System

Abstract

To provide a system that efficiently generates emails customized for individual customers.SOLUTION: A system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit inputs information. The analysis unit analyzes the information input by the reception unit. The generation unit generates a customized email based on the information analyzed by the analysis unit. The confirmation unit confirms the email generated by the generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to efficiently generate emails customized for individual customers, posing challenges to improving business efficiency.

[0005] The system according to the embodiment aims to efficiently generate emails customized for individual customers. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit inputs information. The analysis unit analyzes the information input by the reception unit. The generation unit generates a customized email based on the information analyzed by the analysis unit. The confirmation unit confirms the email generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently generate emails customized for individual customers. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention utilizes the Writer extension of a generation AI to automatically generate the content and reply to email notifications about various products, such as product schedules, delivery status, and activation status, for corporate sales, creating emails with customized content for individual customers. In this system, corporate sales representatives input information about product schedules, delivery status, and activation status, and the generation AI analyzes the input information and generates customized email notifications for individual customers. The generation AI creates optimal email content by referencing past email history and a customer database, taking into account each customer's needs and past interactions. Furthermore, the generation AI analyzes the content of customer replies and automatically generates appropriate reply emails. This enables corporate sales representatives to respond quickly and appropriately. For example, detailed reports, including estimated delivery and activation dates, are sent to certain customers, while brief reports are sent to other customers. Furthermore, the generation AI analyzes the content of customer replies and automatically generates appropriate reply emails, enabling quick and appropriate responses. This significantly reduces the time it takes for corporate sales representatives to create email notifications about product schedules, delivery status, and activation status. In addition, by creating emails with content customized for individual customers, it is possible to expect an improvement in customer satisfaction.

[0029] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit inputs information. The information includes, but is not limited to, text data, numerical data, and image data. For example, a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products into the reception unit. The analysis unit uses a generation AI to analyze the information input by the reception unit. The analysis may be performed using, but is not limited to, methods such as text analysis, data mining, and statistical analysis. The generation unit uses the generation AI to generate a customized email based on the information analyzed by the analysis unit. The generated email is generated according to criteria such as, but not limited to, customization based on personal information or past behavioral history. The confirmation unit confirms the generated email. The confirmation unit includes, for example, a confirmation process for ensuring the quality of the generated email. The confirmation process may include, but is not limited to, criteria such as grammatical accuracy, content relevance, and customer satisfaction. As a result, the system according to the embodiment automates a series of processes from inputting information to analyzing, generating emails, and confirming them, thereby achieving business efficiency and customization.

[0030] The reception unit inputs information. Examples of such information include, but are not limited to, text data, numerical data, and image data. For example, a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products into the reception unit. Specifically, the reception unit receives information through a user interface. The user interface can take the form of a web browser or a mobile application and is designed for intuitive user operation. For example, text data is input through an input form or text area, and numerical data is input using a slider or numeric input field. Image data is received through a file upload function and a preview is displayed as needed. Furthermore, the reception unit temporarily stores the input information and performs basic data validation before sending it to a database. For example, the reception unit checks whether required fields have been entered and the data format, and provides feedback to the user if there are any errors. This allows the reception unit to collect accurate and complete information and provide the data necessary for subsequent analysis processes.

[0031] The analysis unit uses the generation AI to analyze the information input by the reception unit. The analysis can be performed using methods such as, but not limited to, text analysis, data mining, and statistical analysis. Specifically, the generation AI analyzes text data using natural language processing technology to extract important keywords and phrases. For example, text analysis involves morphological and contextual analysis to understand the meaning and intent of a document. Data mining involves discovering patterns and trends from large data sets, including numerical and image data. Statistical analysis involves analyzing data distributions and correlations to gain statistical insights. The generation AI combines these analytical techniques to analyze the input information from multiple angles and identify user needs and trends. Furthermore, the analysis unit can utilize past data and external data sources to perform more accurate analysis. For example, by referencing past product sales data and customer behavior history and comparing it with current data, it can predict future demand and customer preferences. The analysis results are visualized in dashboards and reports, making them easy for users to understand. This allows the analysis unit to quickly and accurately analyze the input information and provide the insights needed for the subsequent generation process.

[0032] The generation unit uses the generation AI to generate customized emails based on the information analyzed by the analysis unit. The generated emails are generated based on criteria such as, but not limited to, personal information and past behavioral history. Specifically, the generation AI automatically generates email content optimized for each user based on insights provided by the analysis unit. For example, personal information-based customization includes content tailored to the user's name, past purchase history, and interests. Past behavioral history-based customization provides information related to products and services the user has viewed in the past. The generation AI uses natural language generation technology to generate grammatically accurate and easy-to-read sentences. Furthermore, the generation unit automatically adjusts the design and layout of the email to create visually appealing emails. For example, it appropriately positions images and graphics to attract the user's attention. The generation unit also temporarily stores the generated emails and awaits a quality check by the verification unit. This allows the generation unit to quickly provide users with personalized, high-quality emails.

[0033] The verification unit checks the generated emails. The verification unit includes, for example, a verification process to ensure the quality of the generated emails. The verification process includes, but is not limited to, criteria such as grammatical accuracy, content relevance, and customer satisfaction. Specifically, the verification unit performs a grammar check on the generated emails to correct typographical errors and grammatical errors. The verification unit also checks the relevance of the content and evaluates whether it matches the user's needs and interests. Furthermore, the verification unit checks whether the tone and style of the emails are appropriate to improve customer satisfaction. The verification unit can use AI-based grammar checkers and content evaluation tools to automate these checks. For example, it can use natural language processing technology to evaluate whether the content of the email matches the user's profile and past behavioral history. The verification unit can also randomly sample generated emails and perform manual quality checks. This allows the verification unit to maintain a high level of quality in the generated emails and provide users with reliable information. Furthermore, the verification unit establishes a feedback loop to provide feedback on issues discovered in the verification process to the generation unit and analysis unit, thereby improving the overall system. This allows the verification unit to guarantee the quality of the generated emails and improve the reliability and effectiveness of the entire system.

[0034] The system includes a reference unit that references past email history or a customer database. The reference unit references past email history or a customer database. Past email history includes, for example, email history for the past year, email history with a specific customer, etc., but is not limited to these examples. The customer database includes, for example, basic customer information, purchase history, inquiry history, etc., but is not limited to these examples. By referencing past email history or the customer database, the reference unit can generate more accurate customized emails. Some or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input past email history or a customer database into AI, which can select the most appropriate data.

[0035] The system includes a reply analysis unit that analyzes the content of replies from customers. The reply analysis unit analyzes the content of replies from customers. The reply content may include, but is not limited to, text messages, attachments, links, etc. The reply analysis unit analyzes the content of replies from customers, enabling a prompt and appropriate response. Some or all of the above-described processing in the reply analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply analysis unit can input the content of replies from customers into AI, which can select the optimal analysis method.

[0036] The system includes a reply generation unit that generates an appropriate reply email. The reply generation unit generates the appropriate reply email. Examples of appropriate reply emails include, but are not limited to, accurate answers to customer questions and quick responses. By generating an appropriate reply email, the reply generation unit can improve the efficiency and quality of customer service. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can input the content of a reply from a customer into AI, which can then generate an optimal reply email.

[0037] The generation unit can generate email content taking into account the needs or past interactions of each customer. The generation unit uses a generation AI to generate email content taking into account the needs and past interactions of each customer. Needs include, for example, but are not limited to, survey results, purchase history, and inquiry content. Past interactions include, for example, but are not limited to, interactions over the past year and interactions on specific topics. The generation unit can generate more personalized emails by using the generation AI to take into account the needs and past interactions of each customer. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input customer needs and past interactions into AI, which then generates optimal email content.

[0038] The verification unit may include a verification process to ensure the quality of the generated email. The verification unit includes a verification process to ensure the quality of the generated email. Examples of quality include, but are not limited to, grammatical accuracy, content relevance, and customer satisfaction. Examples of the verification process include, but are not limited to, multiple checkpoints and the role of reviewers. The verification unit improves customer satisfaction by ensuring the quality of the generated email. Some or all of the above-described processing in the verification unit may be performed using, or without, AI. For example, the verification unit may input the generated email into AI, which then evaluates the quality.

[0039] The reception unit can analyze past input history and select the optimal input method. The reception unit analyzes past input history and selects the optimal input method. The input history includes, for example, input history for the past year, input history related to a specific task, etc., but is not limited to these examples. The optimal input method includes, for example, the user's input speed, error rate, user preference, etc., but is not limited to these examples. The reception unit, for example, preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used in a specific time period based on the user's past input history. Furthermore, the reception unit can analyze patterns of information entered by the user in the past and suggest the optimal input method. In this way, the analysis of the past input history can suggest the optimal input method for the user. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the past input history into AI, which can select the optimal input method.

[0040] The reception unit may filter information based on the user's current work situation or areas of interest when inputting the information. The reception unit may filter information based on the user's current work situation or areas of interest when inputting the information. Examples of work situations include, but are not limited to, current tasks, work progress, and work priorities. Examples of areas of interest include, but are not limited to, past search history, purchase history, and survey results. For example, the reception unit may prioritize input of information related to a project currently being carried out by the user. The reception unit may also filter and input highly relevant information based on the user's areas of interest. Furthermore, the reception unit may filter information so that only necessary information is input according to the user's work situation. By filtering information based on the user's work situation and areas of interest, only necessary information can be efficiently input. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the user's work situation and areas of interest to AI, which may then filter out the most appropriate information.

[0041] When inputting information, the reception unit can prioritize inputting highly relevant information in consideration of the user's geographical location information. When inputting information, the reception unit prioritizes inputting highly relevant information in consideration of the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data, IP addresses, location information services, etc. Examples of highly relevant information include, but are not limited to, geographical proximity and information related to the user's current location. For example, when the user is in a specific area, the reception unit prioritizes inputting information related to that area. Furthermore, the reception unit can also prioritize inputting information related to locations close to the user's current location. Furthermore, when the user is traveling, the reception unit can also prioritize inputting information related to the user's destination. This allows highly relevant information to be efficiently input by considering the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information to AI, which can select optimal information.

[0042] The reception unit may analyze the user's social media activity and input relevant information when inputting information. The reception unit may analyze the user's social media activity and input relevant information when inputting information. Social media activity may include, but is not limited to, the content of posts, the number of likes, and the number of followers. Related information may include, but is not limited to, information related to the content of social media posts and information related to the user's areas of interest. The reception unit may input relevant information based on, for example, information shared by the user on social media. The reception unit may also analyze the user's social media activity history and input highly relevant information. Furthermore, the reception unit may input related information based on information about accounts the user follows on social media. This allows for efficient input of highly relevant information by analyzing the user's social media activity. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input the user's social media activity into AI, which may select optimal information.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the information during analysis. The analysis unit can adjust the level of detail of the analysis based on the importance of the information during analysis. Examples of importance include, but are not limited to, the impact on business, urgency, and user interest. Examples of detail include, but are not limited to, the number of detailed data points, the depth of the analysis, and the range of information to display. For example, the analysis unit performs a detailed analysis of information with high importance. The analysis unit can also perform a concise analysis of information with low importance. Furthermore, the analysis unit can gradually adjust the level of detail of the analysis depending on the importance of the information. This enables efficient analysis by adjusting the level of detail of the analysis depending on the importance of the information. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the importance of the information into AI, which can then determine the optimal level of detail.

[0044] The analysis unit can apply different analysis algorithms depending on the classification of information during analysis. The analysis unit applies different analysis algorithms depending on the classification of information during analysis. Categories include, but are not limited to, text data, numerical data, and image data. Analysis algorithms include, but are not limited to, machine learning algorithms, statistical analysis algorithms, and data mining algorithms. For example, the analysis unit applies a schedule analysis algorithm to product schedule information. The analysis unit can also apply a delivery analysis algorithm to delivery status information. Furthermore, the analysis unit can apply an activation analysis algorithm to activation status information. This enables more accurate analysis by applying an analysis algorithm depending on the category of information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the category of information into AI, which then applies the optimal analysis algorithm.

[0045] The analysis unit can determine the analysis priority based on the submission date and time of the information during analysis. The analysis unit determines the analysis priority based on the submission date and time of the information during analysis. The submission date and time includes, but is not limited to, a timestamp, submission history, system log, etc. The priority includes, but is not limited to, the importance, urgency, and submission date and time of the information. For example, the analysis unit prioritizes analysis of the most recent information. The analysis unit can also postpone information that was submitted earlier. Furthermore, the analysis unit can gradually adjust the analysis priority depending on the submission date. In this way, by determining the analysis priority based on the submission date and time of the information, the most recent information can be prioritized for analysis. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission date and time of the information into AI, which can then determine the optimal priority.

[0046] The analysis unit can adjust the order of analysis based on the relationships between information during analysis. The analysis unit can adjust the order of analysis based on the relationships between information during analysis. Examples of relationships include, but are not limited to, co-occurrence network analysis, correlation analysis, and clustering. Examples of the order include, but are not limited to, the importance, relevance, and submission date and time of information. For example, the analysis unit prioritizes analysis of highly relevant information. The analysis unit can also postpone analysis of less relevant information. Furthermore, the analysis unit can gradually adjust the order of analysis according to the relevance of the information. This enables efficient analysis by adjusting the order of analysis based on the relevance of the information. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the relationships between information into AI, which can then determine the optimal order.

[0047] The generation unit can adjust the level of detail of the email based on the importance of the information when generating the email. The generation unit can adjust the level of detail of the email based on the importance of the information when generating the email. Examples of importance include, but are not limited to, the impact on business, urgency, and user interest. Examples of detail include, but are not limited to, detailed explanations, summaries, and bullet points. The generation unit can generate detailed emails for information with high importance, for example. The generation unit can also generate concise emails for information with low importance. Furthermore, the generation unit can gradually adjust the level of detail of the email based on the importance of the information. This enables efficient email generation by adjusting the level of detail of the email based on the importance of the information. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the importance of the information into AI, which can then determine the optimal level of detail.

[0048] The generation unit can apply different generation algorithms depending on the classification of information when generating an email. The generation unit applies different generation algorithms depending on the classification of information when generating an email. Categories include, but are not limited to, text data, numerical data, and image data. Generation algorithms include, but are not limited to, natural language generation algorithms and template-based generation algorithms. For example, the generation unit applies a schedule generation algorithm to product schedule information. The generation unit can also apply a delivery generation algorithm to delivery status information. The generation unit can also apply an activation generation algorithm to activation status information. This enables more accurate email generation by applying a generation algorithm depending on the category of information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category of information into AI, which then applies the optimal generation algorithm.

[0049] The generation unit can determine the priority of emails based on the submission date and time of information when generating emails. The generation unit can determine the priority of emails based on the submission date and time of information when generating emails. The submission date and time can include, but are not limited to, a timestamp, a submission history, a system log, etc. The priority can include, but are not limited to, the importance, urgency, and submission date and time of information, for example. The generation unit, for example, prioritizes including the most recent information in the email. The generation unit can also postpone information that was submitted earlier. Furthermore, the generation unit can gradually adjust the priority of emails depending on the submission date. In this way, by determining the priority of emails based on the submission date and time of information, the most recent information can be prioritized and included in the email. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the submission date and time of information into AI, which can then determine the optimal priority.

[0050] The generation unit can adjust the order of emails based on the relationships between information when generating emails. The generation unit adjusts the order of emails based on the relationships between information when generating emails. Examples of relationships include, but are not limited to, co-occurrence network analysis, correlation analysis, and clustering. Examples of order include, but are not limited to, the importance, relevance, and submission date and time of information. For example, the generation unit prioritizes including highly relevant information in the email. The generation unit can also postpone less relevant information. Furthermore, the generation unit can gradually adjust the order of emails according to the relevance of the information. This enables efficient email generation by adjusting the order of emails based on the relevance of the information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the relationships between information into AI, which can then determine the optimal order.

[0051] The confirmation unit can select an appropriate confirmation method by referring to past confirmation history when confirming. The confirmation unit can select an appropriate confirmation method by referring to past confirmation history when confirming. The confirmation history can include, for example, confirmation history for the past year, confirmation history related to a specific task, etc., but is not limited to these examples. The confirmation method can include, for example, manual confirmation, automatic confirmation, multiple checkpoints, etc., but is not limited to these examples. The confirmation unit, for example, preferentially suggests a confirmation method that the user has used in the past. The confirmation unit can also predict and suggest a confirmation method to be used in a specific time period based on the user's past confirmation history. Furthermore, the confirmation unit can analyze patterns of information that the user has confirmed in the past and suggest an optimal confirmation method. In this way, by referring to the past confirmation history, the optimal confirmation method for the user can be suggested. Some or all of the above-described processing in the confirmation unit can be performed using, for example, AI, or can be performed without using AI. For example, the confirmation unit can input the past confirmation history into AI, which can select the optimal confirmation method.

[0052] The confirmation unit can apply different confirmation methods depending on the classification of information during confirmation. The confirmation unit applies different confirmation methods depending on the classification of information during confirmation. Information categories include, but are not limited to, for example, product schedule information, delivery status information, and activation status information. Confirmation methods include, but are not limited to, for example, a schedule confirmation method, a delivery confirmation method, and an activation confirmation method. For example, the confirmation unit applies a schedule confirmation method to product schedule information. The confirmation unit can also apply a delivery confirmation method to delivery status information. Furthermore, the confirmation unit can also apply an activation confirmation method to activation status information. This enables more accurate confirmation by applying a confirmation method depending on the information category. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the information category into AI, which can then apply the most appropriate confirmation method.

[0053] The confirmation unit can adjust the confirmation order based on the submission date and time of the information during confirmation. The confirmation unit adjusts the confirmation order based on the submission date and time of the information during confirmation. The submission date and time may include, but are not limited to, a timestamp, submission history, system log, etc. The order may include, but are not limited to, the importance, relevance, and submission date and time of the information. For example, the confirmation unit prioritizes checking the most recent information. The confirmation unit can also postpone information that was submitted earlier. Furthermore, the confirmation unit can gradually adjust the confirmation order depending on the submission date. In this way, by adjusting the confirmation order based on the submission date and time of the information, the most recent information can be prioritized for confirmation. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the submission date and time of the information into AI, which can then determine the optimal order.

[0054] The confirmation unit can adjust the confirmation order based on the relationship between information during confirmation. The confirmation unit can adjust the confirmation order based on the relationship between information during confirmation. Examples of the relationship include, but are not limited to, co-occurrence network analysis, correlation analysis, and clustering. Examples of the order include, but are not limited to, the importance, relevance, and submission date and time of information. For example, the confirmation unit prioritizes checking highly relevant information. The confirmation unit can also postpone checking less relevant information. Furthermore, the confirmation unit can gradually adjust the confirmation order according to the relevance of the information. This enables efficient confirmation by adjusting the confirmation order based on the relevance of the information. Some or all of the above-described processing in the confirmation unit can be performed using, for example, AI, or without AI. For example, the confirmation unit can input the relationship between information into AI, which can then determine the optimal order.

[0055] The reference unit can select appropriate data by referring to past reference history when referencing data. The reference unit can select appropriate data by referring to past reference history when referencing data. Reference history includes, but is not limited to, reference history for the past year, reference history related to a specific task, etc. The reference unit, for example, preferentially displays data that the user has frequently referenced in the past. The reference unit can also predict and suggest data to be used in a specific time period based on the user's past reference history. Furthermore, the reference unit can analyze patterns of data that the user has referenced in the past and suggest optimal data. In this way, optimal data for the user can be suggested by referring to the past reference history. Some or all of the above-described processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can input past reference history into AI, which can select optimal data.

[0056] The reference unit can weight the reference data based on the submission date and time of the data when referencing. The reference unit weights the reference data based on the submission date and time of the data when referencing. The submission date and time includes, but is not limited to, a timestamp, a submission history, a system log, etc. Examples of weighting include, but are not limited to, preferentially referencing the most recent data, postponing data submitted earlier, and gradually adjusting the weighting of the reference data depending on the submission date. In this way, by weighting the reference data based on the submission date and time of the data, the most recent data can be preferentially referenced. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input the submission date and time of the data into AI, which can then determine the optimal weighting.

[0057] The reply analysis unit can select an appropriate analysis method by referring to past reply history when analyzing replies. The reply analysis unit can select an appropriate analysis method by referring to past reply history when analyzing replies. The reply history includes, for example, reply history from the past year, reply history related to a specific task, etc., but is not limited to these examples. The reply analysis unit, for example, prioritizes and suggests reply methods used by the user in the past. The reply analysis unit can also predict and suggest reply methods to be used during specific time periods based on the user's past reply history. Furthermore, the reply analysis unit can analyze patterns of the content of the user's past replies and suggest the optimal analysis method. In this way, by referring to the past reply history, the optimal analysis method for the user can be suggested. Some or all of the above-described processing in the reply analysis unit can be performed, for example, using AI, or can be performed without using AI. For example, the reply analysis unit can input past reply history into AI, which can select the optimal analysis method.

[0058] The reply analysis unit can adjust the analysis order based on the submission date and time of the reply content when analyzing the reply. The reply analysis unit can adjust the analysis order based on the submission date and time of the reply content when analyzing the reply. The submission date and time can be, for example, a timestamp, a submission history, a system log, etc., but is not limited to these examples. The order can be, for example, based on the importance of the information, relevance, and submission date and time, but is not limited to these examples. The reply analysis unit, for example, prioritizes analyzing the most recent reply content. The reply analysis unit can also postpone replies submitted earlier. Furthermore, the reply analysis unit can gradually adjust the reply analysis order depending on the submission date. In this way, by adjusting the analysis order based on the submission date and time of the reply content, the most recent reply content can be prioritized for analysis. Some or all of the above-described processing in the reply analysis unit can be performed using, for example, AI, or without AI. For example, the reply analysis unit can input the submission date and time of the reply content into AI, which can then determine the optimal order.

[0059] When generating a reply email, the reply generation unit can adjust the level of detail of the reply email based on the importance of the reply content. When generating a reply email, the reply generation unit adjusts the level of detail of the reply email based on the importance of the reply content. Examples of importance include, but are not limited to, the impact on business, the urgency, and the user's interest. Examples of detail include, but are not limited to, a detailed explanation, a summary, and bullet points. For example, the reply generation unit generates a detailed reply email for reply content with high importance. The reply generation unit can also generate a concise reply email for reply content with low importance. Furthermore, the reply generation unit can gradually adjust the level of detail of the reply email depending on the importance of the reply content. This allows for efficient generation of reply emails by adjusting the level of detail of the reply email depending on the importance of the reply content. Some or all of the above-described processing in the reply generation unit may be performed using, or without, AI. For example, the reply generation unit can input the importance of the reply content into AI, which can then determine the optimal level of detail.

[0060] When generating a reply email, the reply generation unit can determine the priority of the reply email based on the submission date and time of the reply content. When generating a reply email, the reply generation unit determines the priority of the reply email based on the submission date and time of the reply content. The submission date and time may include, but are not limited to, a timestamp, a submission history, a system log, etc. The priority may include, but are not limited to, the importance of the information, the urgency, and the submission date and time. For example, the reply generation unit may prioritize including the most recent reply content in the reply email. The reply generation unit may also postpone reply content that was submitted earlier. Furthermore, the reply generation unit may gradually adjust the priority of the reply email depending on the submission date and time. In this way, by determining the priority of the reply email based on the submission date and time of the reply content, the most recent reply content can be prioritized and included in the email. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit may input the submission date and time of the reply content into AI, which may determine the optimal priority.

[0061] The reply generation unit can adjust the order of reply emails based on the relationships between the reply contents when generating reply emails. The reply generation unit adjusts the order of reply emails based on the relationships between the reply contents when generating reply emails. Examples of the relationships include, but are not limited to, co-occurrence network analysis, correlation analysis, and clustering. Examples of the order include, but are not limited to, the importance of information, relevance, and submission date and time. For example, the reply generation unit prioritizes including highly relevant information in the reply email. The reply generation unit can also postpone less relevant information. Furthermore, the reply generation unit can gradually adjust the order of reply emails based on the relevance of the information. This enables efficient generation of reply emails by adjusting the order of reply emails based on the relevance of the reply contents. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can input the relationships between the reply contents into AI, which can then determine the optimal order.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] The reference section can obtain information in real time from external databases and APIs and refer to the latest data. For example, it can obtain information such as product inventory status and market trends from external databases and reflect this in the email content provided to customers. The reference section can also evaluate the reliability of the obtained data and use only the most reliable data. Furthermore, the reference section can automatically update the obtained data and always keep it up-to-date. This makes it possible to generate more accurate customized emails by utilizing external data.

[0064] The reply generator can include images and videos in the reply emails it generates. For example, by attaching an explanatory video or product image to a customer's question, the reply can be made easier to understand. The reply generator can also automatically insert related materials and links based on the customer's interests. Furthermore, the reply generator can customize the design of the reply email and generate emails that match the brand image. This makes it possible to provide reply emails that are visually appealing and contain a lot of information.

[0065] When generating email content, the generation unit analyzes a customer's purchasing history and behavioral patterns to suggest products that the customer is likely to purchase next. For example, it can suggest related new products or upgraded versions to a customer who has previously purchased a specific product. The generation unit can also predict a customer's purchasing cycle and send reminder emails at appropriate times. Furthermore, the generation unit can provide personalized promotion and campaign information based on the customer's interests. This can increase customer purchasing motivation and is expected to increase sales.

[0066] The verification unit can be equipped with a translation function to make the content of generated emails multilingual. For example, an email generated in English can be automatically translated into Japanese or Chinese, and sent to customers in each country in the appropriate language. The verification unit can also evaluate the quality of the translation and make corrections as necessary. Furthermore, the verification unit can translate while taking into account the cultural background and business etiquette of each language, thereby achieving more natural and effective communication. This enables global customer service and supports international business development.

[0067] The reception unit can provide an auto-completion function for input content based on the user's past input history. For example, it can automatically suggest product names or customer names that have been entered in the past, making input work more efficient. The reception unit can also learn frequently used phrases and standard phrases and suggest them at the appropriate time. Furthermore, the reception unit can also be equipped with a function to analyze the user's input patterns and predict and automatically correct input errors. This makes it possible to utilize past input history and is expected to improve the efficiency and accuracy of input work.

[0068] When inputting information, the reception unit can prioritize the input contents based on the user's current work situation and areas of interest. For example, it can suggest that information related to an ongoing project be input preferentially. It can also prioritize the input of highly relevant information based on the user's areas of interest. Furthermore, the reception unit can filter the information so that only necessary information is input according to the user's work situation. This allows information to be input efficiently based on the user's work situation and areas of interest.

[0069] The processing flow of the first embodiment will be briefly explained below.

[0070] Step 1: The reception unit inputs information. Information includes, but is not limited to, text data, numerical data, and image data. For example, a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products into the reception unit. Step 2: The analysis unit uses the generation AI to analyze the information input by the reception unit. The analysis is performed by methods such as, but not limited to, text analysis, data mining, and statistical analysis. Step 3: The generation unit uses the generation AI to generate a customized email based on the information analyzed by the analysis unit. The generated email is generated according to criteria such as, but not limited to, customization based on personal information or past behavioral history. Step 4: The verification unit verifies the generated email. The verification unit includes, for example, a verification process to ensure the quality of the generated email. The verification process includes, but is not limited to, criteria such as grammatical accuracy, content relevance, and customer satisfaction.

[0071] (Example 2) A system according to an embodiment of the present invention utilizes the Writer extension of a generation AI to automatically generate the content and reply to email notifications about various products, such as product schedules, delivery status, and activation status, for corporate sales, creating emails with customized content for individual customers. In this system, corporate sales representatives input information about product schedules, delivery status, and activation status, and the generation AI analyzes the input information and generates customized email notifications for individual customers. The generation AI creates optimal email content by referencing past email history and a customer database, taking into account each customer's needs and past interactions. Furthermore, the generation AI analyzes the content of customer replies and automatically generates appropriate reply emails. This enables corporate sales representatives to respond quickly and appropriately. For example, detailed reports, including estimated delivery and activation dates, are sent to certain customers, while brief reports are sent to other customers. Furthermore, the generation AI analyzes the content of customer replies and automatically generates appropriate reply emails, enabling quick and appropriate responses. This significantly reduces the time it takes for corporate sales representatives to create email notifications about product schedules, delivery status, and activation status. In addition, by creating emails with content customized for individual customers, it is possible to expect an improvement in customer satisfaction.

[0072] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit inputs information. The information includes, but is not limited to, text data, numerical data, and image data. For example, a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products into the reception unit. The analysis unit uses a generation AI to analyze the information input by the reception unit. The analysis may be performed using, but is not limited to, methods such as text analysis, data mining, and statistical analysis. The generation unit uses the generation AI to generate a customized email based on the information analyzed by the analysis unit. The generated email is generated according to criteria such as, but not limited to, customization based on personal information or past behavioral history. The confirmation unit confirms the generated email. The confirmation unit includes, for example, a confirmation process for ensuring the quality of the generated email. The confirmation process may include, but is not limited to, criteria such as grammatical accuracy, content relevance, and customer satisfaction. As a result, the system according to the embodiment automates a series of processes from inputting information to analyzing, generating emails, and confirming them, thereby achieving business efficiency and customization.

[0073] The reception unit inputs information. Examples of such information include, but are not limited to, text data, numerical data, and image data. For example, a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products into the reception unit. Specifically, the reception unit receives information through a user interface. The user interface can take the form of a web browser or a mobile application and is designed for intuitive user operation. For example, text data is input through an input form or text area, and numerical data is input using a slider or numeric input field. Image data is received through a file upload function and a preview is displayed as needed. Furthermore, the reception unit temporarily stores the input information and performs basic data validation before sending it to a database. For example, the reception unit checks whether required fields have been entered and the data format, and provides feedback to the user if there are any errors. This allows the reception unit to collect accurate and complete information and provide the data necessary for subsequent analysis processes.

[0074] The analysis unit uses the generation AI to analyze the information input by the reception unit. The analysis can be performed using methods such as, but not limited to, text analysis, data mining, and statistical analysis. Specifically, the generation AI analyzes text data using natural language processing technology to extract important keywords and phrases. For example, text analysis involves morphological and contextual analysis to understand the meaning and intent of a document. Data mining involves discovering patterns and trends from large data sets, including numerical and image data. Statistical analysis involves analyzing data distributions and correlations to gain statistical insights. The generation AI combines these analytical techniques to analyze the input information from multiple angles and identify user needs and trends. Furthermore, the analysis unit can utilize past data and external data sources to perform more accurate analysis. For example, by referencing past product sales data and customer behavior history and comparing it with current data, it can predict future demand and customer preferences. The analysis results are visualized in dashboards and reports, making them easy for users to understand. This allows the analysis unit to quickly and accurately analyze the input information and provide the insights needed for the subsequent generation process.

[0075] The generation unit uses the generation AI to generate customized emails based on the information analyzed by the analysis unit. The generated emails are generated based on criteria such as, but not limited to, personal information and past behavioral history. Specifically, the generation AI automatically generates email content optimized for each user based on insights provided by the analysis unit. For example, personal information-based customization includes content tailored to the user's name, past purchase history, and interests. Past behavioral history-based customization provides information related to products and services the user has viewed in the past. The generation AI uses natural language generation technology to generate grammatically accurate and easy-to-read sentences. Furthermore, the generation unit automatically adjusts the design and layout of the email to create visually appealing emails. For example, it appropriately positions images and graphics to attract the user's attention. The generation unit also temporarily stores the generated emails and awaits a quality check by the verification unit. This allows the generation unit to quickly provide users with personalized, high-quality emails.

[0076] The verification unit checks the generated emails. The verification unit includes, for example, a verification process to ensure the quality of the generated emails. The verification process includes, but is not limited to, criteria such as grammatical accuracy, content relevance, and customer satisfaction. Specifically, the verification unit performs a grammar check on the generated emails to correct typographical errors and grammatical errors. The verification unit also checks the relevance of the content and evaluates whether it matches the user's needs and interests. Furthermore, the verification unit checks whether the tone and style of the emails are appropriate to improve customer satisfaction. The verification unit can use AI-based grammar checkers and content evaluation tools to automate these checks. For example, it can use natural language processing technology to evaluate whether the content of the email matches the user's profile and past behavioral history. The verification unit can also randomly sample generated emails and perform manual quality checks. This allows the verification unit to maintain a high level of quality in the generated emails and provide users with reliable information. Furthermore, the verification unit establishes a feedback loop to provide feedback on issues discovered in the verification process to the generation unit and analysis unit, thereby improving the overall system. This allows the verification unit to guarantee the quality of the generated emails and improve the reliability and effectiveness of the entire system.

[0077] The system includes a reference unit that references past email history or a customer database. The reference unit references past email history or a customer database. Past email history includes, for example, email history for the past year, email history with a specific customer, etc., but is not limited to these examples. The customer database includes, for example, basic customer information, purchase history, inquiry history, etc., but is not limited to these examples. By referencing past email history or the customer database, the reference unit can generate more accurate customized emails. Some or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input past email history or a customer database into AI, which can select the most appropriate data.

[0078] The system includes a reply analysis unit that analyzes the content of replies from customers. The reply analysis unit analyzes the content of replies from customers. The reply content may include, but is not limited to, text messages, attachments, links, etc. The reply analysis unit analyzes the content of replies from customers, enabling a prompt and appropriate response. Some or all of the above-described processing in the reply analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply analysis unit can input the content of replies from customers into AI, which can select the optimal analysis method.

[0079] The system includes a reply generation unit that generates an appropriate reply email. The reply generation unit generates the appropriate reply email. Examples of appropriate reply emails include, but are not limited to, accurate answers to customer questions and quick responses. By generating an appropriate reply email, the reply generation unit can improve the efficiency and quality of customer service. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can input the content of a reply from a customer into AI, which can then generate an optimal reply email.

[0080] The generation unit can generate email content taking into account the needs or past interactions of each customer. The generation unit uses a generation AI to generate email content taking into account the needs and past interactions of each customer. Needs include, for example, but are not limited to, survey results, purchase history, and inquiry content. Past interactions include, for example, but are not limited to, interactions over the past year and interactions on specific topics. The generation unit can generate more personalized emails by using the generation AI to take into account the needs and past interactions of each customer. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input customer needs and past interactions into AI, which then generates optimal email content.

[0081] The verification unit may include a verification process to ensure the quality of the generated email. The verification unit includes a verification process to ensure the quality of the generated email. Examples of quality include, but are not limited to, grammatical accuracy, content relevance, and customer satisfaction. Examples of the verification process include, but are not limited to, multiple checkpoints and the role of reviewers. The verification unit improves customer satisfaction by ensuring the quality of the generated email. Some or all of the above-described processing in the verification unit may be performed using, or without, AI. For example, the verification unit may input the generated email into AI, which then evaluates the quality.

[0082] The reception unit can estimate the user's emotions and adjust the timing of information input based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can delay the input timing to allow the user to input information in a relaxed state. Furthermore, if the user is relaxed, the reception unit can also prompt the user to input information immediately. Furthermore, if the user is in a hurry, the reception unit can also accelerate the input timing to allow the user to input information quickly. This adjusts the timing of information input according to the user's emotions, reducing the user's stress and enabling efficient information input. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data into an AI, which can then determine the optimal input timing.

[0083] The reception unit can analyze past input history and select the optimal input method. The reception unit analyzes past input history and selects the optimal input method. The input history includes, for example, input history for the past year, input history related to a specific task, etc., but is not limited to these examples. The optimal input method includes, for example, the user's input speed, error rate, user preference, etc., but is not limited to these examples. The reception unit, for example, preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used in a specific time period based on the user's past input history. Furthermore, the reception unit can analyze patterns of information entered by the user in the past and suggest the optimal input method. In this way, the analysis of the past input history can suggest the optimal input method for the user. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the past input history into AI, which can select the optimal input method.

[0084] The reception unit may filter information based on the user's current work situation or areas of interest when inputting the information. The reception unit may filter information based on the user's current work situation or areas of interest when inputting the information. Examples of work situations include, but are not limited to, current tasks, work progress, and work priorities. Examples of areas of interest include, but are not limited to, past search history, purchase history, and survey results. For example, the reception unit may prioritize input of information related to a project currently being carried out by the user. The reception unit may also filter and input highly relevant information based on the user's areas of interest. Furthermore, the reception unit may filter information so that only necessary information is input according to the user's work situation. By filtering information based on the user's work situation and areas of interest, only necessary information can be efficiently input. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the user's work situation and areas of interest to AI, which may then filter out the most appropriate information.

[0085] The reception unit can estimate the user's emotions and determine the priority of information to be input based on the estimated user emotions. For example, when the user is feeling stressed, the reception unit postpones input of less important information. Furthermore, when the user is relaxed, the reception unit can also prioritize input of more important information. Furthermore, when the user is in a hurry, the reception unit can input the most important information first. Thus, by determining the priority of information according to the user's emotions, important information can be input preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, 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-described processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data into an AI, which can then optimally prioritize the information.

[0086] When inputting information, the reception unit can prioritize inputting highly relevant information in consideration of the user's geographical location information. When inputting information, the reception unit prioritizes inputting highly relevant information in consideration of the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data, IP addresses, location information services, etc. Examples of highly relevant information include, but are not limited to, geographical proximity and information related to the user's current location. For example, when the user is in a specific area, the reception unit prioritizes inputting information related to that area. Furthermore, the reception unit can also prioritize inputting information related to locations close to the user's current location. Furthermore, when the user is traveling, the reception unit can also prioritize inputting information related to the user's destination. This allows highly relevant information to be efficiently input by considering the user's geographical location information. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information to AI, which can select optimal information.

[0087] The reception unit may analyze the user's social media activity and input relevant information when inputting information. The reception unit may analyze the user's social media activity and input relevant information when inputting information. Social media activity may include, but is not limited to, the content of posts, the number of likes, and the number of followers. Related information may include, but is not limited to, information related to the content of social media posts and information related to the user's areas of interest. The reception unit may input relevant information based on, for example, information shared by the user on social media. The reception unit may also analyze the user's social media activity history and input highly relevant information. Furthermore, the reception unit may input related information based on information about accounts the user follows on social media. This allows for efficient input of highly relevant information by analyzing the user's social media activity. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input the user's social media activity into AI, which may select optimal information.

[0088] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, the analysis unit can provide detailed analysis results when the user is relaxed. The analysis unit can also provide concise analysis results when the user is in a hurry. Furthermore, the analysis unit can provide visually easy-to-understand analysis results when the user is stressed. By adjusting the way the analysis is presented based on the user's emotions, it is possible to provide analysis results that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into an AI, which can then determine the optimal way to present the emotion.

[0089] The analysis unit can adjust the level of detail of the analysis based on the importance of the information during analysis. The analysis unit can adjust the level of detail of the analysis based on the importance of the information during analysis. Examples of importance include, but are not limited to, the impact on business, urgency, and user interest. Examples of detail include, but are not limited to, the number of detailed data points, the depth of the analysis, and the range of information to display. For example, the analysis unit performs a detailed analysis of information with high importance. The analysis unit can also perform a concise analysis of information with low importance. Furthermore, the analysis unit can gradually adjust the level of detail of the analysis depending on the importance of the information. This enables efficient analysis by adjusting the level of detail of the analysis depending on the importance of the information. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the importance of the information into AI, which can then determine the optimal level of detail.

[0090] The analysis unit can apply different analysis algorithms depending on the classification of information during analysis. The analysis unit applies different analysis algorithms depending on the classification of information during analysis. Categories include, but are not limited to, text data, numerical data, and image data. Analysis algorithms include, but are not limited to, machine learning algorithms, statistical analysis algorithms, and data mining algorithms. For example, the analysis unit applies a schedule analysis algorithm to product schedule information. The analysis unit can also apply a delivery analysis algorithm to delivery status information. Furthermore, the analysis unit can apply an activation analysis algorithm to activation status information. This enables more accurate analysis by applying an analysis algorithm depending on the category of information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the category of information into AI, which then applies the optimal analysis algorithm.

[0091] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can provide a short and concise analysis result. Furthermore, if the user is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the user is stressed, the analysis unit can provide a visually easy-to-understand analysis result. By adjusting the length of the analysis according to the user's emotions, optimal analysis results can be provided for the user. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into an AI, which then determines the optimal length of the analysis.

[0092] The analysis unit can determine the analysis priority based on the submission date and time of the information during analysis. The analysis unit determines the analysis priority based on the submission date and time of the information during analysis. The submission date and time includes, but is not limited to, a timestamp, submission history, system log, etc. The priority includes, but is not limited to, the importance, urgency, and submission date and time of the information. For example, the analysis unit prioritizes analysis of the most recent information. The analysis unit can also postpone information that was submitted earlier. Furthermore, the analysis unit can gradually adjust the analysis priority depending on the submission date. In this way, by determining the analysis priority based on the submission date and time of the information, the most recent information can be prioritized for analysis. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the submission date and time of the information into AI, which can then determine the optimal priority.

[0093] The analysis unit can adjust the order of analysis based on the relationships between information during analysis. The analysis unit can adjust the order of analysis based on the relationships between information during analysis. Examples of relationships include, but are not limited to, co-occurrence network analysis, correlation analysis, and clustering. Examples of the order include, but are not limited to, the importance, relevance, and submission date and time of information. For example, the analysis unit prioritizes analysis of highly relevant information. The analysis unit can also postpone analysis of less relevant information. Furthermore, the analysis unit can gradually adjust the order of analysis according to the relevance of the information. This enables efficient analysis by adjusting the order of analysis based on the relevance of the information. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the relationships between information into AI, which can then determine the optimal order.

[0094] The generation unit can estimate the user's emotions and adjust the expression style of the generated email based on the estimated user's emotions. For example, if the user is relaxed, the generation unit can generate an email containing detailed expressions. If the user is in a hurry, the generation unit can also generate an email containing concise expressions. Furthermore, if the user is stressed, the generation unit can also generate an email containing visually easy-to-understand expressions. This allows the generation of more appropriate emails by adjusting the expression style of the email 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 can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotion data into AI, which can then determine the optimal expression style.

[0095] The generation unit can adjust the level of detail of the email based on the importance of the information when generating the email. The generation unit can adjust the level of detail of the email based on the importance of the information when generating the email. Examples of importance include, but are not limited to, the impact on business, urgency, and user interest. Examples of detail include, but are not limited to, detailed explanations, summaries, and bullet points. The generation unit can generate detailed emails for information with high importance, for example. The generation unit can also generate concise emails for information with low importance. Furthermore, the generation unit can gradually adjust the level of detail of the email based on the importance of the information. This enables efficient email generation by adjusting the level of detail of the email based on the importance of the information. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the importance of the information into AI, which can then determine the optimal level of detail.

[0096] The generation unit can apply different generation algorithms depending on the classification of information when generating an email. The generation unit applies different generation algorithms depending on the classification of information when generating an email. Categories include, but are not limited to, text data, numerical data, and image data. Generation algorithms include, but are not limited to, natural language generation algorithms and template-based generation algorithms. For example, the generation unit applies a schedule generation algorithm to product schedule information. The generation unit can also apply a delivery generation algorithm to delivery status information. The generation unit can also apply an activation generation algorithm to activation status information. This enables more accurate email generation by applying a generation algorithm depending on the category of information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category of information into AI, which then applies the optimal generation algorithm.

[0097] The generation unit can estimate the user's emotions and adjust the length of the email to be generated based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate a short, to-the-point email. Furthermore, if the user is relaxed, the generation unit can generate a longer email with detailed explanations. Furthermore, if the user is stressed, the generation unit can generate a visually easy-to-understand email. This allows the length of the email to be adjusted according to the user's emotions, resulting in a more appropriate email. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotion data into AI, which can then determine the optimal length of the email.

[0098] The generation unit can determine the priority of emails based on the submission date and time of information when generating emails. The generation unit can determine the priority of emails based on the submission date and time of information when generating emails. The submission date and time can include, but are not limited to, a timestamp, a submission history, a system log, etc. The priority can include, but are not limited to, the importance, urgency, and submission date and time of information, for example. The generation unit, for example, prioritizes including the most recent information in the email. The generation unit can also postpone information that was submitted earlier. Furthermore, the generation unit can gradually adjust the priority of emails depending on the submission date. In this way, by determining the priority of emails based on the submission date and time of information, the most recent information can be prioritized and included in the email. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the submission date and time of information into AI, which can then determine the optimal priority.

[0099] The generation unit can adjust the order of emails based on the relationships between information when generating emails. The generation unit adjusts the order of emails based on the relationships between information when generating emails. Examples of relationships include, but are not limited to, co-occurrence network analysis, correlation analysis, and clustering. Examples of order include, but are not limited to, the importance, relevance, and submission date and time of information. For example, the generation unit prioritizes including highly relevant information in the email. The generation unit can also postpone less relevant information. Furthermore, the generation unit can gradually adjust the order of emails according to the relevance of the information. This enables efficient email generation by adjusting the order of emails based on the relevance of the information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the relationships between information into AI, which can then determine the optimal order.

[0100] The confirmation unit can estimate the user's emotions and adjust the confirmation method based on the estimated user emotions. For example, the confirmation unit can provide detailed confirmation procedures when the user is relaxed. Furthermore, the confirmation unit can provide simple confirmation procedures when the user is in a hurry. Furthermore, the confirmation unit can provide visually easy-to-understand confirmation procedures when the user is stressed. This allows the confirmation method to be adjusted according to the user's emotions, thereby providing a more appropriate confirmation procedure. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the confirmation unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the confirmation unit can input the user's emotion data into an AI, which can then determine the optimal confirmation method.

[0101] The confirmation unit can select an appropriate confirmation method by referring to past confirmation history when confirming. The confirmation unit can select an appropriate confirmation method by referring to past confirmation history when confirming. The confirmation history can include, for example, confirmation history for the past year, confirmation history related to a specific task, etc., but is not limited to these examples. The confirmation method can include, for example, manual confirmation, automatic confirmation, multiple checkpoints, etc., but is not limited to these examples. The confirmation unit, for example, preferentially suggests a confirmation method that the user has used in the past. The confirmation unit can also predict and suggest a confirmation method to be used in a specific time period based on the user's past confirmation history. Furthermore, the confirmation unit can analyze patterns of information that the user has confirmed in the past and suggest an optimal confirmation method. In this way, by referring to the past confirmation history, the optimal confirmation method for the user can be suggested. Some or all of the above-described processing in the confirmation unit can be performed using, for example, AI, or can be performed without using AI. For example, the confirmation unit can input the past confirmation history into AI, which can select the optimal confirmation method.

[0102] The confirmation unit can apply different confirmation methods depending on the classification of information during confirmation. The confirmation unit applies different confirmation methods depending on the classification of information during confirmation. Information categories include, but are not limited to, for example, product schedule information, delivery status information, and activation status information. Confirmation methods include, but are not limited to, for example, a schedule confirmation method, a delivery confirmation method, and an activation confirmation method. For example, the confirmation unit applies a schedule confirmation method to product schedule information. The confirmation unit can also apply a delivery confirmation method to delivery status information. Furthermore, the confirmation unit can also apply an activation confirmation method to activation status information. This enables more accurate confirmation by applying a confirmation method depending on the information category. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the information category into AI, which can then apply the most appropriate confirmation method.

[0103] The confirmation unit can estimate the user's emotions and determine the priority of confirmations based on the estimated user emotions. For example, if the user is feeling stressed, the confirmation unit can postpone less important confirmations. Furthermore, if the user is relaxed, the confirmation unit can prioritize more important confirmations. Furthermore, if the user is in a hurry, the confirmation unit can perform the most important confirmation first. In this way, by determining the priority of confirmations according to the user's emotions, important confirmations can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the confirmation unit can be performed using an AI, for example, or without an AI. For example, the confirmation unit can input the user's emotion data into an AI, which can then determine the optimal priority.

[0104] The confirmation unit can adjust the confirmation order based on the submission date and time of the information during confirmation. The confirmation unit adjusts the confirmation order based on the submission date and time of the information during confirmation. The submission date and time may include, but are not limited to, a timestamp, submission history, system log, etc. The order may include, but are not limited to, the importance, relevance, and submission date and time of the information. For example, the confirmation unit prioritizes checking the most recent information. The confirmation unit can also postpone information that was submitted earlier. Furthermore, the confirmation unit can gradually adjust the confirmation order depending on the submission date. In this way, by adjusting the confirmation order based on the submission date and time of the information, the most recent information can be prioritized for confirmation. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the submission date and time of the information into AI, which can then determine the optimal order.

[0105] The confirmation unit can adjust the confirmation order based on the relationship between information during confirmation. The confirmation unit can adjust the confirmation order based on the relationship between information during confirmation. Examples of the relationship include, but are not limited to, co-occurrence network analysis, correlation analysis, and clustering. Examples of the order include, but are not limited to, the importance, relevance, and submission date and time of information. For example, the confirmation unit prioritizes checking highly relevant information. The confirmation unit can also postpone checking less relevant information. Furthermore, the confirmation unit can gradually adjust the confirmation order according to the relevance of the information. This enables efficient confirmation by adjusting the confirmation order based on the relevance of the information. Some or all of the above-described processing in the confirmation unit can be performed using, for example, AI, or without AI. For example, the confirmation unit can input the relationship between information into AI, which can then determine the optimal order.

[0106] The reference unit can estimate the user's emotions and select data to reference based on the estimated user emotions. For example, when the user is relaxed, the reference unit can refer to detailed data. When the user is in a hurry, the reference unit can also refer to concise data. Furthermore, when the user is stressed, the reference unit can also refer to visually easy-to-understand data. This allows more appropriate data to be referenced by selecting data to reference according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reference unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the reference unit can input the user's emotion data into an AI, which can select the optimal data.

[0107] The reference unit can select appropriate data by referring to past reference history when referencing data. The reference unit can select appropriate data by referring to past reference history when referencing data. Reference history includes, but is not limited to, reference history for the past year, reference history related to a specific task, etc. The reference unit, for example, preferentially displays data that the user has frequently referenced in the past. The reference unit can also predict and suggest data to be used in a specific time period based on the user's past reference history. Furthermore, the reference unit can analyze patterns of data that the user has referenced in the past and suggest optimal data. In this way, optimal data for the user can be suggested by referring to the past reference history. Some or all of the above-described processing in the reference unit may be performed, for example, using AI, or may be performed without using AI. For example, the reference unit can input past reference history into AI, which can select optimal data.

[0108] The reference unit can estimate the user's emotions and adjust the frequency of reference based on the estimated user's emotions. For example, when the user is relaxed, the reference unit can frequently reference data. Furthermore, when the user is in a hurry, the reference unit can also frequently reference visually easy-to-understand data. By adjusting the frequency of reference according to the user's emotions, data can be referenced at a more appropriate frequency. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reference unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the reference unit can input the user's emotion data into an AI, which can then determine the optimal reference frequency.

[0109] The reference unit can weight the reference data based on the submission date and time of the data when referencing. The reference unit weights the reference data based on the submission date and time of the data when referencing. The submission date and time includes, but is not limited to, a timestamp, a submission history, a system log, etc. Examples of weighting include, but are not limited to, preferentially referencing the most recent data, postponing data submitted earlier, and gradually adjusting the weighting of the reference data depending on the submission date. In this way, by weighting the reference data based on the submission date and time of the data, the most recent data can be preferentially referenced. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input the submission date and time of the data into AI, which can then determine the optimal weighting.

[0110] The reply analysis unit can estimate the user's emotions and adjust the reply analysis method based on the estimated user emotions. For example, the reply analysis unit can perform a detailed analysis when the user is relaxed. The reply analysis unit can also perform a concise analysis when the user is in a hurry. Furthermore, the reply analysis unit can perform a visually easy-to-understand analysis when the user is stressed. This allows for adjusting the reply analysis method according to the user's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reply analysis unit can be performed using, for example, an AI, or without an AI. For example, the reply analysis unit can input the user's emotion data into an AI, which can then determine the optimal analysis method.

[0111] The reply analysis unit can select an appropriate analysis method by referring to past reply history when analyzing replies. The reply analysis unit can select an appropriate analysis method by referring to past reply history when analyzing replies. The reply history includes, for example, reply history from the past year, reply history related to a specific task, etc., but is not limited to these examples. The reply analysis unit, for example, prioritizes and suggests reply methods used by the user in the past. The reply analysis unit can also predict and suggest reply methods to be used during specific time periods based on the user's past reply history. Furthermore, the reply analysis unit can analyze patterns of the content of the user's past replies and suggest the optimal analysis method. In this way, by referring to the past reply history, the optimal analysis method for the user can be suggested. Some or all of the above-described processing in the reply analysis unit can be performed, for example, using AI, or can be performed without using AI. For example, the reply analysis unit can input past reply history into AI, which can select the optimal analysis method.

[0112] The reply analysis unit can estimate the user's emotions and determine the priority of reply analysis based on the estimated user emotions. For example, if the user is feeling stressed, the reply analysis unit can postpone analysis of less important replies. Furthermore, if the user is relaxed, the reply analysis unit can prioritize analysis of more important replies. Furthermore, if the user is in a hurry, the reply analysis unit can analyze the most important replies first. Thus, by determining the priority of reply analysis according to the user's emotions, important reply analysis can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reply analysis unit can be performed using, for example, an AI, or without an AI. For example, the reply analysis unit can input the user's emotion data into an AI, which can then determine the optimal priority.

[0113] The reply analysis unit can adjust the analysis order based on the submission date and time of the reply content when analyzing the reply. The reply analysis unit can adjust the analysis order based on the submission date and time of the reply content when analyzing the reply. The submission date and time can be, for example, a timestamp, a submission history, a system log, etc., but is not limited to these examples. The order can be, for example, based on the importance of the information, relevance, and submission date and time, but is not limited to these examples. The reply analysis unit, for example, prioritizes analyzing the most recent reply content. The reply analysis unit can also postpone replies submitted earlier. Furthermore, the reply analysis unit can gradually adjust the reply analysis order depending on the submission date. In this way, by adjusting the analysis order based on the submission date and time of the reply content, the most recent reply content can be prioritized for analysis. Some or all of the above-described processing in the reply analysis unit can be performed using, for example, AI, or without AI. For example, the reply analysis unit can input the submission date and time of the reply content into AI, which can then determine the optimal order.

[0114] The reply generation unit can estimate the user's emotions and adjust the expression style of the reply email based on the estimated user emotions. For example, if the user is relaxed, the reply generation unit can generate a reply email containing detailed expressions. If the user is in a hurry, the reply generation unit can also generate a reply email containing concise expressions. Furthermore, if the user is stressed, the reply generation unit can also generate a reply email containing visually easy-to-understand expressions. This allows for the generation of a more appropriate reply email by adjusting the expression style of the reply email according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reply generation unit can be performed using AI, for example, or without AI. For example, the reply generation unit can input the user's emotion data into AI, which can then determine the optimal expression style.

[0115] When generating a reply email, the reply generation unit can adjust the level of detail of the reply email based on the importance of the reply content. When generating a reply email, the reply generation unit adjusts the level of detail of the reply email based on the importance of the reply content. Examples of importance include, but are not limited to, the impact on business, the urgency, and the user's interest. Examples of detail include, but are not limited to, a detailed explanation, a summary, and bullet points. For example, the reply generation unit generates a detailed reply email for reply content with high importance. The reply generation unit can also generate a concise reply email for reply content with low importance. Furthermore, the reply generation unit can gradually adjust the level of detail of the reply email depending on the importance of the reply content. This allows for efficient generation of reply emails by adjusting the level of detail of the reply email depending on the importance of the reply content. Some or all of the above-described processing in the reply generation unit may be performed using, or without, AI. For example, the reply generation unit can input the importance of the reply content into AI, which can then determine the optimal level of detail.

[0116] The reply generation unit can estimate the user's emotions and adjust the length of the reply email based on the estimated user emotions. For example, if the user is in a hurry, the reply generation unit can generate a short, to-the-point reply email. Furthermore, if the user is relaxed, the reply generation unit can generate a longer reply email with detailed explanations. Furthermore, if the user is stressed, the reply generation unit can generate a visually easy-to-understand reply email. This allows the length of the reply email to be adjusted according to the user's emotions, resulting in a more appropriate reply email. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reply generation unit can be performed using, for example, AI, or without AI. For example, the reply generation unit can input the user's emotion data into AI, which can then determine the optimal length of the email.

[0117] When generating a reply email, the reply generation unit can determine the priority of the reply email based on the submission date and time of the reply content. When generating a reply email, the reply generation unit determines the priority of the reply email based on the submission date and time of the reply content. The submission date and time may include, but are not limited to, a timestamp, a submission history, a system log, etc. The priority may include, but are not limited to, the importance of the information, the urgency, and the submission date and time. For example, the reply generation unit may prioritize including the most recent reply content in the reply email. The reply generation unit may also postpone reply content that was submitted earlier. Furthermore, the reply generation unit may gradually adjust the priority of the reply email depending on the submission date and time. In this way, by determining the priority of the reply email based on the submission date and time of the reply content, the most recent reply content can be prioritized and included in the email. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit may input the submission date and time of the reply content into AI, which may determine the optimal priority.

[0118] The reply generation unit can adjust the order of reply emails based on the relationships between the reply contents when generating reply emails. The reply generation unit adjusts the order of reply emails based on the relationships between the reply contents when generating reply emails. Examples of the relationships include, but are not limited to, co-occurrence network analysis, correlation analysis, and clustering. Examples of the order include, but are not limited to, the importance of information, relevance, and submission date and time. For example, the reply generation unit prioritizes including highly relevant information in the reply email. The reply generation unit can also postpone less relevant information. Furthermore, the reply generation unit can gradually adjust the order of reply emails based on the relevance of the information. This enables efficient generation of reply emails by adjusting the order of reply emails based on the relevance of the reply contents. Some or all of the above-described processing in the reply generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reply generation unit can input the relationships between the reply contents into AI, which can then determine the optimal order.

[0119] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0120] The reception unit can analyze the user's voice input and convert it into text data using voice recognition technology. For example, when a corporate sales representative inputs schedules and delivery status for various products by voice, the reception unit converts the voice into text in real time and sends it to the analysis unit. In addition, by providing a function to remove background noise during voice input, more accurate text data can be generated. Furthermore, the system can analyze the user's speaking rate and intonation during voice input to estimate the user's emotions and level of urgency. As a result, utilizing voice input can improve the efficiency of corporate sales representatives' input work and enable faster responses.

[0121] The reference section can obtain information in real time from external databases and APIs and refer to the latest data. For example, it can obtain information such as product inventory status and market trends from external databases and reflect this in the email content provided to customers. The reference section can also evaluate the reliability of the obtained data and use only the most reliable data. Furthermore, the reference section can automatically update the obtained data and always keep it up-to-date. This makes it possible to generate more accurate customized emails by utilizing external data.

[0122] The reply analysis unit can analyze the emotions contained in the customer's replies and propose responses based on those emotions. For example, if a customer expresses dissatisfaction, the reply analysis unit can propose specific measures to resolve that dissatisfaction. Also, if a customer is satisfied, the reply analysis unit can make additional suggestions to further increase that satisfaction. Furthermore, the reply analysis unit can track changes in the customer's emotions and provide information that is useful for building long-term relationships. This makes it possible to respond appropriately based on the customer's emotions, which is expected to improve customer satisfaction.

[0123] The reply generator can include images and videos in the reply emails it generates. For example, by attaching an explanatory video or product image to a customer's question, the reply can be made easier to understand. The reply generator can also automatically insert related materials and links based on the customer's interests. Furthermore, the reply generator can customize the design of the reply email and generate emails that match the brand image. This makes it possible to provide reply emails that are visually appealing and contain a lot of information.

[0124] When generating email content, the generation unit analyzes a customer's purchasing history and behavioral patterns to suggest products that the customer is likely to purchase next. For example, it can suggest related new products or upgraded versions to a customer who has previously purchased a specific product. The generation unit can also predict a customer's purchasing cycle and send reminder emails at appropriate times. Furthermore, the generation unit can provide personalized promotion and campaign information based on the customer's interests. This can increase customer purchasing motivation and is expected to increase sales.

[0125] The verification unit can be equipped with a translation function to make the content of generated emails multilingual. For example, an email generated in English can be automatically translated into Japanese or Chinese, and sent to customers in each country in the appropriate language. The verification unit can also evaluate the quality of the translation and make corrections as necessary. Furthermore, the verification unit can translate while taking into account the cultural background and business etiquette of each language, thereby achieving more natural and effective communication. This enables global customer service and supports international business development.

[0126] The reception unit can estimate the user's emotions and customize the input interface based on the estimated user emotions. For example, if the user is feeling stressed, a simple and intuitive interface can be provided to facilitate input work. Alternatively, if the user is relaxed, detailed options and customization functions can be provided. Furthermore, the reception unit can change the color and design of the interface according to the user's emotions to provide a comfortable operating environment. This can be expected to improve the efficiency of input work and user satisfaction by providing an interface that takes the user's emotions into consideration.

[0127] The reception unit can provide an auto-completion function for input content based on the user's past input history. For example, it can automatically suggest product names or customer names that have been entered in the past, making input work more efficient. The reception unit can also learn frequently used phrases and standard phrases and suggest them at the appropriate time. Furthermore, the reception unit can also be equipped with a function to analyze the user's input patterns and predict and automatically correct input errors. This makes it possible to utilize past input history and is expected to improve the efficiency and accuracy of input work.

[0128] When inputting information, the reception unit can prioritize the input contents based on the user's current work situation and areas of interest. For example, it can suggest that information related to an ongoing project be input preferentially. It can also prioritize the input of highly relevant information based on the user's areas of interest. Furthermore, the reception unit can filter the information so that only necessary information is input according to the user's work situation. This allows information to be input efficiently based on the user's work situation and areas of interest.

[0129] The reception unit can estimate the user's emotions and determine the priority of input contents based on the estimated user's emotions. For example, if the user is feeling stressed, less important information can be put off. Also, if the user is relaxed, more important information can be input preferentially. Furthermore, if the user is in a hurry, the most important information can be input first. In this way, by determining the priority of information according to the user's emotions, important information can be input preferentially.

[0130] The processing flow of the second embodiment will be briefly explained below.

[0131] Step 1: The reception unit inputs information. Information includes, but is not limited to, text data, numerical data, and image data. For example, a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products into the reception unit. Step 2: The analysis unit uses the generation AI to analyze the information input by the reception unit. The analysis is performed by methods such as, but not limited to, text analysis, data mining, and statistical analysis. Step 3: The generation unit uses the generation AI to generate a customized email based on the information analyzed by the analysis unit. The generated email is generated according to criteria such as, but not limited to, customization based on personal information or past behavioral history. Step 4: The verification unit verifies the generated email. The verification unit includes, for example, a verification process to ensure the quality of the generated email. The verification process may include, but is not limited to, criteria such as grammatical accuracy, content relevance, and customer satisfaction.

[0132] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0133] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats including voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. The AIs other than the generation AI are, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but are not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or in whole by AI, but are not limited to these examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0134] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0135] Each of the above-described elements, including the reception unit, analysis unit, generation unit, confirmation unit, reference unit, reply analysis unit, and reply generation unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14, and a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the input information using a generation AI. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and generates a customized email based on the analyzed information. The confirmation unit is implemented, for example, by the control unit 46A of the smart device 14, and checks the quality of the generated email. The reference unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and references past email history and a customer database. The reply analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of the reply from the customer. The reply generation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and generates an appropriate reply email. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0136] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0137] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0144] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0145] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0146] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0148] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0150] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0151] Each of the multiple elements, including the reception unit, analysis unit, generation unit, confirmation unit, reference unit, reply analysis unit, and reply generation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the input information using a generation AI. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a customized email based on the analyzed information. The confirmation unit is realized, for example, by the control unit 46A of the smart glasses 214, and checks the quality of the generated email. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and references past email history and a customer database. The reply analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of the reply from the customer. The reply generation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and generates an appropriate reply email. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0152] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0153] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0154] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0155] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0156] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0157] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0158] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0159] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0160] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0161] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0162] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0163] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0164] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0165] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0166] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0167] Each of the multiple elements, including the above-described reception unit, analysis unit, generation unit, confirmation unit, reference unit, reply analysis unit, and reply generation unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314, and a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the input information using a generation AI. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and generates a customized email based on the analyzed information. The confirmation unit is implemented, for example, by the control unit 46A of the headset terminal 314, and checks the quality of the generated email. The reference unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and references past email history and a customer database. The reply analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of the reply from the customer. The reply generation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and generates an appropriate reply email. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0168] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0169] 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.

[0170] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0171] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0172] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0173] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0174] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0175] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0176] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0177] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0178] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0179] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0180] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0181] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0182] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0183] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0184] Each of the multiple elements, including the reception unit, analysis unit, generation unit, confirmation unit, reference unit, reply analysis unit, and reply generation unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the robot 414, and a corporate sales representative inputs information such as schedules, delivery status, and activation status for various products. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the input information using a generation AI. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and generates a customized email based on the analyzed information. The confirmation unit is implemented, for example, by the control unit 46A of the robot 414, and checks the quality of the generated email. The reference unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and references past email history and a customer database. The reply analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of the reply from the customer. The reply generation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and generates an appropriate reply email. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0185] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0186] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0187] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0188] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0189] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0190] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0191] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0192] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0193] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0194] 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.

[0195] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0196] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0197] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0198] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0199] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0200] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0201] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0202] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0203] (Appendix 1) a reception section for inputting information; an analysis unit that analyzes the information input by the reception unit; a generation unit that generates a customized email based on the information analyzed by the analysis unit; a confirmation unit that confirms the email generated by the generation unit; Equipped with A system characterized by: (Appendix 2) Includes a reference section for past email history or customer database 2. The system of claim 1. (Appendix 3) Equipped with a reply analysis unit that analyzes the content of replies from customers 2. The system of claim 1. (Appendix 4) Equipped with a reply generation unit that generates appropriate reply emails 2. The system of claim 1. (Appendix 5) The generation unit Generate email content that takes into account each customer's needs or past interactions 2. The system of claim 1. (Appendix 6) The confirmation unit Includes a review process to ensure the quality of generated emails 2. The system of claim 1. (Appendix 7) The reception unit Estimates the user's emotions and adjusts the timing of information input based on the estimated user emotions. 2. The system of claim 1. (Appendix 8) The reception unit Analyze past input history and select the optimal input method 2. The system of claim 1. (Appendix 9) The reception unit Filter information as it is entered based on the user's current job status or area of ​​interest 2. The system of claim 1. (Appendix 10) The reception unit Estimate the user's emotions and prioritize the information to be input based on the estimated user emotions. 2. The system of claim 1. (Appendix 11) The reception unit When entering information, prioritize the most relevant information based on the user's geographic location 2. The system of claim 1. (Appendix 12) The reception unit When you enter information, analyze your social media activity and enter relevant information 2. The system of claim 1. (Appendix 13) The analysis unit Inferring user emotions and adjusting the presentation of analysis based on the estimated user emotions 2. The system of claim 1. (Appendix 14) The analysis unit During analysis, adjust the level of detail based on the importance of the information 2. The system of claim 1. (Appendix 15) The analysis unit During analysis, different analysis algorithms are applied depending on the classification of the information. 2. The system of claim 1. (Appendix 16) The analysis unit Inferring user sentiment and adjusting the length of the analysis based on the estimated user sentiment 2. The system of claim 1. (Appendix 17) The analysis unit During analysis, the analysis is prioritized based on the date and time of submission of the information. 2. The system of claim 1. (Appendix 18) The analysis unit During analysis, adjust the order of analysis based on the relationship of the information 2. The system of claim 1. (Appendix 19) The generation unit Inferring user emotions and adjusting the way emails are generated based on the estimated user emotions 2. The system of claim 1. (Appendix 20) The generation unit When generating emails, adjust the level of detail in the email based on the importance of the information 2. The system of claim 1. (Appendix 21) The generation unit When generating emails, different generation algorithms are applied depending on the classification of the information. 2. The system of claim 1. (Appendix 22) The generation unit Estimate the user's emotions and adjust the length of the email to be generated based on the estimated user emotions. 2. The system of claim 1. (Appendix 23) The generation unit When generating emails, prioritize them based on when the information was submitted 2. The system of claim 1. (Appendix 24) The generation unit When generating emails, adjust the order of emails based on the relevance of the information 2. The system of claim 1. (Appendix 25) The confirmation unit Estimate the user's emotions and adjust the confirmation method based on the estimated user emotions 2. The system of claim 1. (Appendix 26) The confirmation unit When verifying, refer to past verification history to select the appropriate verification method. 2. The system of claim 1. (Appendix 27) The confirmation unit When verifying, apply different verification methods depending on the classification of the information. 2. The system of claim 1. (Appendix 28) The confirmation unit Estimate the user's emotions and determine the priority of confirmations based on the estimated user emotions. 2. The system of claim 1. (Appendix 29) The confirmation unit During verification, adjust the order of verification based on when the information was submitted 2. The system of claim 1. (Appendix 30) The confirmation unit During review, adjust the order of review based on the relevance of the information 2. The system of claim 1. (Appendix 31) The reference portion is Estimate the user's emotions and select the data to reference based on the estimated user emotions. 3. The system of claim 2. (Appendix 32) The reference portion is When referencing data, select appropriate data by referring to past reference history. 3. The system of claim 2. (Appendix 33) The reference portion is Estimate the user's emotions and adjust the frequency of references based on the estimated user emotions. 3. The system of claim 2. (Appendix 34) The reference portion is At the time of reference, the reference data is weighted based on the submission date and time of the data. 3. The system of claim 2. (Appendix 35) The reply analysis unit Inferring user emotions and adjusting reply analysis methods based on the estimated user emotions 4. The system of claim 3. (Appendix 36) The reply analysis unit When analyzing replies, refer to past reply history to select the appropriate analysis method 4. The system of claim 3. (Appendix 37) The reply analysis unit Estimate the user's emotions and determine the priority of reply analysis based on the estimated user emotions. 4. The system of claim 3. (Appendix 38) The reply analysis unit When parsing replies, adjust the order of analysis based on the submission date and time of the reply content. 4. The system of claim 3. (Appendix 39) The reply generation unit Inferring the user's emotions and adjusting the way the reply email is written based on the estimated user's emotions 5. The system of claim 4. (Appendix 40) The reply generation unit When generating a reply email, adjust the detail level of the reply email based on the importance of the reply content 5. The system of claim 4. (Appendix 41) The reply generation unit Inferring user sentiment and adjusting the length of reply emails based on the estimated sentiment 5. The system of claim 4. (Appendix 42) The reply generation unit When generating a reply email, prioritize the reply email based on the submission date and time of the reply 5. The system of claim 4. (Appendix 43) The reply generation unit When generating replies, adjust the order of replies based on the relevance of the replies 5. The system of claim 4. [Explanation of symbols]

[0204] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception section for inputting information; an analysis unit that analyzes the information input by the reception unit; a generation unit that generates a customized email based on the information analyzed by the analysis unit; a confirmation unit for confirming the email generated by the generation unit; Equipped A system characterized by:

2. Equipped with a reference section that can refer to past email history or customer database 2. The system of claim 1 .

3. Equipped with a reply analysis section that analyzes the contents of replies from customers 2. The system of claim 1 .

4. Equipped with a reply generation unit that generates appropriate reply emails 2. The system of claim 1 .

5. The generation unit is Generate email content that takes into account each customer's needs or past interactions 2. The system of claim 1 .

6. The confirmation unit is Includes a review process to ensure the quality of generated emails 2. The system of claim 1 .

7. The reception unit is To estimate a user's emotions and adjust the timing of information input based on the estimated user's emotions 2. The system of claim 1 .

8. The reception unit is Analyze past input history and select the optimal input method 2. The system of claim 1 .

9. The reception unit is Filter information as it is entered based on the user's current job status or interests 2. The system of claim 1 .

Images