system

Abstract

Provide a system. 【Solution means】 Data acquisition means for inputting diagnostic information, Data analysis means for analyzing the diagnostic information and proposing a specialized field suitable for the symptoms, Information search means for searching for experts based on the proposed specialized field and evaluating the recommendation degree, Document generation means for automatically generating an introduction document by combining the analysis results and the recommended expert information, Data providing means for outputting the introduction document, User interface means for the user to input health information into the terminal by voice or input operation, Communication means for transmitting data from the terminal to the server in real time, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, it has been difficult for a doctor to introduce a patient in a field outside their specialty to an appropriate specialist due to lack of information and complexity of selection. Also, creating a referral letter takes time and effort, imposing a burden on the medical field. The present invention aims to solve these problems and improve the efficiency of the medical referral process.

Means for Solving the Problems

[0005]

[0005] The present invention provides a system that inputs diagnostic information, analyzes the information, and proposes a suitable specialty area. Furthermore, it has a function of searching for experts and evaluating the degree of recommendation based on the analysis results. By automatically generating a referral document combining the most suitable expert information and the analysis results and providing it to the user, the efficiency of medical referral is improved.

[0006] "Diagnostic information" refers to a patient's symptoms, medical history, and related medical data, and is input data for evaluation based on medical judgment.

[0007] "Analysis" is the process of extracting relevant patterns and characteristics from input diagnostic information and generating information that contributes to the assessment of a specialized field.

[0008] A "specialized field" refers to an area of ​​medicine in which one possesses specialized knowledge and skills, and signifies the appropriate medical department based on the patient's symptoms.

[0009] "Proposal" refers to the act of selecting an appropriate area of ​​expertise based on the analysis results and presenting it to the user.

[0010] A "specialist" refers to a healthcare professional who possesses a high level of expertise in a specific field and is qualified to treat and diagnose patients.

[0011] The "recommendation level" is an indicator of suitability when selecting an expert, and is calculated based on the analysis results and other evaluation criteria.

[0012] A "referral document" is an official document containing diagnostic and expert information, created to refer a patient to an appropriate specialist.

[0013] "Automatic generation" refers to the process by which a computer system autonomously generates documents and data without human intervention. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0016] First, the language used in the following description will be explained.

[0017] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0018] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0019] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention begins with a user in a medical setting using a terminal to input patient diagnostic information. The terminal converts this information into a processable data format and sends it to a server. The server passes the received diagnostic information to an AI analysis module, which analyzes the information and processes it to identify the appropriate area of ​​expertise corresponding to the symptoms.

[0036] Based on the specialized field information obtained from the analysis results, the server accesses a nationwide database of specialists to search for experts. Based on geographical information and the specialists' past clinical experience, it evaluates their suitability and lists highly recommended specialists. The server then refers to this list to support the user in selecting the most suitable specialty.

[0037] Next, the server automatically generates a referral document based on the diagnostic information, analyzed specialty areas, and recommended specialists. The generated referral document is sent to the terminal accessed by the user. The user can review it and add any necessary information. Finally, the completed referral document is provided to the patient via the terminal.

[0038] For example, in the case of a patient complaining of heart-related problems, the user enters their symptoms on the terminal. The server uses an analysis module to identify a cardiologist, searches a nationwide database for the appropriate specialist, and lists the most suitable specialist for the user. Based on this information, the server generates a referral letter and presents it to the user on the terminal in a format that can be reviewed and edited. This enables rapid and efficient medical referrals.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user uses a terminal to input patient symptoms and diagnostic information. The terminal converts this information into the appropriate format and sends it to the server.

[0042] Step 2:

[0043] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing to extract characteristic symptoms from the input information and identify related patterns.

[0044] Step 3:

[0045] Based on the analysis results from the AI ​​analysis module, the server identifies the most appropriate area of ​​expertise for the symptoms. The identified area of ​​expertise is stored within the server and used in the next processing step.

[0046] Step 4:

[0047] The server accesses a nationwide database of experts based on the specified area of ​​expertise. Database matching is used to search for experts matching the area of ​​expertise.

[0048] Step 5:

[0049] The server evaluates the recommendation level of experts, taking into account geographical information and the experts' clinical experience. Based on the evaluation results, it generates a list of highly recommended experts.

[0050] Step 6:

[0051] The server automatically generates a referral document using diagnostic information, analyzed specialty areas, and a list of recommended specialists. The referral document includes detailed information such as the diagnosis and recommended specialists.

[0052] Step 7:

[0053] The server sends the generated introductory document to the user's terminal. The user can then use the terminal to review the document and make corrections or additional comments as needed.

[0054] Step 8:

[0055] The referral document, once reviewed and corrected by the user, is provided to the patient via the terminal. The patient can then use this referral document to see the recommended specialist.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] In healthcare settings, it is crucial to quickly and efficiently identify and refer patients to specialists appropriate to their symptoms. However, conventional methods suffer from insufficient accuracy in analyzing diagnostic information and inefficient specialist searches, resulting in delays in finding the right specialist. Furthermore, the generation of referral documents requires manual editing, placing a burden on healthcare professionals.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for converting diagnostic data into a processable format, means for analyzing the converted data to identify areas suitable for the symptoms, and means for searching for specialists based on the identified areas and evaluating the degree of recommendation. This makes it possible to efficiently search for specialists suitable for the patient's symptoms and provide highly accurate recommendations in a short time. Furthermore, by automatically generating referral documents and outputting them in a format that users can easily review and modify, the burden on healthcare professionals can be reduced.

[0061] "Diagnostic data" refers to information collected to assess a patient's health status, including symptoms, medical history, and clinical test results entered into electronic medical record systems.

[0062] A "processable format" refers to a data format that has been converted for efficient analysis and retrieval within a system, and usually refers to standard formats such as JSON or XML.

[0063] "Area of ​​expertise appropriate for symptoms" refers to the medical specialty that is most suitable for the patient's specific symptoms or condition, based on the analyzed diagnostic data.

[0064] "Methods for searching for experts" refers to the processes and techniques used to query databases and extract experts in specific medical fields.

[0065] "Methods for evaluating recommendation levels" refer to algorithms used to determine the suitability of experts, and these evaluations are based on geographical information, past clinical experience, and other factors.

[0066] A "referral document" is a document intended for the specialist to whom a patient is referred, and it includes the patient's diagnostic data, analysis results, and information about the recommended specialist.

[0067] A "prompt statement" is an instruction statement used when performing natural language processing using a generative AI model; it is an input statement used to generate a specific output.

[0068] This invention is a system that automates everything from inputting diagnostic information in a medical setting to generating expert recommendations and referral documents. The system operates using a terminal, a server, an AI analysis module, and a generation AI model.

[0069] First, the user inputs patient diagnostic data using a terminal. The terminal converts this data into a processable format and sends it to the server using a secure communication protocol. On the server, the converted data is passed to an AI analysis module, which uses a machine learning model to identify the appropriate specialty area for the input symptoms. This analysis may utilize programming languages ​​such as Python or AI frameworks such as TENSORFLOW®.

[0070] Next, the server accesses a nationwide database of experts based on the acquired expertise information. This access uses a database management system and issues SQL queries to search for appropriate experts. The search results are evaluated based on geographical information and past experience, and a list of experts to inform the user about is generated.

[0071] Subsequently, the server uses a generative AI model to create the referral document. This model utilizes natural language processing technology to automatically generate the referral letter based on the analyzed information. The generated document is presented in a format that the user can review and edit on their device. Users can easily make corrections using the provided interface.

[0072] As a concrete example, for a patient complaining of heart problems, the user inputs their symptoms on a terminal. The server uses an analysis module to identify cardiology as the appropriate field and recommends relevant specialists. Based on this information, the AI ​​model creates a referral letter and outputs the document in natural language, using prompts such as, "Symptoms: Heart problems. Please generate a referral letter to a specialist in the appropriate field, cardiology."

[0073] This invention improves the work efficiency of healthcare professionals and enables rapid and accurate referrals to specialists for patients.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user uses a terminal to input patient diagnostic data. This data includes symptoms, medical history, and clinical test results. The terminal converts the entered data into JSON or XML format and sends it to the server as structured data. A dedicated data processing application installed on the terminal is used for this conversion.

[0077] Step 2:

[0078] The server receives data sent from the terminal and decodes it using a secure communication protocol (e.g., HTTPS). The server then passes the decoded data to an AI analysis module. The input is structured diagnostic data, and the AI ​​analysis module uses this data to identify the appropriate specialty area for the symptoms. A machine learning model written in Python is used for the analysis, and the identified specialty area is obtained as output.

[0079] Step 3:

[0080] The server accesses a nationwide database of specialists based on the specialized fields identified through analysis. The server issues SQL queries that consider geographical information and the specialists' past clinical experience to search for appropriate specialists. The input is the identified specialized field and location information, and the output is a list of specialists with their recommendation levels evaluated. This makes it possible to identify the specialist best suited to the user.

[0081] Step 4:

[0082] The server automatically generates referral documents using a generative AI model. Based on analysis results and expert recommendations, this model uses natural language processing techniques to create prompts and output referral documents. An example prompt is: "Symptoms: Heart problems. Please generate a referral letter to a specialist in the appropriate field, cardiology." The output is a structured natural language document.

[0083] Step 5:

[0084] The server sends the generated referral document to the user. The user can review the referral document on their terminal and make modifications as needed using interactive editing tools. The output is the finalized referral document, which the user can save in a format such as PDF and prepare to provide to the patient.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] In medical settings and at home, there is a need to quickly and accurately analyze patient diagnostic information and find the appropriate specialist without hassle. However, existing systems require a great deal of manual work, from information input to analysis and specialist recommendations, making efficient and accurate diagnostic support difficult. In particular, improving user convenience and providing reliable, real-time medical services are key challenges.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes data acquisition means for inputting diagnostic information, data analysis means for analyzing the diagnostic information and suggesting a specialized field appropriate to the symptoms, and communication means for communicating information in real time. This allows users to easily input health information through a terminal, enabling rapid and accurate diagnostic support based on that information.

[0090] "Diagnostic information" refers to data about a patient's health status and symptoms, and is essential basic information for health management in medical settings and at home.

[0091] "Data acquisition means" refers to an interface that has the function of allowing users to input diagnostic information via a terminal.

[0092] A "data analysis tool" is a software module that analyzes input diagnostic information and suggests a specialized field appropriate to the symptoms based on that information.

[0093] An "information retrieval tool" is an algorithm for searching for appropriate experts and evaluating their recommendation level based on a proposed area of ​​expertise.

[0094] A "document generation means" is a processing device for automatically creating an introductory document based on analysis results and recommended expert information.

[0095] "Data provision means" refers to technology for displaying and outputting generated introductory documents to the terminal accessed by the user.

[0096] "User interface means" refers to devices and software used by users to input health information via voice or input operations.

[0097] "Communication means" refers to network technology used to transmit data from a terminal to a server in real time.

[0098] The system for realizing this invention has the function of efficiently acquiring the user's health information and providing diagnostic support based on that information. The user provides health information via voice input or touch input using a terminal such as smart glasses. The terminal collects this information using a data acquisition means and transmits it to a smartphone via Bluetooth.

[0099] The smartphone converts the data into a predefined format and transfers it to a server via a cloud service such as Firebase. The server processes the received data using data analysis tools and suggests areas of expertise related to the symptoms using generative AI models such as TensorFlow. Furthermore, it uses information retrieval tools to search for appropriate experts from an expert database based on the suggested areas of expertise and evaluates the degree of recommendation. Finally, it automatically generates an introductory document combining the analysis results and information on the recommended experts using document generation tools and notifies the user's device via data provision tools.

[0100] For example, if a user voice-inputs "blood pressure is a little high" during a morning health check, the system will recommend a cardiologist and notify the user of this information on their smart glasses. An example of a prompt to the generative AI model used in this process is, "Based on the symptoms reported by the user, please search the national database for the most suitable cardiologist and recommend them."

[0101] Thus, the present invention is a system that enables users to easily input health information and receive quick and accurate recommendations from specialists through advanced AI analysis.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The user provides health information via voice or touch input using smart glasses. The input at this stage is data related to the user's health status. The device collects this health information using data acquisition means and transmits the data to a smartphone via Bluetooth.

[0105] Step 2:

[0106] The smartphone converts the received health information into a predefined data format. This conversion process classifies the audio or text information into numerical values ​​and categories, making it analyzable by a cloud server such as Firebase. The converted data is then output and sent to the cloud server.

[0107] Step 3:

[0108] The server receives data transmitted via the cloud. The received data is processed using data analysis tools, and the input symptom data is analyzed using generative AI models such as TensorFlow. The calculation performed here is to identify the most relevant medical specialty based on the data.

[0109] Step 4:

[0110] The server uses information retrieval tools to search a database of experts based on the proposed area of ​​expertise. This step also considers the user's location information, including geographical information, to evaluate the most appropriate experts and create a recommendation list. The output is a list of proposed experts.

[0111] Step 5:

[0112] The server combines the analysis results and recommended expert information using a document generation system to automatically generate an introductory document. At this stage, the generation AI model uses prompt sentences as templates to generate a document in natural language.

[0113] Step 6:

[0114] The server sends the final referral document to the user's terminal via a data delivery system. The user receives a notification through smart glasses and can review the referral document. This allows the user to access specialists smoothly.

[0115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0116] This invention provides a system for use in medical settings where users input patient diagnostic information into a terminal and then propose appropriate areas of expertise based on that information. In addition, the system incorporates an emotion engine that recognizes the user's emotions, and this information is used in the analysis process to improve the accuracy of the analysis.

[0117] The user inputs patient diagnostic information digitally via a terminal. The server receives this information and passes it to the AI ​​analysis module. The AI ​​analysis module uses natural language processing and machine learning algorithms to extract features related to the patient's symptoms from the input information and identify the appropriate area of ​​expertise. Simultaneously, an emotion engine acquires the user's emotional data, which is considered to improve the accuracy of the analysis.

[0118] Based on the analysis results, the server accesses a nationwide database of experts to search for experts corresponding to the proposed area of ​​expertise. Data from the sentiment engine also influences the expert recommendation rating and is used to list the most suitable experts for the user.

[0119] Next, the server automatically generates a referral document based on the diagnostic information, analysis results, and recommended specialist information. Sentiment data is used to adjust the wording in the referral document and provide additional information. The generated referral document is sent to the terminal, where the user can review it and make revisions as needed.

[0120] For example, if a patient reports symptoms related to stress or anxiety, the user's emotional engine recognizes this and considers its relevance in the diagnostic process. The analysis suggests specialist areas such as psychosomatic medicine or psychiatry, and further recommends specialists who take the patient's emotional state into consideration. This emotional information is taken into account in the referral letter, ensuring that the patient is referred to a more appropriate and empathetic specialist.

[0121] In this way, the present invention provides a new method for improving the accuracy of medical information analysis and efficiently referring patients to specialists who are suitable for their needs.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The user uses a terminal to input patient diagnostic information. The terminal converts this information into a digital format and sends it to the server.

[0125] Step 2:

[0126] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing technology to extract related symptom patterns and identify the appropriate area of ​​expertise.

[0127] Step 3:

[0128] Simultaneously, the emotion engine analyzes the user's emotional state while operating the device. Emotional data is extracted from factors such as the user's voice tone and the speed of their actions.

[0129] Step 4:

[0130] The server combines the results of the AI ​​analysis module with emotional data to suggest a specialized field appropriate for the symptoms. The user's emotions are taken into consideration in the suggestions, improving the accuracy of the analysis.

[0131] Step 5:

[0132] The server searches a nationwide database of experts based on the specified area of ​​expertise. Search results are evaluated based on factors such as distance, track record, and user sentiment data to determine their recommendation level.

[0133] Step 6:

[0134] The server automatically generates a referral document using diagnostic information, analyzed areas of expertise, and a list of recommended specialists. The document includes adjustments to the wording based on sentiment data.

[0135] Step 7:

[0136] The server generates an introductory document and sends it to the user's terminal. The user can then use the terminal to review the document and modify or add comments as needed.

[0137] Step 8:

[0138] The referral document, once reviewed and corrected by the user, is provided to the patient via the terminal. The patient can then use this referral document to see the recommended specialist.

[0139] (Example 2)

[0140] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0141] There is a need to provide efficient and highly accurate diagnoses in medical settings and to refer patients to appropriate specialists. Furthermore, it is necessary to offer systems that take user emotions into consideration. Existing systems make it difficult to find specialists that meet users' emotions and individual needs, thus improving diagnostic accuracy and recommendation capabilities.

[0142] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0143] In this invention, the server includes means for inputting diagnostic information, means for analyzing the diagnostic information and suggesting a specialized field appropriate to the symptoms, means for acquiring user emotion information and utilizing it in the analysis process, means for searching for specialists and evaluating the degree of recommendation, and means for automatically generating referral documents. This improves the accuracy of diagnoses in medical settings and makes it possible to efficiently refer patients to the most suitable specialists.

[0144] "Diagnostic information" is a general term for data used in medical settings, such as a patient's symptoms, treatment history, and medical history.

[0145] A "specialized field" refers to a specific medical department or area of ​​expertise within healthcare, encompassing the area of ​​expertise necessary for providing appropriate treatment and diagnosis based on a patient's symptoms.

[0146] "Emotional information" refers to data obtained from the user's facial expressions and voice tone, and is an element used in the diagnostic and expert recommendation processes.

[0147] The term "expert" refers to a medical professional who possesses advanced knowledge and skills in a specific medical field.

[0148] The "analysis process" refers to a series of procedures that identify symptoms and select the most appropriate area of ​​expertise based on diagnostic information.

[0149] "Recommendation level" is an indicator that evaluates the competence and satisfaction level of a professional, and serves as a standard for indicating the best choice for patients and users.

[0150] A "referral document" refers to a document created to summarize a patient's diagnosis and information about recommended specialists, and to convey necessary information in an organized manner.

[0151] "Automatic generation" refers to the process where a program autonomously creates text or content based on necessary data and information.

[0152] This invention provides a system for medical settings that enables efficient suggestion of specialized fields and recommendation of appropriate specialists based on patient diagnostic information. An embodiment of this system is described below.

[0153] Users input patient diagnostic information via terminals used in medical settings. These terminals feature an intuitive interface, enabling users to input information quickly and accurately. The entered information is transmitted to a server in digital format.

[0154] The server passes the received diagnostic information to an AI analysis module. This module primarily uses natural language processing techniques to analyze features related to the patient's symptoms from the input data. The AI ​​analysis module uses TensorFlow and PyTorch as machine learning platforms to support complex data analysis.

[0155] The device also features emotion recognition capabilities, allowing it to acquire user emotional information. This emotional data is considered in the analysis process to improve the quality of patient care. The emotion engine incorporates a common API for performing emotion analysis.

[0156] For example, if a patient exhibits symptoms such as stress or anxiety during their initial consultation, the user inputs this information into their device. The server, through an AI analysis module, suggests specialist areas such as psychosomatic medicine or psychiatry. Furthermore, it considers the patient's emotional needs and recommends the most suitable specialist.

[0157] Examples of prompt statements include the following:

[0158] "The main symptoms patients report are stress and anxiety. Based on the diagnostic information, please suggest the appropriate specialty and specialist."

[0159] The introduction of this system will improve the efficiency of diagnosis and specialist referrals in medical settings, allowing patients to receive more effective medical services.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The user uses a terminal to input patient diagnostic information. This information includes data such as the patient's main symptoms, past medical history, and medical pre-existing conditions. This information is temporarily stored digitally within the terminal, ready to be sent to the next processing step.

[0163] Step 2:

[0164] The terminal sends the entered diagnostic information to the server. The server receives this information and temporarily stores it in its database. This process utilizes a secure communication protocol to ensure that the data is transferred safely.

[0165] Step 3:

[0166] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing technology to tokenize the input information and extract features related to the patient's symptoms. Specifically, for example, it processes text data using an analysis algorithm to identify important keywords. As a result, the appropriate specialty area for the patient is identified.

[0167] Step 4:

[0168] The device activates an emotion engine during user interaction to acquire user emotion information in real time. It collects facial expressions and voice data using a camera and microphone, and analyzes this data using an emotion analysis API. This emotion information is then sent to a server to improve analysis accuracy.

[0169] Step 5:

[0170] The server identifies specialists in the appropriate fields for each patient based on the results of the AI ​​analysis module and emotional information. It accesses a database of specialists and runs a search algorithm, taking into account geographical information and recommendation levels. This generates a list of suitable specialists.

[0171] Step 6:

[0172] The server automatically generates a referral document by combining diagnostic information, a list of specialists, and acquired emotional information. Using natural language generation technology, the information is compiled in a format easily understood by the patient. The generated document is then sent to the terminal.

[0173] Step 7:

[0174] The user reviews the referral document generated on the terminal and makes corrections as needed. The interface includes a function that allows direct text editing, enabling the user to adjust the document content on the spot. The final, reviewed document is then provided to the patient.

[0175] In this way, efficient and highly accurate diagnoses and expert referrals are achieved throughout the entire system.

[0176] (Application Example 2)

[0177] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0178] In recent years, the medical field has seen an increasing demand for the rapid and accurate transmission of patient medical information to specialists. Furthermore, consideration of patients' mental state and emotions in treatment and referrals has become increasingly important. However, effective methods for quantifying emotions and reflecting them in diagnosis have not yet been established, resulting in situations where patients are not referred to the most suitable specialist. There is a need for technology to solve this problem and provide patient-centered medical services.

[0179] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0180] In this invention, the server includes means for inputting diagnostic information, means for analyzing the diagnostic information and suggesting a specialty area appropriate to the symptoms, means for searching for a specialist based on the suggested specialty area and evaluating the degree of recommendation, means for automatically generating a referral document by combining the analysis results and recommended specialist information, means for identifying the user's emotions and considering them in the diagnostic information, and means for adjusting the specialist recommendation based on the identified emotions. This makes it possible to comprehensively analyze the patient's diagnostic information and emotions, and select and refer them to the most suitable specialist.

[0181] "Diagnostic information" refers to a variety of data necessary for medical treatment, such as a patient's symptoms, medical history, and test results.

[0182] A "specialized field" refers to a field within the medical profession that focuses on specific medical treatments or therapies.

[0183] A "specialist" is a healthcare professional who possesses knowledge and experience in a specific area of ​​expertise and is qualified to provide medical care and treatment to patients.

[0184] "Emotions" refer to the psychological state and mood of a user or patient, and are one of the elements considered in diagnostic information.

[0185] A "referral document" is a document automatically generated based on analysis results to refer a patient to a recommended specialist.

[0186] The system in this invention provides a solution for efficiently inputting and analyzing patient diagnostic information in a medical setting. The server receives diagnostic information input via a terminal and sends it to an AI analysis module. This module uses natural language processing and machine learning algorithms to extract features from the diagnostic information and identify specialized fields that are appropriate for the patient's symptoms. Specifically, libraries such as "spaCy" and "Transformers" are used for natural language processing. In addition, "Google® Speech-to-Text" is used as the speech recognition engine, and "Microsoft® Azure® Emotion API" is used for emotion recognition, among others.

[0187] Users input information through their devices, and the server processes it to identify the patient's emotional state. The identified emotional data is used to evaluate and select the most suitable professional for each case.

[0188] The analysis results and expert data generated in this way are used in the automated process of generating referral documents. These referral documents reflect emotional data and are created using patient-appropriate language, helping to alleviate patient anxiety and build trust.

[0189] As a concrete example, during a medical consultation, when a user inputs information via voice, the AI ​​can analyze the tone of the patient's voice and assess their emotions. Based on this information, a specialist in psychosomatic medicine or psychiatry can make appropriate recommendations.

[0190] An example of a prompt to input into a generative AI model is, "A child is afraid of the dentist. How will the emotion-recognizing AI analyze his voice and select a friendly dentist?" This prompt requests a detailed explanation of the emotion recognition process and the doctor selection process based on it.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The terminal receives patient diagnostic information from the user via voice or text. Once this information is entered, a natural language processing engine (e.g., Google Speech-to-Text) is used to convert the voice data into text data. The converted data is then sent to the server.

[0194] Step 2:

[0195] The server sends the diagnostic information received from the terminal to the AI ​​analysis module. This module uses natural language processing libraries (e.g., spaCy, Transformers) to extract features from the diagnostic information. This information is used to identify the appropriate specialty area for the patient's symptoms. The input is diagnostic information in text format, and the output is the relevant specialty area.

[0196] Step 3:

[0197] The server uses an emotion recognition API (e.g., Microsoft Azure Emotion API) to retrieve user emotion data from the terminal and analyze it. The input for emotion analysis is the patient's facial expressions and tone of voice, and the output is an evaluation of their emotional state. This data is processed in conjunction with a specified area of ​​expertise.

[0198] Step 4:

[0199] The server generates a list of recommended professionals based on extracted characteristics and sentiment data. Here, it accesses a nationwide professional database to search for the professional best suited to the patient's condition. The output is a list of recommended professionals.

[0200] Step 5:

[0201] The server automatically generates a referral document based on the analysis results and recommended expert information. The generated referral document reflects consideration for the patient's emotions and symptoms. Emotional data is used to adjust the document and add information, resulting in empathetic language. The output is a referral document.

[0202] Step 6:

[0203] The terminal displays the introductory document sent from the server to the user for review. The user can make revisions to the document as needed, and final approval is then given. The output is the final introductory document.

[0204] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0205] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0206] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0210] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0211] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0212] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0213] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0214] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0215] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0216] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0217] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0218] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0219] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0220] This invention begins with a user in a medical setting using a terminal to input patient diagnostic information. The terminal converts this information into a processable data format and sends it to a server. The server passes the received diagnostic information to an AI analysis module, which analyzes the information and processes it to identify the appropriate area of ​​expertise corresponding to the symptoms.

[0221] Based on the specialized field information obtained from the analysis results, the server accesses a nationwide database of specialists to search for experts. Based on geographical information and the specialists' past clinical experience, it evaluates their suitability and lists highly recommended specialists. The server then refers to this list to support the user in selecting the most suitable specialty.

[0222] Next, the server automatically generates a referral document based on the diagnostic information, analyzed specialty areas, and recommended specialists. The generated referral document is sent to the terminal accessed by the user. The user can review it and add any necessary information. Finally, the completed referral document is provided to the patient via the terminal.

[0223] For example, in the case of a patient complaining of heart-related problems, the user enters their symptoms on the terminal. The server uses an analysis module to identify a cardiologist, searches a nationwide database for the appropriate specialist, and lists the most suitable specialist for the user. Based on this information, the server generates a referral letter and presents it to the user on the terminal in a format that can be reviewed and edited. This enables rapid and efficient medical referrals.

[0224] The following describes the processing flow.

[0225] Step 1:

[0226] The user uses a terminal to input patient symptoms and diagnostic information. The terminal converts this information into the appropriate format and sends it to the server.

[0227] Step 2:

[0228] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing to extract characteristic symptoms from the input information and identify related patterns.

[0229] Step 3:

[0230] Based on the analysis results from the AI ​​analysis module, the server identifies the most appropriate area of ​​expertise for the symptoms. The identified area of ​​expertise is stored within the server and used in the next processing step.

[0231] Step 4:

[0232] The server accesses a nationwide database of experts based on the specified area of ​​expertise. Database matching is used to search for experts matching the area of ​​expertise.

[0233] Step 5:

[0234] The server evaluates the recommendation level of experts, taking into account geographical information and the experts' clinical experience. Based on the evaluation results, it generates a list of highly recommended experts.

[0235] Step 6:

[0236] The server automatically generates a referral document using diagnostic information, analyzed specialty areas, and a list of recommended specialists. The referral document includes detailed information such as the diagnosis and recommended specialists.

[0237] Step 7:

[0238] The server sends the generated introductory document to the user's terminal. The user can then use the terminal to review the document and make corrections or additional comments as needed.

[0239] Step 8:

[0240] The referral document, once reviewed and corrected by the user, is provided to the patient via the terminal. The patient can then use this referral document to see the recommended specialist.

[0241] (Example 1)

[0242] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0243] In healthcare settings, it is crucial to quickly and efficiently identify and refer patients to specialists appropriate to their symptoms. However, conventional methods suffer from insufficient accuracy in analyzing diagnostic information and inefficient specialist searches, resulting in delays in finding the right specialist. Furthermore, the generation of referral documents requires manual editing, placing a burden on healthcare professionals.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes means for converting diagnostic data into a processable format, means for analyzing the converted data to identify areas suitable for the symptoms, and means for searching for specialists based on the identified areas and evaluating the degree of recommendation. This makes it possible to efficiently search for specialists suitable for the patient's symptoms and provide highly accurate recommendations in a short time. Furthermore, by automatically generating referral documents and outputting them in a format that users can easily review and modify, the burden on healthcare professionals can be reduced.

[0246] "Diagnostic data" refers to information collected to assess a patient's health status, including symptoms, medical history, and clinical test results entered into electronic medical record systems.

[0247] A "processable format" refers to a data format that has been converted for efficient analysis and retrieval within a system, and usually refers to standard formats such as JSON or XML.

[0248] "Area of ​​expertise appropriate for symptoms" refers to the medical specialty that is most suitable for the patient's specific symptoms or condition, based on the analyzed diagnostic data.

[0249] "Methods for searching for experts" refers to the processes and techniques used to query databases and extract experts in specific medical fields.

[0250] "Methods for evaluating recommendation levels" refer to algorithms used to determine the suitability of experts, and these evaluations are based on geographical information, past clinical experience, and other factors.

[0251] A "referral document" is a document intended for the specialist to whom a patient is referred, and it includes the patient's diagnostic data, analysis results, and information about the recommended specialist.

[0252] A "prompt statement" is an instruction statement used when performing natural language processing using a generative AI model; it is an input statement used to generate a specific output.

[0253] This invention is a system that automates everything from inputting diagnostic information in a medical setting to generating expert recommendations and referral documents. The system operates using a terminal, a server, an AI analysis module, and a generation AI model.

[0254] First, the user inputs patient diagnostic data using a terminal. The terminal converts this data into a processable format and sends it to the server using a secure communication protocol. On the server, the converted data is passed to an AI analysis module, which uses a machine learning model to identify the appropriate area of ​​expertise for the input symptoms. This analysis may utilize programming languages ​​such as Python or AI frameworks such as TensorFlow.

[0255] Next, the server accesses a nationwide database of experts based on the acquired expertise information. This access uses a database management system and issues SQL queries to search for appropriate experts. The search results are evaluated based on geographical information and past experience, and a list of experts to inform the user about is generated.

[0256] Subsequently, the server uses a generative AI model to create the referral document. This model utilizes natural language processing technology to automatically generate the referral letter based on the analyzed information. The generated document is presented in a format that the user can review and edit on their device. Users can easily make corrections using the provided interface.

[0257] As a concrete example, for a patient complaining of heart problems, the user inputs their symptoms on a terminal. The server uses an analysis module to identify cardiology as the appropriate field and recommends relevant specialists. Based on this information, the AI ​​model creates a referral letter and outputs the document in natural language, using prompts such as, "Symptoms: Heart problems. Please generate a referral letter to a specialist in the appropriate field, cardiology."

[0258] This invention improves the work efficiency of healthcare professionals and enables rapid and accurate referrals to specialists for patients.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1:

[0261] The user uses a terminal to input patient diagnostic data. This data includes symptoms, medical history, and clinical test results. The terminal converts the entered data into JSON or XML format and sends it to the server as structured data. A dedicated data processing application installed on the terminal is used for this conversion.

[0262] Step 2:

[0263] The server receives data sent from the terminal and decodes it using a secure communication protocol (e.g., HTTPS). The server then passes the decoded data to an AI analysis module. The input is structured diagnostic data, and the AI ​​analysis module uses this data to identify the appropriate specialty area for the symptoms. A machine learning model written in Python is used for the analysis, and the identified specialty area is obtained as output.

[0264] Step 3:

[0265] The server accesses a nationwide database of specialists based on the specialized fields identified through analysis. The server issues SQL queries that consider geographical information and the specialists' past clinical experience to search for appropriate specialists. The input is the identified specialized field and location information, and the output is a list of specialists with their recommendation levels evaluated. This makes it possible to identify the specialist best suited to the user.

[0266] Step 4:

[0267] The server automatically generates referral documents using a generative AI model. Based on analysis results and expert recommendations, this model uses natural language processing techniques to create prompts and output referral documents. An example prompt is: "Symptoms: Heart problems. Please generate a referral letter to a specialist in the appropriate field, cardiology." The output is a structured natural language document.

[0268] Step 5:

[0269] The server sends the generated referral document to the user. The user can review the referral document on their terminal and make modifications as needed using interactive editing tools. The output is the finalized referral document, which the user can save in a format such as PDF and prepare to provide to the patient.

[0270] (Application Example 1)

[0271] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] In medical settings and at home, there is a need to quickly and accurately analyze patient diagnostic information and find the appropriate specialist without hassle. However, existing systems require a great deal of manual work, from information input to analysis and specialist recommendations, making efficient and accurate diagnostic support difficult. In particular, improving user convenience and providing reliable, real-time medical services are key challenges.

[0273] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0274] In this invention, the server includes data acquisition means for inputting diagnostic information, data analysis means for analyzing the diagnostic information and suggesting a specialized field appropriate to the symptoms, and communication means for communicating information in real time. This allows users to easily input health information through a terminal, enabling rapid and accurate diagnostic support based on that information.

[0275] "Diagnostic information" refers to data about a patient's health status and symptoms, and is essential basic information for health management in medical settings and at home.

[0276] "Data acquisition means" refers to an interface that has the function of allowing users to input diagnostic information via a terminal.

[0277] A "data analysis tool" is a software module that analyzes input diagnostic information and suggests a specialized field appropriate to the symptoms based on that information.

[0278] An "information retrieval tool" is an algorithm for searching for appropriate experts and evaluating their recommendation level based on a proposed area of ​​expertise.

[0279] The "document generation means" is a processing device for automatically creating an introduction document based on the analysis result and the recommended expert information.

[0280] The "data providing means" is a technology for displaying and outputting the generated introduction document to the terminal accessed by the user.

[0281] The "user interface means" is the device and software used for the user to input health information by voice or input operation.

[0282] The "communication means" is a network technology for transmitting data from the terminal to the server in real time.

[0283] The system for realizing this invention has the function of efficiently acquiring the health information of the user and providing diagnostic support based on it. The user provides health information by voice input or touch input using a terminal such as smart glasses. The terminal collects this information by the data acquisition means and transmits it to the smartphone via Bluetooth.

[0284] The smartphone converts the data into a pre-defined format and transfers it to the server through a cloud service such as Firebase. The server processes the received data using the data analysis means and proposes a specialized area related to the symptoms using a generative AI model such as TensorFlow. Furthermore, based on the proposed specialized area using the information search means, an appropriate expert is searched from the expert database and the recommendation degree is evaluated. Then, an introduction document combining the analysis result and the information of the recommended expert is automatically generated using the document generation means and notified to the user's terminal by the data providing means.

[0285] For example, when a user inputs "high blood pressure" via voice during a morning health check, the system recommends a cardiologist and notifies the user's smart glasses of this information. An example of a prompt sentence for the generative AI model used in this process is "Based on the symptoms reported by the user, please search and recommend the most suitable cardiologist from the national database."

[0286] Thus, the present invention is a system that enables users to easily input health information and receive quick and accurate specialist recommendations through advanced AI analysis.

[0287] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0288] Step 1:

[0289] The user provides health information using smart glasses by voice input or touch input. The input at this stage is data related to the user's health status. The terminal collects this health information by means of data acquisition and transmits the data to the smartphone via Bluetooth.

[0290] Step 2:

[0291] The smartphone converts the received health information into a pre-defined data format. In this conversion process, voice or text information is classified into numerical values or categories to make it analyzable by a cloud server such as Firebase. The converted data is output and transmitted to the cloud server.

[0292] Step 3:

[0293] The server receives the data transmitted via the cloud. The received data is processed by data analysis means, and the input symptom data is analyzed using a generative AI model such as TensorFlow. The calculation performed here is to identify the specialist area most relevant to the symptoms based on the data.

[0294] Step 4:

[0295] The server uses information retrieval tools to search a database of experts based on the proposed area of ​​expertise. This step also considers the user's location information, including geographical information, to evaluate the most appropriate experts and create a recommendation list. The output is a list of proposed experts.

[0296] Step 5:

[0297] The server combines the analysis results and recommended expert information using a document generation system to automatically generate an introductory document. At this stage, the generation AI model uses prompt sentences as templates to generate a document in natural language.

[0298] Step 6:

[0299] The server sends the final referral document to the user's terminal via a data delivery system. The user receives a notification through smart glasses and can review the referral document. This allows the user to access specialists smoothly.

[0300] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0301] This invention provides a system for use in medical settings where users input patient diagnostic information into a terminal and then propose appropriate areas of expertise based on that information. In addition, the system incorporates an emotion engine that recognizes the user's emotions, and this information is used in the analysis process to improve the accuracy of the analysis.

[0302] The user inputs the patient's diagnostic information in digital format via a terminal. The server receives this information and passes it to the AI analysis module. The AI analysis module uses natural language processing and machine learning algorithms to extract features related to the patient's symptoms from the input information and identify the appropriate specialty areas. At the same time, the emotion engine obtains the user's emotion data, which is considered to improve the analysis accuracy.

[0303] Based on the analysis results, the server accesses the national expert database and searches for experts corresponding to the proposed specialty areas. The data from the emotion engine also affects the recommendation degree evaluation of experts and is utilized when listing the most suitable experts for the user.

[0304] Next, the server automatically generates an introduction document based on the diagnostic information, analysis results, and recommended expert information. The emotion data is used to adjust the expression in the introduction document and provide additional information. The generated introduction document is sent to the terminal, where the user can view it and make corrections if necessary.

[0305] As a specific example, when a patient complains of symptoms related to stress or anxiety, the user's emotion engine recognizes this and takes it into account during the diagnosis process. Through analysis, specialty areas such as psychosomatic medicine or psychiatry are proposed, and further recommendations for experts who consider the patient's emotions are made. This emotion information is considered in the referral letter, and a mechanism is in place to introduce a more appropriate and friendly specialist to the patient.

[0306] In this way, the present invention provides a new method for improving the analysis accuracy of medical information and efficiently introducing suitable specialists to patients.

[0307] The following describes the processing flow.

[0308] Step 1:

[0309] The user uses the terminal to input the patient's diagnostic information. The terminal converts this information into digital format and sends it to the server.

[0310] Step 2:

[0311] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing technology to extract related symptom patterns and identify the appropriate area of ​​expertise.

[0312] Step 3:

[0313] Simultaneously, the emotion engine analyzes the user's emotional state while operating the device. Emotional data is extracted from factors such as the user's voice tone and the speed of their actions.

[0314] Step 4:

[0315] The server combines the results of the AI ​​analysis module with emotional data to suggest a specialized field appropriate for the symptoms. The user's emotions are taken into consideration in the suggestions, improving the accuracy of the analysis.

[0316] Step 5:

[0317] The server searches a nationwide database of experts based on the specified area of ​​expertise. Search results are evaluated based on factors such as distance, track record, and user sentiment data to determine their recommendation level.

[0318] Step 6:

[0319] The server automatically generates a referral document using diagnostic information, analyzed areas of expertise, and a list of recommended specialists. The document includes adjustments to the wording based on sentiment data.

[0320] Step 7:

[0321] The server generates an introductory document and sends it to the user's terminal. The user can then use the terminal to review the document and modify or add comments as needed.

[0322] Step 8:

[0323] The referral document, once reviewed and corrected by the user, is provided to the patient via the terminal. The patient can then use this referral document to see the recommended specialist.

[0324] (Example 2)

[0325] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0326] There is a need to provide efficient and highly accurate diagnoses in medical settings and to refer patients to appropriate specialists. Furthermore, it is necessary to offer systems that take user emotions into consideration. Existing systems make it difficult to find specialists that meet users' emotions and individual needs, thus improving diagnostic accuracy and recommendation capabilities.

[0327] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0328] In this invention, the server includes means for inputting diagnostic information, means for analyzing the diagnostic information and suggesting a specialized field appropriate to the symptoms, means for acquiring user emotion information and utilizing it in the analysis process, means for searching for specialists and evaluating the degree of recommendation, and means for automatically generating referral documents. This improves the accuracy of diagnoses in medical settings and makes it possible to efficiently refer patients to the most suitable specialists.

[0329] "Diagnostic information" is a general term for data used in medical settings, such as a patient's symptoms, treatment history, and medical history.

[0330] A "specialized field" refers to a specific medical department or area of ​​expertise within healthcare, encompassing the area of ​​expertise necessary for providing appropriate treatment and diagnosis based on a patient's symptoms.

[0331] "Emotional information" refers to data obtained from the user's facial expressions and voice tone, and is an element used in the diagnostic and expert recommendation processes.

[0332] The term "expert" refers to a medical professional who possesses advanced knowledge and skills in a specific medical field.

[0333] The "analysis process" refers to a series of procedures that identify symptoms and select the most appropriate area of ​​expertise based on diagnostic information.

[0334] "Recommendation level" is an indicator that evaluates the competence and satisfaction level of a professional, and serves as a standard for indicating the best choice for patients and users.

[0335] A "referral document" refers to a document created to summarize a patient's diagnosis and information about recommended specialists, and to convey necessary information in an organized manner.

[0336] "Automatic generation" refers to the process where a program autonomously creates text or content based on necessary data and information.

[0337] This invention provides a system for medical settings that enables efficient suggestion of specialized fields and recommendation of appropriate specialists based on patient diagnostic information. An embodiment of this system is described below.

[0338] Users input patient diagnostic information via terminals used in medical settings. These terminals feature an intuitive interface, enabling users to input information quickly and accurately. The entered information is transmitted to a server in digital format.

[0339] The server passes the received diagnostic information to an AI analysis module. This module primarily uses natural language processing techniques to analyze features related to the patient's symptoms from the input data. The AI ​​analysis module uses TensorFlow and PyTorch as machine learning platforms to support complex data analysis.

[0340] The device also features emotion recognition capabilities, allowing it to acquire user emotional information. This emotional data is considered in the analysis process to improve the quality of patient care. The emotion engine incorporates a common API for performing emotion analysis.

[0341] For example, if a patient exhibits symptoms such as stress or anxiety during their initial consultation, the user inputs this information into their device. The server, through an AI analysis module, suggests specialist areas such as psychosomatic medicine or psychiatry. Furthermore, it considers the patient's emotional needs and recommends the most suitable specialist.

[0342] Examples of prompt statements include the following:

[0343] "The main symptoms patients report are stress and anxiety. Based on the diagnostic information, please suggest the appropriate specialty and specialist."

[0344] The introduction of this system will improve the efficiency of diagnosis and specialist referrals in medical settings, allowing patients to receive more effective medical services.

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Step 1:

[0347] The user uses a terminal to input patient diagnostic information. This information includes data such as the patient's main symptoms, past medical history, and medical pre-existing conditions. This information is temporarily stored digitally within the terminal, ready to be sent to the next processing step.

[0348] Step 2:

[0349] The terminal sends the entered diagnostic information to the server. The server receives this information and temporarily stores it in its database. This process utilizes a secure communication protocol to ensure that the data is transferred safely.

[0350] Step 3:

[0351] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing technology to tokenize the input information and extract features related to the patient's symptoms. Specifically, for example, it processes text data using an analysis algorithm to identify important keywords. As a result, the appropriate specialty area for the patient is identified.

[0352] Step 4:

[0353] The device activates an emotion engine during user interaction to acquire user emotion information in real time. It collects facial expressions and voice data using a camera and microphone, and analyzes this data using an emotion analysis API. This emotion information is then sent to a server to improve analysis accuracy.

[0354] Step 5:

[0355] The server identifies specialists in the appropriate fields for each patient based on the results of the AI ​​analysis module and emotional information. It accesses a database of specialists and runs a search algorithm, taking into account geographical information and recommendation levels. This generates a list of suitable specialists.

[0356] Step 6:

[0357] The server automatically generates a referral document by combining diagnostic information, a list of specialists, and acquired emotional information. Using natural language generation technology, the information is compiled in a format easily understood by the patient. The generated document is then sent to the terminal.

[0358] Step 7:

[0359] The user reviews the referral document generated on the terminal and makes corrections as needed. The interface includes a function that allows direct text editing, enabling the user to adjust the document content on the spot. The final, reviewed document is then provided to the patient.

[0360] In this way, efficient and highly accurate diagnoses and expert referrals are achieved throughout the entire system.

[0361] (Application Example 2)

[0362] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0363] In recent years, the medical field has seen an increasing demand for the rapid and accurate transmission of patient medical information to specialists. Furthermore, consideration of patients' mental state and emotions in treatment and referrals has become increasingly important. However, effective methods for quantifying emotions and reflecting them in diagnosis have not yet been established, resulting in situations where patients are not referred to the most suitable specialist. There is a need for technology to solve this problem and provide patient-centered medical services.

[0364] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0365] In this invention, the server includes means for inputting diagnostic information, means for analyzing the diagnostic information and suggesting a specialty area appropriate to the symptoms, means for searching for a specialist based on the suggested specialty area and evaluating the degree of recommendation, means for automatically generating a referral document by combining the analysis results and recommended specialist information, means for identifying the user's emotions and considering them in the diagnostic information, and means for adjusting the specialist recommendation based on the identified emotions. This makes it possible to comprehensively analyze the patient's diagnostic information and emotions, and select and refer them to the most suitable specialist.

[0366] "Diagnostic information" refers to a variety of data necessary for medical treatment, such as a patient's symptoms, medical history, and test results.

[0367] A "specialized field" refers to a field within the medical profession that focuses on specific medical treatments or therapies.

[0368] A "specialist" is a healthcare professional who possesses knowledge and experience in a specific area of ​​expertise and is qualified to provide medical care and treatment to patients.

[0369] "Emotions" refer to the psychological state and mood of a user or patient, and are one of the elements considered in diagnostic information.

[0370] A "referral document" is a document automatically generated based on analysis results to refer a patient to a recommended specialist.

[0371] The system in this invention provides a solution for efficiently inputting and analyzing patient diagnostic information in a medical setting. The server receives diagnostic information input via a terminal and sends it to an AI analysis module. This module uses natural language processing and machine learning algorithms to extract features from the diagnostic information and identify specialized fields that are appropriate for the patient's symptoms. Specifically, libraries such as "spaCy" and "Transformers" are used for natural language processing. In addition, "Google Speech-to-Text" is used as the speech recognition engine, and "Microsoft Azure Emotion API" is used for emotion recognition.

[0372] Users input information through their devices, and the server processes it to identify the patient's emotional state. The identified emotional data is used to evaluate and select the most suitable professional for each case.

[0373] The analysis results and expert data generated in this way are used in the automated process of generating referral documents. These referral documents reflect emotional data and are created using patient-appropriate language, helping to alleviate patient anxiety and build trust.

[0374] As a concrete example, during a medical consultation, when a user inputs information via voice, the AI ​​can analyze the tone of the patient's voice and assess their emotions. Based on this information, a specialist in psychosomatic medicine or psychiatry can make appropriate recommendations.

[0375] An example of a prompt to input into a generative AI model is, "A child is afraid of the dentist. How will the emotion-recognizing AI analyze his voice and select a friendly dentist?" This prompt requests a detailed explanation of the emotion recognition process and the doctor selection process based on it.

[0376] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0377] Step 1:

[0378] The terminal receives patient diagnostic information from the user via voice or text. Once this information is entered, a natural language processing engine (e.g., Google Speech-to-Text) is used to convert the voice data into text data. The converted data is then sent to the server.

[0379] Step 2:

[0380] The server sends the diagnostic information received from the terminal to the AI ​​analysis module. This module uses natural language processing libraries (e.g., spaCy, Transformers) to extract features from the diagnostic information. This information is used to identify the appropriate specialty area for the patient's symptoms. The input is diagnostic information in text format, and the output is the relevant specialty area.

[0381] Step 3:

[0382] The server uses an emotion recognition API (e.g., Microsoft Azure Emotion API) to retrieve user emotion data from the terminal and analyze it. The input for emotion analysis is the patient's facial expressions and tone of voice, and the output is an evaluation of their emotional state. This data is processed in conjunction with a specified area of ​​expertise.

[0383] Step 4:

[0384] The server generates a list of recommended professionals based on extracted characteristics and sentiment data. Here, it accesses a nationwide professional database to search for the professional best suited to the patient's condition. The output is a list of recommended professionals.

[0385] Step 5:

[0386] The server automatically generates a referral document based on the analysis results and recommended expert information. The generated referral document reflects consideration for the patient's emotions and symptoms. Emotional data is used to adjust the document and add information, resulting in empathetic language. The output is a referral document.

[0387] Step 6:

[0388] The terminal displays the introductory document sent from the server to the user for review. The user can make revisions to the document as needed, and final approval is then given. The output is the final introductory document.

[0389] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0390] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0391] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0392] [Third Embodiment]

[0393] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0394] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0395] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0396] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0397] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0398] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0399] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0400] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0401] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0402] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0403] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0404] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0405] This invention begins with a user in a medical setting using a terminal to input patient diagnostic information. The terminal converts this information into a processable data format and sends it to a server. The server passes the received diagnostic information to an AI analysis module, which analyzes the information and processes it to identify the appropriate area of ​​expertise corresponding to the symptoms.

[0406] Based on the specialized field information obtained from the analysis results, the server accesses a nationwide database of specialists to search for experts. Based on geographical information and the specialists' past clinical experience, it evaluates their suitability and lists highly recommended specialists. The server then refers to this list to support the user in selecting the most suitable specialty.

[0407] Next, the server automatically generates a referral document based on the diagnostic information, analyzed specialty areas, and recommended specialists. The generated referral document is sent to the terminal accessed by the user. The user can review it and add any necessary information. Finally, the completed referral document is provided to the patient via the terminal.

[0408] For example, in the case of a patient complaining of heart-related problems, the user enters their symptoms on the terminal. The server uses an analysis module to identify a cardiologist, searches a nationwide database for the appropriate specialist, and lists the most suitable specialist for the user. Based on this information, the server generates a referral letter and presents it to the user on the terminal in a format that can be reviewed and edited. This enables rapid and efficient medical referrals.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The user uses a terminal to input patient symptoms and diagnostic information. The terminal converts this information into the appropriate format and sends it to the server.

[0412] Step 2:

[0413] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing to extract characteristic symptoms from the input information and identify related patterns.

[0414] Step 3:

[0415] Based on the analysis results from the AI ​​analysis module, the server identifies the most appropriate area of ​​expertise for the symptoms. The identified area of ​​expertise is stored within the server and used in the next processing step.

[0416] Step 4:

[0417] The server accesses a nationwide database of experts based on the specified area of ​​expertise. Database matching is used to search for experts matching the area of ​​expertise.

[0418] Step 5:

[0419] The server evaluates the recommendation level of experts, taking into account geographical information and the experts' clinical experience. Based on the evaluation results, it generates a list of highly recommended experts.

[0420] Step 6:

[0421] The server automatically generates a referral document using diagnostic information, analyzed specialty areas, and a list of recommended specialists. The referral document includes detailed information such as the diagnosis and recommended specialists.

[0422] Step 7:

[0423] The server sends the generated introductory document to the user's terminal. The user can then use the terminal to review the document and make corrections or additional comments as needed.

[0424] Step 8:

[0425] The referral document, once reviewed and corrected by the user, is provided to the patient via the terminal. The patient can then use this referral document to see the recommended specialist.

[0426] (Example 1)

[0427] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0428] In healthcare settings, it is crucial to quickly and efficiently identify and refer patients to specialists appropriate to their symptoms. However, conventional methods suffer from insufficient accuracy in analyzing diagnostic information and inefficient specialist searches, resulting in delays in finding the right specialist. Furthermore, the generation of referral documents requires manual editing, placing a burden on healthcare professionals.

[0429] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0430] In this invention, the server includes means for converting diagnostic data into a processable format, means for analyzing the converted data to identify areas suitable for the symptoms, and means for searching for specialists based on the identified areas and evaluating the degree of recommendation. This makes it possible to efficiently search for specialists suitable for the patient's symptoms and provide highly accurate recommendations in a short time. Furthermore, by automatically generating referral documents and outputting them in a format that users can easily review and modify, the burden on healthcare professionals can be reduced.

[0431] "Diagnostic data" refers to information collected to assess a patient's health status, including symptoms, medical history, and clinical test results entered into electronic medical record systems.

[0432] A "processable format" refers to a data format that has been converted for efficient analysis and retrieval within a system, and usually refers to standard formats such as JSON or XML.

[0433] "Area of ​​expertise appropriate for symptoms" refers to the medical specialty that is most suitable for the patient's specific symptoms or condition, based on the analyzed diagnostic data.

[0434] "Methods for searching for experts" refers to the processes and techniques used to query databases and extract experts in specific medical fields.

[0435] "Methods for evaluating recommendation levels" refer to algorithms used to determine the suitability of experts, and these evaluations are based on geographical information, past clinical experience, and other factors.

[0436] A "referral document" is a document intended for the specialist to whom a patient is referred, and it includes the patient's diagnostic data, analysis results, and information about the recommended specialist.

[0437] A "prompt statement" is an instruction statement used when performing natural language processing using a generative AI model; it is an input statement used to generate a specific output.

[0438] This invention is a system that automates everything from inputting diagnostic information in a medical setting to generating expert recommendations and referral documents. The system operates using a terminal, a server, an AI analysis module, and a generation AI model.

[0439] First, the user inputs patient diagnostic data using a terminal. The terminal converts this data into a processable format and sends it to the server using a secure communication protocol. On the server, the converted data is passed to an AI analysis module, which uses a machine learning model to identify the appropriate area of ​​expertise for the input symptoms. This analysis may utilize programming languages ​​such as Python or AI frameworks such as TensorFlow.

[0440] Next, the server accesses a nationwide database of experts based on the acquired expertise information. This access uses a database management system and issues SQL queries to search for appropriate experts. The search results are evaluated based on geographical information and past experience, and a list of experts to inform the user about is generated.

[0441] Subsequently, the server uses a generative AI model to create the referral document. This model utilizes natural language processing technology to automatically generate the referral letter based on the analyzed information. The generated document is presented in a format that the user can review and edit on their device. Users can easily make corrections using the provided interface.

[0442] As a concrete example, for a patient complaining of heart problems, the user inputs their symptoms on a terminal. The server uses an analysis module to identify cardiology as the appropriate field and recommends relevant specialists. Based on this information, the AI ​​model creates a referral letter and outputs the document in natural language, using prompts such as, "Symptoms: Heart problems. Please generate a referral letter to a specialist in the appropriate field, cardiology."

[0443] This invention improves the work efficiency of healthcare professionals and enables rapid and accurate referrals to specialists for patients.

[0444] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0445] Step 1:

[0446] The user uses a terminal to input patient diagnostic data. This data includes symptoms, medical history, and clinical test results. The terminal converts the entered data into JSON or XML format and sends it to the server as structured data. A dedicated data processing application installed on the terminal is used for this conversion.

[0447] Step 2:

[0448] The server receives data sent from the terminal and decodes it using a secure communication protocol (e.g., HTTPS). The server then passes the decoded data to an AI analysis module. The input is structured diagnostic data, and the AI ​​analysis module uses this data to identify the appropriate specialty area for the symptoms. A machine learning model written in Python is used for the analysis, and the identified specialty area is obtained as output.

[0449] Step 3:

[0450] The server accesses a nationwide database of specialists based on the specialized fields identified through analysis. The server issues SQL queries that consider geographical information and the specialists' past clinical experience to search for appropriate specialists. The input is the identified specialized field and location information, and the output is a list of specialists with their recommendation levels evaluated. This makes it possible to identify the specialist best suited to the user.

[0451] Step 4:

[0452] The server automatically generates referral documents using a generative AI model. Based on analysis results and expert recommendations, this model uses natural language processing techniques to create prompts and output referral documents. An example prompt is: "Symptoms: Heart problems. Please generate a referral letter to a specialist in the appropriate field, cardiology." The output is a structured natural language document.

[0453] Step 5:

[0454] The server sends the generated referral document to the user. The user can review the referral document on their terminal and make modifications as needed using interactive editing tools. The output is the finalized referral document, which the user can save in a format such as PDF and prepare to provide to the patient.

[0455] (Application Example 1)

[0456] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0457] In medical settings and at home, there is a need to quickly and accurately analyze patient diagnostic information and find the appropriate specialist without hassle. However, existing systems require a great deal of manual work, from information input to analysis and specialist recommendations, making efficient and accurate diagnostic support difficult. In particular, improving user convenience and providing reliable, real-time medical services are key challenges.

[0458] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0459] In this invention, the server includes data acquisition means for inputting diagnostic information, data analysis means for analyzing the diagnostic information and suggesting a specialized field appropriate to the symptoms, and communication means for communicating information in real time. This allows users to easily input health information through a terminal, enabling rapid and accurate diagnostic support based on that information.

[0460] "Diagnostic information" refers to data about a patient's health status and symptoms, and is essential basic information for health management in medical settings and at home.

[0461] "Data acquisition means" refers to an interface that has the function of allowing users to input diagnostic information via a terminal.

[0462] A "data analysis tool" is a software module that analyzes input diagnostic information and suggests a specialized field appropriate to the symptoms based on that information.

[0463] An "information retrieval tool" is an algorithm for searching for appropriate experts and evaluating their recommendation level based on a proposed area of ​​expertise.

[0464] A "document generation means" is a processing device for automatically creating an introductory document based on analysis results and recommended expert information.

[0465] "Data provision means" refers to technology for displaying and outputting generated introductory documents to the terminal accessed by the user.

[0466] "User interface means" refers to devices and software used by users to input health information via voice or input operations.

[0467] "Communication means" refers to network technology used to transmit data from a terminal to a server in real time.

[0468] The system for realizing this invention has the function of efficiently acquiring the user's health information and providing diagnostic support based on that information. The user provides health information via voice input or touch input using a terminal such as smart glasses. The terminal collects this information using a data acquisition means and transmits it to a smartphone via Bluetooth.

[0469] The smartphone converts the data into a predefined format and transfers it to a server via a cloud service such as Firebase. The server processes the received data using data analysis tools and suggests areas of expertise related to the symptoms using generative AI models such as TensorFlow. Furthermore, it uses information retrieval tools to search for appropriate experts from an expert database based on the suggested areas of expertise and evaluates the degree of recommendation. Finally, it automatically generates an introductory document combining the analysis results and information on the recommended experts using document generation tools and notifies the user's device via data provision tools.

[0470] For example, if a user voice-inputs "blood pressure is a little high" during a morning health check, the system will recommend a cardiologist and notify the user of this information on their smart glasses. An example of a prompt to the generative AI model used in this process is, "Based on the symptoms reported by the user, please search the national database for the most suitable cardiologist and recommend them."

[0471] Thus, the present invention is a system that enables users to easily input health information and receive quick and accurate recommendations from specialists through advanced AI analysis.

[0472] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0473] Step 1:

[0474] The user provides health information via voice or touch input using smart glasses. The input at this stage is data related to the user's health status. The device collects this health information using data acquisition means and transmits the data to a smartphone via Bluetooth.

[0475] Step 2:

[0476] The smartphone converts the received health information into a predefined data format. This conversion process classifies the audio or text information into numerical values ​​and categories, making it analyzable by a cloud server such as Firebase. The converted data is then output and sent to the cloud server.

[0477] Step 3:

[0478] The server receives data transmitted via the cloud. The received data is processed using data analysis tools, and the input symptom data is analyzed using generative AI models such as TensorFlow. The calculation performed here is to identify the most relevant medical specialty based on the data.

[0479] Step 4:

[0480] The server uses information retrieval tools to search a database of experts based on the proposed area of ​​expertise. This step also considers the user's location information, including geographical information, to evaluate the most appropriate experts and create a recommendation list. The output is a list of proposed experts.

[0481] Step 5:

[0482] The server combines the analysis results and recommended expert information using a document generation system to automatically generate an introductory document. At this stage, the generation AI model uses prompt sentences as templates to generate a document in natural language.

[0483] Step 6:

[0484] The server sends the final referral document to the user's terminal via a data delivery system. The user receives a notification through smart glasses and can review the referral document. This allows the user to access specialists smoothly.

[0485] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0486] This invention provides a system for use in medical settings where users input patient diagnostic information into a terminal and then propose appropriate areas of expertise based on that information. In addition, the system incorporates an emotion engine that recognizes the user's emotions, and this information is used in the analysis process to improve the accuracy of the analysis.

[0487] The user inputs patient diagnostic information digitally via a terminal. The server receives this information and passes it to the AI ​​analysis module. The AI ​​analysis module uses natural language processing and machine learning algorithms to extract features related to the patient's symptoms from the input information and identify the appropriate area of ​​expertise. Simultaneously, an emotion engine acquires the user's emotional data, which is considered to improve the accuracy of the analysis.

[0488] Based on the analysis results, the server accesses a nationwide database of experts to search for experts corresponding to the proposed area of ​​expertise. Data from the sentiment engine also influences the expert recommendation rating and is used to list the most suitable experts for the user.

[0489] Next, the server automatically generates a referral document based on the diagnostic information, analysis results, and recommended specialist information. Sentiment data is used to adjust the wording in the referral document and provide additional information. The generated referral document is sent to the terminal, where the user can review it and make revisions as needed.

[0490] For example, if a patient reports symptoms related to stress or anxiety, the user's emotional engine recognizes this and considers its relevance in the diagnostic process. The analysis suggests specialist areas such as psychosomatic medicine or psychiatry, and further recommends specialists who take the patient's emotional state into consideration. This emotional information is taken into account in the referral letter, ensuring that the patient is referred to a more appropriate and empathetic specialist.

[0491] In this way, the present invention provides a new method for improving the accuracy of medical information analysis and efficiently referring patients to specialists who are suitable for their needs.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] The user uses a terminal to input patient diagnostic information. The terminal converts this information into a digital format and sends it to the server.

[0495] Step 2:

[0496] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing technology to extract related symptom patterns and identify the appropriate area of ​​expertise.

[0497] Step 3:

[0498] Simultaneously, the emotion engine analyzes the user's emotional state while operating the device. Emotional data is extracted from factors such as the user's voice tone and the speed of their actions.

[0499] Step 4:

[0500] The server combines the results of the AI ​​analysis module with emotional data to suggest a specialized field appropriate for the symptoms. The user's emotions are taken into consideration in the suggestions, improving the accuracy of the analysis.

[0501] Step 5:

[0502] The server searches a nationwide database of experts based on the specified area of ​​expertise. Search results are evaluated based on factors such as distance, track record, and user sentiment data to determine their recommendation level.

[0503] Step 6:

[0504] The server automatically generates a referral document using diagnostic information, analyzed areas of expertise, and a list of recommended specialists. The document includes adjustments to the wording based on sentiment data.

[0505] Step 7:

[0506] The server generates an introductory document and sends it to the user's terminal. The user can then use the terminal to review the document and modify or add comments as needed.

[0507] Step 8:

[0508] The referral document, once reviewed and corrected by the user, is provided to the patient via the terminal. The patient can then use this referral document to see the recommended specialist.

[0509] (Example 2)

[0510] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0511] There is a need to provide efficient and highly accurate diagnoses in medical settings and to refer patients to appropriate specialists. Furthermore, it is necessary to offer systems that take user emotions into consideration. Existing systems make it difficult to find specialists that meet users' emotions and individual needs, thus improving diagnostic accuracy and recommendation capabilities.

[0512] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0513] In this invention, the server includes means for inputting diagnostic information, means for analyzing the diagnostic information and suggesting a specialized field appropriate to the symptoms, means for acquiring user emotion information and utilizing it in the analysis process, means for searching for specialists and evaluating the degree of recommendation, and means for automatically generating referral documents. This improves the accuracy of diagnoses in medical settings and makes it possible to efficiently refer patients to the most suitable specialists.

[0514] "Diagnostic information" is a general term for data used in medical settings, such as a patient's symptoms, treatment history, and medical history.

[0515] A "specialized field" refers to a specific medical department or area of ​​expertise within healthcare, encompassing the area of ​​expertise necessary for providing appropriate treatment and diagnosis based on a patient's symptoms.

[0516] "Emotional information" refers to data obtained from the user's facial expressions and voice tone, and is an element used in the diagnostic and expert recommendation processes.

[0517] The term "expert" refers to a medical professional who possesses advanced knowledge and skills in a specific medical field.

[0518] The "analysis process" refers to a series of procedures that identify symptoms and select the most appropriate area of ​​expertise based on diagnostic information.

[0519] "Recommendation level" is an indicator that evaluates the competence and satisfaction level of a professional, and serves as a standard for indicating the best choice for patients and users.

[0520] A "referral document" refers to a document created to summarize a patient's diagnosis and information about recommended specialists, and to convey necessary information in an organized manner.

[0521] "Automatic generation" refers to the process where a program autonomously creates text or content based on necessary data and information.

[0522] This invention provides a system for medical settings that enables efficient suggestion of specialized fields and recommendation of appropriate specialists based on patient diagnostic information. An embodiment of this system is described below.

[0523] Users input patient diagnostic information via terminals used in medical settings. These terminals feature an intuitive interface, enabling users to input information quickly and accurately. The entered information is transmitted to a server in digital format.

[0524] The server passes the received diagnostic information to an AI analysis module. This module primarily uses natural language processing techniques to analyze features related to the patient's symptoms from the input data. The AI ​​analysis module uses TensorFlow and PyTorch as machine learning platforms to support complex data analysis.

[0525] The device also features emotion recognition capabilities, allowing it to acquire user emotional information. This emotional data is considered in the analysis process to improve the quality of patient care. The emotion engine incorporates a common API for performing emotion analysis.

[0526] For example, if a patient exhibits symptoms such as stress or anxiety during their initial consultation, the user inputs this information into their device. The server, through an AI analysis module, suggests specialist areas such as psychosomatic medicine or psychiatry. Furthermore, it considers the patient's emotional needs and recommends the most suitable specialist.

[0527] Examples of prompt statements include the following:

[0528] "The main symptoms patients report are stress and anxiety. Based on the diagnostic information, please suggest the appropriate specialty and specialist."

[0529] The introduction of this system will improve the efficiency of diagnosis and specialist referrals in medical settings, allowing patients to receive more effective medical services.

[0530] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0531] Step 1:

[0532] The user uses a terminal to input patient diagnostic information. This information includes data such as the patient's main symptoms, past medical history, and medical pre-existing conditions. This information is temporarily stored digitally within the terminal, ready to be sent to the next processing step.

[0533] Step 2:

[0534] The terminal sends the entered diagnostic information to the server. The server receives this information and temporarily stores it in its database. This process utilizes a secure communication protocol to ensure that the data is transferred safely.

[0535] Step 3:

[0536] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing technology to tokenize the input information and extract features related to the patient's symptoms. Specifically, for example, it processes text data using an analysis algorithm to identify important keywords. As a result, the appropriate specialty area for the patient is identified.

[0537] Step 4:

[0538] The device activates an emotion engine during user interaction to acquire user emotion information in real time. It collects facial expressions and voice data using a camera and microphone, and analyzes this data using an emotion analysis API. This emotion information is then sent to a server to improve analysis accuracy.

[0539] Step 5:

[0540] The server identifies specialists in the appropriate fields for each patient based on the results of the AI ​​analysis module and emotional information. It accesses a database of specialists and runs a search algorithm, taking into account geographical information and recommendation levels. This generates a list of suitable specialists.

[0541] Step 6:

[0542] The server automatically generates a referral document by combining diagnostic information, a list of specialists, and acquired emotional information. Using natural language generation technology, the information is compiled in a format easily understood by the patient. The generated document is then sent to the terminal.

[0543] Step 7:

[0544] The user reviews the referral document generated on the terminal and makes corrections as needed. The interface includes a function that allows direct text editing, enabling the user to adjust the document content on the spot. The final, reviewed document is then provided to the patient.

[0545] In this way, efficient and highly accurate diagnoses and expert referrals are achieved throughout the entire system.

[0546] (Application Example 2)

[0547] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0548] In recent years, the medical field has seen an increasing demand for the rapid and accurate transmission of patient medical information to specialists. Furthermore, consideration of patients' mental state and emotions in treatment and referrals has become increasingly important. However, effective methods for quantifying emotions and reflecting them in diagnosis have not yet been established, resulting in situations where patients are not referred to the most suitable specialist. There is a need for technology to solve this problem and provide patient-centered medical services.

[0549] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0550] In this invention, the server includes means for inputting diagnostic information, means for analyzing the diagnostic information and suggesting a specialty area appropriate to the symptoms, means for searching for a specialist based on the suggested specialty area and evaluating the degree of recommendation, means for automatically generating a referral document by combining the analysis results and recommended specialist information, means for identifying the user's emotions and considering them in the diagnostic information, and means for adjusting the specialist recommendation based on the identified emotions. This makes it possible to comprehensively analyze the patient's diagnostic information and emotions, and select and refer them to the most suitable specialist.

[0551] "Diagnostic information" refers to a variety of data necessary for medical treatment, such as a patient's symptoms, medical history, and test results.

[0552] A "specialized field" refers to a field within the medical profession that focuses on specific medical treatments or therapies.

[0553] A "specialist" is a healthcare professional who possesses knowledge and experience in a specific area of ​​expertise and is qualified to provide medical care and treatment to patients.

[0554] "Emotions" refer to the psychological state and mood of a user or patient, and are one of the elements considered in diagnostic information.

[0555] A "referral document" is a document automatically generated based on analysis results to refer a patient to a recommended specialist.

[0556] The system in this invention provides a solution for efficiently inputting and analyzing patient diagnostic information in a medical setting. The server receives diagnostic information input via a terminal and sends it to an AI analysis module. This module uses natural language processing and machine learning algorithms to extract features from the diagnostic information and identify specialized fields that are appropriate for the patient's symptoms. Specifically, libraries such as "spaCy" and "Transformers" are used for natural language processing. In addition, "Google Speech-to-Text" is used as the speech recognition engine, and "Microsoft Azure Emotion API" is used for emotion recognition.

[0557] Users input information through their devices, and the server processes it to identify the patient's emotional state. The identified emotional data is used to evaluate and select the most suitable professional for each case.

[0558] The analysis results and expert data generated in this way are used in the automated process of generating referral documents. These referral documents reflect emotional data and are created using patient-appropriate language, helping to alleviate patient anxiety and build trust.

[0559] As a concrete example, during a medical consultation, when a user inputs information via voice, the AI ​​can analyze the tone of the patient's voice and assess their emotions. Based on this information, a specialist in psychosomatic medicine or psychiatry can make appropriate recommendations.

[0560] An example of a prompt to input into a generative AI model is, "A child is afraid of the dentist. How will the emotion-recognizing AI analyze his voice and select a friendly dentist?" This prompt requests a detailed explanation of the emotion recognition process and the doctor selection process based on it.

[0561] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0562] Step 1:

[0563] The terminal receives patient diagnostic information from the user via voice or text. Once this information is entered, a natural language processing engine (e.g., Google Speech-to-Text) is used to convert the voice data into text data. The converted data is then sent to the server.

[0564] Step 2:

[0565] The server sends the diagnostic information received from the terminal to the AI ​​analysis module. This module uses natural language processing libraries (e.g., spaCy, Transformers) to extract features from the diagnostic information. This information is used to identify the appropriate specialty area for the patient's symptoms. The input is diagnostic information in text format, and the output is the relevant specialty area.

[0566] Step 3:

[0567] The server uses an emotion recognition API (e.g., Microsoft Azure Emotion API) to retrieve user emotion data from the terminal and analyze it. The input for emotion analysis is the patient's facial expressions and tone of voice, and the output is an evaluation of their emotional state. This data is processed in conjunction with a specified area of ​​expertise.

[0568] Step 4:

[0569] The server generates a list of recommended professionals based on extracted characteristics and sentiment data. Here, it accesses a nationwide professional database to search for the professional best suited to the patient's condition. The output is a list of recommended professionals.

[0570] Step 5:

[0571] The server automatically generates a referral document based on the analysis results and recommended expert information. The generated referral document reflects consideration for the patient's emotions and symptoms. Emotional data is used to adjust the document and add information, resulting in empathetic language. The output is a referral document.

[0572] Step 6:

[0573] The terminal displays the introductory document sent from the server to the user for review. The user can make revisions to the document as needed, and final approval is then given. The output is the final introductory document.

[0574] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0575] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0576] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0577] [Fourth Embodiment]

[0578] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0579] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0580] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0581] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0582] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0583] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0584] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0585] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0586] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0587] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0588] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0589] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0590] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0591] This invention begins with a user in a medical setting using a terminal to input patient diagnostic information. The terminal converts this information into a processable data format and sends it to a server. The server passes the received diagnostic information to an AI analysis module, which analyzes the information and processes it to identify the appropriate area of ​​expertise corresponding to the symptoms.

[0592] Based on the specialized field information obtained from the analysis results, the server accesses a nationwide database of specialists to search for experts. Based on geographical information and the specialists' past clinical experience, it evaluates their suitability and lists highly recommended specialists. The server then refers to this list to support the user in selecting the most suitable specialty.

[0593] Next, the server automatically generates a referral document based on the diagnostic information, analyzed specialty areas, and recommended specialists. The generated referral document is sent to the terminal accessed by the user. The user can review it and add any necessary information. Finally, the completed referral document is provided to the patient via the terminal.

[0594] For example, in the case of a patient complaining of heart-related problems, the user enters their symptoms on the terminal. The server uses an analysis module to identify a cardiologist, searches a nationwide database for the appropriate specialist, and lists the most suitable specialist for the user. Based on this information, the server generates a referral letter and presents it to the user on the terminal in a format that can be reviewed and edited. This enables rapid and efficient medical referrals.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The user uses a terminal to input patient symptoms and diagnostic information. The terminal converts this information into the appropriate format and sends it to the server.

[0598] Step 2:

[0599] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing to extract characteristic symptoms from the input information and identify related patterns.

[0600] Step 3:

[0601] Based on the analysis results from the AI ​​analysis module, the server identifies the most appropriate area of ​​expertise for the symptoms. The identified area of ​​expertise is stored within the server and used in the next processing step.

[0602] Step 4:

[0603] The server accesses a nationwide database of experts based on the specified area of ​​expertise. Database matching is used to search for experts matching the area of ​​expertise.

[0604] Step 5:

[0605] The server evaluates the recommendation level of experts, taking into account geographical information and the experts' clinical experience. Based on the evaluation results, it generates a list of highly recommended experts.

[0606] Step 6:

[0607] The server automatically generates a referral document using diagnostic information, analyzed specialty areas, and a list of recommended specialists. The referral document includes detailed information such as the diagnosis and recommended specialists.

[0608] Step 7:

[0609] The server sends the generated introductory document to the user's terminal. The user can then use the terminal to review the document and make corrections or additional comments as needed.

[0610] Step 8:

[0611] The referral document, once reviewed and corrected by the user, is provided to the patient via the terminal. The patient can then use this referral document to see the recommended specialist.

[0612] (Example 1)

[0613] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0614] In healthcare settings, it is crucial to quickly and efficiently identify and refer patients to specialists appropriate to their symptoms. However, conventional methods suffer from insufficient accuracy in analyzing diagnostic information and inefficient specialist searches, resulting in delays in finding the right specialist. Furthermore, the generation of referral documents requires manual editing, placing a burden on healthcare professionals.

[0615] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0616] In this invention, the server includes means for converting diagnostic data into a processable format, means for analyzing the converted data to identify areas suitable for the symptoms, and means for searching for specialists based on the identified areas and evaluating the degree of recommendation. This makes it possible to efficiently search for specialists suitable for the patient's symptoms and provide highly accurate recommendations in a short time. Furthermore, by automatically generating referral documents and outputting them in a format that users can easily review and modify, the burden on healthcare professionals can be reduced.

[0617] "Diagnostic data" refers to information collected to assess a patient's health status, including symptoms, medical history, and clinical test results entered into electronic medical record systems.

[0618] A "processable format" refers to a data format that has been converted for efficient analysis and retrieval within a system, and usually refers to standard formats such as JSON or XML.

[0619] "Area of ​​expertise appropriate for symptoms" refers to the medical specialty that is most suitable for the patient's specific symptoms or condition, based on the analyzed diagnostic data.

[0620] "Methods for searching for experts" refers to the processes and techniques used to query databases and extract experts in specific medical fields.

[0621] "Methods for evaluating recommendation levels" refer to algorithms used to determine the suitability of experts, and these evaluations are based on geographical information, past clinical experience, and other factors.

[0622] A "referral document" is a document intended for the specialist to whom a patient is referred, and it includes the patient's diagnostic data, analysis results, and information about the recommended specialist.

[0623] A "prompt statement" is an instruction statement used when performing natural language processing using a generative AI model; it is an input statement used to generate a specific output.

[0624] This invention is a system that automates everything from inputting diagnostic information in a medical setting to generating expert recommendations and referral documents. The system operates using a terminal, a server, an AI analysis module, and a generation AI model.

[0625] First, the user inputs patient diagnostic data using a terminal. The terminal converts this data into a processable format and sends it to the server using a secure communication protocol. On the server, the converted data is passed to an AI analysis module, which uses a machine learning model to identify the appropriate area of ​​expertise for the input symptoms. This analysis may utilize programming languages ​​such as Python or AI frameworks such as TensorFlow.

[0626] Next, the server accesses a nationwide database of experts based on the acquired expertise information. This access uses a database management system and issues SQL queries to search for appropriate experts. The search results are evaluated based on geographical information and past experience, and a list of experts to inform the user about is generated.

[0627] Subsequently, the server uses a generative AI model to create the referral document. This model utilizes natural language processing technology to automatically generate the referral letter based on the analyzed information. The generated document is presented in a format that the user can review and edit on their device. Users can easily make corrections using the provided interface.

[0628] As a concrete example, for a patient complaining of heart problems, the user inputs their symptoms on a terminal. The server uses an analysis module to identify cardiology as the appropriate field and recommends relevant specialists. Based on this information, the AI ​​model creates a referral letter and outputs the document in natural language, using prompts such as, "Symptoms: Heart problems. Please generate a referral letter to a specialist in the appropriate field, cardiology."

[0629] This invention improves the work efficiency of healthcare professionals and enables rapid and accurate referrals to specialists for patients.

[0630] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0631] Step 1:

[0632] The user uses a terminal to input patient diagnostic data. This data includes symptoms, medical history, and clinical test results. The terminal converts the entered data into JSON or XML format and sends it to the server as structured data. A dedicated data processing application installed on the terminal is used for this conversion.

[0633] Step 2:

[0634] The server receives data sent from the terminal and decodes it using a secure communication protocol (e.g., HTTPS). The server then passes the decoded data to an AI analysis module. The input is structured diagnostic data, and the AI ​​analysis module uses this data to identify the appropriate specialty area for the symptoms. A machine learning model written in Python is used for the analysis, and the identified specialty area is obtained as output.

[0635] Step 3:

[0636] The server accesses a nationwide database of specialists based on the specialized fields identified through analysis. The server issues SQL queries that consider geographical information and the specialists' past clinical experience to search for appropriate specialists. The input is the identified specialized field and location information, and the output is a list of specialists with their recommendation levels evaluated. This makes it possible to identify the specialist best suited to the user.

[0637] Step 4:

[0638] The server automatically generates referral documents using a generative AI model. Based on analysis results and expert recommendations, this model uses natural language processing techniques to create prompts and output referral documents. An example prompt is: "Symptoms: Heart problems. Please generate a referral letter to a specialist in the appropriate field, cardiology." The output is a structured natural language document.

[0639] Step 5:

[0640] The server sends the generated referral document to the user. The user can review the referral document on their terminal and make modifications as needed using interactive editing tools. The output is the finalized referral document, which the user can save in a format such as PDF and prepare to provide to the patient.

[0641] (Application Example 1)

[0642] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] In medical settings and at home, there is a need to quickly and accurately analyze patient diagnostic information and find the appropriate specialist without hassle. However, existing systems require a great deal of manual work, from information input to analysis and specialist recommendations, making efficient and accurate diagnostic support difficult. In particular, improving user convenience and providing reliable, real-time medical services are key challenges.

[0644] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0645] In this invention, the server includes data acquisition means for inputting diagnostic information, data analysis means for analyzing the diagnostic information and suggesting a specialized field appropriate to the symptoms, and communication means for communicating information in real time. This allows users to easily input health information through a terminal, enabling rapid and accurate diagnostic support based on that information.

[0646] "Diagnostic information" refers to data about a patient's health status and symptoms, and is essential basic information for health management in medical settings and at home.

[0647] "Data acquisition means" refers to an interface that has the function of allowing users to input diagnostic information via a terminal.

[0648] A "data analysis tool" is a software module that analyzes input diagnostic information and suggests a specialized field appropriate to the symptoms based on that information.

[0649] An "information retrieval tool" is an algorithm for searching for appropriate experts and evaluating their recommendation level based on a proposed area of ​​expertise.

[0650] A "document generation means" is a processing device for automatically creating an introductory document based on analysis results and recommended expert information.

[0651] "Data provision means" refers to technology for displaying and outputting generated introductory documents to the terminal accessed by the user.

[0652] "User interface means" refers to devices and software used by users to input health information via voice or input operations.

[0653] "Communication means" refers to network technology used to transmit data from a terminal to a server in real time.

[0654] The system for realizing this invention has the function of efficiently acquiring the user's health information and providing diagnostic support based on that information. The user provides health information via voice input or touch input using a terminal such as smart glasses. The terminal collects this information using a data acquisition means and transmits it to a smartphone via Bluetooth.

[0655] The smartphone converts the data into a predefined format and transfers it to a server via a cloud service such as Firebase. The server processes the received data using data analysis tools and suggests areas of expertise related to the symptoms using generative AI models such as TensorFlow. Furthermore, it uses information retrieval tools to search for appropriate experts from an expert database based on the suggested areas of expertise and evaluates the degree of recommendation. Finally, it automatically generates an introductory document combining the analysis results and information on the recommended experts using document generation tools and notifies the user's device via data provision tools.

[0656] For example, if a user voice-inputs "blood pressure is a little high" during a morning health check, the system will recommend a cardiologist and notify the user of this information on their smart glasses. An example of a prompt to the generative AI model used in this process is, "Based on the symptoms reported by the user, please search the national database for the most suitable cardiologist and recommend them."

[0657] Thus, the present invention is a system that enables users to easily input health information and receive quick and accurate recommendations from specialists through advanced AI analysis.

[0658] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0659] Step 1:

[0660] The user provides health information via voice or touch input using smart glasses. The input at this stage is data related to the user's health status. The device collects this health information using data acquisition means and transmits the data to a smartphone via Bluetooth.

[0661] Step 2:

[0662] The smartphone converts the received health information into a predefined data format. This conversion process classifies the audio or text information into numerical values ​​and categories, making it analyzable by a cloud server such as Firebase. The converted data is then output and sent to the cloud server.

[0663] Step 3:

[0664] The server receives data transmitted via the cloud. The received data is processed using data analysis tools, and the input symptom data is analyzed using generative AI models such as TensorFlow. The calculation performed here is to identify the most relevant medical specialty based on the data.

[0665] Step 4:

[0666] The server uses information retrieval tools to search a database of experts based on the proposed area of ​​expertise. This step also considers the user's location information, including geographical information, to evaluate the most appropriate experts and create a recommendation list. The output is a list of proposed experts.

[0667] Step 5:

[0668] The server combines the analysis results and recommended expert information using a document generation system to automatically generate an introductory document. At this stage, the generation AI model uses prompt sentences as templates to generate a document in natural language.

[0669] Step 6:

[0670] The server sends the final referral document to the user's terminal via a data delivery system. The user receives a notification through smart glasses and can review the referral document. This allows the user to access specialists smoothly.

[0671] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0672] This invention provides a system for use in medical settings where users input patient diagnostic information into a terminal and then propose appropriate areas of expertise based on that information. In addition, the system incorporates an emotion engine that recognizes the user's emotions, and this information is used in the analysis process to improve the accuracy of the analysis.

[0673] The user inputs patient diagnostic information digitally via a terminal. The server receives this information and passes it to the AI ​​analysis module. The AI ​​analysis module uses natural language processing and machine learning algorithms to extract features related to the patient's symptoms from the input information and identify the appropriate area of ​​expertise. Simultaneously, an emotion engine acquires the user's emotional data, which is considered to improve the accuracy of the analysis.

[0674] Based on the analysis results, the server accesses a nationwide database of experts to search for experts corresponding to the proposed area of ​​expertise. Data from the sentiment engine also influences the expert recommendation rating and is used to list the most suitable experts for the user.

[0675] Next, the server automatically generates a referral document based on the diagnostic information, analysis results, and recommended specialist information. Sentiment data is used to adjust the wording in the referral document and provide additional information. The generated referral document is sent to the terminal, where the user can review it and make revisions as needed.

[0676] For example, if a patient reports symptoms related to stress or anxiety, the user's emotional engine recognizes this and considers its relevance in the diagnostic process. The analysis suggests specialist areas such as psychosomatic medicine or psychiatry, and further recommends specialists who take the patient's emotional state into consideration. This emotional information is taken into account in the referral letter, ensuring that the patient is referred to a more appropriate and empathetic specialist.

[0677] In this way, the present invention provides a new method for improving the accuracy of medical information analysis and efficiently referring patients to specialists who are suitable for their needs.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] The user uses a terminal to input patient diagnostic information. The terminal converts this information into a digital format and sends it to the server.

[0681] Step 2:

[0682] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing technology to extract related symptom patterns and identify the appropriate area of ​​expertise.

[0683] Step 3:

[0684] Simultaneously, the emotion engine analyzes the user's emotional state while operating the device. Emotional data is extracted from factors such as the user's voice tone and the speed of their actions.

[0685] Step 4:

[0686] The server combines the results of the AI ​​analysis module with emotional data to suggest a specialized field appropriate for the symptoms. The user's emotions are taken into consideration in the suggestions, improving the accuracy of the analysis.

[0687] Step 5:

[0688] The server searches a nationwide database of experts based on the specified area of ​​expertise. Search results are evaluated based on factors such as distance, track record, and user sentiment data to determine their recommendation level.

[0689] Step 6:

[0690] The server automatically generates a referral document using diagnostic information, analyzed areas of expertise, and a list of recommended specialists. The document includes adjustments to the wording based on sentiment data.

[0691] Step 7:

[0692] The server generates an introductory document and sends it to the user's terminal. The user can then use the terminal to review the document and modify or add comments as needed.

[0693] Step 8:

[0694] The referral document, once reviewed and corrected by the user, is provided to the patient via the terminal. The patient can then use this referral document to see the recommended specialist.

[0695] (Example 2)

[0696] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] There is a need to provide efficient and highly accurate diagnoses in medical settings and to refer patients to appropriate specialists. Furthermore, it is necessary to offer systems that take user emotions into consideration. Existing systems make it difficult to find specialists that meet users' emotions and individual needs, thus improving diagnostic accuracy and recommendation capabilities.

[0698] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0699] In this invention, the server includes means for inputting diagnostic information, means for analyzing the diagnostic information and suggesting a specialized field appropriate to the symptoms, means for acquiring user emotion information and utilizing it in the analysis process, means for searching for specialists and evaluating the degree of recommendation, and means for automatically generating referral documents. This improves the accuracy of diagnoses in medical settings and makes it possible to efficiently refer patients to the most suitable specialists.

[0700] "Diagnostic information" is a general term for data used in medical settings, such as a patient's symptoms, treatment history, and medical history.

[0701] A "specialized field" refers to a specific medical department or area of ​​expertise within healthcare, encompassing the area of ​​expertise necessary for providing appropriate treatment and diagnosis based on a patient's symptoms.

[0702] "Emotional information" refers to data obtained from the user's facial expressions and voice tone, and is an element used in the diagnostic and expert recommendation processes.

[0703] The term "expert" refers to a medical professional who possesses advanced knowledge and skills in a specific medical field.

[0704] The "analysis process" refers to a series of procedures that identify symptoms and select the most appropriate area of ​​expertise based on diagnostic information.

[0705] "Recommendation level" is an indicator that evaluates the competence and satisfaction level of a professional, and serves as a standard for indicating the best choice for patients and users.

[0706] A "referral document" refers to a document created to summarize a patient's diagnosis and information about recommended specialists, and to convey necessary information in an organized manner.

[0707] "Automatic generation" refers to the process where a program autonomously creates text or content based on necessary data and information.

[0708] This invention provides a system for medical settings that enables efficient suggestion of specialized fields and recommendation of appropriate specialists based on patient diagnostic information. An embodiment of this system is described below.

[0709] Users input patient diagnostic information via terminals used in medical settings. These terminals feature an intuitive interface, enabling users to input information quickly and accurately. The entered information is transmitted to a server in digital format.

[0710] The server passes the received diagnostic information to an AI analysis module. This module primarily uses natural language processing techniques to analyze features related to the patient's symptoms from the input data. The AI ​​analysis module uses TensorFlow and PyTorch as machine learning platforms to support complex data analysis.

[0711] The device also features emotion recognition capabilities, allowing it to acquire user emotional information. This emotional data is considered in the analysis process to improve the quality of patient care. The emotion engine incorporates a common API for performing emotion analysis.

[0712] For example, if a patient exhibits symptoms such as stress or anxiety during their initial consultation, the user inputs this information into their device. The server, through an AI analysis module, suggests specialist areas such as psychosomatic medicine or psychiatry. Furthermore, it considers the patient's emotional needs and recommends the most suitable specialist.

[0713] Examples of prompt statements include the following:

[0714] "The main symptoms patients report are stress and anxiety. Based on the diagnostic information, please suggest the appropriate specialty and specialist."

[0715] The introduction of this system will improve the efficiency of diagnosis and specialist referrals in medical settings, allowing patients to receive more effective medical services.

[0716] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0717] Step 1:

[0718] The user uses a terminal to input patient diagnostic information. This information includes data such as the patient's main symptoms, past medical history, and medical pre-existing conditions. This information is temporarily stored digitally within the terminal, ready to be sent to the next processing step.

[0719] Step 2:

[0720] The terminal sends the entered diagnostic information to the server. The server receives this information and temporarily stores it in its database. This process utilizes a secure communication protocol to ensure that the data is transferred safely.

[0721] Step 3:

[0722] The server passes the received diagnostic information to the AI ​​analysis module. The AI ​​analysis module uses natural language processing technology to tokenize the input information and extract features related to the patient's symptoms. Specifically, for example, it processes text data using an analysis algorithm to identify important keywords. As a result, the appropriate specialty area for the patient is identified.

[0723] Step 4:

[0724] The device activates an emotion engine during user interaction to acquire user emotion information in real time. It collects facial expressions and voice data using a camera and microphone, and analyzes this data using an emotion analysis API. This emotion information is then sent to a server to improve analysis accuracy.

[0725] Step 5:

[0726] The server identifies specialists in the appropriate fields for each patient based on the results of the AI ​​analysis module and emotional information. It accesses a database of specialists and runs a search algorithm, taking into account geographical information and recommendation levels. This generates a list of suitable specialists.

[0727] Step 6:

[0728] The server automatically generates a referral document by combining diagnostic information, a list of specialists, and acquired emotional information. Using natural language generation technology, the information is compiled in a format easily understood by the patient. The generated document is then sent to the terminal.

[0729] Step 7:

[0730] The user reviews the referral document generated on the terminal and makes corrections as needed. The interface includes a function that allows direct text editing, enabling the user to adjust the document content on the spot. The final, reviewed document is then provided to the patient.

[0731] In this way, efficient and highly accurate diagnoses and expert referrals are achieved throughout the entire system.

[0732] (Application Example 2)

[0733] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0734] In recent years, the medical field has seen an increasing demand for the rapid and accurate transmission of patient medical information to specialists. Furthermore, consideration of patients' mental state and emotions in treatment and referrals has become increasingly important. However, effective methods for quantifying emotions and reflecting them in diagnosis have not yet been established, resulting in situations where patients are not referred to the most suitable specialist. There is a need for technology to solve this problem and provide patient-centered medical services.

[0735] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0736] In this invention, the server includes means for inputting diagnostic information, means for analyzing the diagnostic information and suggesting a specialty area appropriate to the symptoms, means for searching for a specialist based on the suggested specialty area and evaluating the degree of recommendation, means for automatically generating a referral document by combining the analysis results and recommended specialist information, means for identifying the user's emotions and considering them in the diagnostic information, and means for adjusting the specialist recommendation based on the identified emotions. This makes it possible to comprehensively analyze the patient's diagnostic information and emotions, and select and refer them to the most suitable specialist.

[0737] "Diagnostic information" refers to a variety of data necessary for medical treatment, such as a patient's symptoms, medical history, and test results.

[0738] A "specialized field" refers to a field within the medical profession that focuses on specific medical treatments or therapies.

[0739] A "specialist" is a healthcare professional who possesses knowledge and experience in a specific area of ​​expertise and is qualified to provide medical care and treatment to patients.

[0740] "Emotions" refer to the psychological state and mood of a user or patient, and are one of the elements considered in diagnostic information.

[0741] A "referral document" is a document automatically generated based on analysis results to refer a patient to a recommended specialist.

[0742] The system in this invention provides a solution for efficiently inputting and analyzing patient diagnostic information in a medical setting. The server receives diagnostic information input via a terminal and sends it to an AI analysis module. This module uses natural language processing and machine learning algorithms to extract features from the diagnostic information and identify specialized fields that are appropriate for the patient's symptoms. Specifically, libraries such as "spaCy" and "Transformers" are used for natural language processing. In addition, "Google Speech-to-Text" is used as the speech recognition engine, and "Microsoft Azure Emotion API" is used for emotion recognition.

[0743] Users input information through their devices, and the server processes it to identify the patient's emotional state. The identified emotional data is used to evaluate and select the most suitable professional for each case.

[0744] The analysis results and expert data generated in this way are used in the automated process of generating referral documents. These referral documents reflect emotional data and are created using patient-appropriate language, helping to alleviate patient anxiety and build trust.

[0745] As a concrete example, during a medical consultation, when a user inputs information via voice, the AI ​​can analyze the tone of the patient's voice and assess their emotions. Based on this information, a specialist in psychosomatic medicine or psychiatry can make appropriate recommendations.

[0746] An example of a prompt to input into a generative AI model is, "A child is afraid of the dentist. How will the emotion-recognizing AI analyze his voice and select a friendly dentist?" This prompt requests a detailed explanation of the emotion recognition process and the doctor selection process based on it.

[0747] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0748] Step 1:

[0749] The terminal receives patient diagnostic information from the user via voice or text. Once this information is entered, a natural language processing engine (e.g., Google Speech-to-Text) is used to convert the voice data into text data. The converted data is then sent to the server.

[0750] Step 2:

[0751] The server sends the diagnostic information received from the terminal to the AI ​​analysis module. This module uses natural language processing libraries (e.g., spaCy, Transformers) to extract features from the diagnostic information. This information is used to identify the appropriate specialty area for the patient's symptoms. The input is diagnostic information in text format, and the output is the relevant specialty area.

[0752] Step 3:

[0753] The server uses an emotion recognition API (e.g., Microsoft Azure Emotion API) to retrieve user emotion data from the terminal and analyze it. The input for emotion analysis is the patient's facial expressions and tone of voice, and the output is an evaluation of their emotional state. This data is processed in conjunction with a specified area of ​​expertise.

[0754] Step 4:

[0755] The server generates a list of recommended professionals based on extracted characteristics and sentiment data. Here, it accesses a nationwide professional database to search for the professional best suited to the patient's condition. The output is a list of recommended professionals.

[0756] Step 5:

[0757] The server automatically generates a referral document based on the analysis results and recommended expert information. The generated referral document reflects consideration for the patient's emotions and symptoms. Emotional data is used to adjust the document and add information, resulting in empathetic language. The output is a referral document.

[0758] Step 6:

[0759] The terminal displays the introductory document sent from the server to the user for review. The user can make revisions to the document as needed, and final approval is then given. The output is the final introductory document.

[0760] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0761] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0762] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0763] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0764] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0765] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0766] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0767] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0768] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0769] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0770] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0771] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0772] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0773] 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.

[0774] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0775] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0776] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0777] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0778] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0779] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0780] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0781] The following is further disclosed regarding the embodiments described above.

[0782] (Claim 1)

[0783] A means of entering diagnostic information,

[0784] A means of analyzing the aforementioned diagnostic information and proposing a specialized field appropriate to the symptoms,

[0785] A means for searching for experts based on the proposed specialized fields and evaluating the degree of recommendation,

[0786] A means for automatically generating an introductory document by combining the aforementioned analysis results and recommended expert information,

[0787] means for outputting the aforementioned introductory document,

[0788] A system that includes this.

[0789] (Claim 2)

[0790] The system according to claim 1, wherein the search means for the aforementioned expert takes geographical information into consideration during the search.

[0791] (Claim 3)

[0792] The system according to claim 1, wherein the introductory document generation means includes an interface that allows the user to arbitrarily modify the information.

[0793] "Example 1"

[0794] (Claim 1)

[0795] A means of inputting diagnostic data,

[0796] Means for converting the aforementioned diagnostic data into a format that can be processed,

[0797] A means for analyzing the converted data to identify a region suitable for the symptoms,

[0798] A means for searching for experts based on the aforementioned identified areas and evaluating the degree of recommendation,

[0799] A means for generating introductory documents using the aforementioned analysis results and recommended expert information,

[0800] A means for outputting the aforementioned introductory document in a format that the user can review and modify,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the means for searching for the aforementioned expert takes into account geographical information and past experience.

[0804] (Claim 3)

[0805] The system according to claim 1, wherein the referral document generation means uses a prompt statement when generating the document.

[0806] "Application Example 1"

[0807] (Claim 1)

[0808] A means for acquiring data to input diagnostic information,

[0809] A data analysis means for analyzing the aforementioned diagnostic information and proposing a specialized field appropriate to the symptoms,

[0810] Information retrieval means for searching for experts based on the proposed specialized fields and evaluating the degree of recommendation,

[0811] A document generation means for automatically generating an introductory document by combining the aforementioned analysis results and recommended expert information,

[0812] A data provision means for outputting the aforementioned introductory document,

[0813] A user interface means for the user to input health information into the terminal by voice or input operation,

[0814] A communication method for sending data from a terminal to a server in real time,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, wherein the information retrieval means performs the search while taking geographic information into consideration.

[0818] (Claim 3)

[0819] The system according to claim 1, wherein the document generation means includes an interface that allows the user to arbitrarily modify the information.

[0820] "Example 2 of combining an emotion engine"

[0821] (Claim 1)

[0822] A means of entering diagnostic information,

[0823] A means of analyzing the aforementioned diagnostic information and proposing a specialized field appropriate to the symptoms,

[0824] A means of acquiring user sentiment information and utilizing it in the analysis process,

[0825] A means for searching for experts based on the proposed specialized fields and evaluating the degree of recommendation,

[0826] A means for automatically generating an introductory document by combining the aforementioned analysis results and recommended expert information,

[0827] The means includes an interface that outputs the aforementioned introductory document and allows the user to review and modify it,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, wherein the means for searching for experts takes geographical information into consideration and reflects sentiment information in the expert recommendation score.

[0831] (Claim 3)

[0832] The system according to claim 1, wherein the analysis means extracts features from diagnostic information using natural language processing technology and machine learning technology.

[0833] "Application example 2 when combining with an emotional engine"

[0834] (Claim 1)

[0835] A means of entering diagnostic information,

[0836] A means of analyzing the aforementioned diagnostic information and proposing a specialized field appropriate to the symptoms,

[0837] A means for searching for experts based on the proposed specialized fields and evaluating the degree of recommendation,

[0838] A means for automatically generating an introductory document by combining the aforementioned analysis results and recommended expert information,

[0839] means for outputting the aforementioned introductory document,

[0840] A means of identifying user emotions and taking them into consideration in diagnostic information,

[0841] A means of adjusting expert recommendations based on identified emotions,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, wherein the search means for the aforementioned expert takes geographical information into consideration during the search.

[0845] (Claim 3)

[0846] The system according to claim 1, wherein the introductory document generation means includes an interface that allows the user to arbitrarily modify the information. [Explanation of Symbols]

[0847] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring data to input diagnostic information, A data analysis means for analyzing the aforementioned diagnostic information and proposing a specialized field appropriate to the symptoms, Information retrieval means for searching for experts based on the proposed specialized fields and evaluating the degree of recommendation, A document generation means for automatically generating an introductory document by combining the aforementioned analysis results and recommended expert information, A data provision means for outputting the aforementioned introductory document, A user interface means for the user to input health information into the terminal by voice or input operation, A communication method for sending data from a terminal to a server in real time, A system that includes this.

2. The system according to claim 1, wherein the information retrieval means performs the search while taking geographical information into consideration.

3. The system according to claim 1, wherein the document generation means includes an interface that allows the user to arbitrarily modify the information.

Images