system

Abstract

The system according to the embodiment aims to automate and streamline the process of creating a letter of introduction. [Solution] A system according to an embodiment includes a reception unit, a generation unit, a format unit, a check unit, and a deletion unit. The reception unit inputs patient information. The generation unit automatically creates a referral letter based on the information input by the reception unit. The format unit converts the referral letter generated by the generation unit into a unified format. The check unit performs error checks on the referral letter converted by the format unit. The deletion unit deletes personal information from the referral letter confirmed by the check unit.

Description

[Technical Field]

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

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

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

[0004] With previous technology, creating hospital referral letters was time-consuming and resource-intensive, and posed challenges such as incorrect or missing information and inconsistent formatting.

[0005] The system according to the embodiment aims to automate and streamline the process of creating a letter of introduction. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, a format unit, a check unit, and a deletion unit. The reception unit inputs patient information. The generation unit automatically creates a referral letter based on the information input by the reception unit. The format unit converts the referral letter generated by the generation unit into a unified format. The check unit checks for errors in the referral letter converted by the format unit. The deletion unit deletes personal information from the referral letter confirmed by the check unit. [Effects of the Invention]

[0007] The system according to the embodiment can automate and streamline the process of creating a referral letter. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An automatic referral letter creation system according to an embodiment of the present invention efficiently inputs patient information, and a generation AI automatically creates a referral letter, converts it into a unified format, performs error checks, and deletes personal information. The automatic referral letter creation system inputs patient information, and a generation AI analyzes the information to automatically create a referral letter. The generated referral letter is converted into a unified format and checked for errors. Finally, personal information is deleted, and the referral letter is completed. For example, in the automatic referral letter creation system, a medical institution inputs patient information, including the patient's name, age, medical treatment details, and the name of the referring hospital. This information is input into the generation AI. Next, the automatic referral letter creation system uses the generation AI to analyze the input information and automatically create a referral letter. The generation AI generates appropriate referral letter content based on the input information. For example, the generation AI creates a referral letter containing the necessary information for the referring hospital based on the patient's medical treatment details. Next, the automatic referral letter creation system converts the generated referral letter into a unified format. A formatting unit converts the generated referral letter into a unified format. This makes the format of the referral letter consistent and easy to read. Next, the automatic referral letter creation system checks the contents of the generated referral letter to check for any errors or omissions in the information. A checking unit checks the contents of the generated referral letter to check for any errors or omissions in the information. This improves the quality of the referral letter. Finally, the automatic referral letter creation system deletes personal information from the referral letter. A deletion unit deletes personal information from the referral letter to protect privacy. This prevents the leakage of personal information. As a result, the automatic referral letter creation system improves the operational efficiency of medical institutions and the quality of patient care. As a result, the automatic referral letter creation system can improve the operational efficiency of medical institutions and the quality of patient care. For example, medical institutions can reduce the time and resources required to create referral letters and focus on caring for patients. In addition, the quality of referral letters improves, and information is provided to referring hospitals accurately and quickly. Furthermore, protection of personal information is strengthened, and patient privacy is protected.

[0029] The automatic referral letter creation system according to the embodiment includes a reception unit, a generation unit, a formatting unit, a check unit, and a deletion unit. The reception unit inputs patient information. The patient information includes, but is not limited to, the patient's name, age, gender, and medical history. The reception unit inputs, for example, basic patient information, medical treatment details, and referral destination information. The reception unit can also input the patient information in digital format. The generation unit uses a generation AI to automatically create a referral letter based on the information input by the reception unit. The generation unit generates a referral letter including information required for the referral destination hospital, for example, based on the patient's medical treatment details. The generation unit can also use the generation AI to analyze the patient information and generate appropriate referral letter content. For example, the generation AI generates the referral letter using a text generation AI (e.g., LLM). The formatting unit converts the referral letter generated by the generation unit into a unified format. For example, the formatting unit converts the generated referral letter into a unified format. This makes the format of the referral letter consistent and easy to read. The check unit checks for errors in the referral letter converted by the formatting unit. The checking unit, for example, checks the contents of the generated referral letter to check for errors or omissions in the information. The checking unit can perform, for example, spelling check, grammar check, and information consistency check. The deletion unit deletes personal information from the referral letter checked by the checking unit. The deletion unit deletes personal information such as name, address, and telephone number from the referral letter. This makes it possible to prevent leakage of personal information. As a result, the automatic referral letter creation system according to the embodiment can efficiently input, generate, format convert, check for errors, and delete personal information about patients.

[0030] The reception unit can input basic information about the patient, details of medical treatment, and information about the referral destination. The basic information about the patient includes, for example, name, age, gender, address, etc., but is not limited to these examples. The reception unit, for example, inputs the basic information about the patient. The reception unit can also input details of medical treatment. The details of medical treatment include, for example, diagnosis results, details of treatment, prescribed medications, etc., but is not limited to these examples. The reception unit, for example, inputs details of medical treatment. The reception unit can also input information about the referral destination. The information about the referral destination includes, for example, the name of the medical institution, the address, the name of the doctor in charge, etc., but is not limited to these examples. The reception unit, for example, inputs information about the referral destination. This allows the basic information about the patient, details of medical treatment, and information about the referral destination to be input accurately.

[0031] The generation unit can generate appropriate referral letter content based on the input information. The generation unit generates a referral letter including information required for the referring hospital, for example, based on the patient's medical treatment. The generation unit can also analyze patient information and generate appropriate referral letter content, for example, using a generation AI. The generation AI generates a referral letter using, for example, a text generation AI (e.g., LLM). The generation unit can also generate appropriate referral letter content based on the patient information, using the generation AI. For example, the generation AI generates a referral letter including information required for the referring hospital, based on the patient's medical treatment. This makes it possible to generate an appropriate referral letter based on the input information.

[0032] The formatting unit can convert the generated letters of referral into a unified format. For example, the formatting unit can convert the generated letters of referral into a unified format based on criteria such as font size, layout, and item order. This makes the format of the letters of referral consistent and easy to read. For example, the formatting unit can convert the generated letters of referral into a unified format. The formatting unit can also adjust the format of the generated letters of referral. For example, the formatting unit can adjust the font size and layout of the letters of referral to convert them into a format that is easy to read. This makes the format of the letters of referral consistent and easy to read.

[0033] The checking unit can check the contents of the generated letter of introduction and check for any errors or omissions in the information. For example, the checking unit can check the contents of the generated letter of introduction and check for any errors or omissions in the information. The checking unit can perform, for example, spelling check, grammar check, and information consistency check. For example, the checking unit can check the contents of the generated letter of introduction and check for any errors or omissions in the information. The checking unit can also correct any errors or omissions in the information to improve the quality of the generated letter of introduction. For example, the checking unit corrects any erroneous information and completes any missing information. This can improve the quality of the letter of introduction.

[0034] The deletion unit can delete personal information from the referral letter. For example, the deletion unit deletes personal information such as name, address, and telephone number from the referral letter. For example, the deletion unit deletes personal information from the referral letter to protect privacy. For example, the deletion unit deletes personal information from the referral letter. The deletion unit can also delete personal information from the referral letter to prevent leakage of personal information. For example, the deletion unit deletes personal information from the referral letter to protect privacy. This makes it possible to prevent leakage of personal information. Some or all of the above-described processing in the deletion unit may be performed using AI, or may be performed without using AI, for example. For example, the deletion unit can delete personal information using an AI model that deletes personal information from the referral letter.

[0035] The reception unit can analyze the patient's past medical history and select the optimal information input method. For example, if the patient has preferred voice input in the past, the reception unit can preferentially suggest voice input. For example, if the patient has frequently used text input in the past, the reception unit can also recommend text input. For example, if the patient has used image input in the past, the reception unit can also select image input. This makes it possible to select the optimal information input method based on the patient's past medical history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select the optimal information input method using an AI model that analyzes the patient's past medical history.

[0036] The reception unit can filter information based on the patient's current health condition and areas of interest when inputting information. For example, if the patient's current health condition is poor, the reception unit minimizes the number of input items. For example, if the patient has a specific area of ​​interest, the reception unit can also prioritize input of information related to that area. For example, if the patient has a specific medical history, the reception unit can also prioritize input of information related to that medical history. This makes it possible to input information according to the patient's health condition and areas of interest. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can filter information when inputting information using an AI model that analyzes the patient's health condition and areas of interest.

[0037] When inputting information, the reception unit can select an appropriate input means according to the patient's input method. For example, if the patient desires voice input, the reception unit can provide voice input preferentially. For example, if the patient desires text input, the reception unit can also provide text input preferentially. For example, if the patient desires image input, the reception unit can also provide image input preferentially. This makes it possible to input information according to the patient's desired input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select an appropriate input means using an AI model that analyzes the patient's input method.

[0038] The reception unit can prioritize input of highly relevant information based on the patient's geographical location information when inputting information. For example, if the patient lives in a specific area, the reception unit can prioritize input of information related to that area. For example, if the patient visits a specific hospital, the reception unit can also prioritize input of information related to that hospital. For example, if the patient plans to receive medical treatment in a specific area, the reception unit can also prioritize input of information related to that area. This allows highly relevant information to be prioritized based on the patient's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can use an AI model that analyzes the patient's geographical location information to prioritize input of highly relevant information when inputting information.

[0039] The reception unit can analyze the patient's social media activity and input relevant information when inputting information. The reception unit can input relevant information based on, for example, health information shared by the patient on social media. The reception unit can also input information related to medical institutions that the patient follows on social media. The reception unit can also input relevant information based on, for example, health-related groups that the patient joins on social media. This allows input of relevant information based on the patient's social media activity. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input relevant information when inputting information using an AI model that analyzes the patient's social media activity.

[0040] The reception unit can customize the input method by reflecting the patient's past feedback when inputting information. For example, if the patient has preferred voice input in the past, the reception unit can preferentially provide voice input. For example, if the patient has frequently used text input in the past, the reception unit can also recommend text input. For example, if the patient has used image input in the past, the reception unit can also select image input. This allows the input method to be customized based on the patient's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can customize the input method when inputting information by using an AI model that analyzes the patient's past feedback.

[0041] When generating a referral letter, the generation unit can adjust the level of detail in the referral letter based on the patient's medical treatment. For example, if the patient's medical treatment is complex, the generation unit generates a referral letter including detailed information. For example, if the patient's medical treatment is simple, the generation unit can also generate a concise referral letter. For example, the generation unit can also generate a referral letter that appropriately includes necessary information depending on the patient's medical treatment. This makes it possible to adjust the level of detail in the referral letter depending on the patient's medical treatment. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can adjust the level of detail in the referral letter using an AI model that analyzes the patient's medical treatment.

[0042] The generation unit can apply different generation algorithms depending on the patient category when generating a referral letter. For example, in the case of a pediatric patient, the generation unit can apply a generation algorithm that uses expressions for children. For example, in the case of an elderly patient, the generation unit can also apply a generation algorithm that uses expressions for the elderly. For example, in the case of a patient with a specific disease, the generation unit can also apply a generation algorithm that uses expressions specialized for that disease. This makes it possible to apply the optimal generation algorithm depending on the patient category. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can apply different generation algorithms when generating a referral letter using an AI model that analyzes the patient category.

[0043] When generating a referral letter, the generation unit can improve the accuracy of the generation by referring to the patient's past referral letter results. The generation unit, for example, analyzes the patient's past referral letters and generates a referral letter containing similar content. The generation unit can also improve the accuracy of the generation by, for example, feedback from the patient's past referral letters. The generation unit can also generate an optimal referral letter by referring to, for example, successful cases of the patient's past referral letters. This makes it possible to improve the accuracy of the generation by referring to the patient's past referral letter results. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can improve the accuracy of the generation when generating a referral letter by using an AI model that analyzes the patient's past referral letter results.

[0044] The generation unit can determine the priority of referral letters based on the timing of the patient's medical examination when generating the referral letters. For example, if the patient's medical examination date is approaching, the generation unit generates the referral letters with priority. For example, if the patient's medical examination date is far away, the generation unit can also postpone generating the referral letters. For example, the generation unit can also generate the referral letters at an appropriate time depending on the timing of the patient's medical examination. This makes it possible to determine the priority of referral letters based on the timing of the patient's medical examination. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can determine the priority when generating the referral letters using an AI model that analyzes the timing of the patient's medical examination.

[0045] The generation unit can adjust the order of referral letters based on the relevance of patients when generating the referral letters. For example, if the patient's medical treatment details are highly relevant, the generation unit can generate the referral letters preferentially. For example, if the patient's medical treatment details are less relevant, the generation unit can also postpone generating the referral letters. For example, the generation unit can also generate the referral letters in an appropriate order depending on the patient's medical treatment details. This makes it possible to adjust the order of referral letters based on the relevance of patients. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can adjust the order when generating the referral letters using an AI model that analyzes the relevance of patients.

[0046] When generating a referral letter, the generation unit can adjust the use of technical terminology in the referral letter according to the patient's level of expertise. For example, if the patient has technical expertise, the generation unit generates a referral letter that uses a lot of technical terminology. For example, if the patient does not have technical expertise, the generation unit can also generate a referral letter that uses easy-to-understand language. For example, the generation unit can also generate a referral letter that uses appropriate language according to the patient's level of expertise. This makes it possible to generate a referral letter that uses appropriate language according to the patient's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can adjust the use of technical terminology when generating a referral letter using an AI model that analyzes the patient's level of expertise.

[0047] The formatting unit can adjust the level of detail in the format based on the importance of the referral letter during format conversion. For example, if the importance of the referral letter is high, the formatting unit can provide a format including detailed information. For example, if the importance of the referral letter is low, the formatting unit can also provide a concise format. For example, the formatting unit can also provide a format with appropriate level of detail depending on the importance of the referral letter. This allows the level of detail in the format to be adjusted depending on the importance of the referral letter. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can adjust the level of detail during format conversion using an AI model that analyzes the importance of the referral letter.

[0048] The formatting unit can apply different formatting algorithms depending on the category of the referral letter during format conversion. For example, in the case of a referral letter for a pediatric patient, the formatting unit can apply a format for children. For example, in the case of a referral letter for an elderly patient, the formatting unit can also apply a format for elderly people. For example, in the case of a referral letter for a patient with a specific disease, the formatting unit can also apply a format specialized for that disease. This allows the optimal formatting algorithm to be applied depending on the category of the referral letter. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can apply different formatting algorithms during format conversion using an AI model that analyzes the category of the referral letter.

[0049] During format conversion, the formatting unit can improve the accuracy of the format by referring to the patient's past formatting results. For example, the formatting unit analyzes the patient's past referral letter formats and applies a similar format. For example, the formatting unit can also improve the accuracy of the format based on feedback from the patient's past formats. For example, the formatting unit can provide an optimal format by referring to successful formatting examples from the patient's past. This allows the accuracy of the format to be improved by referring to the patient's past formatting results. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can improve the accuracy during format conversion by using an AI model that analyzes the patient's past formatting results.

[0050] The formatting unit can determine the priority of formats based on the submission date of the letter of introduction during format conversion. For example, the formatting unit prioritizes format conversion when the submission date of the letter of introduction is approaching. For example, the formatting unit can postpone format conversion when the submission date of the letter of introduction is far away. For example, the formatting unit can also convert formats at an appropriate time depending on the submission date of the letter of introduction. This makes it possible to determine the priority of formats depending on the submission date of the letter of introduction. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can determine the priority during format conversion using an AI model that analyzes the submission date of the letter of introduction.

[0051] The formatting unit can adjust the order of the formats based on the relevance of the letters of referral during format conversion. For example, if the relevance of the letters of referral is high, the formatting unit prioritizes format conversion. For example, if the relevance of the letters of referral is low, the formatting unit can also postpone format conversion. For example, the formatting unit can also convert the formats in an appropriate order depending on the relevance of the letters of referral. This makes it possible to adjust the order of the formats depending on the relevance of the letters of referral. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can adjust the order during format conversion using an AI model that analyzes the relevance of the letters of referral.

[0052] The formatting unit can adjust the use of technical terminology in the format during format conversion according to the patient's level of expertise. For example, if the patient has technical expertise, the formatting unit can provide a format that uses a lot of technical terminology. For example, if the patient does not have technical expertise, the formatting unit can also provide a format that uses easy-to-understand expressions. For example, the formatting unit can also provide a format that uses appropriate expressions according to the patient's level of expertise. This makes it possible to provide a format that uses appropriate expressions according to the patient's level of expertise. Some or all of the above-described processing in the formatting unit can be performed using, for example, AI, or can be performed without using AI. For example, the formatting unit can adjust the use of technical terminology during format conversion using an AI model that analyzes the patient's level of expertise.

[0053] The check unit can improve the accuracy of the check by taking into account the interrelationships between letters of referral during error checks. For example, the check unit checks to ensure that the contents of the letter of referral do not contradict other letters of referral. For example, if the contents of the letter of referral are related to other letters of referral, the check unit can also check by taking into account that relationship. For example, if the contents of the letter of referral match other letters of referral, the check unit can also check by confirming that match. This improves the accuracy of the check by taking into account the interrelationships between letters of referral. Some or all of the above-mentioned processing in the check unit may be performed using, for example, AI, or may be performed without using AI. For example, the check unit can improve the accuracy of the error check by using an AI model that analyzes the interrelationships between letters of referral.

[0054] When checking for errors, the check unit can take into account the attribute information of the person who submitted the letter of referral. For example, if the submitter is a doctor, the check unit can take into account the person's specialized knowledge when checking. For example, if the submitter is a nurse, the check unit can also take into account the person's specialized knowledge when checking. For example, if the submitter is an office worker, the check unit can also take into account the person's specialized knowledge when checking. In this way, by taking into account the attribute information of the person who submitted the letter of referral, the accuracy of the check can be improved. Some or all of the above-mentioned processing in the check unit may be performed using, for example, AI, or may be performed without using AI. For example, the check unit can improve the accuracy of error checks by using an AI model that analyzes the attribute information of the submitter.

[0055] The check unit can weight the checks based on the frequency of referral submissions during error checks. For example, if the submission frequency is high, the check unit can perform strict error checks. For example, if the submission frequency is low, the check unit can also perform flexible error checks. For example, the check unit can also weight the checks appropriately according to the submission frequency. By weighting the checks based on the frequency of referral submissions, the accuracy of the checks can be improved. Some or all of the above-described processing in the check unit can be performed using, for example, AI, or can be performed without using AI. For example, the check unit can weight the error checks using an AI model that analyzes the submission frequency.

[0056] The check unit can perform an error check while taking into account the geographic distribution of the referral letters. For example, if the recipients of the referral letters are concentrated in a specific region, the check unit checks while taking into account the characteristics of that region. For example, if the recipients of the referral letters are spread over a wide area, the check unit can also perform an error check while taking into account the characteristics of each region. For example, if the recipients of the referral letters are biased toward a specific region, the check unit can also perform an error check while taking into account that bias. In this way, by performing an error check while taking into account the geographic distribution of the referral letters, the accuracy of the error check can be improved. Some or all of the above-described processing in the check unit may be performed using, for example, AI, or may be performed without using AI. For example, the check unit can improve the accuracy of the error check by using an AI model that analyzes the geographic distribution.

[0057] The checking unit can improve the accuracy of the check by referring to the related literature of the letter of referral during the error check. For example, the checking unit can check whether the contents of the letter of referral match the related literature. For example, the checking unit can also check whether the contents of the letter of referral are consistent with the related literature. For example, the checking unit can also check whether the contents of the letter of referral are relevant to the related literature. This can improve the accuracy of the check by referring to the related literature of the letter of referral. Some or all of the above-mentioned processing in the checking unit can be performed using, for example, AI, or can be performed without using AI. For example, the checking unit can improve the accuracy during the error check by using an AI model that analyzes the related literature.

[0058] The check unit can perform an error check while taking into account the market value of the letter of introduction. For example, if the market value of the letter of introduction is high, the check unit can perform a strict error check. For example, if the market value of the letter of introduction is low, the check unit can also perform a flexible error check. For example, the check unit can also perform an appropriate error check depending on the market value of the letter of introduction. In this way, by performing a check while taking into account the market value of the letter of introduction, the accuracy of the check can be improved. Some or all of the above-mentioned processing in the check unit can be performed using, for example, AI, or can be performed without using AI. For example, the check unit can improve the accuracy of the error check by using an AI model that analyzes market value.

[0059] When deleting information, the deletion unit can improve the accuracy of deletion by taking into account the interrelationships between letters of introduction. For example, the deletion unit deletes information so that the contents of the letter of introduction do not contradict other letters of introduction. For example, if the contents of the letter of introduction are related to other letters of introduction, the deletion unit can also delete the information by taking into account the interrelationships. For example, if the contents of the letter of introduction match other letters of introduction, the deletion unit can also confirm the match and delete the information. This improves the accuracy of deletion by taking into account the interrelationships between letters of introduction. Some or all of the above-described processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can improve the accuracy when deleting information by using an AI model that analyzes interrelationships.

[0060] When deleting information, the deletion unit can perform the deletion taking into consideration the attribute information of the person who submitted the letter of referral. For example, if the submitter is a doctor, the deletion unit can perform the deletion taking into consideration the person's expertise. For example, if the submitter is a nurse, the deletion unit can also perform the deletion taking into consideration the person's expertise. For example, if the submitter is an office worker, the deletion unit can also perform the deletion taking into consideration the person's expertise. In this way, by performing the deletion taking into consideration the attribute information of the person who submitted the letter of referral, the accuracy of the deletion can be improved. Some or all of the above-mentioned processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can improve the accuracy when deleting information by using an AI model that analyzes the attribute information of the submitter.

[0061] The deletion unit can weight the deletion based on the frequency of referral submissions when deleting information. For example, the deletion unit performs strict information deletion when the submission frequency is high. For example, the deletion unit can also perform flexible information deletion when the submission frequency is low. The deletion unit can also perform appropriate weighting according to the submission frequency, for example. By weighting the deletion based on the frequency of referral submissions, the accuracy of deletion can be improved. Some or all of the above-described processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can weight the information when deleting it using an AI model that analyzes the submission frequency.

[0062] When deleting information, the deletion unit can perform the deletion taking into account the geographical distribution of referral letters. For example, if the destinations for referral letters are concentrated in a specific region, the deletion unit deletes the information taking into account the characteristics of that region. For example, if the destinations for referral letters are spread over a wide area, the deletion unit can also delete the information taking into account the characteristics of each region. For example, if the destinations for referral letters are biased toward a specific region, the deletion unit can also delete the information taking into account that bias. In this way, by performing deletion taking into account the geographical distribution of referral letters, the accuracy of the deletion can be improved. Some or all of the above-described processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can improve the accuracy when deleting information by using an AI model that analyzes the geographical distribution.

[0063] When deleting information, the deletion unit can improve the accuracy of deletion by referring to related literature in the letter of introduction. For example, the deletion unit checks whether the contents of the letter of introduction match the related literature. For example, the deletion unit can also check whether the contents of the letter of introduction are consistent with the related literature. For example, the deletion unit can also check whether the contents of the letter of introduction are relevant to the related literature. This can improve the accuracy of deletion by referring to the related literature in the letter of introduction. Some or all of the above-mentioned processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can improve the accuracy when deleting information by using an AI model that analyzes related literature.

[0064] The deletion unit can delete information while taking into consideration the market value of the letter of introduction. For example, if the market value of the letter of introduction is high, the deletion unit can delete information strictly. For example, if the market value of the letter of introduction is low, the deletion unit can also delete information flexibly. For example, the deletion unit can also delete information appropriately according to the market value of the letter of introduction. In this way, by deleting information while taking into consideration the market value of the letter of introduction, the accuracy of deletion can be improved. Some or all of the above-mentioned processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can improve the accuracy of information deletion by using an AI model that analyzes market value.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The reception unit can analyze the patient's past medical history and select the optimal information input method. For example, if the patient has preferred voice input in the past, it can preferentially suggest voice input. If the patient has frequently used text input in the past, it can also recommend text input. If the patient has used image input in the past, it can also select image input. This makes it possible to select the optimal information input method based on the patient's past medical history.

[0067] When generating a referral letter, the generation unit can adjust the level of detail in the referral letter based on the patient's medical treatment. For example, if the patient's medical treatment is complex, a referral letter including detailed information can be generated. If the patient's medical treatment is simple, a concise referral letter can also be generated. A referral letter that appropriately includes necessary information depending on the patient's medical treatment can also be generated. This makes it possible to adjust the level of detail in the referral letter depending on the patient's medical treatment.

[0068] During format conversion, the format unit can adjust the level of detail in the format based on the importance of the referral. For example, if the importance of the referral is high, a format including detailed information is provided. If the importance of the referral is low, a concise format can be provided. A format with an appropriate level of detail can also be provided depending on the importance of the referral. This makes it possible to adjust the level of detail in the format depending on the importance of the referral.

[0069] The checking unit can improve the accuracy of the check by taking into account the interrelationships between letters of referral when checking for errors. For example, it checks to ensure that the contents of a letter of referral do not contradict other letters of referral. If the contents of a letter of referral are related to other letters of referral, it can also check by taking into account that relationship. If the contents of a letter of referral match other letters of referral, it can also check by confirming that match. In this way, it is possible to improve the accuracy of the check by taking into account the interrelationships between letters of referral.

[0070] The deletion unit can improve the accuracy of deletion by taking into account the interrelationships between letters of introduction when deleting information. For example, the deletion unit deletes the information so that the contents of the letter of introduction do not contradict other letters of introduction. If the contents of the letter of introduction are related to other letters of introduction, the deletion unit can also take into account the relevance. If the contents of the letter of introduction match other letters of introduction, the deletion unit can confirm the match and delete the information. This makes it possible to improve the accuracy of deletion by taking into account the interrelationships between letters of introduction.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The reception desk inputs patient information, including name, age, gender, medical history, etc. The reception desk can also digitally input basic patient information, treatment details, and referral information. Step 2: The generation unit uses a generation AI to automatically create a referral letter based on the information entered by the reception unit. The generation unit generates a referral letter containing the information required by the referring hospital based on the patient's medical treatment. The generation AI generates the referral letter using a text generation AI (e.g., LLM). Step 3: The formatting unit converts the referral letters generated by the generation unit into a unified format, which makes the format of the referral letters consistent and easy to read. Step 4: The Checking Unit checks for errors in the letter of introduction converted by the Formatting Unit. The Checking Unit checks the contents of the generated letter of introduction to ensure there are no errors or missing information. It can perform spelling checks, grammar checks, and information consistency checks. Step 5: The deletion unit deletes personal information from the referral letter that has been confirmed by the checking unit. The deletion unit deletes personal information such as name, address, and telephone number from the referral letter. This prevents the leakage of personal information.

[0073] (Example 2) An automatic referral letter creation system according to an embodiment of the present invention efficiently inputs patient information, and a generation AI automatically creates a referral letter, converts it into a unified format, performs error checks, and deletes personal information. The automatic referral letter creation system inputs patient information, and a generation AI analyzes the information to automatically create a referral letter. The generated referral letter is converted into a unified format and checked for errors. Finally, personal information is deleted, and the referral letter is completed. For example, in the automatic referral letter creation system, a medical institution inputs patient information, including the patient's name, age, medical treatment details, and the name of the referring hospital. This information is input into the generation AI. Next, the automatic referral letter creation system uses the generation AI to analyze the input information and automatically create a referral letter. The generation AI generates appropriate referral letter content based on the input information. For example, the generation AI creates a referral letter containing the necessary information for the referring hospital based on the patient's medical treatment details. Next, the automatic referral letter creation system converts the generated referral letter into a unified format. A formatting unit converts the generated referral letter into a unified format. This makes the format of the referral letter consistent and easy to read. Next, the automatic referral letter creation system checks the contents of the generated referral letter to check for any errors or omissions in the information. A checking unit checks the contents of the generated referral letter to check for any errors or omissions in the information. This improves the quality of the referral letter. Finally, the automatic referral letter creation system deletes personal information from the referral letter. A deletion unit deletes personal information from the referral letter to protect privacy. This prevents the leakage of personal information. As a result, the automatic referral letter creation system improves the operational efficiency of medical institutions and the quality of patient care. As a result, the automatic referral letter creation system can improve the operational efficiency of medical institutions and the quality of patient care. For example, medical institutions can reduce the time and resources required to create referral letters and focus on caring for patients. In addition, the quality of referral letters improves, and information is provided to referring hospitals accurately and quickly. Furthermore, protection of personal information is strengthened, and patient privacy is protected.

[0074] The automatic referral letter creation system according to the embodiment includes a reception unit, a generation unit, a formatting unit, a check unit, and a deletion unit. The reception unit inputs patient information. The patient information includes, but is not limited to, the patient's name, age, gender, and medical history. The reception unit inputs, for example, basic patient information, medical treatment details, and referral destination information. The reception unit can also input the patient information in digital format. The generation unit uses a generation AI to automatically create a referral letter based on the information input by the reception unit. The generation unit generates a referral letter including information required for the referral destination hospital, for example, based on the patient's medical treatment details. The generation unit can also use the generation AI to analyze the patient information and generate appropriate referral letter content. For example, the generation AI generates the referral letter using a text generation AI (e.g., LLM). The formatting unit converts the referral letter generated by the generation unit into a unified format. For example, the formatting unit converts the generated referral letter into a unified format. This makes the format of the referral letter consistent and easy to read. The check unit checks for errors in the referral letter converted by the formatting unit. The checking unit, for example, checks the contents of the generated referral letter to check for errors or omissions in the information. The checking unit can perform, for example, spelling check, grammar check, and information consistency check. The deletion unit deletes personal information from the referral letter checked by the checking unit. The deletion unit deletes personal information such as name, address, and telephone number from the referral letter. This makes it possible to prevent leakage of personal information. As a result, the automatic referral letter creation system according to the embodiment can efficiently input, generate, format convert, check for errors, and delete personal information about patients.

[0075] The reception unit can input basic information about the patient, details of medical treatment, and information about the referral destination. The basic information about the patient includes, for example, name, age, gender, address, etc., but is not limited to these examples. The reception unit, for example, inputs the basic information about the patient. The reception unit can also input details of medical treatment. The details of medical treatment include, for example, diagnosis results, details of treatment, prescribed medications, etc., but is not limited to these examples. The reception unit, for example, inputs details of medical treatment. The reception unit can also input information about the referral destination. The information about the referral destination includes, for example, the name of the medical institution, the address, the name of the doctor in charge, etc., but is not limited to these examples. The reception unit, for example, inputs information about the referral destination. This allows the basic information about the patient, details of medical treatment, and information about the referral destination to be input accurately.

[0076] The generation unit can generate appropriate referral letter content based on the input information. The generation unit generates a referral letter including information required for the referring hospital, for example, based on the patient's medical treatment. The generation unit can also analyze patient information and generate appropriate referral letter content, for example, using a generation AI. The generation AI generates a referral letter using, for example, a text generation AI (e.g., LLM). The generation unit can also generate appropriate referral letter content based on the patient information, using the generation AI. For example, the generation AI generates a referral letter including information required for the referring hospital, based on the patient's medical treatment. This makes it possible to generate an appropriate referral letter based on the input information.

[0077] The formatting unit can convert the generated letters of referral into a unified format. For example, the formatting unit can convert the generated letters of referral into a unified format based on criteria such as font size, layout, and item order. This makes the format of the letters of referral consistent and easy to read. For example, the formatting unit can convert the generated letters of referral into a unified format. The formatting unit can also adjust the format of the generated letters of referral. For example, the formatting unit can adjust the font size and layout of the letters of referral to convert them into a format that is easy to read. This makes the format of the letters of referral consistent and easy to read.

[0078] The checking unit can check the contents of the generated letter of introduction and check for any errors or omissions in the information. For example, the checking unit can check the contents of the generated letter of introduction and check for any errors or omissions in the information. The checking unit can perform, for example, spelling check, grammar check, and information consistency check. For example, the checking unit can check the contents of the generated letter of introduction and check for any errors or omissions in the information. The checking unit can also correct any errors or omissions in the information to improve the quality of the generated letter of introduction. For example, the checking unit corrects any erroneous information and completes any missing information. This can improve the quality of the letter of introduction.

[0079] The deletion unit can delete personal information from the referral letter. For example, the deletion unit deletes personal information such as name, address, and telephone number from the referral letter. For example, the deletion unit deletes personal information from the referral letter to protect privacy. For example, the deletion unit deletes personal information from the referral letter. The deletion unit can also delete personal information from the referral letter to prevent leakage of personal information. For example, the deletion unit deletes personal information from the referral letter to protect privacy. This makes it possible to prevent leakage of personal information. Some or all of the above-described processing in the deletion unit may be performed using AI, or may be performed without using AI, for example. For example, the deletion unit can delete personal information using an AI model that deletes personal information from the referral letter.

[0080] The reception unit can estimate the patient's emotions and adjust the timing of information input based on the estimated patient's emotions. For example, if the patient is nervous, the reception unit delays the timing of input so that the patient can relax. For example, if the patient is relaxed, the reception unit can adjust the timing so that the patient can input information smoothly. For example, if the patient is in a hurry, the reception unit can advance the timing so that the patient can input information quickly. This allows the timing of information input to be adjusted according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. Examples of generative AI include, but are not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can estimate the patient's emotions using an AI model that estimates the patient's emotions and adjust the timing of information input.

[0081] The reception unit can analyze the patient's past medical history and select the optimal information input method. For example, if the patient has preferred voice input in the past, the reception unit can preferentially suggest voice input. For example, if the patient has frequently used text input in the past, the reception unit can also recommend text input. For example, if the patient has used image input in the past, the reception unit can also select image input. This makes it possible to select the optimal information input method based on the patient's past medical history. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select the optimal information input method using an AI model that analyzes the patient's past medical history.

[0082] The reception unit can filter information based on the patient's current health condition and areas of interest when inputting information. For example, if the patient's current health condition is poor, the reception unit minimizes the number of input items. For example, if the patient has a specific area of ​​interest, the reception unit can also prioritize input of information related to that area. For example, if the patient has a specific medical history, the reception unit can also prioritize input of information related to that medical history. This makes it possible to input information according to the patient's health condition and areas of interest. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can filter information when inputting information using an AI model that analyzes the patient's health condition and areas of interest.

[0083] When inputting information, the reception unit can select an appropriate input means according to the patient's input method. For example, if the patient desires voice input, the reception unit can provide voice input preferentially. For example, if the patient desires text input, the reception unit can also provide text input preferentially. For example, if the patient desires image input, the reception unit can also provide image input preferentially. This makes it possible to input information according to the patient's desired input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can select an appropriate input means using an AI model that analyzes the patient's input method.

[0084] The reception unit can estimate the patient's emotions and determine the priority of information to be input based on the estimated patient's emotions. For example, if the patient is nervous, the reception unit can prioritize input of important information. For example, if the patient is relaxed, the reception unit can also prioritize input of detailed information. For example, if the patient is in a hurry, the reception unit can also prioritize input of the most necessary information. This allows the priority of information to be determined according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can determine the priority of information based on emotions using an AI model that estimates the patient's emotions.

[0085] The reception unit can prioritize input of highly relevant information based on the patient's geographical location information when inputting information. For example, if the patient lives in a specific area, the reception unit can prioritize input of information related to that area. For example, if the patient visits a specific hospital, the reception unit can also prioritize input of information related to that hospital. For example, if the patient plans to receive medical treatment in a specific area, the reception unit can also prioritize input of information related to that area. This allows highly relevant information to be prioritized based on the patient's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can use an AI model that analyzes the patient's geographical location information to prioritize input of highly relevant information when inputting information.

[0086] The reception unit can analyze the patient's social media activity and input relevant information when inputting information. The reception unit can input relevant information based on, for example, health information shared by the patient on social media. The reception unit can also input information related to medical institutions that the patient follows on social media. The reception unit can also input relevant information based on, for example, health-related groups that the patient joins on social media. This allows input of relevant information based on the patient's social media activity. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input relevant information when inputting information using an AI model that analyzes the patient's social media activity.

[0087] The reception unit can customize the input method by reflecting the patient's past feedback when inputting information. For example, if the patient has preferred voice input in the past, the reception unit can preferentially provide voice input. For example, if the patient has frequently used text input in the past, the reception unit can also recommend text input. For example, if the patient has used image input in the past, the reception unit can also select image input. This allows the input method to be customized based on the patient's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can customize the input method when inputting information by using an AI model that analyzes the patient's past feedback.

[0088] The generation unit can estimate the patient's emotions and adjust the way the referral letter is written based on the estimated patient's emotions. For example, if the patient is nervous, the generation unit uses concise and easy-to-understand language. For example, if the patient is relaxed, the generation unit can use language that includes detailed information. For example, if the patient is in a hurry, the generation unit can use language that focuses on the main points. This allows the way the referral letter is written to be adjusted based on the patient's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the generation unit can adjust the way the referral letter is written based on the patient's emotions using an AI model that estimates the patient's emotions.

[0089] When generating a referral letter, the generation unit can adjust the level of detail in the referral letter based on the patient's medical treatment. For example, if the patient's medical treatment is complex, the generation unit generates a referral letter including detailed information. For example, if the patient's medical treatment is simple, the generation unit can also generate a concise referral letter. For example, the generation unit can also generate a referral letter that appropriately includes necessary information depending on the patient's medical treatment. This makes it possible to adjust the level of detail in the referral letter depending on the patient's medical treatment. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can adjust the level of detail in the referral letter using an AI model that analyzes the patient's medical treatment.

[0090] The generation unit can apply different generation algorithms depending on the patient category when generating a referral letter. For example, in the case of a pediatric patient, the generation unit can apply a generation algorithm that uses expressions for children. For example, in the case of an elderly patient, the generation unit can also apply a generation algorithm that uses expressions for the elderly. For example, in the case of a patient with a specific disease, the generation unit can also apply a generation algorithm that uses expressions specialized for that disease. This makes it possible to apply the optimal generation algorithm depending on the patient category. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can apply different generation algorithms when generating a referral letter using an AI model that analyzes the patient category.

[0091] When generating a referral letter, the generation unit can improve the accuracy of the generation by referring to the patient's past referral letter results. The generation unit, for example, analyzes the patient's past referral letters and generates a referral letter containing similar content. The generation unit can also improve the accuracy of the generation by, for example, feedback from the patient's past referral letters. The generation unit can also generate an optimal referral letter by referring to, for example, successful cases of the patient's past referral letters. This makes it possible to improve the accuracy of the generation by referring to the patient's past referral letter results. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can improve the accuracy of the generation when generating a referral letter by using an AI model that analyzes the patient's past referral letter results.

[0092] The generation unit can estimate the patient's emotions and adjust the length of the referral letter based on the estimated patient emotions. For example, if the patient is nervous, the generation unit generates a short, concise referral letter. For example, if the patient is relaxed, the generation unit can generate a longer referral letter containing detailed information. For example, if the patient is in a hurry, the generation unit can generate a short referral letter that can be read quickly. This allows the length of the referral letter to be adjusted according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without AI. For example, the generation unit can adjust the length of the referral letter based on the patient's emotions using an AI model that estimates the patient's emotions.

[0093] The generation unit can determine the priority of referral letters based on the timing of the patient's medical examination when generating the referral letters. For example, if the patient's medical examination date is approaching, the generation unit generates the referral letters with priority. For example, if the patient's medical examination date is far away, the generation unit can also postpone generating the referral letters. For example, the generation unit can also generate the referral letters at an appropriate time depending on the timing of the patient's medical examination. This makes it possible to determine the priority of referral letters based on the timing of the patient's medical examination. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can determine the priority when generating the referral letters using an AI model that analyzes the timing of the patient's medical examination.

[0094] The generation unit can adjust the order of referral letters based on the relevance of patients when generating the referral letters. For example, if the patient's medical treatment details are highly relevant, the generation unit can generate the referral letters preferentially. For example, if the patient's medical treatment details are less relevant, the generation unit can also postpone generating the referral letters. For example, the generation unit can also generate the referral letters in an appropriate order depending on the patient's medical treatment details. This makes it possible to adjust the order of referral letters based on the relevance of patients. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can adjust the order when generating the referral letters using an AI model that analyzes the relevance of patients.

[0095] When generating a referral letter, the generation unit can adjust the use of technical terminology in the referral letter according to the patient's level of expertise. For example, if the patient has technical expertise, the generation unit generates a referral letter that uses a lot of technical terminology. For example, if the patient does not have technical expertise, the generation unit can also generate a referral letter that uses easy-to-understand language. For example, the generation unit can also generate a referral letter that uses appropriate language according to the patient's level of expertise. This makes it possible to generate a referral letter that uses appropriate language according to the patient's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can adjust the use of technical terminology when generating a referral letter using an AI model that analyzes the patient's level of expertise.

[0096] The formatting unit can estimate the patient's emotions and adjust the format display method based on the estimated patient's emotions. For example, if the patient is nervous, the formatting unit can provide a simple, highly visible format. For example, if the patient is relaxed, the formatting unit can provide a format containing detailed information. For example, if the patient is in a hurry, the formatting unit can provide a format that focuses on the main points. This allows the format display method to be adjusted according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the formatting unit may be performed using AI, or may be performed without AI. For example, the formatting unit can adjust the format display method based on the patient's emotions using an AI model that estimates the patient's emotions.

[0097] The formatting unit can adjust the level of detail in the format based on the importance of the referral letter during format conversion. For example, if the importance of the referral letter is high, the formatting unit can provide a format including detailed information. For example, if the importance of the referral letter is low, the formatting unit can also provide a concise format. For example, the formatting unit can also provide a format with appropriate level of detail depending on the importance of the referral letter. This allows the level of detail in the format to be adjusted depending on the importance of the referral letter. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can adjust the level of detail during format conversion using an AI model that analyzes the importance of the referral letter.

[0098] The formatting unit can apply different formatting algorithms depending on the category of the referral letter during format conversion. For example, in the case of a referral letter for a pediatric patient, the formatting unit can apply a format for children. For example, in the case of a referral letter for an elderly patient, the formatting unit can also apply a format for elderly people. For example, in the case of a referral letter for a patient with a specific disease, the formatting unit can also apply a format specialized for that disease. This allows the optimal formatting algorithm to be applied depending on the category of the referral letter. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can apply different formatting algorithms during format conversion using an AI model that analyzes the category of the referral letter.

[0099] During format conversion, the formatting unit can improve the accuracy of the format by referring to the patient's past formatting results. For example, the formatting unit analyzes the patient's past referral letter formats and applies a similar format. For example, the formatting unit can also improve the accuracy of the format based on feedback from the patient's past formats. For example, the formatting unit can provide an optimal format by referring to successful formatting examples from the patient's past. This allows the accuracy of the format to be improved by referring to the patient's past formatting results. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can improve the accuracy during format conversion by using an AI model that analyzes the patient's past formatting results.

[0100] The formatting unit can estimate the patient's emotions and adjust the length of the format based on the estimated patient emotions. For example, if the patient is nervous, the formatting unit can provide a short, concise format. For example, if the patient is relaxed, the formatting unit can provide a longer format with detailed information. For example, if the patient is in a hurry, the formatting unit can provide a short format that is quick to read. This allows the length of the format to be adjusted according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Examples of the generative AI include, but are not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the formatting unit may be performed using AI, or may be performed without AI. For example, the formatting unit can adjust the length of the format based on the patient's emotions using an AI model that estimates the patient's emotions.

[0101] The formatting unit can determine the priority of formats based on the submission date of the letter of introduction during format conversion. For example, the formatting unit prioritizes format conversion when the submission date of the letter of introduction is approaching. For example, the formatting unit can postpone format conversion when the submission date of the letter of introduction is far away. For example, the formatting unit can also convert formats at an appropriate time depending on the submission date of the letter of introduction. This makes it possible to determine the priority of formats depending on the submission date of the letter of introduction. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can determine the priority during format conversion using an AI model that analyzes the submission date of the letter of introduction.

[0102] The formatting unit can adjust the order of the formats based on the relevance of the letters of referral during format conversion. For example, if the relevance of the letters of referral is high, the formatting unit prioritizes format conversion. For example, if the relevance of the letters of referral is low, the formatting unit can also postpone format conversion. For example, the formatting unit can also convert the formats in an appropriate order depending on the relevance of the letters of referral. This makes it possible to adjust the order of the formats depending on the relevance of the letters of referral. Some or all of the above-described processing in the formatting unit may be performed using, for example, AI, or may be performed without using AI. For example, the formatting unit can adjust the order during format conversion using an AI model that analyzes the relevance of the letters of referral.

[0103] The formatting unit can adjust the use of technical terminology in the format during format conversion according to the patient's level of expertise. For example, if the patient has technical expertise, the formatting unit can provide a format that uses a lot of technical terminology. For example, if the patient does not have technical expertise, the formatting unit can also provide a format that uses easy-to-understand expressions. For example, the formatting unit can also provide a format that uses appropriate expressions according to the patient's level of expertise. This makes it possible to provide a format that uses appropriate expressions according to the patient's level of expertise. Some or all of the above-described processing in the formatting unit can be performed using, for example, AI, or can be performed without using AI. For example, the formatting unit can adjust the use of technical terminology during format conversion using an AI model that analyzes the patient's level of expertise.

[0104] The check unit can estimate the patient's emotions and adjust the error check criteria based on the estimated patient's emotions. For example, if the patient is nervous, the check unit can perform strict error checks. For example, if the patient is relaxed, the check unit can also perform flexible error checks. For example, if the patient is in a hurry, the check unit can also perform quick error checks. This allows the error check criteria to be adjusted according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the check unit can be performed using, for example, AI, or without AI. For example, the check unit can adjust the error check criteria based on emotions using an AI model that estimates the patient's emotions.

[0105] The check unit can improve the accuracy of the check by taking into account the interrelationships between letters of referral during error checks. For example, the check unit checks to ensure that the contents of the letter of referral do not contradict other letters of referral. For example, if the contents of the letter of referral are related to other letters of referral, the check unit can also check by taking into account that relationship. For example, if the contents of the letter of referral match other letters of referral, the check unit can also check by confirming that match. This improves the accuracy of the check by taking into account the interrelationships between letters of referral. Some or all of the above-mentioned processing in the check unit may be performed using, for example, AI, or may be performed without using AI. For example, the check unit can improve the accuracy of the error check by using an AI model that analyzes the interrelationships between letters of referral.

[0106] When checking for errors, the check unit can take into account the attribute information of the person who submitted the letter of referral. For example, if the submitter is a doctor, the check unit can take into account the person's specialized knowledge when checking. For example, if the submitter is a nurse, the check unit can also take into account the person's specialized knowledge when checking. For example, if the submitter is an office worker, the check unit can also take into account the person's specialized knowledge when checking. In this way, by taking into account the attribute information of the person who submitted the letter of referral, the accuracy of the check can be improved. Some or all of the above-mentioned processing in the check unit may be performed using, for example, AI, or may be performed without using AI. For example, the check unit can improve the accuracy of error checks by using an AI model that analyzes the attribute information of the submitter.

[0107] The check unit can weight the checks based on the frequency of referral submissions during error checks. For example, if the submission frequency is high, the check unit can perform strict error checks. For example, if the submission frequency is low, the check unit can also perform flexible error checks. For example, the check unit can also weight the checks appropriately according to the submission frequency. By weighting the checks based on the frequency of referral submissions, the accuracy of the checks can be improved. Some or all of the above-described processing in the check unit can be performed using, for example, AI, or can be performed without using AI. For example, the check unit can weight the error checks using an AI model that analyzes the submission frequency.

[0108] The check unit can estimate the patient's emotions and adjust the order in which the error check results are displayed based on the estimated patient's emotions. For example, if the patient is nervous, the check unit can prioritize displaying important errors. For example, if the patient is relaxed, the check unit can also prioritize displaying detailed errors. For example, if the patient is in a hurry, the check unit can also prioritize displaying errors that require quick correction. This allows the order in which the error check results are displayed to be adjusted according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-mentioned processing in the check unit may be performed using AI, or may be performed without AI. For example, the check unit can adjust the order in which the error check results are displayed based on emotions using an AI model that estimates the patient's emotions.

[0109] The check unit can perform an error check while taking into account the geographic distribution of the referral letters. For example, if the recipients of the referral letters are concentrated in a specific region, the check unit checks while taking into account the characteristics of that region. For example, if the recipients of the referral letters are spread over a wide area, the check unit can also perform an error check while taking into account the characteristics of each region. For example, if the recipients of the referral letters are biased toward a specific region, the check unit can also perform an error check while taking into account that bias. In this way, by performing an error check while taking into account the geographic distribution of the referral letters, the accuracy of the error check can be improved. Some or all of the above-described processing in the check unit may be performed using, for example, AI, or may be performed without using AI. For example, the check unit can improve the accuracy of the error check by using an AI model that analyzes the geographic distribution.

[0110] The checking unit can improve the accuracy of the check by referring to the related literature of the letter of referral during the error check. For example, the checking unit can check whether the contents of the letter of referral match the related literature. For example, the checking unit can also check whether the contents of the letter of referral are consistent with the related literature. For example, the checking unit can also check whether the contents of the letter of referral are relevant to the related literature. This can improve the accuracy of the check by referring to the related literature of the letter of referral. Some or all of the above-mentioned processing in the checking unit can be performed using, for example, AI, or can be performed without using AI. For example, the checking unit can improve the accuracy during the error check by using an AI model that analyzes the related literature.

[0111] The check unit can perform an error check while taking into account the market value of the letter of introduction. For example, if the market value of the letter of introduction is high, the check unit can perform a strict error check. For example, if the market value of the letter of introduction is low, the check unit can also perform a flexible error check. For example, the check unit can also perform an appropriate error check depending on the market value of the letter of introduction. In this way, by performing a check while taking into account the market value of the letter of introduction, the accuracy of the check can be improved. Some or all of the above-mentioned processing in the check unit can be performed using, for example, AI, or can be performed without using AI. For example, the check unit can improve the accuracy of the error check by using an AI model that analyzes market value.

[0112] The deletion unit can estimate the patient's emotions and determine the priority of information to be deleted based on the estimated patient's emotions. For example, if the patient is nervous, the deletion unit can prioritize deleting important information. For example, if the patient is relaxed, the deletion unit can also prioritize deleting detailed information. For example, if the patient is in a hurry, the deletion unit can also prioritize deleting information that needs to be deleted quickly. This makes it possible to determine the priority of information to be deleted based on the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can use an AI model that estimates the patient's emotions to determine the priority of information to be deleted based on emotions.

[0113] When deleting information, the deletion unit can improve the accuracy of deletion by taking into account the interrelationships between letters of introduction. For example, the deletion unit deletes information so that the contents of the letter of introduction do not contradict other letters of introduction. For example, if the contents of the letter of introduction are related to other letters of introduction, the deletion unit can also delete the information by taking into account the interrelationships. For example, if the contents of the letter of introduction match other letters of introduction, the deletion unit can also confirm the match and delete the information. This improves the accuracy of deletion by taking into account the interrelationships between letters of introduction. Some or all of the above-described processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can improve the accuracy when deleting information by using an AI model that analyzes interrelationships.

[0114] When deleting information, the deletion unit can perform the deletion taking into consideration the attribute information of the person who submitted the letter of referral. For example, if the submitter is a doctor, the deletion unit can perform the deletion taking into consideration the person's expertise. For example, if the submitter is a nurse, the deletion unit can also perform the deletion taking into consideration the person's expertise. For example, if the submitter is an office worker, the deletion unit can also perform the deletion taking into consideration the person's expertise. In this way, by performing the deletion taking into consideration the attribute information of the person who submitted the letter of referral, the accuracy of the deletion can be improved. Some or all of the above-mentioned processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can improve the accuracy when deleting information by using an AI model that analyzes the attribute information of the submitter.

[0115] The deletion unit can weight the deletion based on the frequency of referral submissions when deleting information. For example, the deletion unit performs strict information deletion when the submission frequency is high. For example, the deletion unit can also perform flexible information deletion when the submission frequency is low. The deletion unit can also perform appropriate weighting according to the submission frequency, for example. By weighting the deletion based on the frequency of referral submissions, the accuracy of deletion can be improved. Some or all of the above-described processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can weight the information when deleting it using an AI model that analyzes the submission frequency.

[0116] The deletion unit can estimate the patient's emotions and adjust the display method of information to be deleted based on the estimated patient's emotions. For example, if the patient is nervous, the deletion unit can prioritize displaying important information. For example, if the patient is relaxed, the deletion unit can also prioritize displaying detailed information. For example, if the patient is in a hurry, the deletion unit can also prioritize displaying information that needs to be deleted quickly. This allows the display method of information to be deleted to be adjusted according to the patient's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. Examples of the generation AI include, but are not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-mentioned processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can adjust the display method of information to be deleted based on emotions using an AI model that estimates the patient's emotions.

[0117] When deleting information, the deletion unit can perform the deletion taking into account the geographical distribution of referral letters. For example, if the destinations for referral letters are concentrated in a specific region, the deletion unit deletes the information taking into account the characteristics of that region. For example, if the destinations for referral letters are spread over a wide area, the deletion unit can also delete the information taking into account the characteristics of each region. For example, if the destinations for referral letters are biased toward a specific region, the deletion unit can also delete the information taking into account that bias. In this way, by performing deletion taking into account the geographical distribution of referral letters, the accuracy of the deletion can be improved. Some or all of the above-described processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can improve the accuracy when deleting information by using an AI model that analyzes the geographical distribution.

[0118] When deleting information, the deletion unit can improve the accuracy of deletion by referring to related literature in the letter of introduction. For example, the deletion unit checks whether the contents of the letter of introduction match the related literature. For example, the deletion unit can also check whether the contents of the letter of introduction are consistent with the related literature. For example, the deletion unit can also check whether the contents of the letter of introduction are relevant to the related literature. This can improve the accuracy of deletion by referring to the related literature in the letter of introduction. Some or all of the above-mentioned processing in the deletion unit may be performed using, for example, AI, or may be performed without using AI. For example, the deletion unit can improve the accuracy when deleting information by using an AI model that analyzes related literature.

[0119] The deletion unit can delete information while taking into consideration the market value of the letter of introduction. For example, if the market value of the letter of introduction is high, the deletion unit can delete information strictly. For example, if the market value of the letter of introduction is low, the deletion unit can also delete information flexibly. For example, the deletion unit can also delete information appropriately according to the market value of the letter of introduction. In this way, by deleting information while taking into consideration the market value of the letter of introduction, the accuracy of deletion can be improved. Some or all of the above-mentioned processing in the deletion unit can be performed using, for example, AI, or can be performed without using AI. For example, the deletion unit can improve the accuracy of information deletion by using an AI model that analyzes market value. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, format unit, check unit, and deletion unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and inputs patient information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically creates a referral letter using a generation AI. The format unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the generated referral letter into a unified format. The check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs error checks on the generated referral letter. The deletion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and deletes personal information from the referral letter. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, format unit, check unit, and deletion unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and inputs patient information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically creates a referral letter using a generation AI. The format unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the generated referral letter into a unified format. The check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs error checks on the generated referral letter. The deletion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and deletes personal information from the referral letter. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, generation unit, format unit, check unit, and deletion unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset-type terminal 314 and inputs patient information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically creates a referral letter using a generation AI. The format unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the generated referral letter into a unified format. The check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs error checks on the generated referral letter. The deletion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and deletes personal information from the referral letter. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, generation unit, format unit, check unit, and deletion unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and inputs patient information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and automatically creates a referral letter using a generation AI. The format unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the generated referral letter into a unified format. The check unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs error checks on the generated referral letter. The deletion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and deletes personal information from the referral letter.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The reception unit can estimate the patient's emotions and adjust the timing of information input based on the estimated patient's emotions. For example, if the patient is nervous, the timing of input can be delayed to allow the patient to relax. If the patient is relaxed, the timing can also be adjusted to allow the patient to input information smoothly. If the patient is in a hurry, the timing can also be advanced to allow the patient to input information quickly. In this way, the timing of information input can be adjusted according to the patient's emotions.

[0122] The generation unit can estimate the patient's emotions and adjust the way the referral letter is written based on the estimated patient's emotions. For example, if the patient is nervous, concise and easy-to-understand expressions can be used. If the patient is relaxed, expressions containing detailed information can be used. If the patient is in a hurry, expressions that get straight to the point can be used. This allows the way the referral letter is written to be adjusted according to the patient's emotions.

[0123] The formatting unit can estimate the patient's emotions and adjust the format display method based on the estimated patient's emotions. For example, if the patient is nervous, a simple, highly visible format can be provided. If the patient is relaxed, a format including detailed information can be provided. If the patient is in a hurry, a format that focuses on the main points can be provided. In this way, the format display method can be adjusted according to the patient's emotions.

[0124] The check unit can estimate the patient's emotions and adjust the error check criteria based on the estimated patient's emotions. For example, if the patient is nervous, strict error checks can be performed. If the patient is relaxed, flexible error checks can be performed. If the patient is in a hurry, quick error checks can be performed. This allows the error check criteria to be adjusted according to the patient's emotions.

[0125] The deletion unit can estimate the patient's emotions and determine the priority of information to be deleted based on the estimated patient's emotions. For example, if the patient is nervous, important information can be deleted with priority. If the patient is relaxed, detailed information can be deleted with priority. If the patient is in a hurry, information that needs to be deleted quickly can be deleted with priority. In this way, the priority of information to be deleted can be determined according to the patient's emotions.

[0126] The reception unit can analyze the patient's past medical history and select the optimal information input method. For example, if the patient has preferred voice input in the past, it can preferentially suggest voice input. If the patient has frequently used text input in the past, it can also recommend text input. If the patient has used image input in the past, it can also select image input. This makes it possible to select the optimal information input method based on the patient's past medical history.

[0127] When generating a referral letter, the generation unit can adjust the level of detail in the referral letter based on the patient's medical treatment. For example, if the patient's medical treatment is complex, a referral letter including detailed information can be generated. If the patient's medical treatment is simple, a concise referral letter can also be generated. A referral letter that appropriately includes necessary information depending on the patient's medical treatment can also be generated. This makes it possible to adjust the level of detail in the referral letter depending on the patient's medical treatment.

[0128] During format conversion, the format unit can adjust the level of detail in the format based on the importance of the referral. For example, if the importance of the referral is high, a format including detailed information is provided. If the importance of the referral is low, a concise format can be provided. A format with an appropriate level of detail can also be provided depending on the importance of the referral. This makes it possible to adjust the level of detail in the format depending on the importance of the referral.

[0129] The checking unit can improve the accuracy of the check by taking into account the interrelationships between letters of referral when checking for errors. For example, it checks to ensure that the contents of a letter of referral do not contradict other letters of referral. If the contents of a letter of referral are related to other letters of referral, it can also check by taking into account that relationship. If the contents of a letter of referral match other letters of referral, it can also check by confirming that match. In this way, it is possible to improve the accuracy of the check by taking into account the interrelationships between letters of referral.

[0130] The deletion unit can improve the accuracy of deletion by taking into account the interrelationships between letters of introduction when deleting information. For example, the deletion unit deletes the information so that the contents of the letter of introduction do not contradict other letters of introduction. If the contents of the letter of introduction are related to other letters of introduction, the deletion unit can also take into account the relevance. If the contents of the letter of introduction match other letters of introduction, the deletion unit can confirm the match and delete the information. This makes it possible to improve the accuracy of deletion by taking into account the interrelationships between letters of introduction.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The reception desk inputs patient information, including name, age, gender, medical history, etc. The reception desk can also digitally input basic patient information, treatment details, and referral information. Step 2: The generation unit uses a generation AI to automatically create a referral letter based on the information entered by the reception unit. The generation unit generates a referral letter containing the information required by the referring hospital based on the patient's medical treatment. The generation AI generates the referral letter using a text generation AI (e.g., LLM). Step 3: The formatting unit converts the referral letters generated by the generation unit into a unified format, which makes the format of the referral letters consistent and easy to read. Step 4: The Checking Unit checks for errors in the letter of introduction converted by the Formatting Unit. The Checking Unit checks the contents of the generated letter of introduction to ensure there are no errors or missing information. It can perform spelling checks, grammar checks, and information consistency checks. Step 5: The deletion unit deletes personal information from the referral letter that has been confirmed by the checking unit. The deletion unit deletes personal information such as name, address, and telephone number from the referral letter. This prevents the leakage of personal information.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] 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.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] 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.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0177] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] 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.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0189] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0194] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0195] 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.

[0196] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0197] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0198] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0199] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0202] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0204] [Explanation of symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit for inputting patient information; a generation unit that automatically generates a letter of introduction based on the information input by the reception unit; a formatting unit that converts the letters of introduction generated by the generating unit into a unified format; a check unit that performs an error check on the letter of introduction converted by the format unit; a deletion unit that deletes personal information from the letter of introduction confirmed by the checking unit. A system characterized by:

2. The reception unit Enter basic patient information, medical details, and referral information 2. The system of claim 1.

3. The generation unit Generate appropriate referral content based on the information entered 2. The system of claim 1.

4. The format unit Converting generated letters of introduction into a unified format 2. The system of claim 1.

5. The checking unit Check the contents of the generated letter of introduction to see if there are any errors or omissions.

2. The system of claim 1.

6. The deletion unit Remove personal information from the referral letter 2. The system of claim 1.

7. The reception unit Estimate the patient's emotions and adjust the timing of information input based on the estimated patient emotions 2. The system of claim 1.

8. The reception unit Analyze the patient's past medical history and select the appropriate information entry method 2. The system of claim 1.

Images