System

Abstract

An object of the system according to the embodiment is to provide primary medical advice on a symptom of a customer and alleviate anxiety.SOLUTION: A system according to an embodiment includes a data collecting unit, a symptom input unit, an advice providing unit, a purchase link providing unit, a feedback collecting unit, and a reward providing unit. The data collection unit collects data related to symptoms of a customer using a camera or a sensor. The symptom input unit allows the customer to directly input his / her symptoms. The advice providing unit provides medical advice based on the data collected by the data collection unit and the symptom input unit. The purchase link providing unit provides a purchase link of a related product based on the advice provided by the advice providing unit. The feedback collection unit collects feedback on an effect after the customer executes the advice. The reward providing unit provides a reward to the customer based on the feedback collected by the feedback collecting unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately provide means to alleviate customers' anxiety about symptoms on holidays and at night, and there is room for improvement.

[0005] The system according to the embodiment aims to provide primary medical advice for the customer's symptoms and ease their anxiety. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, a symptom input unit, an advice providing unit, a purchase link providing unit, a feedback collection unit, and a reward providing unit. The data collection unit collects data on a customer's symptoms using a camera or a sensor. The symptom input unit allows the customer to directly input their symptoms. The advice providing unit provides medical advice based on the data collected by the data collection unit and the symptom input unit. The purchase link providing unit provides a purchase link for a related product based on the advice provided by the advice providing unit. The feedback collection unit collects feedback on the effect after the customer implements the advice. The reward providing unit provides a reward to the customer based on the feedback collected by the feedback collection unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide first-line medical advice for the customer's symptoms and ease their anxiety. [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 primary medical advice system according to an embodiment of the present invention is a system in which a generative AI provides medical advice using functions such as cameras, sensors, and direct input of symptoms, etc. This enables the primary medical advice system to alleviate customer anxiety and provide appropriate medical advice even on holidays and at night.

[0029] A primary medical advice system according to an embodiment includes a data collection unit, a symptom input unit, an advice providing unit, a purchase link providing unit, a feedback collection unit, and a reward providing unit. The data collection unit collects data on a customer's symptoms using a camera and sensors. For example, images of skin rashes and swellings are taken with a camera, and biometric data such as body temperature and heart rate are acquired with a sensor. The data collection unit then inputs this data into the generation AI. The symptom input unit allows the customer to directly input their symptoms. For example, specific symptoms such as "I have a headache" or "I have a sore throat" can be input. The advice providing unit uses the generation AI to provide medical advice based on the data collected by the data collection unit and the symptom input unit. For example, the advice provided may be specific advice such as "These symptoms may be a cold. Take over-the-counter cold medicine and get plenty of rest." The purchase link providing unit provides a purchase link for a related product based on the advice provided by the advice providing unit. For example, the link may be presented in the form of "This medicine is effective for these symptoms. You can purchase it here." The feedback collection unit collects feedback on the effectiveness of the advice after the customer follows it. For example, a function is provided for inputting feedback such as, "I took the medicine as advised and my symptoms improved." The reward providing unit provides rewards to customers based on the feedback collected by the feedback collecting unit. For example, rewards such as points are awarded. As a result, the primary medical advice system according to the embodiment collects data on the customer's symptoms, provides appropriate medical advice, and provides feedback on the effectiveness of the advice, thereby easing customer anxiety and increasing the reliability of the advice provided by AI.

[0030] The data collection unit converts data collected by cameras and sensors into 3D models, enabling more detailed symptom analysis. For example, the data collection unit converts images of skin rashes or swellings taken with a camera into 3D models to perform a three-dimensional analysis of the symptoms. This allows for a detailed understanding of the depth and spread of the rash. The data collection unit also integrates biometric data, such as body temperature and heart rate, acquired by sensors into the 3D model to analyze overall health. For example, it visually displays fluctuations in body temperature and heart rate rhythm. Furthermore, the data collection unit uses the 3D model to analyze the progression of symptoms over time. For example, it displays the spread of the rash and changes in swelling over time to track the progression of symptoms. This conversion into a 3D model enables a three-dimensional analysis of symptoms, enabling more detailed medical advice to be provided.

[0031] The data collection unit can integrate a customer's past health data with real-time data to analyze long-term health trends. For example, the data collection unit integrates a customer's past health data (e.g., past diagnostic results and treatment history) with data collected in real time to analyze long-term health trends. For example, it compares past body temperature fluctuations with current body temperature. The data collection unit also performs analysis based on past health data to identify the cause of current symptoms. For example, it references the time and circumstances in which similar symptoms occurred in the past and evaluates their relevance to current symptoms. Furthermore, the data collection unit analyzes long-term health trends and provides preventive medical advice. For example, it identifies trends in seasonal symptoms from past data and suggests preventive measures. In this way, by integrating past health data with real-time data, long-term health trends can be analyzed and preventive medical advice can be provided.

[0032] The data collection unit can display data collected by cameras and sensors on home smart devices to promote self-diagnosis. For example, the data collection unit can display images of skin rashes or swellings taken with a camera on the smart mirror to enable customers to self-diagnose. For example, the spread and color changes of the rash can be checked in real time. The data collection unit can also display biometric data obtained by sensors, such as body temperature and heart rate, on the smart mirror to enable customers to understand their own health status. For example, it can display graphs of body temperature fluctuations and heart rate rhythms. Furthermore, the data collection unit's generative AI can provide self-diagnosis advice based on the data displayed on the smart mirror. For example, it can analyze images of a rash and suggest possible symptoms. In this way, displaying data on home smart devices makes it easier for customers to self-diagnose.

[0033] The data collection unit can add different sensors to collect more diversified data. For example, the data collection unit can add an odor sensor to analyze the customer's body odor and breath. For example, it can detect odors associated with specific illnesses and help identify symptoms. The data collection unit can also integrate data from the odor sensor and camera to perform more detailed symptom analysis. For example, it can simultaneously analyze skin rashes and changes in body odor to identify the cause of symptoms. Furthermore, the data collection unit can input data from the odor sensor into a generative AI to provide medical advice based on the odor. For example, if a specific odor is detected, it can suggest the possibility of a related illness. By adding different sensors, more diversified data collection becomes possible, allowing for more detailed medical advice to be provided.

[0034] The symptom input unit can use natural language processing technology to analyze in detail the symptoms entered by the customer and provide specific medical advice. For example, the symptom input unit uses natural language processing technology to analyze the symptoms entered by the customer and provide detailed medical advice. For example, when an input such as "I have a headache" is made, the type and cause of the headache are identified. The symptom input unit also uses natural language processing technology to automatically extract related symptoms and medical history from the customer's symptom input and provide comprehensive medical advice. For example, when an input such as "I have a sore throat" is made, the symptom input unit refers to the customer's past cold history. Furthermore, the symptom input unit analyzes the symptoms entered by the customer and suggests specific treatments and medications. For example, when an input such as "I have a stomachache" is made, the symptom input unit suggests the possibility of indigestion or gastritis and suggests appropriate medications. In this way, by using natural language processing technology, the symptoms entered by the customer can be analyzed in detail and more specific medical advice can be provided.

[0035] The symptom input unit can search for similar past cases based on the symptoms entered by the customer and provide reference information. The symptom input unit, for example, searches a database for similar past cases based on the symptoms entered by the customer and provides reference information. For example, in response to an input such as "I have a rash," past cases of rash are presented. The symptom input unit also analyzes the customer's symptom input and extracts and provides treatments and effects from similar past cases. For example, in response to an input such as "I have a persistent cough," treatments for past cough cases are presented. Furthermore, the symptom input unit provides statistical data on similar past cases based on the symptoms entered by the customer. For example, in response to an input such as "I have a headache," the frequency of occurrence of past headache cases and the effects of treatment are presented. In this way, by searching for similar past cases and providing reference information, it is possible to provide useful information to the customer.

[0036] The symptom input unit can use voice recognition technology to allow customers to input symptoms by voice. The symptom input unit, for example, introduces voice recognition technology that allows customers to input symptoms by voice. For example, simply saying "I have a headache" automatically inputs the symptoms. The symptom input unit also uses voice recognition technology to convert the customer's symptom input into text and input it into the generation AI. For example, if the customer says "I have a sore throat," the content is converted into text and analyzed. Furthermore, the symptom input unit uses voice recognition technology to allow multiple symptoms to be input at once. For example, if the customer says "I have a headache and a sore throat," both symptoms are automatically input. In this way, the use of voice recognition technology allows customers to input symptoms by voice, saving time and effort.

[0037] The symptom input unit can gamify symptom input, allowing customers to enjoy entering their symptoms. For example, the symptom input unit gamifies symptom input and provides an interface that allows customers to enjoy entering their symptoms. For example, a game can be developed that uses characters to enter symptoms. The symptom input unit can also format symptom input as a quiz, allowing customers to enter their symptoms by answering questions. For example, a format in which customers answer questions such as, "Which part hurts?" The symptom input unit can also implement a points system for symptom input, where points are accumulated each time an input is made. For example, points can be accumulated by accurately entering symptoms, and rewards can be obtained. In this way, gamifying symptom input allows customers to enjoy entering their symptoms.

[0038] The advice providing unit can improve reliability by using the generating AI to refer to past medical data and research papers. For example, the advice providing unit adds a function to refer to past medical data to the advice provided by the generating AI. For example, it provides advice based on past diagnosis results and treatment history. The advice providing unit also adds a function to refer to the latest research papers to the advice provided by the generating AI. For example, it provides advice based on the latest medical research. Furthermore, the advice providing unit integrates past medical data and research papers to improve the reliability of the advice provided by the generating AI. For example, it provides advice that combines past data and the latest research. In this way, by referring to past medical data and research papers, it is possible to improve the reliability of the advice provided by the generating AI.

[0039] The advice providing unit can use the generation AI to provide advice that takes into account local medical resources. For example, the advice providing unit adds a function that takes into account local medical resources to the advice provided by the generation AI. For example, it provides advice based on information about nearby pharmacies and hospitals. The advice providing unit also references a local medical resource database and reflects this in the advice provided by the generation AI. For example, it may suggest medicines that can be purchased at nearby pharmacies. Furthermore, the generation AI works with local medical institutions to provide advice that takes into account local medical resources. For example, it may recommend a consultation at a nearby hospital. This makes it possible to provide more practical and appropriate medical advice by taking into account local medical resources.

[0040] The advice providing unit can use the generation AI to automatically translate the advice it provides into different languages, promoting international use. For example, the advice providing unit adds a function to automatically translate the advice provided by the generation AI and provide it in different languages. For example, it translates into multiple languages ​​such as English, French, and Chinese. The advice providing unit also provides the automatically translated advice on a multilingual platform to promote international use. For example, it allows users of different languages ​​to receive the same advice. Furthermore, the advice providing unit collects feedback from an international perspective based on the translated advice and improves the quality of the advice. For example, it provides advice that is appropriate for different cultures and medical systems. This allows the advice to be automatically translated into different languages, promoting international use.

[0041] The advice providing unit can use the generation AI to provide advice in visual note or video format to make it easier to understand. For example, the advice providing unit converts the advice provided by the generation AI into a visual note and displays it visually. For example, it indicates important points with diagrams or icons. The advice providing unit also provides the advice in video format to make it easier for customers to understand. For example, it explains the advice content using animations or live-action videos. Furthermore, the advice providing unit develops tools that automatically generate advice in visual note or video format to make it easier for customers to understand the advice. For example, it provides a function to visualize the advice content with drag and drop. As a result, providing advice in visual note or video format makes it easier for customers to understand.

[0042] The purchase link providing unit can analyze a customer's purchase history and develop an algorithm that recommends the most suitable product. The purchase link providing unit, for example, analyzes a customer's past purchase history and develops an algorithm that recommends the most suitable product. For example, related products are recommended based on medicines and health products purchased in the past. The purchase link providing unit also analyzes a customer's preferences and needs based on the purchase history and makes personalized product recommendations. For example, related products are recommended to customers who prefer specific brands or ingredients. Furthermore, the purchase link providing unit integrates purchase history and symptom data to develop an algorithm that recommends the most suitable product. For example, the next product to be purchased is recommended based on past symptoms and the effects of purchased medicines. This makes it possible to develop an algorithm that recommends the most suitable product by analyzing a customer's purchase history.

[0043] The purchase link providing unit can add videos to the purchase link that explain how to use the product and its effects. For example, the purchase link providing unit adds videos to the purchase link that explain how to use the product, allowing customers to use it correctly. For example, a video may explain how to take medication and precautions. The purchase link providing unit also adds videos to the purchase link that explain the effects of the product, allowing customers to understand the product's effects. For example, a video may explain the effects and side effects of medication. Furthermore, the purchase link providing unit develops a tool that automatically generates videos that explain how to use the product and its effects, and adds them to the purchase link. For example, a video may be automatically generated based on product information and embedded in the link. In this way, adding a video to the purchase link that explains how to use the product and its effects allows customers to correctly understand and use the product.

[0044] The purchase link providing unit can notify the customer of the purchase link to their smart device. For example, the purchase link providing unit may notify the customer of the purchase link to their smartphone, allowing for easy access. For example, the link may be pushed immediately after receiving the advice. The purchase link providing unit may also notify the customer of the purchase link to their smartwatch, allowing for easy access. For example, the link may be displayed on the screen of the smartwatch. Furthermore, the purchase link providing unit may utilize the notification function of the smart device to provide the purchase link in a timely manner. For example, the link may be notified within a certain period of time after the customer receives the advice. In this way, by notifying the customer of the purchase link to their smart device, the customer can easily access the purchase link.

[0045] The purchase link providing unit can add a function to share the purchase link to the customer's social media account. For example, the purchase link providing unit adds a function to share the purchase link to the customer's social media account, allowing the information to be shared with other users. For example, the purchase link providing unit posts the link on Facebook or Twitter. When the customer shares the purchase link, the purchase link providing unit automatically generates a comment explaining how to use the product and its effects. For example, the purchase link providing unit adds a comment such as, "My symptoms improved after using this medicine." Furthermore, the purchase link providing unit utilizes the sharing function on social media to promote the spread of the purchase link. For example, the purchase link providing unit can provide an incentive so that the shared link reaches many users. This allows the information to be shared with other users by sharing the purchase link on social media.

[0046] The feedback collection unit can analyze the feedback content and develop an algorithm that continuously improves the accuracy of advice. The feedback collection unit, for example, analyzes the feedback content from customers and develops an algorithm that improves the accuracy of advice. For example, it identifies areas for improvement in advice based on feedback data. The feedback collection unit also analyzes the feedback content and builds a system that continuously improves the accuracy of advice provided by the generation AI. For example, it uses the feedback data as learning data. Furthermore, the feedback collection unit analyzes the feedback content in real time and develops an algorithm that instantly improves the accuracy of advice. For example, it updates the advice every time feedback is received. This makes it possible to develop an algorithm that continuously improves the accuracy of advice by analyzing the feedback content.

[0047] The feedback collection unit can provide individual advice to customers based on the feedback. The feedback collection unit, for example, builds a system that provides individual advice based on feedback from customers. For example, it analyzes the feedback content and provides the most suitable advice to the customer. The feedback collection unit also evaluates the customer's symptoms and treatment effects based on the feedback data and provides individual advice. For example, it refers to the feedback content and adjusts the next advice. Furthermore, the feedback collection unit develops a system that personalizes advice to customers based on feedback. For example, it learns the feedback content and provides advice that meets the customer's needs. As a result, by providing individual advice based on feedback, the accuracy of advice to customers can be improved.

[0048] The feedback collection unit can link the feedback with the customer's health management app to support comprehensive health management. The feedback collection unit, for example, links the feedback data with the customer's health management app to build a system that supports comprehensive health management. For example, the feedback content is automatically reflected in the health management app. The feedback collection unit also links with the health management app to provide comprehensive health advice based on the feedback data. For example, it provides advice on diet and exercise based on the feedback content. Furthermore, the feedback collection unit integrates the feedback data with the health management app to develop a system that comprehensively evaluates the customer's health condition. For example, it calculates a health score based on the feedback content. In this way, by linking the feedback with the health management app, comprehensive health management can be supported.

[0049] The feedback collection unit can automatically add the feedback to the customer's medical record and share it with the medical institution. The feedback collection unit, for example, builds a system that automatically adds feedback data to the customer's medical record and shares it with the medical institution. For example, the feedback content is automatically reflected in the electronic medical record. The feedback collection unit also works with the medical institution to provide comprehensive medical advice based on the feedback data. For example, the doctor will provide advice at the next appointment based on the feedback content. Furthermore, the feedback collection unit integrates the feedback data into the medical record and develops a system that comprehensively evaluates the customer's health condition. For example, the treatment plan is adjusted based on the feedback content. In this way, feedback can be automatically added to the medical record and shared with the medical institution, allowing comprehensive medical advice to be provided.

[0050] The reward provision unit can analyze sales incentive data and identify the most effective sales strategy. For example, the reward provision unit analyzes sales incentive data and develops an algorithm to identify the most effective sales strategy. For example, it identifies effective incentives based on past sales data. The reward provision unit also analyzes customer purchasing behavior based on the sales incentive data and proposes an optimal sales strategy. For example, it evaluates whether a specific incentive increases purchasing motivation. Furthermore, the reward provision unit analyzes sales incentive data in real time and builds a system to instantly identify effective sales strategies. For example, it monitors the effects of incentives in real time. In this way, the most effective sales strategy can be identified by analyzing the sales incentive data.

[0051] The reward providing unit can utilize the sales incentive data to optimize marketing campaigns. For example, the reward providing unit analyzes the sales incentive data and builds a system that utilizes it to optimize marketing campaigns. For example, it adjusts the content of the campaign based on the effectiveness of the incentive. The reward providing unit also analyzes customer purchasing behavior based on the sales incentive data and proposes optimal marketing campaigns. For example, it evaluates whether a specific incentive will increase purchasing motivation. Furthermore, the reward providing unit analyzes the sales incentive data in real time and builds a system that instantly identifies effective marketing campaigns. For example, it monitors the effectiveness of incentives in real time. In this way, by utilizing the sales incentive data to optimize marketing campaigns, effective campaigns can be implemented.

[0052] The reward provision unit can link sales incentives with customer loyalty programs to build long-term customer relationships. For example, the reward provision unit links sales incentives with customer loyalty programs to build a system for building long-term customer relationships. For example, the incentives are awarded as loyalty points. The reward provision unit also links with loyalty programs to analyze customer purchasing behavior based on sales incentives. For example, it evaluates the impact of awarding loyalty points on purchasing motivation. Furthermore, the reward provision unit integrates sales incentives with loyalty programs to develop a system for comprehensively evaluating customer purchasing behavior. For example, it analyzes the effects of incentives and loyalty points simultaneously. In this way, by linking sales incentives with loyalty programs, long-term customer relationships can be built.

[0053] The reward providing unit can add a function for sharing sales incentives on customers' social media accounts. For example, the reward providing unit adds a function for sharing sales incentives on customers' social media accounts, allowing information to be shared with other users. For example, the reward providing unit posts incentive information on Facebook or Twitter. When a customer shares a sales incentive, the reward providing unit automatically generates a comment explaining the content and effect of the incentive. For example, the reward providing unit adds a comment such as "This incentive helped me get a good deal on my purchase." Furthermore, the reward providing unit utilizes a sharing function on social media to promote the spread of sales incentives. For example, the reward providing unit provides incentives so that the shared incentive information reaches many users. In this way, by sharing the sales incentive on social media, the information can be shared with other users.

[0054] The system can develop data collection and analysis algorithms to address new medical fields. For example, the system develops data collection and analysis algorithms to address new medical fields. For example, an algorithm is built to collect and analyze psychiatric symptom data. The system also develops data collection and analysis algorithms to address the dental field. For example, an algorithm is built to collect and analyze dental image data. Furthermore, the system integrates data collection and analysis algorithms to address new medical fields and builds a system that provides comprehensive medical advice. For example, psychiatric and dental data is integrated to provide comprehensive advice. This allows the application range of the system to be expanded by developing data collection and analysis algorithms to address new medical fields.

[0055] The system can add services to address new industries. For example, the system adds a service to address new industries. For example, the system provides training plans and exercise advice to address the fitness field. The system also adds a service to address the nutrition field. For example, the system provides meal plans and nutrition advice. Furthermore, the system integrates services to address new industries to build a system that supports comprehensive health management. For example, the system integrates fitness and nutrition data to provide comprehensive advice. This allows the system's scope of application to be expanded by adding services to address new industries.

[0056] The system can provide services across different platforms. For example, the system may provide services on a web platform, allowing customers to access them from their PCs. For example, the system may provide medical advice on a website. The system may also provide services on a mobile app, allowing customers to access them from their smartphones. For example, the system may allow customers to enter symptoms and receive advice through the app. Furthermore, the system may integrate services across different platforms to provide a seamless user experience. For example, the system may synchronize data between the web and mobile app, allowing the same information to be accessed from both. This allows services to be provided across different platforms, allowing customers to access them from a variety of devices.

[0057] The system can make the service available in different languages ​​to promote international use. For example, the system can make the service available in different languages ​​to promote international use. For example, the system can provide medical advice in multiple languages, such as English, French, and Chinese. The system can also develop a multilingual interface to allow customers to use the service in their own language. For example, a language selection function can be added to allow customers to receive advice in their preferred language. Furthermore, the system can introduce a translation algorithm to provide services available in different languages. For example, the system can automatically translate medical advice and provide it in different languages. This can promote international use by making the service available in different languages.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The data collection unit can also collect lifestyle data of customers and predict their health status. For example, it can record the customer's diet and exercise amount and predict changes in their health status. The data collection unit can also monitor the customer's sleep patterns and evaluate their sleep quality. Furthermore, the data collection unit can measure the customer's stress level and provide advice on stress management. In this way, collecting customer lifestyle data enables more comprehensive health management.

[0060] The symptom input unit can also provide relevant health information based on the symptoms entered by the customer. For example, if a customer enters "I have a headache," the unit can provide general information and preventative measures regarding headaches. The symptom input unit can also suggest relevant health articles and research papers based on the symptoms entered by the customer. Furthermore, the symptom input unit can provide health-related FAQs based on the symptoms entered by the customer. This allows customers to easily obtain information about their symptoms.

[0061] The advice provider can also use generative AI to personalize the advice it provides to meet the individual needs of each customer. For example, it can provide customized advice based on the customer's past health data and current symptoms. The advice provider can also adjust the advice content based on the customer's lifestyle and preferences. Furthermore, the advice provider can continuously improve the accuracy of the advice based on customer feedback. This allows the customer to receive the most appropriate medical advice.

[0062] The purchase link providing unit can also analyze a customer's purchase history and develop an algorithm that recommends the most suitable product. For example, it can recommend related products based on medicines and health products purchased in the past. The purchase link providing unit can also analyze a customer's preferences and needs based on the purchase history and make personalized product recommendations. Furthermore, the purchase link providing unit can integrate purchase history and symptom data to develop an algorithm that recommends the most suitable product. This makes it possible to develop an algorithm that recommends the most suitable product by analyzing a customer's purchase history.

[0063] The feedback collection unit can also analyze the feedback content and develop an algorithm that continuously improves the accuracy of advice. For example, it can identify areas for improvement in advice based on feedback data. The feedback collection unit can also analyze the feedback content and build a system that continuously improves the accuracy of advice provided by the generation AI. Furthermore, the feedback collection unit can analyze the feedback content in real time and develop an algorithm that immediately improves the accuracy of advice. This makes it possible to develop an algorithm that continuously improves the accuracy of advice by analyzing the feedback content.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The data collection unit uses cameras and sensors to collect data on the customer's symptoms. For example, the camera takes pictures of skin rashes and swelling, and the sensors acquire biometric data such as body temperature and heart rate. The data collection unit then inputs this data into the generation AI. Step 2: The symptom input section allows customers to directly input their symptoms. For example, they can input specific symptoms such as "I have a headache" or "I have a sore throat." Step 3: The advice provider uses the generated AI to provide medical advice based on the data collected by the data collection and symptom input components. For example, it may provide specific advice such as, "These symptoms may be due to a cold. Take over-the-counter cold medicine and get plenty of rest." Step 4: The purchase link provider provides a purchase link for a related product based on the advice provided by the advice provider. For example, the link may be presented in the form of "This medicine is effective for this symptom. You can purchase it here." Step 5: The feedback collection unit collects feedback about the effects of the advice after the customer has taken it. For example, it provides a function to input feedback such as, "I took the medicine as advised, and my symptoms improved." Step 6: The reward providing unit provides a reward to the customer based on the feedback collected by the feedback collecting unit, for example, by awarding rewards such as points.

[0066] (Example 2) The primary medical advice system according to an embodiment of the present invention is a system in which a generative AI provides medical advice using functions such as cameras, sensors, and direct input of symptoms, etc. This enables the primary medical advice system to alleviate customer anxiety and provide appropriate medical advice even on holidays and at night.

[0067] A primary medical advice system according to an embodiment includes a data collection unit, a symptom input unit, an advice providing unit, a purchase link providing unit, a feedback collection unit, and a reward providing unit. The data collection unit collects data on a customer's symptoms using a camera and sensors. For example, images of skin rashes and swellings are taken with a camera, and biometric data such as body temperature and heart rate are acquired with a sensor. The data collection unit then inputs this data into the generation AI. The symptom input unit allows the customer to directly input their symptoms. For example, specific symptoms such as "I have a headache" or "I have a sore throat" can be input. The advice providing unit uses the generation AI to provide medical advice based on the data collected by the data collection unit and the symptom input unit. For example, the advice provided may be specific advice such as "These symptoms may be a cold. Take over-the-counter cold medicine and get plenty of rest." The purchase link providing unit provides a purchase link for a related product based on the advice provided by the advice providing unit. For example, the link may be presented in the form of "This medicine is effective for these symptoms. You can purchase it here." The feedback collection unit collects feedback on the effectiveness of the advice after the customer follows it. For example, a function is provided for inputting feedback such as, "I took the medicine as advised and my symptoms improved." The reward providing unit provides rewards to customers based on the feedback collected by the feedback collecting unit. For example, rewards such as points are awarded. As a result, the primary medical advice system according to the embodiment collects data on the customer's symptoms, provides appropriate medical advice, and provides feedback on the effectiveness of the advice, thereby easing customer anxiety and increasing the reliability of the advice provided by AI.

[0068] The data collection unit converts data collected by cameras and sensors into 3D models, enabling more detailed symptom analysis. For example, the data collection unit converts images of skin rashes or swellings taken with a camera into 3D models to perform a three-dimensional analysis of the symptoms. This allows for a detailed understanding of the depth and spread of the rash. The data collection unit also integrates biometric data, such as body temperature and heart rate, acquired by sensors into the 3D model to analyze overall health. For example, it visually displays fluctuations in body temperature and heart rate rhythm. Furthermore, the data collection unit uses the 3D model to analyze the progression of symptoms over time. For example, it displays the spread of the rash and changes in swelling over time to track the progression of symptoms. This conversion into a 3D model enables a three-dimensional analysis of symptoms, enabling more detailed medical advice to be provided.

[0069] The data collection unit can integrate a customer's past health data with real-time data to analyze long-term health trends. For example, the data collection unit integrates a customer's past health data (e.g., past diagnostic results and treatment history) with data collected in real time to analyze long-term health trends. For example, it compares past body temperature fluctuations with current body temperature. The data collection unit also performs analysis based on past health data to identify the cause of current symptoms. For example, it references the time and circumstances in which similar symptoms occurred in the past and evaluates their relevance to current symptoms. Furthermore, the data collection unit analyzes long-term health trends and provides preventive medical advice. For example, it identifies trends in seasonal symptoms from past data and suggests preventive measures. In this way, by integrating past health data with real-time data, long-term health trends can be analyzed and preventive medical advice can be provided.

[0070] The data collection unit can use the emotion estimation function to estimate the emotional state from the customer's facial expression and tone of voice and evaluate their stress level. The data collection unit, for example, analyzes the customer's facial expression captured by a camera to estimate their emotional state. For example, it evaluates the customer's stress level from facial expressions such as smiling or furrowing of the brow. The data collection unit also uses a microphone to analyze the customer's tone of voice to estimate their emotional state. For example, it evaluates the customer's level of tension or relaxation from the pitch and speed of their voice. Furthermore, the data collection unit integrates data on facial expression and tone of voice to evaluate their overall emotional state. For example, a more accurate emotion estimation is possible when facial expression and tone of voice match. This allows the customer's emotional state to be estimated and their stress level to be evaluated, thereby providing more appropriate medical advice.

[0071] The data collection unit can display data collected by cameras and sensors on home smart devices to promote self-diagnosis. For example, the data collection unit can display images of skin rashes or swellings taken with a camera on the smart mirror to enable customers to self-diagnose. For example, the spread and color changes of the rash can be checked in real time. The data collection unit can also display biometric data obtained by sensors, such as body temperature and heart rate, on the smart mirror to enable customers to understand their own health status. For example, it can display graphs of body temperature fluctuations and heart rate rhythms. Furthermore, the data collection unit's generative AI can provide self-diagnosis advice based on the data displayed on the smart mirror. For example, it can analyze images of a rash and suggest possible symptoms. In this way, displaying data on home smart devices makes it easier for customers to self-diagnose.

[0072] The data collection unit can add different sensors to collect more diversified data. For example, the data collection unit can add an odor sensor to analyze the customer's body odor and breath. For example, it can detect odors associated with specific illnesses and help identify symptoms. The data collection unit can also integrate data from the odor sensor and camera to perform more detailed symptom analysis. For example, it can simultaneously analyze skin rashes and changes in body odor to identify the cause of symptoms. Furthermore, the data collection unit can input data from the odor sensor into a generative AI to provide medical advice based on the odor. For example, if a specific odor is detected, it can suggest the possibility of a related illness. By adding different sensors, more diversified data collection becomes possible, allowing for more detailed medical advice to be provided.

[0073] The data collection unit can use the emotion estimation function to monitor the anxiety and stress felt by the customer during data collection in real time and provide advice on how to relax. The data collection unit, for example, analyzes the customer's facial expressions captured by a camera to monitor the anxiety and stress during data collection in real time. For example, it evaluates the stress level from frowns and eye movements. The data collection unit also analyzes the tone of the customer's voice using a microphone to monitor the emotional state during data collection in real time. For example, it evaluates the level of tension from the pitch and speed of the voice. Furthermore, the data collection unit provides advice on how to relax in real time based on the emotion estimation data. For example, it suggests deep breathing or playing relaxing music. In this way, the customer's anxiety and stress during data collection can be monitored in real time and advice on how to relax can be provided, thereby reducing the customer's psychological burden.

[0074] The symptom input unit can use natural language processing technology to analyze in detail the symptoms entered by the customer and provide specific medical advice. For example, the symptom input unit uses natural language processing technology to analyze the symptoms entered by the customer and provide detailed medical advice. For example, when an input such as "I have a headache" is made, the type and cause of the headache are identified. The symptom input unit also uses natural language processing technology to automatically extract related symptoms and medical history from the customer's symptom input and provide comprehensive medical advice. For example, when an input such as "I have a sore throat" is made, the symptom input unit refers to the customer's past cold history. Furthermore, the symptom input unit analyzes the symptoms entered by the customer and suggests specific treatments and medications. For example, when an input such as "I have a stomachache" is made, the symptom input unit suggests the possibility of indigestion or gastritis and suggests appropriate medications. In this way, by using natural language processing technology, the symptoms entered by the customer can be analyzed in detail and more specific medical advice can be provided.

[0075] The symptom input unit can search for similar past cases based on the symptoms entered by the customer and provide reference information. The symptom input unit, for example, searches a database for similar past cases based on the symptoms entered by the customer and provides reference information. For example, in response to an input such as "I have a rash," past cases of rash are presented. The symptom input unit also analyzes the customer's symptom input and extracts and provides treatments and effects from similar past cases. For example, in response to an input such as "I have a persistent cough," treatments for past cough cases are presented. Furthermore, the symptom input unit provides statistical data on similar past cases based on the symptoms entered by the customer. For example, in response to an input such as "I have a headache," the frequency of occurrence of past headache cases and the effects of treatment are presented. In this way, by searching for similar past cases and providing reference information, it is possible to provide useful information to the customer.

[0076] The symptom input unit can use the emotion estimation function to analyze the emotional state of a customer when they enter their symptoms and provide psychological support. The symptom input unit, for example, analyzes the facial expression of a customer when they enter their symptoms and estimates their emotional state. For example, it can detect anxiety or stress from the facial expression when they enter their symptoms and provide psychological support. The symptom input unit also analyzes the tone of the customer's voice and estimates their emotional state when they enter their symptoms. For example, it can evaluate the level of tension from the pitch and speed of their voice and provide advice on how to relax. Furthermore, the symptom input unit provides psychological support when they enter their symptoms based on the emotion estimation data. For example, it can suggest an encouraging message or a way to relax to a customer who is feeling anxious. In this way, it is possible to analyze the emotional state of a customer when they enter their symptoms and provide psychological support, thereby reducing their anxiety.

[0077] The symptom input unit can use voice recognition technology to allow customers to input symptoms by voice. The symptom input unit, for example, introduces voice recognition technology that allows customers to input symptoms by voice. For example, simply saying "I have a headache" automatically inputs the symptoms. The symptom input unit also uses voice recognition technology to convert the customer's symptom input into text and input it into the generation AI. For example, if the customer says "I have a sore throat," the content is converted into text and analyzed. Furthermore, the symptom input unit uses voice recognition technology to allow multiple symptoms to be input at once. For example, if the customer says "I have a headache and a sore throat," both symptoms are automatically input. In this way, the use of voice recognition technology allows customers to input symptoms by voice, saving time and effort.

[0078] The symptom input unit can gamify symptom input, allowing customers to enjoy entering their symptoms. For example, the symptom input unit gamifies symptom input and provides an interface that allows customers to enjoy entering their symptoms. For example, a game can be developed that uses characters to enter symptoms. The symptom input unit can also format symptom input as a quiz, allowing customers to enter their symptoms by answering questions. For example, a format in which customers answer questions such as, "Which part hurts?" The symptom input unit can also implement a points system for symptom input, where points are accumulated each time an input is made. For example, points can be accumulated by accurately entering symptoms, and rewards can be obtained. In this way, gamifying symptom input allows customers to enjoy entering their symptoms.

[0079] The symptom input unit can use the emotion estimation function to analyze the emotions of customers when they enter their symptoms in real time and optimize the input content. The symptom input unit, for example, analyzes the facial expression of the customer when they enter their symptoms and estimates their emotional state in real time. For example, it detects anxiety or stress from the facial expression when they enter their symptoms and optimizes the input content. The symptom input unit also analyzes the tone of the customer's voice and estimates their emotional state when they enter their symptoms in real time. For example, it evaluates the level of tension from the pitch and speed of the voice and optimizes the input content. Furthermore, the symptom input unit provides advice when entering symptoms in real time based on the emotion estimation data. For example, it suggests simplifying the input content for a customer who is feeling anxious. In this way, by analyzing the emotions of customers when they enter their symptoms in real time and optimizing the input content, more accurate symptom input is possible.

[0080] The advice providing unit can improve reliability by using the generating AI to refer to past medical data and research papers. For example, the advice providing unit adds a function to refer to past medical data to the advice provided by the generating AI. For example, it provides advice based on past diagnosis results and treatment history. The advice providing unit also adds a function to refer to the latest research papers to the advice provided by the generating AI. For example, it provides advice based on the latest medical research. Furthermore, the advice providing unit integrates past medical data and research papers to improve the reliability of the advice provided by the generating AI. For example, it provides advice that combines past data and the latest research. In this way, by referring to past medical data and research papers, it is possible to improve the reliability of the advice provided by the generating AI.

[0081] The advice providing unit can use the generation AI to provide advice that takes into account local medical resources. For example, the advice providing unit adds a function that takes into account local medical resources to the advice provided by the generation AI. For example, it provides advice based on information about nearby pharmacies and hospitals. The advice providing unit also references a local medical resource database and reflects this in the advice provided by the generation AI. For example, it may suggest medicines that can be purchased at nearby pharmacies. Furthermore, the generation AI works with local medical institutions to provide advice that takes into account local medical resources. For example, it may recommend a consultation at a nearby hospital. This makes it possible to provide more practical and appropriate medical advice by taking into account local medical resources.

[0082] The advice providing unit can use the emotion estimation function to provide advice according to the customer's emotional state, thereby enhancing psychological support. The advice providing unit, for example, uses the emotion estimation function to analyze the customer's emotional state in real time and provides advice based on the results. For example, it provides advice that gives a sense of security to a customer who is feeling anxious. In addition, the advice providing unit uses the generation AI to analyze emotional data in order to provide advice according to the customer's emotional state. For example, it suggests relaxation methods to a customer who is feeling stressed. Furthermore, the advice providing unit provides advice to enhance psychological support for the customer based on the emotion estimation data. For example, it provides an encouraging message to elicit positive emotions. In this way, by providing advice according to the customer's emotional state, psychological support can be enhanced and customer anxiety can be reduced.

[0083] The advice providing unit can use the generation AI to automatically translate the advice it provides into different languages, promoting international use. For example, the advice providing unit adds a function to automatically translate the advice provided by the generation AI and provide it in different languages. For example, it translates into multiple languages ​​such as English, French, and Chinese. The advice providing unit also provides the automatically translated advice on a multilingual platform to promote international use. For example, it allows users of different languages ​​to receive the same advice. Furthermore, the advice providing unit collects feedback from an international perspective based on the translated advice and improves the quality of the advice. For example, it provides advice that is appropriate for different cultures and medical systems. This allows the advice to be automatically translated into different languages, promoting international use.

[0084] The advice providing unit can use the generation AI to provide advice in visual note or video format to make it easier to understand. For example, the advice providing unit converts the advice provided by the generation AI into a visual note and displays it visually. For example, it indicates important points with diagrams or icons. The advice providing unit also provides the advice in video format to make it easier for customers to understand. For example, it explains the advice content using animations or live-action videos. Furthermore, the advice providing unit develops tools that automatically generate advice in visual note or video format to make it easier for customers to understand the advice. For example, it provides a function to visualize the advice content with drag and drop. As a result, providing advice in visual note or video format makes it easier for customers to understand.

[0085] The advice providing unit uses the emotion estimation function to analyze the emotions of the customer when receiving advice in real time, and can provide advice at the optimal timing. The advice providing unit, for example, uses the emotion estimation function to analyze the emotional state of the customer when receiving advice in real time. For example, it analyzes facial expressions and tone of voice before and after receiving the advice. The advice providing unit also builds a system that provides advice at the optimal timing depending on the emotional state of the customer. For example, it provides advice when the customer is relaxed. Furthermore, the advice providing unit dynamically adjusts the timing of providing advice based on the emotion estimation data. For example, it changes the timing of providing advice depending on changes in the customer's emotions. In this way, the effectiveness of the advice can be maximized by analyzing the emotions of the customer when receiving advice in real time and providing advice at the optimal timing.

[0086] The purchase link providing unit can analyze a customer's purchase history and develop an algorithm that recommends the most suitable product. The purchase link providing unit, for example, analyzes a customer's past purchase history and develops an algorithm that recommends the most suitable product. For example, related products are recommended based on medicines and health products purchased in the past. The purchase link providing unit also analyzes a customer's preferences and needs based on the purchase history and makes personalized product recommendations. For example, related products are recommended to customers who prefer specific brands or ingredients. Furthermore, the purchase link providing unit integrates purchase history and symptom data to develop an algorithm that recommends the most suitable product. For example, the next product to be purchased is recommended based on past symptoms and the effects of purchased medicines. This makes it possible to develop an algorithm that recommends the most suitable product by analyzing a customer's purchase history.

[0087] The purchase link providing unit can add videos to the purchase link that explain how to use the product and its effects. For example, the purchase link providing unit adds videos to the purchase link that explain how to use the product, allowing customers to use it correctly. For example, a video may explain how to take medication and precautions. The purchase link providing unit also adds videos to the purchase link that explain the effects of the product, allowing customers to understand the product's effects. For example, a video may explain the effects and side effects of medication. Furthermore, the purchase link providing unit develops a tool that automatically generates videos that explain how to use the product and its effects, and adds them to the purchase link. For example, a video may be automatically generated based on product information and embedded in the link. In this way, adding a video to the purchase link that explains how to use the product and its effects allows customers to correctly understand and use the product.

[0088] The purchase link providing unit uses the emotion estimation function to analyze the emotion of the customer when they click on the purchase link and can make suggestions to increase their willingness to purchase. The purchase link providing unit, for example, uses the emotion estimation function to analyze the emotional state of the customer when they click on the purchase link. For example, it analyzes facial expressions and tone of voice before and after the click to evaluate their willingness to purchase. The purchase link providing unit also makes suggestions to increase their willingness to purchase based on the customer's emotional state. For example, it displays messages or images that elicit positive emotions. Furthermore, the purchase link providing unit dynamically adjusts the timing and content of the purchase link display based on the emotion estimation data. For example, it displays the link when the customer is relaxed to increase their willingness to purchase. In this way, the purchase rate can be improved by analyzing the emotion of the customer when they click on the purchase link and making suggestions to increase their willingness to purchase.

[0089] The purchase link providing unit can notify the customer of the purchase link to their smart device. For example, the purchase link providing unit may notify the customer of the purchase link to their smartphone, allowing for easy access. For example, the link may be pushed immediately after receiving the advice. The purchase link providing unit may also notify the customer of the purchase link to their smartwatch, allowing for easy access. For example, the link may be displayed on the screen of the smartwatch. Furthermore, the purchase link providing unit may utilize the notification function of the smart device to provide the purchase link in a timely manner. For example, the link may be notified within a certain period of time after the customer receives the advice. In this way, by notifying the customer of the purchase link to their smart device, the customer can easily access the purchase link.

[0090] The purchase link providing unit can add a function to share the purchase link to the customer's social media account. For example, the purchase link providing unit adds a function to share the purchase link to the customer's social media account, allowing the information to be shared with other users. For example, the purchase link providing unit posts the link on Facebook or Twitter. When the customer shares the purchase link, the purchase link providing unit automatically generates a comment explaining how to use the product and its effects. For example, the purchase link providing unit adds a comment such as, "My symptoms improved after using this medicine." Furthermore, the purchase link providing unit utilizes the sharing function on social media to promote the spread of the purchase link. For example, the purchase link providing unit can provide an incentive so that the shared link reaches many users. This allows the information to be shared with other users by sharing the purchase link on social media.

[0091] The purchase link providing unit uses the emotion estimation function to analyze the emotion of a customer when they click on a purchase link in real time, and can provide the link at the optimal timing. The purchase link providing unit, for example, uses the emotion estimation function to analyze the emotional state of a customer when they click on a purchase link in real time. For example, it analyzes facial expressions and tone of voice before and after the click to identify the optimal timing. The purchase link providing unit also builds a system that provides a purchase link at the optimal timing based on the customer's emotional state. For example, it provides the link when the customer is relaxed. Furthermore, the purchase link providing unit dynamically adjusts the timing of providing the purchase link based on the emotion estimation data. For example, it changes the timing of providing the link in response to changes in the customer's emotion. In this way, it is possible to analyze the emotion of a customer when they click on a purchase link in real time and provide the link at the optimal timing, thereby increasing purchasing motivation.

[0092] The feedback collection unit can analyze the feedback content and develop an algorithm that continuously improves the accuracy of advice. The feedback collection unit, for example, analyzes the feedback content from customers and develops an algorithm that improves the accuracy of advice. For example, it identifies areas for improvement in advice based on feedback data. The feedback collection unit also analyzes the feedback content and builds a system that continuously improves the accuracy of advice provided by the generation AI. For example, it uses the feedback data as learning data. Furthermore, the feedback collection unit analyzes the feedback content in real time and develops an algorithm that instantly improves the accuracy of advice. For example, it updates the advice every time feedback is received. This makes it possible to develop an algorithm that continuously improves the accuracy of advice by analyzing the feedback content.

[0093] The feedback collection unit can provide individual advice to customers based on the feedback. The feedback collection unit, for example, builds a system that provides individual advice based on feedback from customers. For example, it analyzes the feedback content and provides the most suitable advice to the customer. The feedback collection unit also evaluates the customer's symptoms and treatment effects based on the feedback data and provides individual advice. For example, it refers to the feedback content and adjusts the next advice. Furthermore, the feedback collection unit develops a system that personalizes advice to customers based on feedback. For example, it learns the feedback content and provides advice that meets the customer's needs. As a result, by providing individual advice based on feedback, the accuracy of advice to customers can be improved.

[0094] The feedback collection unit can use the emotion estimation function to analyze the customer's emotions at the time of feedback and optimize the type and amount of reward. The feedback collection unit, for example, analyzes the customer's facial expression at the time of feedback and estimates the emotional state. For example, it detects satisfaction or dissatisfaction from the facial expression when feedback is entered and adjusts the type and amount of reward. The feedback collection unit also analyzes the tone of the customer's voice and estimates the emotional state at the time of feedback. For example, it evaluates satisfaction from the pitch and speed of the voice and optimizes the type and amount of reward. Furthermore, the feedback collection unit builds a system that optimizes rewards at the time of feedback based on the emotion estimation data. For example, it provides higher rewards to customers with positive emotions. In this way, customer satisfaction can be improved by analyzing the customer's emotions at the time of feedback and optimizing the type and amount of reward.

[0095] The feedback collection unit can link the feedback with the customer's health management app to support comprehensive health management. The feedback collection unit, for example, links the feedback data with the customer's health management app to build a system that supports comprehensive health management. For example, the feedback content is automatically reflected in the health management app. The feedback collection unit also links with the health management app to provide comprehensive health advice based on the feedback data. For example, it provides advice on diet and exercise based on the feedback content. Furthermore, the feedback collection unit integrates the feedback data with the health management app to develop a system that comprehensively evaluates the customer's health condition. For example, it calculates a health score based on the feedback content. In this way, by linking the feedback with the health management app, comprehensive health management can be supported.

[0096] The feedback collection unit can automatically add the feedback to the customer's medical record and share it with the medical institution. The feedback collection unit, for example, builds a system that automatically adds feedback data to the customer's medical record and shares it with the medical institution. For example, the feedback content is automatically reflected in the electronic medical record. The feedback collection unit also works with the medical institution to provide comprehensive medical advice based on the feedback data. For example, the doctor will provide advice at the next appointment based on the feedback content. Furthermore, the feedback collection unit integrates the feedback data into the medical record and develops a system that comprehensively evaluates the customer's health condition. For example, the treatment plan is adjusted based on the feedback content. In this way, feedback can be automatically added to the medical record and shared with the medical institution, allowing comprehensive medical advice to be provided.

[0097] The feedback collection unit can use the emotion estimation function to analyze the customer's emotion at the time of feedback in real time and provide a reward at the optimal timing. The feedback collection unit, for example, uses the emotion estimation function to analyze the customer's emotional state at the time of feedback in real time. For example, it analyzes facial expressions and tone of voice when feedback is entered and provides a reward at the optimal timing. The feedback collection unit also builds a system that provides a reward at the optimal timing based on the customer's emotional state. For example, it provides a reward when the customer is satisfied. Furthermore, the feedback collection unit dynamically adjusts the timing of providing the reward based on the emotion estimation data. For example, it changes the timing of providing the reward according to changes in the customer's emotion. In this way, customer satisfaction can be improved by analyzing the customer's emotion at the time of feedback in real time and providing a reward at the optimal timing.

[0098] The reward provision unit can analyze sales incentive data and identify the most effective sales strategy. For example, the reward provision unit analyzes sales incentive data and develops an algorithm to identify the most effective sales strategy. For example, it identifies effective incentives based on past sales data. The reward provision unit also analyzes customer purchasing behavior based on the sales incentive data and proposes an optimal sales strategy. For example, it evaluates whether a specific incentive increases purchasing motivation. Furthermore, the reward provision unit analyzes sales incentive data in real time and builds a system to instantly identify effective sales strategies. For example, it monitors the effects of incentives in real time. In this way, the most effective sales strategy can be identified by analyzing the sales incentive data.

[0099] The reward providing unit can utilize the sales incentive data to optimize marketing campaigns. For example, the reward providing unit analyzes the sales incentive data and builds a system that utilizes it to optimize marketing campaigns. For example, it adjusts the content of the campaign based on the effectiveness of the incentive. The reward providing unit also analyzes customer purchasing behavior based on the sales incentive data and proposes optimal marketing campaigns. For example, it evaluates whether a specific incentive will increase purchasing motivation. Furthermore, the reward providing unit analyzes the sales incentive data in real time and builds a system that instantly identifies effective marketing campaigns. For example, it monitors the effectiveness of incentives in real time. In this way, by utilizing the sales incentive data to optimize marketing campaigns, effective campaigns can be implemented.

[0100] The reward providing unit can provide incentives to increase a customer's willingness to purchase using the emotion estimation function. The reward providing unit, for example, uses the emotion estimation function to analyze a customer's emotional state in real time and provide incentives to increase their willingness to purchase. For example, it displays messages or images to elicit positive emotions. The reward providing unit also builds a system that provides optimal incentives based on the customer's emotional state. For example, it provides incentives when the customer is relaxed. Furthermore, the reward providing unit dynamically adjusts the timing and content of providing incentives based on the emotion estimation data. For example, it changes the timing of providing incentives according to changes in the customer's emotions. In this way, by using the emotion estimation function, it is possible to provide incentives to increase a customer's willingness to purchase.

[0101] The reward provision unit can link sales incentives with customer loyalty programs to build long-term customer relationships. For example, the reward provision unit links sales incentives with customer loyalty programs to build a system for building long-term customer relationships. For example, the incentives are awarded as loyalty points. The reward provision unit also links with loyalty programs to analyze customer purchasing behavior based on sales incentives. For example, it evaluates the impact of awarding loyalty points on purchasing motivation. Furthermore, the reward provision unit integrates sales incentives with loyalty programs to develop a system for comprehensively evaluating customer purchasing behavior. For example, it analyzes the effects of incentives and loyalty points simultaneously. In this way, by linking sales incentives with loyalty programs, long-term customer relationships can be built.

[0102] The reward providing unit can add a function for sharing sales incentives on customers' social media accounts. For example, the reward providing unit adds a function for sharing sales incentives on customers' social media accounts, allowing information to be shared with other users. For example, the reward providing unit posts incentive information on Facebook or Twitter. When a customer shares a sales incentive, the reward providing unit automatically generates a comment explaining the content and effect of the incentive. For example, the reward providing unit adds a comment such as "This incentive helped me get a good deal on my purchase." Furthermore, the reward providing unit utilizes a sharing function on social media to promote the spread of sales incentives. For example, the reward providing unit provides incentives so that the shared incentive information reaches many users. In this way, by sharing the sales incentive on social media, the information can be shared with other users.

[0103] The reward providing unit can use the emotion estimation function to analyze the emotion of the customer when receiving the incentive in real time and provide the incentive at the optimal timing. The reward providing unit, for example, uses the emotion estimation function to analyze the emotional state of the customer when receiving the incentive in real time. For example, it analyzes facial expressions and tone of voice before and after receiving the incentive to identify the optimal timing. The reward providing unit also builds a system that provides incentives at the optimal timing based on the emotional state of the customer. For example, it provides the incentive when the customer is relaxed. Furthermore, the reward providing unit dynamically adjusts the timing of providing the incentive based on the emotion estimation data. For example, it changes the timing of providing the incentive according to changes in the customer's emotion. In this way, it is possible to analyze the emotion of the customer when receiving the incentive in real time and provide the incentive at the optimal timing, thereby improving customer satisfaction.

[0104] The system can develop data collection and analysis algorithms to address new medical fields. For example, the system develops data collection and analysis algorithms to address new medical fields. For example, an algorithm is built to collect and analyze psychiatric symptom data. The system also develops data collection and analysis algorithms to address the dental field. For example, an algorithm is built to collect and analyze dental image data. Furthermore, the system integrates data collection and analysis algorithms to address new medical fields and builds a system that provides comprehensive medical advice. For example, psychiatric and dental data is integrated to provide comprehensive advice. This allows the application range of the system to be expanded by developing data collection and analysis algorithms to address new medical fields.

[0105] The system can add services to address new industries. For example, the system adds a service to address new industries. For example, the system provides training plans and exercise advice to address the fitness field. The system also adds a service to address the nutrition field. For example, the system provides meal plans and nutrition advice. Furthermore, the system integrates services to address new industries to build a system that supports comprehensive health management. For example, the system integrates fitness and nutrition data to provide comprehensive advice. This allows the system's scope of application to be expanded by adding services to address new industries.

[0106] The system can use the emotion estimation function to analyze the customer's emotions when using a new service and improve the quality of the service. For example, the system uses the emotion estimation function to analyze the customer's emotional state when using a new service. For example, the system analyzes facial expressions and tone of voice while using the service and evaluates the quality of the service. The system also builds a system for improving the quality of the new service based on the customer's emotional state. For example, the system provides the service when the customer is relaxed. Furthermore, the system provides feedback to improve the quality of the new service based on the emotion estimation data. For example, the system adjusts the content of the service based on the customer's emotional response. In this way, customer satisfaction can be increased by analyzing the customer's emotions when using a new service and improving the quality of the service.

[0107] The system can provide services across different platforms. For example, the system may provide services on a web platform, allowing customers to access them from their PCs. For example, the system may provide medical advice on a website. The system may also provide services on a mobile app, allowing customers to access them from their smartphones. For example, the system may allow customers to enter symptoms and receive advice through the app. Furthermore, the system may integrate services across different platforms to provide a seamless user experience. For example, the system may synchronize data between the web and mobile app, allowing the same information to be accessed from both. This allows services to be provided across different platforms, allowing customers to access them from a variety of devices.

[0108] The system can make the service available in different languages ​​to promote international use. For example, the system can make the service available in different languages ​​to promote international use. For example, the system can provide medical advice in multiple languages, such as English, French, and Chinese. The system can also develop a multilingual interface to allow customers to use the service in their own language. For example, a language selection function can be added to allow customers to receive advice in their preferred language. Furthermore, the system can introduce a translation algorithm to provide services available in different languages. For example, the system can automatically translate medical advice and provide it in different languages. This can promote international use by making the service available in different languages.

[0109] The system uses the emotion estimation function to analyze the customer's emotions in real time when using a new service, and can provide the service at the optimal timing. For example, the system uses the emotion estimation function to analyze the customer's emotional state in real time when using a new service. For example, the system analyzes facial expressions and tone of voice while using the service, and provides the service at the optimal timing. The system also builds a system that provides the service at the optimal timing based on the customer's emotional state. For example, the system provides the service when the customer is relaxed. Furthermore, the system dynamically adjusts the timing of providing the service based on the emotion estimation data. For example, the system changes the timing of providing the service according to changes in the customer's emotions. In this way, customer satisfaction can be increased by analyzing the customer's emotions in real time when using a new service and providing the service at the optimal timing.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The data collection unit can also collect lifestyle data of customers and predict their health status. For example, it can record the customer's diet and exercise amount and predict changes in their health status. The data collection unit can also monitor the customer's sleep patterns and evaluate their sleep quality. Furthermore, the data collection unit can measure the customer's stress level and provide advice on stress management. In this way, collecting customer lifestyle data enables more comprehensive health management.

[0112] The data collection unit can also use the emotion estimation function to analyze the customer's emotional state and provide stress management advice. For example, the data collection unit can evaluate the customer's stress level from their facial expressions and tone of voice and suggest relaxation methods. The data collection unit can also provide advice on exercise or meditation to reduce stress based on the customer's emotional state. Furthermore, the data collection unit can provide customized advice for stress management based on the emotion estimation data. This allows for more effective stress management by analyzing the customer's emotional state.

[0113] The symptom input unit can also provide relevant health information based on the symptoms entered by the customer. For example, if a customer enters "I have a headache," the unit can provide general information and preventative measures regarding headaches. The symptom input unit can also suggest relevant health articles and research papers based on the symptoms entered by the customer. Furthermore, the symptom input unit can provide health-related FAQs based on the symptoms entered by the customer. This allows customers to easily obtain information about their symptoms.

[0114] The symptom input unit can also use the emotion estimation function to analyze the emotional state of the customer when entering symptoms and optimize the input process. For example, if the customer is feeling anxious, the input process can be simplified. The symptom input unit can also provide a support message at the time of input based on the customer's emotional state. Furthermore, the symptom input unit can customize the input process based on the emotion estimation data to allow the customer to enter symptoms in a relaxed manner. This reduces stress when the customer enters their symptoms.

[0115] The advice provider can also use generative AI to personalize the advice it provides to meet the individual needs of each customer. For example, it can provide customized advice based on the customer's past health data and current symptoms. The advice provider can also adjust the advice content based on the customer's lifestyle and preferences. Furthermore, the advice provider can continuously improve the accuracy of the advice based on customer feedback. This allows the customer to receive the most appropriate medical advice.

[0116] The advice providing unit can also use the emotion estimation function to provide advice according to the emotional state of the customer, thereby enhancing psychological support. For example, if the customer is feeling anxious, the advice providing unit can provide advice that gives the customer a sense of security. The advice providing unit can also provide advice on relaxation methods and stress management based on the emotional state of the customer. Furthermore, the advice providing unit can also provide customized advice to enhance psychological support for the customer based on the emotion estimation data. This makes it possible to enhance psychological support by providing advice according to the customer's emotional state.

[0117] The purchase link providing unit can also analyze a customer's purchase history and develop an algorithm that recommends the most suitable product. For example, it can recommend related products based on medicines and health products purchased in the past. The purchase link providing unit can also analyze a customer's preferences and needs based on the purchase history and make personalized product recommendations. Furthermore, the purchase link providing unit can integrate purchase history and symptom data to develop an algorithm that recommends the most suitable product. This makes it possible to develop an algorithm that recommends the most suitable product by analyzing a customer's purchase history.

[0118] The purchase link providing unit can also use the emotion estimation function to analyze the emotions of customers when they click on a purchase link and make suggestions to increase their willingness to purchase. For example, it can analyze facial expressions and tone of voice before and after the click to evaluate their willingness to purchase. The purchase link providing unit can also display messages and images to increase the customer's willingness to purchase based on the customer's emotional state. Furthermore, the purchase link providing unit can dynamically adjust the timing and content of the purchase link display based on the emotion estimation data. This allows the purchase rate to be improved by analyzing the emotions of customers when they click on a purchase link and making suggestions to increase their willingness to purchase.

[0119] The feedback collection unit can also analyze the feedback content and develop an algorithm that continuously improves the accuracy of advice. For example, it can identify areas for improvement in advice based on feedback data. The feedback collection unit can also analyze the feedback content and build a system that continuously improves the accuracy of advice provided by the generation AI. Furthermore, the feedback collection unit can analyze the feedback content in real time and develop an algorithm that immediately improves the accuracy of advice. This makes it possible to develop an algorithm that continuously improves the accuracy of advice by analyzing the feedback content.

[0120] The feedback collection unit can also use the emotion estimation function to analyze the customer's emotions at the time of feedback and optimize the type and amount of reward. For example, it can detect satisfaction or dissatisfaction from the customer's facial expression when the feedback is entered and adjust the type and amount of reward. The feedback collection unit can also analyze the tone of the customer's voice to estimate the customer's emotional state at the time of feedback. Furthermore, the feedback collection unit can build a system that optimizes rewards at the time of feedback based on the emotion estimation data. This makes it possible to improve customer satisfaction by analyzing the customer's emotions at the time of feedback and optimizing the type and amount of reward.

[0121] The processing flow of the second embodiment will be briefly explained below.

[0122] Step 1: The data collection unit uses cameras and sensors to collect data on the customer's symptoms. For example, the camera takes pictures of skin rashes and swelling, and the sensors acquire biometric data such as body temperature and heart rate. The data collection unit then inputs this data into the generation AI. Step 2: The symptom input section allows customers to directly input their symptoms. For example, they can input specific symptoms such as "I have a headache" or "I have a sore throat." Step 3: The advice provider uses the generated AI to provide medical advice based on the data collected by the data collection and symptom input components. For example, it may provide specific advice such as, "These symptoms may be due to a cold. Take over-the-counter cold medicine and get plenty of rest." Step 4: The purchase link provider provides a purchase link for a related product based on the advice provided by the advice provider. For example, the link may be presented in the form of "This medicine is effective for this symptom. You can purchase it here." Step 5: The feedback collection unit collects feedback about the effects of the advice after the customer has taken it. For example, it provides a function to input feedback such as, "I took the medicine as advised, and my symptoms improved." Step 6: The reward providing unit provides a reward to the customer based on the feedback collected by the feedback collecting unit, for example, by awarding rewards such as points.

[0123] 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.

[0124] 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.

[0125] 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.

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

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

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

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

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

[0131] 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).

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

[0133] 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.

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

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0136] 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.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires 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.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may 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.

[0141] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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."

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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]

[0190] 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 data collection unit that collects data on the symptoms of the customer using a camera or a sensor; a symptom input section in which the customer directly inputs their own symptoms; an advice providing unit that provides medical advice based on the data collected by the data collecting unit and the symptom input unit; a purchase link providing unit that provides a purchase link for a related product based on the advice provided by the advice providing unit; a feedback collection unit that collects feedback on the effect after the customer has implemented the advice; a reward providing unit that provides rewards to customers based on the feedback collected by the feedback collecting unit. A system characterized by:

2. The data collection unit The data collected by the cameras and sensors is converted into a 3D model for more detailed symptom analysis.

2. The system of claim 1.

3. The data collection unit Integrate the customer's historical health data with real-time data to analyze long-term health trends.

2. The system of claim 1.

4. The data collection unit Inferring the emotional state of the customer from their facial expression or tone of voice to assess their stress level 2. The system of claim 1.

5. The data collection unit The data collected by the camera and the sensor is displayed on a home smart device to facilitate self-diagnosis.

2. The system of claim 1.

6. The data collection unit Add different sensors to collect more diverse data 2. The system of claim 1.

7. The data collection unit Monitoring the anxiety and stress felt by the customer in real time during data collection and providing the customer with advice to relax 2. The system of claim 1.

8. The symptom input unit Using natural language processing technology, the symptoms entered by the customer are analyzed in detail and specific medical advice is provided.

2. The system of claim 1.

Images