System

Abstract

An object of the system according to the embodiment is to automatically collect and summarize conversation contents with a customer and record the conversation contents as a medical record for each customer.SOLUTION: A system according to an embodiment includes a conversation collection unit, a summarization unit, and a medical chart generation unit. The conversation collection unit collects conversation contents with a customer. The summarization unit summarizes the conversation content collected by the conversation collection unit. The medical chart generation unit records the content summarized by the summarization unit as a medical chart for each customer.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] Conventional technology has had the problem of making it difficult to efficiently record conversations with customers during face-to-face customer service and use the information in future customer service encounters.

[0005] The system according to the embodiment aims to automatically collect and summarize conversations with customers and record them as medical records for each customer. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversation collection unit, a summarization unit, and a medical record generation unit. The conversation collection unit collects conversation content with customers. The summarization unit summarizes the conversation content collected by the conversation collection unit. The medical record generation unit records the content summarized by the summarization unit as a medical record for each customer. [Effects of the Invention]

[0007] The system according to the embodiment can automatically collect and summarize conversations with customers and record them as medical records for each customer. [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) The automatic medical record generation system according to an embodiment of the present invention is a system in which the contents of conversations with customers are automatically collected, summarized by a generation AI, and recorded as a medical record. As a result, the automatic medical record generation system automatically collects the contents of conversations with customers, summarizes them, and records them as a medical record, which can be used for future customer service.

[0029] An automatic medical record generation system according to an embodiment includes a conversation collection unit, a summarization unit, and a medical record generation unit. The conversation collection unit collects conversation content with a customer. For example, it records face-to-face conversations using a microphone and saves them as audio data. It can also record telephone conversations and save them as audio data. It can also collect online chat content as text data. For example, the conversation collection unit records face-to-face conversations using a high-sensitivity microphone and saves them as audio data. It uses a call recording function to save telephone conversations as audio data. It automatically collects chat logs and saves them as text data. The summarization unit summarizes the conversation content collected by the conversation collection unit. For example, the generation AI concisely summarizes the conversation content using a text generation AI (e.g., LLM). It can also summarize the conversation content using a multimodal generation AI. It can also extract and summarize important parts of sentences. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses keyword extraction technology to identify particularly important information from the conversation and summarizes it based on that information. The medical record generation unit records the content summarized by the summarization unit as a medical record for each customer. For example, the medical record generation unit records the summarized content in the medical record in text format. The medical record generation unit can also record the summarized content in the medical record in image format. The medical record generation unit can also record the summarized content in database format. For example, the medical record generation unit saves the summarized content as a text file and records it as a medical record. The summarized content can also be saved as an image file and recorded as a medical record. The summarized content can also be saved in a database and recorded as a medical record. As a result, the automatic medical record generation system according to the embodiment automatically collects the content of conversations with customers, summarizes it, and records it as a medical record, allowing it to be used in future customer service. For example, the output unit displays the medical record to staff via a web application or mobile application.If you would like to have a paper copy of your medical record, you can print it out using a printer. By sending the medical record via email, you can quickly share information by sending it directly to staff.

[0030] The conversation collection unit can collect not only voice but also text chat and email content. For example, the conversation collection unit collects the content of text chat with customers and records it in a medical record. For example, it collects the content of chats in an online reservation system. The conversation collection unit also collects the content of emails from customers and records it in a medical record. For example, it analyzes and records the content of reservation confirmation emails and inquiry emails. The conversation collection unit also collects and integrates the content of voice, text chat, and email and records it in a medical record. For example, it centrally manages multiple means of communication. This allows for the collection of not only voice but also text chat and email content, making it possible to generate more detailed medical records.

[0031] The conversation collection unit can automatically translate conversation content in different languages ​​and generate medical records that support multiple languages. For example, the conversation collection unit uses a generation AI to automatically translate conversation content in different languages ​​and record it in a medical record. For example, a conversation in English is translated into Japanese and recorded. The conversation collection unit also generates medical records that support multiple languages, making it possible to accommodate customers who speak different languages. For example, medical records are generated in multiple languages ​​such as English, Chinese, and Spanish. The conversation collection unit also uses an automatic translation function to translate conversation content in different languages ​​in real time and record it in a medical record. For example, conversations with foreign customers are instantly translated and recorded. In this way, conversation content in different languages ​​can be automatically translated and a multilingual medical record can be generated, making it possible to accommodate customers who speak different languages.

[0032] The summarization unit can also reference the customer's past medical record information to generate a more accurate summary. For example, the generation AI of the summarization unit references the customer's past medical record information and summarizes the content of the current conversation. For example, it generates a summary taking into account past concerns and requests. The summarization unit also summarizes the content of the current conversation more accurately based on the customer's past medical record information. For example, it generates a summary that reflects past treatment details and advice. The summarization unit also analyzes past medical record information and extracts important points when summarizing the content of the current conversation. For example, it extracts and summarizes important keywords based on past medical record information. In this way, by referencing past medical record information, a more accurate summary can be generated.

[0033] The summarization unit can automatically tag the summary content to improve searchability. For example, the generation AI automatically tags the summary content to improve the searchability of medical records. For example, tags such as "hair concerns" and "treatment details" are attached. The summarization unit also extracts related keywords from the summary content and automatically tags them. For example, specific keywords such as "dryness" and "bedhead" are attached as tags. The summarization unit also strengthens the search function of medical records based on the tagged summary content. For example, tags can be used to quickly search past medical records. In this way, the searchability of medical records is improved by automatically tagging the summary content.

[0034] The medical record generation unit can share the summarized medical record information with other staff members, allowing the entire team to utilize the customer information. The medical record generation unit, for example, shares the summarized medical record information with other staff members, allowing the entire team to utilize the customer information. For example, it stores the medical records in a shared folder that can be accessed by all staff members. The medical record generation unit also builds a system that allows the medical record information summarized by the generation AI to be shared among staff members in real time. For example, it introduces a cloud-based medical record management system. The medical record generation unit also makes it easy for other staff members to refer to the summarized medical record information. For example, it displays the medical record information on a staff dashboard. This allows the entire team to utilize the customer information by sharing the summarized medical record information with other staff members.

[0035] The medical record generation unit visualizes the summary content and displays it in graphs and charts, making it easier to understand visually. For example, the generation AI in the medical record generation unit visualizes the summary content and displays it in graphs and charts. For example, it displays the customer's concerns and requests in pie charts or bar graphs. The medical record generation unit also visualizes the summarized medical record information to make it easier for staff to understand visually. For example, it displays treatment history and advice content in timeline format. The medical record generation unit also makes it possible to grasp customer information at a glance based on the visualized summary content. For example, it displays the customer's emotional state and treatment history in graphs. In this way, visualizing the summary content makes it easier to understand visually.

[0036] The system can use voice recognition to analyze a customer's voiceprint and verify their identity. For example, the system uses generation AI to analyze a customer's voiceprint using voice recognition technology to verify their identity. For example, it analyzes the voiceprint when a customer speaks their name to verify their identity. The system can also register a customer's voiceprint data in advance and verify the voiceprint when the customer visits the store to verify their identity. For example, it registers voiceprint data when making a reservation and verifies it when the customer visits the store. The system can also use voice recognition technology to analyze a customer's voiceprint in real time to verify their identity. For example, it analyzes the voiceprint every time a customer speaks to verify their identity. This makes it possible to generate and manage accurate medical records by using voice recognition to analyze a customer's voiceprint and verify their identity.

[0037] The system can verify the customer's identity by using facial recognition to match the customer's facial photograph. For example, the system uses facial recognition technology with a generation AI to verify the customer's identity. For example, the system compares a facial photograph taken with a camera when the customer visits the store with a pre-registered facial photograph. The system can also register a customer's facial photograph in advance and perform facial recognition when the customer visits the store to verify the customer's identity. For example, a facial photograph is registered when a reservation is made and compared when the customer visits the store. The system can also use facial recognition technology to analyze a customer's facial photograph in real time to verify the customer's identity. For example, a facial photograph is taken with a camera when a customer enters the store and is immediately compared. This allows the system to verify the customer's identity by using facial recognition to match the customer's facial photograph, making it possible to create and manage accurate medical records.

[0038] The system can also refer to a customer's past store visit history and purchase history to perform more accurate identity verification. For example, the system uses generation AI to refer to a customer's past store visit history and purchase history to verify identity. For example, it verifies identity by comparing past store visit history with current information. The system also improves the accuracy of identity verification based on the customer's purchase history. For example, it compares products and services purchased in the past with current information. The system also references past store visit history and purchase history to detect fraudulent activity during identity verification. For example, if there is information that does not match the past history, it detects the possibility of fraudulent activity. This enables more accurate identity verification by referring to a customer's past store visit history and purchase history.

[0039] The system verifies the customer's identity in advance via a smartphone app, simplifying the procedures when the customer visits the store. For example, the system uses a smartphone app to build a system that verifies the customer's identity in advance. For example, a facial photo and voiceprint are registered in the app, and these are compared when the customer visits the store. The system also simplifies the procedures when the customer visits the store by having the customer verify their identity in advance via a smartphone app. For example, the system allows the customer to complete identity verification via the app, enabling smooth entry when the customer visits the store. The system also reduces waiting time when the customer visits the store by verifying the customer's identity in advance via a smartphone app. For example, the system allows the customer to complete identity verification via the app, enabling the customer to receive service immediately when the customer visits the store. In this way, the system simplifies the procedures when the customer visits the store by verifying the customer's identity in advance via a smartphone app.

[0040] When extracting advice for a customer, the system can also refer to the customer's past medical record information and advice history. For example, the generation AI in the system references the customer's past medical record information and advice history to extract current advice. For example, the current advice is generated based on the content of past advice. The system also customizes the current advice based on the customer's past medical record information. For example, the system provides advice taking into account the content of past treatments and advice history. The generation AI in the system also analyzes past medical record information and advice history to identify important points when extracting current advice. For example, it extracts important keywords based on the content of past advice and provides advice. This makes it possible to provide more appropriate advice by referring to the customer's past medical record information and advice history.

[0041] The system can customize the advice content to suit the customer's lifestyle and preferences. For example, the generation AI analyzes the customer's lifestyle and preferences and customizes the advice content. For example, it provides advice that suits the customer's lifestyle and preferences. The system also personalizes the advice content based on customer preference data. For example, it provides advice taking into account the customer's preferred styles and products. The generation AI also analyzes the customer's lifestyle and preferences in real time and dynamically customizes the advice content. For example, it provides advice that suits the customer's current situation. This allows the system to provide more appropriate advice by customizing the advice content to suit the customer's lifestyle and preferences.

[0042] The system can visually explain the advice content using videos and images. For example, the system uses a generative AI to visually explain the advice content using videos and images. For example, it may explain how to style a hairstyle using a video. The system may also visually explain the advice content using images and illustrations. For example, it may show skin care steps using images. The system may also use videos and images to make the advice content visually easier to understand. For example, it may explain the treatment steps in a video so that the customer can recreate them at home. In this way, the advice content is explained visually using videos and images, making it easier for customers to understand.

[0043] The system can provide advice as a step-by-step guide so that the customer can put the advice into practice at home. For example, the system uses a generative AI to provide advice as a step-by-step guide. For example, hair care procedures are explained by breaking them down into specific steps. The system also provides the advice content as a detailed guide so that the customer can put the advice into practice at home. For example, skin care procedures are explained step by step. The system also uses a step-by-step guide to make it easier for the customer to put the advice into practice. For example, treatment procedures are explained by breaking them down into specific steps so that the customer can reproduce them at home. In this way, by providing advice as a step-by-step guide, it becomes easier for the customer to put the advice into practice at home.

[0044] When generating a thank-you email for a visit, the system can also refer to the customer's past visit history and advice history. For example, the generation AI of the system references the customer's past visit history and advice history to generate a thank-you email for a visit. For example, the system creates an email based on the customer's past treatment details and advice. The system also generates a personalized thank-you email based on the customer's past visit history. For example, the system creates an email that reflects the service details from past visits. The system also references the customer's past advice history to include the advice details in the thank-you email for the visit. For example, the system creates an email that reiterates past advice. This allows the system to provide a more personalized email by referencing the customer's past visit history and advice history when generating a thank-you email for a visit.

[0045] The system can customize email content to suit a customer's lifestyle and preferences. For example, the system's generation AI analyzes a customer's lifestyle and preferences and customizes the email content. For example, it creates an email introducing products and services that match the customer's preferences. The system also generates personalized thank-you emails based on customer preference data. For example, it creates an email that reflects the customer's preferred style and products. The system also analyzes a customer's lifestyle and preferences in real time and dynamically customizes the email content. For example, it creates an email that matches the customer's current situation. This allows the system to provide more personalized emails by customizing the email content to suit the customer's lifestyle and preferences.

[0046] The system can visually explain the contents of an email using videos and images. For example, the system uses a generative AI to visually explain the contents of an email using videos and images. For example, a video explaining how to style a hairstyle. The system also visually explains the contents of an email using images and illustrations. For example, images showing skin care procedures. The system also uses videos and images to make the contents of an email easier to understand visually. For example, a video explaining the steps of a treatment so that the customer can recreate it at home. In this way, the contents of an email can be visually explained using videos and images, making it easier for customers to understand.

[0047] The system can provide emails as step-by-step guides so that customers can practice at home. For example, the system uses a generative AI to provide emails as step-by-step guides. For example, hair care procedures are explained by breaking them down into specific steps. The system also provides the email content as a detailed guide so that customers can practice at home. For example, skin care procedures are explained step by step. The system also uses step-by-step guides to make it easier for customers to practice the email content. For example, treatment procedures are explained by breaking them down into specific steps so that customers can reproduce them at home. In this way, providing emails as step-by-step guides makes it easier for customers to practice at home.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The automatic medical record generation system can further include a health data collection unit that monitors the health condition of customers. For example, sensors can be installed to check the health condition of customers when they visit the store, collecting data such as body temperature, blood pressure, and heart rate. The health data collection unit can also collect data from wearable devices provided by customers and record it in the medical record. For example, it can collect heart rate data and sleep data from a smartwatch. The health data collection unit can also monitor the customer's health condition in real time and issue an alert if an abnormality is detected. For example, it can notify staff if the heart rate is abnormally high. This makes it possible to monitor the customer's health condition and generate more detailed medical records.

[0050] The automatic medical record generation system can further include a preference analysis unit that analyzes customer preferences and past purchase history. For example, it collects data on products and services that customers have purchased in the past and analyzes their preferences. The preference analysis unit can also collect data on products and services that customers have viewed online and analyze their preferences. For example, it can estimate preferences based on products that customers have viewed on websites. The preference analysis unit can also customize products and services to be suggested for the next store visit based on the customer's preferences. For example, it can make suggestions based on the customer's preferred style and color. This allows for an analysis of customer preferences and the provision of more personalized services.

[0051] The automatic medical record generation system can further include a lifestyle collection unit that collects information about the customer's lifestyle. For example, it collects information about the customer's daily exercise and eating habits. The lifestyle collection unit can also collect data from applications and devices used by the customer to analyze the customer's lifestyle. For example, it can collect exercise data from a fitness app and dietary data from a food recording app. The lifestyle collection unit can also provide health and beauty advice based on the customer's lifestyle. For example, it can suggest exercise to a customer who is not getting enough exercise. This allows the system to collect information about the customer's lifestyle and provide more appropriate advice.

[0052] The automatic medical record generation system can further include a stress monitoring unit that monitors the stress level of customers. For example, a sensor can be installed to measure the stress level of customers when they visit the store. The stress monitoring unit can also collect data from wearable devices provided by customers to monitor stress levels. For example, it can collect heart rate variability data from a smartwatch. The stress monitoring unit can also monitor the stress level of customers in real time and issue an alert if an abnormality is detected. For example, it can notify staff if the stress level is high. This makes it possible to monitor the stress level of customers and generate more detailed medical records.

[0053] The automatic medical record generation system can further include a sleep monitoring unit that monitors the sleep state of the customer. For example, it can collect data from a wearable device provided by the customer to monitor the sleep state. The sleep monitoring unit can also collect data from a sleep tracking app used by the customer and analyze the sleep state. For example, it can collect sleep data from a smartphone app. The sleep monitoring unit can also monitor the sleep state of the customer in real time and issue an alert if an abnormality is detected. For example, it can notify staff if the quality of sleep is low. This makes it possible to monitor the sleep state of the customer and generate a more detailed medical record.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The conversation collection unit collects the content of conversations with customers. For example, face-to-face conversations are recorded using a high-sensitivity microphone and saved as audio data. Telephone conversations are saved as audio data using a call recording function. The content of online chats is automatically collected as a chat log and saved as text data. Step 2: The summarization unit summarizes the conversation content collected by the conversation collection unit. For example, the generation AI may use a text generation AI (e.g., LLM) to concisely summarize the conversation content. The generation AI may also use a multimodal generation AI to summarize the conversation content. The generation AI may use keyword extraction technology to pick out particularly important information from the conversation content and use that information to create a summary. Step 3: The medical record generation unit records the content summarized by the summarization unit as a medical record for each customer. For example, the medical record generation unit saves the summarized content as a text file and records it as a medical record. The summarized content can also be saved as an image file and recorded as a medical record. The summarized content can also be saved in a database and recorded as a medical record.

[0056] (Example 2) The automatic medical record generation system according to an embodiment of the present invention is a system in which the contents of conversations with customers are automatically collected, summarized by a generation AI, and recorded as a medical record. As a result, the automatic medical record generation system automatically collects the contents of conversations with customers, summarizes them, and records them as a medical record, which can be used for future customer service.

[0057] An automatic medical record generation system according to an embodiment includes a conversation collection unit, a summarization unit, and a medical record generation unit. The conversation collection unit collects conversation content with a customer. For example, it records face-to-face conversations using a microphone and saves them as audio data. It can also record telephone conversations and save them as audio data. It can also collect online chat content as text data. For example, the conversation collection unit records face-to-face conversations using a high-sensitivity microphone and saves them as audio data. It uses a call recording function to save telephone conversations as audio data. It automatically collects chat logs and saves them as text data. The summarization unit summarizes the conversation content collected by the conversation collection unit. For example, the generation AI concisely summarizes the conversation content using a text generation AI (e.g., LLM). It can also summarize the conversation content using a multimodal generation AI. It can also extract and summarize important parts of sentences. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses keyword extraction technology to identify particularly important information from the conversation and summarizes it based on that information. The medical record generation unit records the content summarized by the summarization unit as a medical record for each customer. For example, the medical record generation unit records the summarized content in the medical record in text format. The medical record generation unit can also record the summarized content in the medical record in image format. The medical record generation unit can also record the summarized content in database format. For example, the medical record generation unit saves the summarized content as a text file and records it as a medical record. The summarized content can also be saved as an image file and recorded as a medical record. The summarized content can also be saved in a database and recorded as a medical record. As a result, the automatic medical record generation system according to the embodiment automatically collects the content of conversations with customers, summarizes it, and records it as a medical record, allowing it to be used in future customer service. For example, the output unit displays the medical record to staff via a web application or mobile application.If you would like to have a paper copy of your medical record, you can print it out using a printer. By sending the medical record via email, you can quickly share information by sending it directly to staff.

[0058] The conversation collection unit can analyze the tone of a customer's voice and speaking rate to estimate and record their emotional state. For example, the generation AI in the conversation collection unit analyzes the tone of a customer's voice to estimate their emotional state. For example, if a customer is speaking excitedly, the tone is analyzed and their emotional state is recorded. The conversation collection unit also analyzes the speed at which the customer speaks to estimate their emotional state. For example, if a customer is speaking quickly, they may be feeling nervous or impatient, so this emotion is recorded. The conversation collection unit also analyzes the combination of tone of voice and speaking rate to estimate a more accurate emotional state. For example, if a customer is speaking slowly in a low tone, it is estimated that they are relaxed. In this way, by analyzing and recording the customer's emotional state, more detailed medical records can be generated.

[0059] The conversation collection unit can also collect non-verbal information by analyzing the customer's facial expressions and gestures using a camera. The conversation collection unit, for example, uses a camera to analyze the customer's facial expressions and estimate their emotional state. For example, emotions are recorded by analyzing facial expressions such as smiles and frowns. The conversation collection unit also analyzes the customer's gestures using a camera to collect non-verbal information. For example, hand movements and posture are analyzed to estimate the customer's emotions and intentions. The conversation collection unit also analyzes facial expressions and gestures in combination to collect more accurate non-verbal information. For example, smiles and hand movements are analyzed simultaneously to estimate the customer's satisfaction level. In this way, by collecting the customer's non-verbal information, more detailed medical records can be generated.

[0060] The conversation collection unit can analyze the customer's emotions in real time regarding what is being said and record changes in emotions. For example, the conversation collection unit uses a generation AI to analyze the customer's emotions in real time regarding what is being said and record changes in emotions. For example, it records changes in emotions every time the topic changes. The conversation collection unit also analyzes changes in the customer's emotions in real time and records them in a medical record. For example, it records changes in emotions when the customer moves from a positive topic to a negative topic. The conversation collection unit also uses an emotion estimation function to monitor changes in the customer's emotions in real time and record important changes in emotions in the medical record. For example, it records the moment when the customer suddenly becomes emotional. In this way, by recording changes in the customer's emotions in real time, more detailed medical records can be generated.

[0061] The conversation collection unit can collect not only voice but also text chat and email content. For example, the conversation collection unit collects the content of text chat with customers and records it in a medical record. For example, it collects the content of chats in an online reservation system. The conversation collection unit also collects the content of emails from customers and records it in a medical record. For example, it analyzes and records the content of reservation confirmation emails and inquiry emails. The conversation collection unit also collects and integrates the content of voice, text chat, and email and records it in a medical record. For example, it centrally manages multiple means of communication. This allows for the collection of not only voice but also text chat and email content, making it possible to generate more detailed medical records.

[0062] The conversation collection unit can automatically translate conversation content in different languages ​​and generate medical records that support multiple languages. For example, the conversation collection unit uses a generation AI to automatically translate conversation content in different languages ​​and record it in a medical record. For example, a conversation in English is translated into Japanese and recorded. The conversation collection unit also generates medical records that support multiple languages, making it possible to accommodate customers who speak different languages. For example, medical records are generated in multiple languages ​​such as English, Chinese, and Spanish. The conversation collection unit also uses an automatic translation function to translate conversation content in different languages ​​in real time and record it in a medical record. For example, conversations with foreign customers are instantly translated and recorded. In this way, conversation content in different languages ​​can be automatically translated and a multilingual medical record can be generated, making it possible to accommodate customers who speak different languages.

[0063] The conversation collection unit can analyze the customer's emotions regarding what is being said and generate questions to elicit positive emotions. For example, the conversation collection unit uses a generation AI to analyze the customer's emotions regarding what is being said and generates questions to elicit positive emotions. For example, it asks questions that move the customer to a positive topic. The conversation collection unit also uses an emotion estimation function to analyze the customer's emotional state and generate interactive questions to elicit positive emotions. For example, it asks questions that help the customer relax. The conversation collection unit also analyzes changes in the customer's emotions in real time and dynamically generates questions to elicit positive emotions. For example, it asks questions that move the customer from a negative topic to a positive topic. This enables better customer service by generating questions that elicit positive emotions in customers.

[0064] The summarization unit can also reference the customer's past medical record information to generate a more accurate summary. For example, the generation AI of the summarization unit references the customer's past medical record information and summarizes the content of the current conversation. For example, it generates a summary taking into account past concerns and requests. The summarization unit also summarizes the content of the current conversation more accurately based on the customer's past medical record information. For example, it generates a summary that reflects past treatment details and advice. The summarization unit also analyzes past medical record information and extracts important points when summarizing the content of the current conversation. For example, it extracts and summarizes important keywords based on past medical record information. In this way, by referencing past medical record information, a more accurate summary can be generated.

[0065] The summarization unit can automatically tag the summary content to improve searchability. For example, the generation AI automatically tags the summary content to improve the searchability of medical records. For example, tags such as "hair concerns" and "treatment details" are attached. The summarization unit also extracts related keywords from the summary content and automatically tags them. For example, specific keywords such as "dryness" and "bedhead" are attached as tags. The summarization unit also strengthens the search function of medical records based on the tagged summary content. For example, tags can be used to quickly search past medical records. In this way, the searchability of medical records is improved by automatically tagging the summary content.

[0066] The summarization unit uses the emotion estimation function to highlight emotional elements included in the summary content and clearly record the customer's emotional state. For example, the summarization unit uses a generation AI to highlight emotional elements included in the summary content and record them in the medical record. For example, it highlights emotional elements such as "the customer was very satisfied." The summarization unit also uses the emotion estimation function to clearly record positive and negative emotions included in the summary content. For example, it records an emotional state such as "the customer was feeling anxious." The summarization unit also highlights emotional elements included in the summary content so that it can be used as a reference for the next customer service session. For example, it records an emotional state such as "the customer was relaxed" in the medical record. In this way, by highlighting emotional elements, the customer's emotional state can be clearly recorded.

[0067] The medical record generation unit can share the summarized medical record information with other staff members, allowing the entire team to utilize the customer information. The medical record generation unit, for example, shares the summarized medical record information with other staff members, allowing the entire team to utilize the customer information. For example, it stores the medical records in a shared folder that can be accessed by all staff members. The medical record generation unit also builds a system that allows the medical record information summarized by the generation AI to be shared among staff members in real time. For example, it introduces a cloud-based medical record management system. The medical record generation unit also makes it easy for other staff members to refer to the summarized medical record information. For example, it displays the medical record information on a staff dashboard. This allows the entire team to utilize the customer information by sharing the summarized medical record information with other staff members.

[0068] The medical record generation unit visualizes the summary content and displays it in graphs and charts, making it easier to understand visually. For example, the generation AI in the medical record generation unit visualizes the summary content and displays it in graphs and charts. For example, it displays the customer's concerns and requests in pie charts or bar graphs. The medical record generation unit also visualizes the summarized medical record information to make it easier for staff to understand visually. For example, it displays treatment history and advice content in timeline format. The medical record generation unit also makes it possible to grasp customer information at a glance based on the visualized summary content. For example, it displays the customer's emotional state and treatment history in graphs. In this way, visualizing the summary content makes it easier to understand visually.

[0069] The medical record generation unit uses the emotion estimation function to collect the emotional reactions of staff members to the summary content, which can be used to improve the medical record. For example, the medical record generation unit uses a generation AI to collect the emotional reactions of staff members to the summary content, which can be used to improve the medical record. For example, the emotions felt by staff members regarding the summary content are recorded. The medical record generation unit also uses the emotion estimation function to analyze the emotional reactions of staff members and identify areas for improvement in the medical record. For example, it improves summary content that the staff members are dissatisfied with. The medical record generation unit also improves the quality of the summary content based on the emotional reactions of staff members. For example, it improves the medical record by referring to summary content that has a high number of positive emotional reactions. In this way, collecting the emotional reactions of staff members can be used to improve the medical record.

[0070] The system can use voice recognition to analyze a customer's voiceprint and verify their identity. For example, the system uses generation AI to analyze a customer's voiceprint using voice recognition technology to verify their identity. For example, it analyzes the voiceprint when a customer speaks their name to verify their identity. The system can also register a customer's voiceprint data in advance and verify the voiceprint when the customer visits the store to verify their identity. For example, it registers voiceprint data when making a reservation and verifies it when the customer visits the store. The system can also use voice recognition technology to analyze a customer's voiceprint in real time to verify their identity. For example, it analyzes the voiceprint every time a customer speaks to verify their identity. This makes it possible to generate and manage accurate medical records by using voice recognition to analyze a customer's voiceprint and verify their identity.

[0071] The system can verify the customer's identity by using facial recognition to match the customer's facial photograph. For example, the system uses facial recognition technology with a generation AI to verify the customer's identity. For example, the system compares a facial photograph taken with a camera when the customer visits the store with a pre-registered facial photograph. The system can also register a customer's facial photograph in advance and perform facial recognition when the customer visits the store to verify the customer's identity. For example, a facial photograph is registered when a reservation is made and compared when the customer visits the store. The system can also use facial recognition technology to analyze a customer's facial photograph in real time to verify the customer's identity. For example, a facial photograph is taken with a camera when a customer enters the store and is immediately compared. This allows the system to verify the customer's identity by using facial recognition to match the customer's facial photograph, making it possible to create and manage accurate medical records.

[0072] The system can improve the accuracy of identity verification by using the emotion estimation function to analyze the emotional state of a customer. For example, the system uses the emotion estimation function to analyze the emotional state of a customer to improve the accuracy of identity verification. For example, the system verifies the customer's identity by analyzing whether the customer is relaxed or nervous. The system also analyzes the customer's emotional state to detect fraudulent behavior during identity verification. For example, if a customer appears unnaturally nervous, it detects the possibility of fraudulent behavior. The system also uses the emotion estimation function to analyze the customer's emotional state in real time to improve the accuracy of identity verification. For example, it verifies the customer's identity by analyzing the emotional state when the customer speaks. In this way, using the emotion estimation function to analyze the customer's emotional state and improve the accuracy of identity verification makes it possible to generate and manage accurate medical records.

[0073] The system can also refer to a customer's past store visit history and purchase history to perform more accurate identity verification. For example, the system uses generation AI to refer to a customer's past store visit history and purchase history to verify identity. For example, it verifies identity by comparing past store visit history with current information. The system also improves the accuracy of identity verification based on the customer's purchase history. For example, it compares products and services purchased in the past with current information. The system also references past store visit history and purchase history to detect fraudulent activity during identity verification. For example, if there is information that does not match the past history, it detects the possibility of fraudulent activity. This enables more accurate identity verification by referring to a customer's past store visit history and purchase history.

[0074] The system verifies the customer's identity in advance via a smartphone app, simplifying the procedures when the customer visits the store. For example, the system uses a smartphone app to build a system that verifies the customer's identity in advance. For example, a facial photo and voiceprint are registered in the app, and these are compared when the customer visits the store. The system also simplifies the procedures when the customer visits the store by having the customer verify their identity in advance via a smartphone app. For example, the system allows the customer to complete identity verification via the app, enabling smooth entry when the customer visits the store. The system also reduces waiting time when the customer visits the store by verifying the customer's identity in advance via a smartphone app. For example, the system allows the customer to complete identity verification via the app, enabling the customer to receive service immediately when the customer visits the store. In this way, the system simplifies the procedures when the customer visits the store by verifying the customer's identity in advance via a smartphone app.

[0075] The system can use the emotion estimation function to design an interface to reduce the stress felt by customers during identity verification. For example, the system uses the emotion estimation function to design an interface to reduce the stress felt by customers during identity verification. For example, the system displays relaxing music or images. The system also analyzes the emotional state of the customer and provides an interface to reduce stress. For example, the system displays a guide message to help the customer relax. The system also uses the emotion estimation function to monitor the customer's stress level in real time and dynamically adjusts the interface to reduce stress. For example, if the customer is nervous, the system displays relaxing content. In this way, the burden on the customer can be reduced by using the emotion estimation function to design an interface to reduce the stress felt by customers.

[0076] When extracting advice for a customer, the system can also refer to the customer's past medical record information and advice history. For example, the generation AI in the system references the customer's past medical record information and advice history to extract current advice. For example, the current advice is generated based on the content of past advice. The system also customizes the current advice based on the customer's past medical record information. For example, the system provides advice taking into account the content of past treatments and advice history. The generation AI in the system also analyzes past medical record information and advice history to identify important points when extracting current advice. For example, it extracts important keywords based on the content of past advice and provides advice. This makes it possible to provide more appropriate advice by referring to the customer's past medical record information and advice history.

[0077] The system can customize the advice content to suit the customer's lifestyle and preferences. For example, the generation AI analyzes the customer's lifestyle and preferences and customizes the advice content. For example, it provides advice that suits the customer's lifestyle and preferences. The system also personalizes the advice content based on customer preference data. For example, it provides advice taking into account the customer's preferred styles and products. The generation AI also analyzes the customer's lifestyle and preferences in real time and dynamically customizes the advice content. For example, it provides advice that suits the customer's current situation. This allows the system to provide more appropriate advice by customizing the advice content to suit the customer's lifestyle and preferences.

[0078] The system can use the emotion estimation function to prioritize the extraction of advice to which the customer has the most positive response. For example, the system uses the emotion estimation function to extract advice to which the customer has the most positive response. For example, it prioritizes providing advice that makes the customer feel happy or satisfied. The system also analyzes the customer's emotional responses and extracts advice that has a high number of positive responses. For example, it identifies advice that has a high number of positive responses based on past data. The system also uses the emotion estimation function to monitor the customer's emotional responses in real time and dynamically extracts advice that has a high number of positive responses. For example, it adjusts the advice according to changes in the customer's emotions. This improves customer satisfaction by prioritizing the extraction of advice to which the customer has the most positive response.

[0079] The system can visually explain the advice content using videos and images. For example, the system uses a generative AI to visually explain the advice content using videos and images. For example, it may explain how to style a hairstyle using a video. The system may also visually explain the advice content using images and illustrations. For example, it may show skin care steps using images. The system may also use videos and images to make the advice content visually easier to understand. For example, it may explain the treatment steps in a video so that the customer can recreate them at home. In this way, the advice content is explained visually using videos and images, making it easier for customers to understand.

[0080] The system can provide advice as a step-by-step guide so that the customer can put the advice into practice at home. For example, the system uses a generative AI to provide advice as a step-by-step guide. For example, hair care procedures are explained by breaking them down into specific steps. The system also provides the advice content as a detailed guide so that the customer can put the advice into practice at home. For example, skin care procedures are explained step by step. The system also uses a step-by-step guide to make it easier for the customer to put the advice into practice. For example, treatment procedures are explained by breaking them down into specific steps so that the customer can reproduce them at home. In this way, by providing advice as a step-by-step guide, it becomes easier for the customer to put the advice into practice at home.

[0081] The system can use the emotion estimation function to collect the customer's emotional reactions to advice and reflect them in the next advice. For example, the generation AI in the system uses the emotion estimation function to collect the customer's emotional reactions to advice and reflect them in the next advice. For example, the system will provide advice that satisfied the customer again next time. The system also analyzes the customer's emotional reactions and reflects them in the next advice. For example, the system will provide advice to which the customer responded positively again next time. The system also uses the emotion estimation function to monitor the customer's emotional reactions in real time and reflect them in the next advice. For example, the system can adjust the advice according to changes in the customer's emotions. In this way, the system can provide more appropriate advice by collecting the customer's emotional reactions to advice and reflecting them in the next advice.

[0082] When generating a thank-you email for a visit, the system can also refer to the customer's past visit history and advice history. For example, the generation AI of the system references the customer's past visit history and advice history to generate a thank-you email for a visit. For example, the system creates an email based on the customer's past treatment details and advice. The system also generates a personalized thank-you email based on the customer's past visit history. For example, the system creates an email that reflects the service details from past visits. The system also references the customer's past advice history to include the advice details in the thank-you email for the visit. For example, the system creates an email that reiterates past advice. This allows the system to provide a more personalized email by referencing the customer's past visit history and advice history when generating a thank-you email for a visit.

[0083] The system can customize email content to suit a customer's lifestyle and preferences. For example, the system's generation AI analyzes a customer's lifestyle and preferences and customizes the email content. For example, it creates an email introducing products and services that match the customer's preferences. The system also generates personalized thank-you emails based on customer preference data. For example, it creates an email that reflects the customer's preferred style and products. The system also analyzes a customer's lifestyle and preferences in real time and dynamically customizes the email content. For example, it creates an email that matches the customer's current situation. This allows the system to provide more personalized emails by customizing the email content to suit the customer's lifestyle and preferences.

[0084] The system can use the emotion estimation function to generate email content that customers will have the most positive reaction to. For example, the system uses the emotion estimation function with a generation AI to generate email content that customers will have the most positive reaction to. For example, it prioritizes including content that makes customers feel happy or satisfied. The system also analyzes customers' emotional reactions and generates email content that has a high rate of positive reactions. For example, it identifies content that has a high rate of positive reactions based on past data. The system also uses the emotion estimation function to monitor customers' emotional reactions in real time and dynamically generate email content that will have the most positive reaction. For example, it adjusts the email content according to changes in the customer's emotions. This improves customer satisfaction by generating email content that customers will have the most positive reaction to.

[0085] The system can visually explain the contents of an email using videos and images. For example, the system uses a generative AI to visually explain the contents of an email using videos and images. For example, a video explaining how to style a hairstyle. The system also visually explains the contents of an email using images and illustrations. For example, images showing skin care procedures. The system also uses videos and images to make the contents of an email easier to understand visually. For example, a video explaining the steps of a treatment so that the customer can recreate it at home. In this way, the contents of an email can be visually explained using videos and images, making it easier for customers to understand.

[0086] The system can provide emails as step-by-step guides so that customers can practice at home. For example, the system uses a generative AI to provide emails as step-by-step guides. For example, hair care procedures are explained by breaking them down into specific steps. The system also provides the email content as a detailed guide so that customers can practice at home. For example, skin care procedures are explained step by step. The system also uses step-by-step guides to make it easier for customers to practice the email content. For example, treatment procedures are explained by breaking them down into specific steps so that customers can reproduce them at home. In this way, providing emails as step-by-step guides makes it easier for customers to practice at home.

[0087] The system can use the emotion estimation function to collect the customer's emotional reactions to emails and reflect them in the content of the next email. For example, the system uses the generative AI to collect the customer's emotional reactions to emails and reflect them in the content of the next email. For example, the system will provide content that satisfied the customer again next time. The system also analyzes the customer's emotional reactions and reflects them in the content of the next email. For example, the system will provide content that the customer responded positively to again next time. The system also uses the emotion estimation function to monitor the customer's emotional reactions in real time and reflect them in the content of the next email. For example, the system can adjust the email content according to changes in the customer's emotions. In this way, by collecting the customer's emotional reactions to emails and reflecting them in the content of the next email, it is possible to provide more appropriate emails.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The automatic medical record generation system can further include a health data collection unit that monitors the health condition of customers. For example, sensors can be installed to check the health condition of customers when they visit the store, collecting data such as body temperature, blood pressure, and heart rate. The health data collection unit can also collect data from wearable devices provided by customers and record it in the medical record. For example, it can collect heart rate data and sleep data from a smartwatch. The health data collection unit can also monitor the customer's health condition in real time and issue an alert if an abnormality is detected. For example, it can notify staff if the heart rate is abnormally high. This makes it possible to monitor the customer's health condition and generate more detailed medical records.

[0090] The automatic medical record generation system can further include a preference analysis unit that analyzes customer preferences and past purchase history. For example, it collects data on products and services that customers have purchased in the past and analyzes their preferences. The preference analysis unit can also collect data on products and services that customers have viewed online and analyze their preferences. For example, it can estimate preferences based on products that customers have viewed on websites. The preference analysis unit can also customize products and services to be suggested for the next store visit based on the customer's preferences. For example, it can make suggestions based on the customer's preferred style and color. This allows for an analysis of customer preferences and the provision of more personalized services.

[0091] The automatic medical record generation system can further include a lifestyle collection unit that collects information about the customer's lifestyle. For example, it collects information about the customer's daily exercise and eating habits. The lifestyle collection unit can also collect data from applications and devices used by the customer to analyze the customer's lifestyle. For example, it can collect exercise data from a fitness app and dietary data from a food recording app. The lifestyle collection unit can also provide health and beauty advice based on the customer's lifestyle. For example, it can suggest exercise to a customer who is not getting enough exercise. This allows the system to collect information about the customer's lifestyle and provide more appropriate advice.

[0092] The automatic medical record generation system can further include a stress monitoring unit that monitors the stress level of customers. For example, a sensor can be installed to measure the stress level of customers when they visit the store. The stress monitoring unit can also collect data from wearable devices provided by customers to monitor stress levels. For example, it can collect heart rate variability data from a smartwatch. The stress monitoring unit can also monitor the stress level of customers in real time and issue an alert if an abnormality is detected. For example, it can notify staff if the stress level is high. This makes it possible to monitor the stress level of customers and generate more detailed medical records.

[0093] The automatic medical record generation system can further include a sleep monitoring unit that monitors the sleep state of the customer. For example, it can collect data from a wearable device provided by the customer to monitor the sleep state. The sleep monitoring unit can also collect data from a sleep tracking app used by the customer and analyze the sleep state. For example, it can collect sleep data from a smartphone app. The sleep monitoring unit can also monitor the sleep state of the customer in real time and issue an alert if an abnormality is detected. For example, it can notify staff if the quality of sleep is low. This makes it possible to monitor the sleep state of the customer and generate a more detailed medical record.

[0094] The automatic medical record generation system can also analyze the emotional state of the customer and provide relaxing music or images based on the estimated emotions. For example, if the customer is nervous, relaxing music can be played. Also, if the customer is feeling stressed, relaxing images can be displayed. For example, images of natural scenery or the ocean can be displayed. The system can also analyze the emotional state of the customer and provide a relaxing environment based on the estimated emotions. For example, the color and brightness of the lighting can be adjusted. In this way, analyzing the emotional state of the customer and providing a relaxing environment makes it possible to provide more comfortable customer service.

[0095] The automatic medical record generation system can also analyze the emotional state of the customer and provide an appropriate aroma based on the estimated emotion. For example, if the customer wants to relax, a lavender aroma can be provided. Alternatively, if the customer wants to concentrate, a peppermint aroma can be provided. For example, if the customer is feeling stressed, a chamomile aroma can be provided. The system can also analyze the customer's emotional state and adjust the type and strength of the aroma based on the estimated emotion. For example, the strength of the aroma can be adjusted to help the customer feel relaxed. This allows for a more comfortable customer service experience by analyzing the customer's emotional state and providing an appropriate aroma.

[0096] The automatic medical record generation system can also analyze the emotional state of the customer and serve an appropriate drink based on the estimated emotion. For example, if the customer wants to relax, herbal tea can be served. Also, if the customer needs energy, coffee can be served. For example, if the customer is feeling stressed, chamomile tea can be served. The system can also analyze the customer's emotional state and adjust the type and temperature of the drink based on the estimated emotion. For example, a hot drink can be served to help the customer relax. This allows for more comfortable customer service by analyzing the customer's emotional state and serving an appropriate drink.

[0097] The automatic medical record generation system can also analyze the customer's emotional state and suggest appropriate activities based on the estimated emotions. For example, if a customer wants to relax, it can suggest yoga or meditation. Also, if a customer needs energy, it can suggest light exercise. For example, if a customer is feeling stressed, it can suggest deep breathing and stretching. It can also analyze the customer's emotional state and adjust the type and intensity of activity based on the estimated emotions. For example, it can suggest light activities to help customers relax. In this way, analyzing the customer's emotional state and suggesting appropriate activities makes it possible to provide more comfortable customer service.

[0098] The automatic medical record generation system can also analyze the emotional state of the customer and provide appropriate advice based on the estimated emotions. For example, if the customer wants to relax, it can provide advice on ways to relax. Also, if the customer needs energy, it can provide advice on ways to increase their energy. For example, if the customer is feeling stressed, it can provide advice on ways to relieve stress. It can also analyze the customer's emotional state and adjust the content and method of advice based on the estimated emotions. For example, it can provide advice in gentle words to help the customer relax. In this way, analyzing the customer's emotional state and providing appropriate advice makes it possible to provide more comfortable customer service.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The conversation collection unit collects the content of conversations with customers. For example, face-to-face conversations are recorded using a high-sensitivity microphone and saved as audio data. Telephone conversations are saved as audio data using a call recording function. The content of online chats is automatically collected as a chat log and saved as text data. Step 2: The summarization unit summarizes the conversation content collected by the conversation collection unit. For example, the generation AI may use a text generation AI (e.g., LLM) to concisely summarize the conversation content. The generation AI may also use a multimodal generation AI to summarize the conversation content. The generation AI may use keyword extraction technology to pick out particularly important information from the conversation content and use that information to create a summary. Step 3: The medical record generation unit records the content summarized by the summarization unit as a medical record for each customer. For example, the medical record generation unit saves the summarized content as a text file and records it as a medical record. The summarized content can also be saved as an image file and recorded as a medical record. The summarized content can also be saved in a database and recorded as a medical record.

[0101] 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.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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 a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification 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 model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, 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 is 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 entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] 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.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text data. 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 model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, 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 is 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 entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0118] 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.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0130] 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.

[0131] 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.

[0132] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text data. 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 model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, 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 is 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 entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] 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.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0146] 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.

[0147] 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.

[0148] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text data. 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 model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, 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 is 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 entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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."

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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. [Explanation of symbols]

[0168] 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 conversation collection unit that collects conversation contents with customers; a summarizing unit that summarizes the conversation content collected by the conversation collecting unit; a medical record generating unit that records the content summarized by the summarizing unit as a medical record for each customer; A system characterized by:

2. The conversation collection unit Analyzing the tone of voice and speaking rate of the customer to estimate and record the emotional state of the customer 2. The system of claim 1.

3. The conversation collection unit The camera analyzes the customer's facial expressions and gestures to collect non-verbal information.

2. The system of claim 1.

4. The conversation collection unit Analyze the customer's emotions regarding what they are saying in real time and record changes in those emotions.

2. The system of claim 1.

5. The conversation collection unit Collect not only audio but also text chat and email content 2. The system of claim 1.

6. The conversation collection unit Automatically translate conversations in different languages ​​and generate multilingual medical records 2. The system of claim 1.

7. The conversation collection unit Analyze the customer's feelings about what they are saying and generate questions to elicit positive emotions 2. The system of claim 1.

Images