information, thereby improving the overall efficiency and accuracy of the system.

[0065] The reference unit accesses past internal reports based on the content of emails read by the input unit. Specifically, the reference unit searches past reports using keyword search and full-text search. Keyword search quickly searches past reports using important keywords extracted from the email content. Full-text search searches the entire text of the report, allowing for the acquisition of more detailed information. Furthermore, the reference unit can also identify similar claims and countermeasures from past reports. For example, it uses natural language processing technology to compare the content of emails with the content of past reports and calculates the similarity. This allows the reference unit to identify countermeasures described in past reports and use them as a reference for future countermeasures. The reference unit displays search results in a ranking format, prioritizing the display of the most relevant reports. The reference unit can also filter search results, limiting searches to specific periods or personnel. This allows the reference unit to efficiently access past reports and quickly acquire necessary information. In addition, the reference unit saves search results to a database for use in subsequent processing. This allows the reference unit to effectively utilize past reports and improve the overall efficiency and accuracy of the system.

[0066] The generation unit generates future countermeasures based on the information identified by the reference unit. Specifically, the generation unit uses a generation AI to generate future countermeasures. The generation AI is input with prompts instructing it to generate countermeasures based on past reports. These prompts include information such as customer complaints, past countermeasures, and the current situation. Based on this information, the generation AI generates the optimal countermeasures. The generation AI uses natural language generation (NLG) technology to generate specific countermeasure proposals as text. For example, the generation AI proposes countermeasures suitable for the new situation, while referring to countermeasures described in past reports. The generated countermeasures are verified by the generation unit and modified as necessary. The generation unit saves the generated countermeasures to a database so that they can be used for subsequent processing. This allows the generation unit to efficiently generate future countermeasures and improve the overall efficiency and accuracy of the system. Furthermore, the generation unit regularly updates the generation AI's training data so that it can generate countermeasures based on the latest information. This allows the generation unit to always provide the optimal countermeasures and improve the reliability and effectiveness of the overall system.

[0067] The creation department prepares reports based on the countermeasures generated by the generation department. Specifically, the creation department prepares reports according to the report format based on the generated countermeasures. The report format includes sections such as title, summary, details, and conclusion. The creation department can also create reports using a generation AI. The generation AI is given prompts to create a report based on the generated countermeasures. These prompts include the report format and necessary information. Based on this information, the generation AI automatically generates each section of the report. For example, the generation AI explains the generated countermeasures in detail, including specific procedures and points to note. The generation AI can also propose future prospects and additional countermeasures in the conclusion section of the report. The creation department reviews the generated reports and makes corrections as needed. The creation department can save the generated reports to a database and share them with other departments and stakeholders as needed. This allows the creation department to efficiently create reports and improve the overall efficiency and accuracy of the system. Furthermore, the creation department regularly updates the generation AI's training data to ensure that reports are based on the latest information. This allows the creation department to consistently provide high-quality reports and improve the reliability and effectiveness of the overall system.

[0068] The reading unit can analyze the content of emails in detail and extract important information. For example, the reading unit can analyze the content of emails using natural language processing techniques. For example, the reading unit can tokenize the content of emails and evaluate the importance of each token. The reading unit can also extract specific keywords or phrases from the content of emails. For example, the reading unit can extract keywords related to customer complaints. Furthermore, the reading unit can use algorithms to analyze the content of emails and extract important information. For example, the reading unit can use algorithms to analyze the content of emails and extract frequently occurring phrases and important information. This allows for a detailed analysis of the content of emails and the extraction of important information, enabling an understanding of the history of customer interactions. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input the content of emails into AI and have the AI ​​perform the extraction of important information.

[0069] The reference unit can refer to past reports and identify similar claims and countermeasures. For example, the reference unit can search past reports using keyword searches. For instance, it can extract specific keywords based on the content of an email and use those keywords to search past reports. The reference unit can also search past reports using full-text searches. For example, it can use the entire content of an email as a search query to search past reports. Furthermore, the reference unit can use algorithms to identify similar claims and countermeasures within past reports. For example, it can analyze the content of past reports and use algorithms to identify similar claims and countermeasures. This allows the reference unit to obtain information for generating future countermeasures by referring to past reports and identifying similar claims and countermeasures. Some or all of the above processing in the reference unit may be performed using AI, or not. For example, the reference unit can input past reports into an AI and have the AI ​​identify similar claims and countermeasures.

[0070] The generation unit can generate future countermeasures based on the information identified by the reference unit. For example, the generation unit can generate future countermeasures using a generation AI. The generation unit inputs a prompt to the generation AI instructing it to generate countermeasures based on past reports, and the generation AI generates the countermeasures. For example, the generation unit inputs the prompt "Generate an apology letter to the customer based on past reports" to the generation AI, and the generation AI generates the apology letter. The generation unit can also use the generation AI to generate countermeasures based on past reports. For example, the generation unit inputs the prompt "Generate improvement measures for customer service based on past reports" to the generation AI, and the generation AI generates improvement measures. In this way, by generating future countermeasures based on the information identified by the reference unit, it is possible to propose appropriate countermeasures. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the generation unit can input information identified by the reference unit into the generation AI and cause the generation AI to execute the generation of future countermeasures.

[0071] The creation unit can create a report based on the countermeasures generated by the generation unit. For example, the creation unit can create a report according to a report format based on the generated countermeasures. The creation unit can also create a report using a generation AI. For example, the creation unit can input a prompt to the generation AI to create a report based on the generated countermeasures, and the generation AI will create the report. The creation unit can also automatically generate the content of the report based on the generated countermeasures. For example, the creation unit can use an algorithm that automatically generates each item of the report based on the generated countermeasures. This enables quick and appropriate customer response by creating a report based on the countermeasures generated by the generation unit. Some or all of the above processes in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input the countermeasures generated by the generation unit into the AI ​​and have the AI ​​create the report.

[0072] The reading unit can estimate the user's emotions and adjust the timing of email loading based on the estimated emotions. The reading unit can estimate the user's emotions, for example, by using an emotion estimation algorithm. For example, the reading unit can analyze the user's facial expressions and voice data to estimate emotions. The reading unit can also adjust the timing of email loading based on the user's emotions. For example, if the user is stressed, the reading unit can delay loading emails and load them when the user is relaxed. If the user is relaxed, the reading unit can load emails immediately to encourage a quick response. Furthermore, if the user is in a hurry, the reading unit can prioritize loading important emails to enable a quick response. In this way, by adjusting the timing of email loading according to the user's emotions, emails can be loaded at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input user emotion data into the AI ​​and have the AI ​​adjust the timing of email loading.

[0073] The reading unit can prioritize the extraction of specific keywords and phrases when analyzing the content of an email. For example, the reading unit can prioritize the extraction of keywords related to customer complaints. For example, it can extract keywords such as "dissatisfaction," "problem," and "complaint." The reading unit can also prioritize the extraction of phrases related to important dates and deadlines. For example, it can extract phrases such as "deadline," "due date," and "delivery date." Furthermore, the reading unit can also prioritize the extraction of keywords related to customer gratitude and satisfaction. For example, it can extract keywords such as "thank you," "satisfied," and "grateful." By prioritizing the extraction of specific keywords and phrases, important information can be grasped quickly. Some or all of the above processing in the reading unit may be performed using AI, for example, or not. For example, the reading unit can input the content of an email into an AI and have the AI ​​perform the extraction of specific keywords and phrases.

[0074] The reading unit can analyze emails while considering the attribute information of the email sender and recipient. For example, if the sender is an important customer, the reading unit will prioritize the analysis of that email. For example, the reading unit will prioritize the analysis of emails from important customers to ensure a quick response. The reading unit can also analyze emails based on the attribute information of recipients who belong to a specific department or position. For example, the reading unit will prioritize the analysis of emails from recipients belonging to a specific department or position. Furthermore, the reading unit can determine the priority of analysis by considering the past communication history of the sender and recipient. For example, the reading unit will prioritize the analysis of important emails based on past communication history. This allows for the prioritization of important emails by considering the attribute information of the email sender and recipient. Some or all of the above processing in the reading unit may be performed using AI, or not. For example, the reading unit can input the attribute information of the email sender and recipient into AI and have AI determine the priority of analysis.

[0075] The reading unit can estimate the user's emotions and determine the priority of extracting important information based on the estimated emotions. For example, the reading unit estimates the user's emotions using an emotion estimation algorithm. For example, it analyzes the user's facial expressions and voice data to estimate emotions. The reading unit can also determine the priority of extracting important information based on the user's emotions. For example, if the user is stressed, the reading unit prioritizes extracting important information to encourage a quick response. If the user is relaxed, the reading unit can extract detailed information to enable a comprehensive response. Furthermore, if the user is in a hurry, the reading unit can extract only the most important information to enable a quick response. This enables a quick response by determining the priority of extracting important information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 reading unit may be performed using AI, or not. For example, the data entry unit can input user emotion data into the AI ​​and have the AI ​​determine the priority for extracting important information.

[0076] The reading unit can analyze emails while considering the geographical location information of the email sender. For example, the reading unit can prioritize analyzing emails from different regions to identify region-specific problems. For example, the reading unit can prioritize analyzing emails from a specific region to identify region-specific problems. The reading unit can also propose region-specific countermeasures based on the sender's geographical location information. For example, the reading unit can analyze emails from a specific region and propose countermeasures appropriate for that region. Furthermore, the reading unit can forward emails to the appropriate department, taking the sender's geographical location information into consideration. For example, the reading unit analyzes emails from a specific region and forwards them to the appropriate department for that region. This allows for the identification of region-specific problems by analyzing emails while considering the sender's geographical location information. Some or all of the above processing in the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input the email sender's geographical location information into AI and have the AI ​​perform the analysis.

[0077] The reading unit can analyze emails while considering the time they were sent. For example, if an email was sent outside of business hours, the reading unit will prioritize its analysis to encourage a quick response. For example, the reading unit will prioritize the analysis of emails sent outside of business hours to ensure a quick response. The reading unit can also analyze emails sent during business hours with the usual priority. For example, the reading unit will analyze emails sent during business hours with the usual priority. Furthermore, if an email was sent during a specific event or campaign period, the reading unit can prioritize its analysis of that email. For example, the reading unit will prioritize the analysis of emails sent during a specific event or campaign period. This allows for a quicker response by considering the time the email was sent during the analysis. Some or all of the above processing in the reading unit may be performed using AI, or not. For example, the reading unit can input the email's sending time into AI and have the AI ​​perform the analysis.

[0078] The reference unit can estimate the user's emotions and adjust the criteria for selecting reports to refer to based on the estimated emotions. For example, the reference unit might estimate the user's emotions using an emotion estimation algorithm. For instance, it might analyze the user's facial expressions or voice data to estimate emotions. The reference unit can also adjust the criteria for selecting reports to refer to based on the user's emotions. For example, if the user is stressed, the reference unit might prioritize concise and to-the-point reports. If the user is relaxed, it might prioritize reports containing detailed information. Furthermore, if the user is in a hurry, it might prioritize reports containing the most important information. This allows for the referencing of more appropriate reports by adjusting the criteria for selecting reports according to 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 reference unit may be performed using AI, or not. For example, the reference section can input user sentiment data into the AI ​​and have the AI ​​adjust the criteria for selecting reports.

[0079] The reference unit can prioritize referencing past reports, taking into account the report's creation date and the author's attribute information. For example, the reference unit can prioritize referencing reports with more recent creation dates and generate countermeasures based on the latest information. For example, the reference unit can prioritize referencing the most recent report and generate countermeasures based on the latest countermeasures. The reference unit can also prioritize referencing reports from individuals with specialized knowledge. For example, the reference unit can prioritize referencing reports from authors with specialized knowledge and generate countermeasures based on highly reliable information. Furthermore, the reference unit can prioritize referencing highly reliable reports based on the creation date and the author's attribute information. For example, the reference unit can prioritize referencing highly reliable reports and generate countermeasures based on accurate information. In this way, by considering the report's creation date and the author's attribute information when referencing, highly reliable reports can be prioritized. Some or all of the above processing in the reference unit may be performed using AI, for example, or not. For example, the reference unit can input the report's creation date and the author's attribute information into AI and have the AI ​​perform the referencing.

[0080] The reference unit can determine the priority of references based on the reliability and evaluation of the report content when referencing. For example, the reference unit can prioritize referencing highly reliable reports to generate accurate countermeasures. For example, the reference unit can prioritize referencing highly reliable reports to generate countermeasures based on accurate information. The reference unit can also prioritize referencing highly rated reports to generate effective countermeasures. For example, the reference unit can prioritize referencing highly rated reports to generate countermeasures based on effective information. Furthermore, the reference unit can select and reference the most suitable report based on reliability and evaluation. For example, the reference unit can select the most suitable report based on reliability and evaluation and generate countermeasures based on the most suitable information. In this way, by determining the priority of references based on the reliability and evaluation of the report content, accurate countermeasures can be generated. Some or all of the above processing in the reference unit may be performed using AI, for example, or not using AI. For example, the reference unit can input the reliability and evaluation of reports into AI and have the AI ​​perform the determination of the reference priority.

[0081] The reference unit can estimate the user's emotions and adjust the display order of the reports it references based on the estimated emotions. The reference unit estimates the user's emotions using, for example, an emotion estimation algorithm. For example, it can analyze the user's facial expressions and voice data to estimate emotions. The reference unit can also adjust the display order of the reports it references based on the user's emotions. For example, if the user is stressed, the reference unit can display important reports at the top to encourage a quick response. If the user is relaxed, the reference unit can display detailed reports at the top to enable a comprehensive response. Furthermore, if the user is in a hurry, the reference unit can display the most important reports at the top to enable a quick response. This allows for a quick response by adjusting the display order of reports according to the user's emotions. Emotion estimation is achieved using, for example, 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 reference unit may be performed using, for example, AI, or not using AI. For example, the reference section can input user sentiment data into the AI ​​and have the AI ​​adjust the display order of reports.

[0082] The reference unit can simultaneously refer to related literature and reference materials in the report when performing a reference. For example, the reference unit can automatically refer to literature related to the report and provide additional information. For example, the reference unit can automatically search for literature related to the report and provide additional information. The reference unit can also simultaneously refer to reference materials listed in the report and provide detailed information. For example, the reference unit can automatically search for reference materials listed in the report and provide detailed information. Furthermore, the reference unit can refer to related literature that complements the content of the report and provide comprehensive information. For example, the reference unit can automatically search for related literature that complements the content of the report and provide comprehensive information. In this way, comprehensive information can be provided by simultaneously referencing related literature and reference materials in the report. Some or all of the above processing in the reference unit may be performed using AI, for example, or not using AI. For example, the reference unit can input the related literature and reference materials of the report into AI and have the AI ​​perform the reference.

[0083] The reference section can be enhanced with a function to summarize and display the contents of a report when it is referenced. For example, the reference section can automatically extract the key points of a report and display them concisely. The reference section can also summarize the contents of a report and highlight important information. Furthermore, the reference section can summarize lengthy sections of a report and display them in a way that can be understood quickly. This allows users to grasp important information quickly by summarizing and displaying the contents of the report. Some or all of the above processing in the reference section may be performed using AI, for example, or without AI. For example, the reference section can input the contents of the report into an AI and have the AI ​​perform the summarization.

[0084] The generation unit can estimate the user's emotions and adjust the way the generated countermeasures are expressed based on the estimated user emotions. For example, the generation unit estimates the user's emotions using an emotion estimation algorithm. For example, the generation unit analyzes the user's facial expressions and voice data to estimate emotions. The generation unit can also adjust the way the generated countermeasures are expressed based on the user's emotions. For example, if the user is stressed, the generation unit uses a concise and clear expression. If the user is relaxed, the generation unit can also use an expression that includes detailed explanations. Furthermore, if the user is in a hurry, the generation unit can use an expression that gets straight to the point. By adjusting the way the generated countermeasures are expressed according to the user's emotions, more appropriate countermeasures can be proposed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust how the countermeasures are expressed.

[0085] The generation unit can generate the optimal countermeasure by considering the effects and results of past countermeasures during the generation process. For example, the generation unit can analyze the effects of past countermeasures and generate the most effective countermeasure. The generation unit can also generate countermeasures that reflect improvements based on the results of past countermeasures. Furthermore, the generation unit can generate the optimal countermeasure by referring to successful examples of past countermeasures. In this way, by generating the optimal countermeasure by considering the effects and results of past countermeasures, it is possible to propose effective countermeasures. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the generation unit can input the effects and results of past countermeasures into a generation AI and have the generation AI execute the generation of the optimal countermeasure.

[0086] The generation unit can generate solutions while considering their feasibility and cost. For example, the generation unit can prioritize generating solutions with high feasibility. The generation unit can also consider costs and generate cost-effective solutions. Furthermore, the generation unit can generate optimal solutions based on feasibility and cost. By considering the feasibility and cost of solutions during generation, it is possible to propose cost-effective solutions. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input the feasibility and cost of solutions into the generation AI and have the generation AI generate the optimal solution.

[0087] The generation unit can estimate the user's emotions and determine the priority of the countermeasures to be generated based on the estimated user emotions. The generation unit can estimate the user's emotions using, for example, an emotion estimation algorithm. For example, the generation unit can estimate emotions by analyzing the user's facial expressions and voice data. The generation unit can also determine the priority of the countermeasures to be generated based on the user's emotions. For example, if the user is feeling stressed, the generation unit will prioritize generating the most important countermeasures. If the user is relaxed, the generation unit can also prioritize generating comprehensive countermeasures. Furthermore, if the user is in a hurry, the generation unit can also prioritize generating countermeasures that can be implemented quickly. This enables a rapid response by determining the priority of the countermeasures to be generated according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI determine the priority of countermeasures.

[0088] The generation unit can perform generation while considering the resources and time required to implement the countermeasures. For example, the generation unit can prioritize generating countermeasures that require fewer resources to implement. The generation unit can also prioritize generating countermeasures that require less time to implement. Furthermore, the generation unit can consider resources and time to generate the optimal countermeasure. By considering the resources and time required to implement the countermeasures during generation, it is possible to propose efficient countermeasures. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the resources and time required to implement the countermeasures into the generation AI and have the generation AI generate the optimal countermeasures.

[0089] The generation unit can evaluate the risks and impacts associated with implementing countermeasures during the generation process. For example, the generation unit can prioritize generating countermeasures with low risk. The generation unit can also prioritize generating countermeasures with minimal impact. Furthermore, the generation unit can evaluate risks and impacts and generate the optimal countermeasure. By evaluating the risks and impacts associated with implementing countermeasures during the generation process, it is possible to propose safe and effective countermeasures. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input the risks and impacts of countermeasures into a generation AI and have the generation AI generate the optimal countermeasure.

[0090] The report generation unit can estimate the user's emotions and adjust the report's presentation based on those emotions. For example, the unit might use an emotion estimation algorithm to estimate the user's emotions. For instance, it might analyze the user's facial expressions or voice data to estimate their emotions. The unit can also adjust the report's presentation based on the user's emotions. For example, if the user is stressed, it might use a concise and clear presentation. If the user is relaxed, it might use a more detailed presentation. Furthermore, if the user is in a hurry, it might use a more to-the-point presentation. This allows for the creation of more appropriate reports by adjusting the report's presentation according to 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 report generation unit may be performed using AI, or not. For example, the creation department can input user emotion data into the AI ​​and have the AI ​​adjust the way the report is presented.

[0091] The report creation department can create reports by referring to the format and style of past reports. For example, the report creation department can create reports with a consistent look and feel based on the format of past reports. The report creation department can also create reports that are easy to read by referring to the style of past reports. Furthermore, the report creation department can create reports efficiently by referring to the format and style of past reports. In this way, reports with a consistent look and feel can be created by referring to the format and style of past reports. Some or all of the above processes in the report creation department may be performed using AI, or not. For example, the report creation department can input the format and style of past reports into AI and have AI create the reports.

[0092] The report creation unit can create reports while considering the attribute information of the report recipient. For example, if the recipient is management, the creation unit can create a concise report that gets straight to the point. For example, if the recipient is management, the creation unit can create a concise report that gets straight to the point. The creation unit can also create reports that include detailed technical information if the recipient is a technical department. For example, if the recipient is a technical department, the creation unit can create reports that include detailed technical information. Furthermore, the creation unit can create reports tailored to the recipient's preferences by referring to the recipient's past feedback. For example, the creation unit can create reports tailored to the recipient's preferences by referring to the recipient's past feedback. In this way, by creating reports while considering the attribute information of the report recipient, it is possible to create reports that are suitable for the recipient. Some or all of the above processes in the creation unit may be performed using AI, for example, or not using AI. For example, the creation unit can input the recipient's attribute information into AI and have AI create the report.

[0093] The report creation unit can estimate the user's emotions and prioritize the content of the report based on the estimated emotions. For example, the unit might use an emotion estimation algorithm to estimate the user's emotions. For instance, it might analyze the user's facial expressions or voice data to estimate their emotions. The unit can also prioritize the content of the report based on the user's emotions. For example, if the user is stressed, the unit will prioritize the most important information. If the user is relaxed, it might prioritize detailed information. Furthermore, if the user is in a hurry, it might prioritize concise information. This allows for a quicker response by prioritizing the report content according to 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 report creation unit may be performed using AI, or not. For example, the creation department can input user sentiment data into the AI ​​and have the AI ​​determine the prioritization of the report's content.

[0094] The creation unit can add a function to summarize and display the contents of a report when it is being created. For example, the creation unit can automatically extract the key points of the report and display them concisely. For example, the creation unit can automatically extract the key points of the report and display them concisely. The creation unit can also summarize the contents of the report and highlight important information. For example, the creation unit can summarize the contents of the report and highlight important information. Furthermore, the creation unit can summarize long sections of the report and display them in a way that can be understood in a short amount of time. For example, the creation unit can summarize long sections of the report and display them in a way that can be understood in a short amount of time. This allows users to grasp important information in a short amount of time by summarizing and displaying the contents of the report. Some or all of the above processes in the creation unit may be performed using AI, for example, or not. For example, the creation unit can input the contents of the report into AI and have AI perform the summarization.

[0095] The creation unit can add a function to create reports in multiple languages ​​when generating reports. For example, the creation unit can automatically translate the report content and display it in multiple languages. The creation unit can also create reports in a language selected by the user. Furthermore, the creation unit can make the report content multilingual to accommodate international customers. For example, the creation unit can make the report content multilingual to accommodate international customers. This allows the creation of reports in multiple languages ​​to accommodate international customers. Some or all of the above processes in the creation unit may be performed using AI, or not. For example, the creation unit can input the report content into AI and have the AI ​​perform the translation.

[0096] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0097] The report generation system can also be equipped with the ability to estimate the user's emotions and adjust the report content based on those emotions. For example, if the user is stressed, the report can be made concise and the key points emphasized. If the user is relaxed, a report containing detailed information can be generated. Furthermore, if the user is in a hurry, the most important information can be prioritized to enable a quick response. In this way, by adjusting the report content according to the user's emotions, a more appropriate report can be provided.

[0098] The report generation system can also include a function to evaluate the trustworthiness of email senders when analyzing email content. For example, if the sender is a trustworthy customer, the email can be prioritized for analysis and a prompt response can be taken. If the sender is a new customer, a detailed analysis can be performed and appropriate countermeasures can be proposed. Furthermore, the trustworthiness can be evaluated by considering the sender's past communication history. By evaluating the trustworthiness of email senders, important emails can be prioritized for analysis, enabling a quick and appropriate response.

[0099] The report generation system can also include a function to analyze the content of past reports and evaluate their quality. For example, it can analyze the content of past reports to identify high-quality reports. Furthermore, it can generate future countermeasures based on these high-quality reports. It can also suggest areas for improvement in reports based on the quality evaluation. This allows for the generation of more effective countermeasures and overall improvement of report quality by evaluating the quality of past reports.

[0100] The report generation system can also be equipped with the ability to estimate the user's emotions and adjust the report format based on those emotions. For example, if the user is stressed, a simple and easy-to-read format can be used. If the user is relaxed, a format containing detailed information can be used. Furthermore, if the user is in a hurry, a format that highlights the key points can be used to enable a quick response. In this way, by adjusting the report format according to the user's emotions, a more appropriate report can be provided.

[0101] The report generation system can also incorporate a function that considers the time of email transmission when analyzing email content. For example, if an email is sent outside of business hours, it can be prioritized for analysis to encourage a quick response. If the email is sent during business hours, it can be analyzed with the usual priority. Furthermore, if the email is sent during a specific event or campaign period, it can be prioritized for analysis. This allows for a quicker response by considering the time of email transmission during analysis.

[0102] The report generation system can also be equipped with a function to estimate the user's emotions and adjust the timing of report creation based on those emotions. For example, if the user is stressed, report creation can be delayed until the user is relaxed. Conversely, if the user is relaxed, the report can be created immediately to encourage a quick response. Furthermore, if the user is in a hurry, important information can be prioritized to enable a quick response. In this way, by adjusting the timing of report creation according to the user's emotions, reports can be created at a more appropriate time.

[0103] The report generation system can also include a function to analyze the content of past reports and suggest improvements. For example, it can analyze the content of past reports and identify areas for improvement. Furthermore, it can generate future countermeasures based on these improvements. It can also make suggestions to improve the quality of reports based on these improvements. In this way, by analyzing the content of past reports and suggesting improvements, the quality of reports can be improved.

[0104] The report generation system can also be equipped with a function to estimate the user's emotions and prioritize the report content based on those emotions. For example, if the user is stressed, the most important information will be prioritized. If the user is relaxed, detailed information will be prioritized. Furthermore, if the user is in a hurry, concise information will be prioritized to enable a quick response. In this way, a quick response is possible by prioritizing the report content according to the user's emotions.

[0105] The report generation system can also incorporate a function that considers the geographical location of the email sender when analyzing email content. For example, it can prioritize the analysis of emails from different regions to identify region-specific problems. It can also propose region-specific countermeasures based on the sender's geographical location. Furthermore, it can forward emails to the appropriate department, taking the sender's geographical location into consideration. In this way, by analyzing emails while considering the sender's geographical location, region-specific problems can be identified and appropriate responses can be taken.

[0106] The report generation system can also be equipped with a function to estimate the user's emotions and adjust the display order of reports based on those emotions. For example, if the user is stressed, important reports can be displayed at the top to encourage a quick response. If the user is relaxed, detailed reports can be displayed at the top to enable a comprehensive response. Furthermore, if the user is in a hurry, the most important reports can be displayed at the top to enable a quick response. In this way, by adjusting the display order of reports according to the user's emotions, a quick response becomes possible.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The reading unit reads emails containing the history and communication with the customer. For example, it retrieves emails from the mail server and analyzes their content. The reading unit can also analyze the email content in detail and extract important information. For example, it can extract customer complaint details and response history. Step 2: The reference unit references past internal reports based on the content of the emails read by the reading unit. For example, it searches past reports using keyword search or full-text search. The reference unit can also identify similar claims or countermeasures from past reports. For example, it can identify countermeasures described in past reports. Step 3: The generation unit generates future countermeasures based on the information identified by the reference unit. For example, it uses a generation AI to generate future countermeasures. The generation unit prompts the generation AI to generate countermeasures based on past reports, and the generation AI generates the countermeasures. Step 4: The creation unit creates a report based on the countermeasures generated by the generation unit. For example, it creates a report according to the report format based on the generated countermeasures. The creation unit can also create reports using the generation AI. For example, it can input a prompt to the generation AI to create a report based on the generated countermeasures, and the generation AI will create the report.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] Each of the multiple elements described above, including the reading unit, reference unit, generation unit, and creation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reading unit is implemented by the control unit 46A of the smart device 14, which retrieves emails from the mail server and analyzes the contents of the emails. The reference unit is implemented by the identification processing unit 290 of the data processing device 12, which searches past company reports and identifies similar claims and countermeasures. The generation unit is implemented by the identification processing unit 290 of the data processing device 12, which generates future countermeasures using generation AI. The creation unit is implemented by the control unit 46A of the smart device 14, which creates a report based on the generated countermeasures. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the reading unit, reference unit, generation unit, and creation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reading unit is implemented by the control unit 46A of the smart glasses 214, which retrieves emails from the mail server and analyzes the contents of the emails. The reference unit is implemented by the identification processing unit 290 of the data processing unit 12, which searches past company reports and identifies similar claims and countermeasures. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates future countermeasures using generation AI. The creation unit is implemented by the control unit 46A of the smart glasses 214, which creates a report based on the generated countermeasures. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the reading unit, reference unit, generation unit, and creation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reading unit is implemented by the control unit 46A of the headset terminal 314, which retrieves emails from the mail server and analyzes the contents of the emails. The reference unit is implemented by the identification processing unit 290 of the data processing unit 12, which searches past company reports and identifies similar claims and countermeasures. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates future countermeasures using generation AI. The creation unit is implemented by the control unit 46A of the headset terminal 314, which creates a report based on the generated countermeasures. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0145] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the reading unit, reference unit, generation unit, and creation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reading unit is implemented by the control unit 46A of the robot 414, which retrieves emails from the mail server and analyzes the contents of the emails. The reference unit is implemented by the identification processing unit 290 of the data processing unit 12, which searches past company reports and identifies similar claims and countermeasures. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which generates future countermeasures using generation AI. The creation unit is implemented by the control unit 46A of the robot 414, which creates a report based on the generated countermeasures. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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."

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] (Note 1) The reading section reads the background information and emails exchanged with customers, A reference unit that references past company reports based on the contents of emails read by the aforementioned reading unit, A generation unit that generates future countermeasures based on the information referenced by the aforementioned reference unit, The system includes a creation unit that creates a report based on the countermeasures generated by the generation unit. A system characterized by the following features. (Note 2) The aforementioned reading unit, Analyze the email content in detail and extract important information. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned reference section is, Refer to past reports to identify similar claims and countermeasures. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Based on the information identified by the reference section, future countermeasures are generated. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned creation unit, Based on the countermeasures generated by the generation unit, a report is created. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reading unit, It estimates the user's emotions and adjusts the email loading timing based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reading unit, When analyzing email content, prioritize extracting specific keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reading unit, When reading emails, the system analyzes them while considering the attribute information of the email sender and recipient. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reading unit, It estimates the user's emotions and determines the priority of extracting important information based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reading unit, When reading emails, the analysis takes into account the geographical location information of the email sender. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reading unit, When reading emails, the analysis takes into account the time the email was sent. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reference section is, We estimate user sentiment and adjust the criteria for selecting reports to refer to based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reference section is, When referring to past reports, consider the date and time the report was created and the attributes of the author. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reference section is, When referencing a report, the priority of references is determined based on the reliability and evaluation of the report's content. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned reference section is, It estimates user sentiment and adjusts the display order of referenced reports based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned reference section is, When referencing, simultaneously refer to the related literature and reference materials in the report. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned reference section is, Add a feature to display a summary of the report's contents when it is referenced. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is We estimate the user's emotions and adjust the way countermeasures are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is During generation, the optimal countermeasure is generated by considering the effectiveness and results of past countermeasures. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is During generation, the feasibility and cost of countermeasures are taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is It estimates user sentiment and determines the priority of actions to be taken based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is During generation, the resources and time required to implement the countermeasures are taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is During generation, the risks and impacts associated with implementing countermeasures are evaluated before generation. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned creation unit, We estimate the user's emotions and adjust the way the report is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned creation unit, When creating a report, refer to the format and style of past reports. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned creation unit, When creating a report, take into account the attributes of the report's recipient. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned creation unit, The system estimates user sentiment and prioritizes the report content based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned creation unit, Add a feature to summarize and display the contents of a report when it is created. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned creation unit, Add a feature to create reports in multiple languages ​​when generating them. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0181] 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 reading section reads the background information and emails exchanged with customers, A reference unit that references past company reports based on the contents of emails read by the aforementioned reading unit, A generation unit that generates future countermeasures based on the information referenced by the aforementioned reference unit, The system includes a creation unit that creates a report based on the countermeasures generated by the generation unit. A system characterized by the following features.

2. The aforementioned reading unit, Analyze the email content in detail and extract important information. The system according to feature 1.

3. The aforementioned reference section is, Refer to past reports to identify similar claims and countermeasures. The system according to feature 1.

4. The generating unit is Based on the information identified by the aforementioned reference unit, future countermeasures are generated. The system according to feature 1.

5. The aforementioned creation unit, A report is prepared based on the countermeasures generated by the aforementioned generation unit. The system according to feature 1.

6. The aforementioned reading unit, It estimates the user's emotions and adjusts the email loading timing based on the estimated emotions. The system according to feature 1.

7. The aforementioned reading unit, When analyzing email content, prioritize extracting specific keywords or phrases. The system according to feature 1.

8. The aforementioned reading unit, When reading emails, the system analyzes them while considering the attribute information of the email sender and recipient. The system according to feature 1.

9. The aforementioned reading unit, It estimates the user's emotions and determines the priority of extracting important information based on the estimated user emotions. The system according to feature 1.

10. The aforementioned reading unit, When reading emails, the analysis takes into account the geographical location information of the email sender. The system according to feature 1.

Images