Program, information processing device, method, and system

Abstract

Provided is a program for operating a server 30 equipped with a processor 39 and memory units 35, 36. The memory units 35, 36 store: a search database which stores execution instruction data used for instructing the server 30 and / or another computer to execute a specific operation; or a program or a machine learning model for generating the execution instruction data. The program causes the processor 39 to execute a first step for receiving an input of medical history information or the like, and a second step for searching the search database using the input received in the first step to acquire execution instruction data for instructing the server 30 and / or another computer to execute a specific operation, or inputting the input received in the first step to a program or a machine learning model to acquire execution instruction data for instructing the server 30 and / or the other computer to execute the specific operation.

Description

Program, information processing device, method and system

[0001] The present disclosure relates to a program, an information processing device, a method, and a system.

[0002] 2. Description of the Related Art Electronic medical records are well known in which a doctor electronically records the contents and results of a medical interview with a patient, and further electronically records the history of medical treatments performed on the patient.

[0003] A technique related to the above-mentioned technique is disclosed in Japanese Patent Laid-Open No. 2003-222999.

[0004] Patent Document 1 discloses technology related to a medical support device. In the medical support device, an input item display means displays input items on a display. An input item selection means selects one of the input items. A speech recognition means uses a selected dictionary to perform speech recognition on the input speech and extracts word candidates for the speech. A word candidate display means displays the extracted word candidates on a display. A selection operation acceptance means accepts an operation to select one word candidate from the word candidates. A memory control means stores the selected word candidate in a memory means as an answer to the selected one of the input items.

[0005] JP 2013-156844 A

[0006] The technology described in Patent Document 1 performs voice recognition processing using a specialized dictionary in the medical field, but even in this case, medical professionals still need to input voice, and there was a need to reduce this effort.

[0007] Therefore, the present disclosure has been made to solve the above problem, and its purpose is to provide a technology that automates the processing of medical information by medical professionals or semi-automates it by requesting user approval.

[0008] A program for operating a computer including a processor and a memory, wherein the memory stores a search database storing execution instruction data used to instruct the computer and / or other computers to perform a specific operation, or a program or machine learning model for generating execution instruction data, the program instructs the processor to execute a first step of accepting input of at least one of medical history information, information entered by a patient, a disease name, a symptom name, a problem in a problem list, and a medical note, and a second step of searching the search database using the input accepted in the first step to obtain execution instruction data for instructing the computer and / or other computers to perform a specific operation, or inputting the input accepted in the first step into the program or machine learning model to obtain execution instruction data for instructing the computer and / or other computers to perform a specific operation.

[0009] According to the present disclosure, it is possible to automate the processing of medical information by medical professionals or semi-automate it by requesting user approval. In addition, the present disclosure semi-automates registration tasks such as document registration and order instruction registration, which are functions for efficiently using electronic medical records, thereby enabling efficient use of electronic medical records.

[0010] FIG. 1 is a diagram illustrating an overall configuration of a system according to an embodiment. FIG. 2 is a diagram illustrating a functional configuration of a terminal device according to an embodiment. FIG. 3 is a diagram illustrating a functional configuration of a server according to an embodiment. FIG. 4 is a diagram illustrating an example of a data structure of a search database according to an embodiment. FIG. 5 is a diagram illustrating another example of a data structure of a search database according to an embodiment. A flowchart illustrating an example of a processing flow in a system according to an embodiment. A flowchart illustrating another example of a processing flow in a system according to an embodiment. A flowchart illustrating yet another example of a processing flow in a system according to an embodiment. A flowchart illustrating yet another example of a processing flow in a system according to an embodiment. A flowchart illustrating yet another example of a processing flow in a system according to an embodiment. A schematic diagram illustrating an example of a screen displayed on a terminal device according to an embodiment. A schematic diagram illustrating yet another example of a screen displayed on a terminal device according to an embodiment. A schematic diagram illustrating yet another example of a screen displayed on a terminal device according to an embodiment. A schematic diagram illustrating yet another example of a screen displayed on a terminal device according to an embodiment. A schematic diagram illustrating yet another example of a screen displayed on a terminal device according to an embodiment. A schematic diagram illustrating yet another example of a screen displayed on a terminal device according to an embodiment. FIG. 10 is a schematic diagram showing yet another example of a screen displayed on a terminal device according to an embodiment. FIG. 11 is a schematic diagram showing yet another example of a screen displayed on a terminal device according to an embodiment. FIG. 12 is a schematic diagram showing yet another example of a screen displayed on a terminal device according to an embodiment. FIG. 13 is a schematic diagram showing yet another example of a screen displayed on a terminal device according to an embodiment. FIG. 14 is a schematic diagram showing yet another example of a screen displayed on a terminal device according to an embodiment. FIG. 15 is a schematic diagram showing yet another example of a screen displayed on a terminal device according to an embodiment. FIG. 16 is a schematic diagram showing yet another example of a screen displayed on a terminal device according to an embodiment.

[0011] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings describing the embodiments, common components are designated by the same reference numerals, and repeated explanations will be omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each drawing is a schematic diagram and is not necessarily a precise illustration.

[0012] In the following description, a "processor" refers to one or more processors. The at least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may also be another type of processor such as a GPU (Graphics Processing Unit). The at least one processor may be a single-core or multi-core processor.

[0013] Furthermore, the at least one processor may be a processor in the broad sense, such as a hardware circuit (for example, a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC)) that performs part or all of the processing.

[0014] In the following explanation, information that produces an output for an input may be described using expressions such as "xxx table," but this information may be data of any structure, or may be a learning model such as a neural network that produces an output for an input. Therefore, a "xxx table" may be called "xxx information."

[0015] Furthermore, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0016] In addition, in the following explanation, processing may be described using the "program" as the subject, but since a program is executed by a processor to perform specified processing while appropriately using a memory unit and / or an interface unit, etc., the subject of the processing may also be the processor (or a device such as a controller that has that processor).

[0017] The program may be installed in a device such as a computer, or may be stored in, for example, a program distribution server or a computer-readable (e.g., non-transitory) recording medium. In the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0018] Furthermore, in the following description, identification numbers are used as identification information for various objects, but other types of identification information (for example, identifiers including alphabetic characters or symbols) may also be used.

[0019] In addition, in the following description, when describing elements of the same type without distinguishing between them, reference symbols (or common symbols among the reference symbols) may be used, and when describing elements of the same type with distinction between them, the identification numbers (or reference symbols) of the elements may be used.

[0020] In the following description, the control lines and information lines are those that are considered necessary for the description, and do not necessarily represent all the control lines and information lines in the product. All components may be interconnected.

[0021] <0 System Overview> The system disclosed herein is a system in which a medical professional, such as a doctor, inputs medical information such as medical history information and medical notes, and then instructs the computer to execute an operation in a computer-interpretable format within this system or another system. Additionally, when the computer returns a result based on the instruction, the system further instructs the computer to execute an operation in a computer-interpretable format, and repeats the above operations. Note that medical history includes records of a patient's medical history, allergy history, family history, and current medical history (present symptoms, course, test findings, and treatment), and is part of the medical record data. While this information is often written in natural language, it can also be stylized using an electronic medical record template. In particular, the medical history, family history, and current medical history can be recorded in separate template formats, and two or three of these can be treated as different inputs during the natural language processing described below to improve accuracy.

[0022] Below, the gist of the system according to the present disclosure will be explained, but the following explanation should not be interpreted in a limiting manner, and the contents of the present disclosure should be understood based on the disclosure in this specification and the ordinary technical knowledge and common sense of a person skilled in the art.

[0023] The system disclosed herein takes as input natural language medical history information including time information, and obtains data for giving instructions to a machine (computer) in accordance with a format (hereinafter referred to as machine-oriented execution instruction data) by performing a similarity search with natural language or natural language in a search database of machine-oriented execution instruction data linked to words or tags, or by generating the data using a generation model or machine processing for machine-oriented execution instruction data, and by issuing execution instructions to the machine, reducing the effort required for humans to enter data into the machine.

[0024] In addition, the system disclosed herein updates the medical history by converting the results or replies of instructions to the machine into text along with time information, and by repeatedly obtaining data for instructions to the machine in accordance with the format from the second time onwards, it continuously reduces the effort required to give instructions to the machine.

[0025] In this case, by combining the natural language of the medical history, the natural language that guides medical professionals to provide execution instruction data to the machine, and the function to obtain execution instruction data for the machine based on these two natural languages, it is possible to simultaneously add to the medical history, navigate execution instructions to a machine with a chat function, and reduce the labor required to input execution instructions to the machine.

[0026] The system according to the present disclosure also includes a user interface for inputting medical history, and a user interface for inputting medical history, obtaining execution instruction data for the machine obtained by using a dedicated search or dedicated generation AI (artificial intelligence), displaying the execution instructions for the machine, and obtaining approval. Note that the execution instructions for the machine in this case include instructions for adding natural language information, instructions for displaying a medical questionnaire, instructions for ordering tests, instructions for prescribing, instructions for entering disease names for medical fees, instructions for sending messages to patients, instructions for RPA, instructions for displaying templates, instructions for entering template data, instructions for displaying filtered test results, instructions for displaying filtered prescription information, instructions for making appointments for medical appointments, etc. Hereinafter, the execution instruction data for the machine includes these instructions.

[0027] In particular, the system according to the present disclosure includes a user interface for inputting a medical history, and a user interface for inputting the medical history, obtaining a plurality of instructions for a machine obtained by using a search, displaying the execution instructions for the machine, and updating the execution instructions by selecting or modifying the date, etc.

[0028] Furthermore, the system according to the present disclosure has a user interface for inputting medical history, a user interface for obtaining one or more instructions for a machine obtained by inputting the medical history and utilizing a search, a user interface for displaying and selecting instructions for execution by the machine, and a user interface for displaying and modifying instructions for execution by the machine and their tags.

[0029] In addition, the system disclosed herein has a screen for inputting medical history, and obtains execution instructions to the machine obtained by using a dedicated generative model for searching using the medical history as input or for issuing execution instructions to the machine, and displays the execution instructions to the machine corresponding to the medical history on the same screen as the search word candidates, and when a button for obtaining approval is pressed, the contents of the instructions are added to the medical history, or as a result of approval of the instructions, the medical history is updated by receiving the results entered by the patient in a questionnaire displayed on another machine, or by obtaining the results of an examination, and the medical history is updated, and execution instruction update candidates for the next machine are displayed, and a user interface for approving them is displayed, and the operation of updating the medical history updated as a result of the approval is repeated.

[0030] When obtaining this approval, it is also possible to display the difference between the current patient and the patient for whom this instruction was given. For example, when a prescription is given to an influenza patient and similar cases are searched for for patients with coughs and runny noses, and execution instruction data is obtained, if the search results show a patient with a cough, runny nose, and fever, natural language processing may be used to clearly display the difference by indicating the presence or absence of symptoms as plus or minus in the symptoms column of the template display, such as: current patient's medical history: cough (+), runny nose (+), fever (-); original medical history of execution data instruction data: cough (+), runny nose (+), fever (+). Furthermore, this information may be displayed in a chronological comparison format in a table format to make it easier to compare and understand.

[0031] In particular, the system disclosed herein has a function for inputting medical history, a user interface for obtaining execution instructions for a machine obtained by searching using the medical history as input or by using a dedicated generative model for issuing execution instructions to a machine, displaying the execution instructions to the machine and obtaining approval, and a function for displaying natural language that guides medical professionals to execute execution instruction data for the machine based on the medical history.

[0032] When updating the medical history, the updated part of the medical history may be highlighted for the user, and an interface may be provided that records that the person updating the medical history is natural language processing, manages the history of the changes, and displays the differences. In particular, when the medical history is recorded using a template, if the template values ​​such as the current medical history, past medical history, family history, and the presence or absence of allergies are updated based on the input content of the medical questionnaire, the updated part may be highlighted to indicate to the user that the information has been added or updated.

[0033] In addition, the system disclosed herein is a system in which a problem list is updated based on a user interface for inputting medical history and natural language written in the interface for writing medical history, and search words are set based on the problem list, and past examinations, past prescriptions, and past machine instructions are searched for.

[0034] Furthermore, the system disclosed herein is a system in which chat text is generated based on the natural language written in the user interface for inputting medical history and the interface for writing medical history, search words are set, and past examinations, past prescriptions, and past machine instructions are searched for.

[0035] Furthermore, the system according to the present disclosure includes data in which at least a medical history or data generated from the medical history and medical instruction information or medical history addition instruction information are stored in pairs, and upon accepting input of the medical history, generates search words based on the medical history, searches for medical instruction information based on the generated search words, and presents the searched information to the user. Furthermore, the frequency of medical instruction information or the names or titles of users who have previously given medical instructions may be displayed.

[0036] <One Embodiment> <1. Overall System Configuration Diagram> FIG. 1 is a diagram showing the overall configuration of a medical support system (hereinafter simply referred to as the "system") 1 according to this embodiment. As shown in FIG. 1, the system 1 includes a plurality of terminal devices (terminal device 10 and terminal device 20 are shown in FIG. 1; hereinafter, they may be collectively referred to as "terminal device 10") and a server 30. The terminal devices 10 and 20 are connected to the server 30 via a network 80 so as to be able to communicate with each other. The network 80 is configured as a wired or wireless network. In this embodiment, the server 30 functions as a web server (including a cloud server) and exchanges information with the terminal devices 10 and 20 via web pages. Furthermore, a web page browser for viewing web pages is installed on the terminal devices 10 and 20, but a dedicated application for providing the services of the server 30 may also be installed so that the web pages can be viewed using the dedicated application.

[0037] The hardware configuration of the terminal device 10 is common to that of the terminal device 20, and therefore the hardware configuration of the terminal device 10 will be described below, and a description of the hardware configuration of the terminal device 20 will be omitted. Note that components of the terminal device 20 that are the same as those of the terminal device 10 are given reference numerals beginning with 2, and the reference numeral system is the same.

[0038] The terminal device 10 is a device operated by a patient. The patient views the medical interview questions of the electronic medical questionnaire displayed on the output device 14 of the terminal device 10 and inputs the medical interview response contents corresponding to the medical interview questions using the input device 13. Note that a medical professional may assist the patient in operating the terminal device 10, i.e., in inputting the medical interview response contents of the electronic medical interview form. The terminal device 10 is realized by a desktop personal computer (PC), a laptop PC, or the like. Alternatively, the terminal device 10 may be, for example, a tablet compatible with a mobile communication system, a mobile terminal such as a smartphone, or the like.

[0039] The terminal device 10 is communicatively connected to the server 30 via a network 80. The terminal device 10 is connected to the network 80 by communicating with communication devices such as a wireless base station 81 compatible with communication standards such as 4G, 5G, and LTE (Long Term Evolution), and a wireless LAN router 82 compatible with wireless LAN (Local Area Network) standards such as IEEE (Institute of Electrical and Electronics Engineers) 802.11. As shown in FIG. 1 , the terminal device 10 includes a communication interface (IF) 12, an input device 13, an output device 14, a memory 15, a storage unit 16, and a processor 19.

[0040] The communication IF 12 is an interface for inputting and outputting signals so that the terminal device 10 can communicate with external devices. The input device 13 is an input device (e.g., a keyboard, a touch panel, a touchpad, a pointing device such as a mouse, etc.) for receiving input operations from a user. The output device 14 is an output device (e.g., a display, a speaker, etc.) for presenting information to a user. The memory 15 is for temporarily storing programs and data processed by the programs, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage unit 16 is a storage device for saving data, such as a flash memory or a HDD (Hard Disc Drive). The processor 19 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0041] The terminal device 20 is a device operated by a medical professional or an administrator of the system 1. Here, the term "medical professional" is a concept that includes doctors, nurses, medical technicians, etc. In the following description, the term "medical professional" will be taken to include the administrator of the system 1, unless a distinction is made between the medical professional and the administrator of the system 1.

[0042] A medical professional uses the terminal device 20 to view medical information and input instructions for the patient, including medical procedures. The input instructions are processed by the server 30 (described later) or an external server 40 outside the system 1, and the processing results are displayed on the terminal device 20. The input results of the electronic medical questionnaire entered by the patient via the terminal device 10 are also displayed on the terminal device 20.

[0043] The server 30 is managed by an administrator of the system 1 of this embodiment, and the stored contents are modified / added / deleted as appropriate by medical professionals who are users of the terminal devices 20. The server 30 is also an electronic medical record device, and medical professionals at medical facilities view the input items and input contents of the electronic medical record via the terminal devices 20 and modify / add to the input contents. At least a portion of the logs of various instruction information, including medical instruction information, which is also a feature of the system according to the present disclosure, is reflected as input contents of the electronic medical record.

[0044] The server 30 is a computer connected to a network 80. The server 30 includes a communication IF 32, an input / output IF 33, a memory 35, a storage 36, and a processor 39.

[0045] The communication IF 32 is an interface for inputting and outputting signals so that the server 30 can communicate with external devices. The input / output IF 33 functions as an interface with an input device for receiving input operations from a user and an output device for presenting information to the user. The memory 35 is for temporarily storing programs and data processed by the programs, etc., and is a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage 36 is a storage device for saving data, such as a flash memory or an HDD (Hard Disc Drive). The processor 39 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0046] <1.1 Functional Configuration of Terminal Device 10> Fig. 2 is a block diagram illustrating an example of the functional configuration of the terminal device 10 illustrated in Fig. 1. The terminal device 10 illustrated in Fig. 2 is realized by, for example, a PC, a mobile terminal, or a wearable terminal. As illustrated in Fig. 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a storage unit 180, and a control unit 190. The blocks included in the terminal device 10 are electrically connected by, for example, a bus or the like.

[0047] The communication unit 120 performs processing such as modulation and demodulation for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on signals generated by the control unit 190 and transmits the signals to an external device (for example, the server 30). The communication unit 120 performs reception processing on signals received from an external device and outputs the signals to the control unit 190.

[0048] The input device 13 is a device through which a user operating the terminal device 10 inputs instructions or information. The input device 13 may be realized by, for example, a keyboard, a mouse, a reader, or the like. If the terminal device 10 is a mobile terminal or the like, the input device 13 may be realized by, for example, a touch-sensitive device 131 through which instructions are input by touching the operation surface. The input device 13 converts instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may also include, for example, a receiving port that receives electrical signals input from an external input device.

[0049] The output device 14 is a device for presenting information to a user operating the terminal device 10. The output device 14 is realized, for example, by a display 141. The display 141 displays data according to the control of the control unit 190. The display 141 is realized, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0050] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of an audio signal. The audio processing unit 17 converts a signal provided from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is realized, for example, by a processor for audio processing. The microphone 171 receives audio input and provides an audio signal corresponding to the audio input to the audio processing unit 17. The speaker 172 converts the audio signal provided from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0051] The storage unit 180 is realized by, for example, the memory 15 and the storage unit 16, and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, electronic medical questionnaire data 182 and image data 183.

[0052] The electronic medical questionnaire data 182 is generated based on the electronic medical questionnaire data 3028 stored in the server 30, and is data of the electronic medical questionnaire into which the patient has inputted the reply contents of the medical questionnaire by operating the terminal device 10.

[0053] The image data 183 is image data used when presenting the electronic medical questionnaire to the patient.

[0054] The control unit 190 is realized when the processor 19 reads the application program 181 stored in the storage unit 180 and executes the instructions included in the application program 181. The control unit 190 controls the operation of the terminal device 10. By operating in accordance with the application program 181 stored in the storage unit 180, the control unit 190 fulfills the functions of an operation reception unit 191, a transmission / reception unit 192, a data processing unit 193, a presentation control unit 194, an electronic medical questionnaire input unit 195, and an electronic medical questionnaire data transmission unit 196.

[0055] The operation reception unit 191 performs processing for receiving instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 receives information based on instructions input from a keyboard, a mouse, or the like.

[0056] The transmitting / receiving unit 192 performs processing for the terminal device 10 to transmit and receive data to and from external devices such as the server 30 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 transmits the details of a task input by a user to the server 30. The transmitting / receiving unit 192 also receives information about the user from the server 30.

[0057] The data processing unit 193 performs calculations on the data received by the terminal device 10 according to the application program 181, and outputs the calculation results to the memory 15 or the like.

[0058] The presentation control unit 194 controls the output device 14 to present information provided from the server 30 to the user. Specifically, for example, the presentation control unit 194 causes the information transmitted from the server 30 to be displayed on the display 141. The presentation control unit 194 also causes the information transmitted from the server 30 to be output from the speaker 172.

[0059] The electronic questionnaire input unit 195 accepts the input of the questionnaire reply content entered by the patient in response to the questionnaire questions in the electronic questionnaire displayed on the display 141 by the presentation control unit 194 (this input of the questionnaire reply content includes a selection input for one of the pre-set questionnaire options), and stores the accepted input of the questionnaire reply content in the electronic questionnaire data 182 by linking it to the questionnaire item associated with this questionnaire reply content.

[0060] The electronic questionnaire data sending unit 196 receives the input of the reply contents of the medical interview from the electronic questionnaire input unit 195 , and sends the electronic questionnaire data 182 stored in the storage unit 180 as electronic questionnaire data 182 to the server 30 .

[0061] <1.2 Functional Configuration of Terminal Device 20> Fig. 3 is a block diagram illustrating an example of the functional configuration of the terminal device 20 shown in Fig. 1. The terminal device 10 shown in Fig. 3 is realized by, for example, a PC, a mobile terminal, or a wearable terminal.

[0062] The functional configuration of the terminal device 20 has much in common with the functional configuration of the terminal device 10, so the following description will focus on the differences from the functional configuration of the terminal device 10.

[0063] The storage unit 280 is realized by, for example, the memory 25, the storage 26, etc., and stores data and programs used by the terminal device 20. The storage unit 280 stores, for example, electronic medical record data 282.

[0064] The electronic medical record data 282 is data entered by a medical professional operating the terminal device 20, and at least a portion of the logs of various instruction information, including medical instruction information, generated by each functional unit of the server 30 described below is reflected as the input content of the electronic medical record.

[0065] The control unit 290 is realized by the processor 29 reading an application program 281 stored in the storage unit 280 and executing instructions included in the application program 281. The control unit 290 controls the operation of the terminal device 20. By operating in accordance with the application program 281 stored in the storage unit 280, the control unit 290 fulfills the functions of an operation reception unit 291, a transmission / reception unit 292, a data processing unit 293, a presentation control unit 294, an instruction information input instruction unit 295, and an electronic medical record data output unit 296.

[0066] The operations of the operation reception unit 291, the transmission / reception unit 292, the data processing unit 293, and the presentation control unit 294 are similar to those of the operation reception unit 191, the transmission / reception unit 192, the data processing unit 193, and the presentation control unit 194 of the terminal device 10, and therefore their explanations are omitted.

[0067] The instruction information input instruction unit 295 performs operations such as approving and selecting various instructions to other computers including the natural language generation model 3023, based on various instruction information including medical instruction information from the natural language generation model 3023, etc. provided in the server 30, and issues various instructions to modules in the server 30 or modules in the external server 40. Details of the medical instruction information and various instruction information will be described later.

[0068] The electronic medical record data output unit 296 outputs information including various instruction information from the instruction information input instruction unit 295 to the server 30 etc. and output from the server 30 etc. based on the various instruction information to the server 30 as electronic medical record data.

[0069] 4 is a diagram showing an example of the functional configuration of the server 30. As shown in FIG. 4, the server 30 functions as a communication unit 301, a storage unit 302, and a control unit 303.

[0070] The communication unit 301 performs processing for the server 30 to communicate with external devices.

[0071] The memory unit 302 includes, for example, electronic medical record data 3022, a natural language generation model 3023, an execution instruction data generation model 3024, medical information data 3025, RPA data 3026, a search database 3027, electronic questionnaire data 3028, and a judgment model 3029.

[0072] The electronic medical record data 3022 is electronic medical record data 3022 for patients who have visited a medical facility using the server 30. Because the electronic medical record data 3022 itself is known, details thereof will be omitted. However, the electronic medical record data 3022 generally includes time-stamped medical history information, patient examination data, and prescription data for the patient. The electronic medical record data 3022 includes input fields and input content associated with these input fields. While there are no particular limitations on the data format of the electronic medical record data 3022, the electronic medical record data 3022 in this embodiment is data written in XAML (Extensible Application Markup Language) converted into JSON (JavaScript Object Notation) format (JavaScript is a registered trademark). It is preferable that the input fields of the electronic medical record data 3022 be assigned identifiers such as numeric strings, and these identifiers also constitute the electronic medical record data 3022.

[0073] In the system 1 of this embodiment, the electronic medical record data 3022 is an example of medical information. As will be described later, logs of interactions between the server 30 and the terminal device 20 and between modules in the server 30 and the external server 40 are also imported as the electronic medical record data 3022 with the approval of the medical professional operating the terminal device 20. Medical records input by the medical professional via the terminal device 20 are also imported as the electronic medical record data 3022 with the approval of the medical professional operating the terminal device 20.

[0074] The natural language generation model 3023, as exemplified by ChatGPT, receives input of natural language and outputs a natural language corresponding to the input natural language. In one example, the natural language generation model 3023 can be fine-tuned to output natural language that explains to the healthcare professional why the execution instruction data to the machine is being presented (i.e., the reason for presenting the execution instruction data), and the natural language can be displayed near a button for inputting approval of the execution instruction data, thereby improving the user experience. The natural language model that generates such natural language can be created by creating a list of three pairs of information: medical history information, machine instruction information, and "natural language that explains to the healthcare professional why the execution instruction data to the machine is being presented," and then performing machine learning to input the medical history information and the machine instruction information to generate "natural language that explains to the healthcare professional why the execution instruction data to the machine is being presented."

[0075] The chat function and the large-scale language model themselves are well-known technologies, so a detailed description of their configuration and generation method will be omitted here.

[0076] Like the natural language generation model 3023, the execution instruction data generation model 3024 is generated by learning in advance using appropriate natural language information so that it can return an appropriate response to specific medical instruction information, etc.

[0077] Examples of the execution instruction data generation model 3024 in the system 1 of this embodiment include an electronic medical questionnaire data generation model that generates electronic medical questionnaire data, an examination order instruction data generation model that generates an appropriate examination order for a specific patient based on the patient's past medical history and interview results, as well as past test details, prescription details, and registered disease name details, a prescription order instruction data generation model that generates an appropriate prescription order for a specific patient, a disease name registration instruction generation model that generates an appropriate disease name registration instruction for a specific patient, and an RPA execution instruction data generation model that generates appropriate RPA (Robotic Process Automation) orders for modules in the server 30 and the external server 40. Here, RPA orders include, for example, instructions for a module that broadcasts information in a medical facility, or a module that generates, sends, or displays information messages for patients in a medical facility, and generate execution instructions for these modules to perform appropriate operations.

[0078] The execution instruction data generation model 3024 is preferably execution instruction data in a format that can be interpreted by the modules in the server 30 and the external server 40, and is used to instruct the modules to perform specific operations.

[0079] The method for generating the natural language generation model 3023 is well known, so we will not explain it here, but the execution instruction data generation model 3024 is, in a sense, a natural language generation model customized for medical instruction information, so its generation method will be described later.

[0080] The medical information data 3025 is data related to medical information accepted by the various information input acceptance module 3035, which will be described later. Typical examples of medical information referred to here include OCR results of a medication notebook, OCR results of a referral letter, medical notes, text or audio information entered by a patient, medical record logs, communication records, printing instructions, logistics information, medical staff attendance information, electronic textbooks, drug interaction information, contraindication information, and information present in medical settings. Medical information is generally a broader concept than an electronic medical record, and some of the medical information data 3025 may overlap with the electronic medical record data 3022.

[0081] A medical note is a document written by a medical professional in a clinical setting that does not necessarily bear any public responsibility. Specifically, it is a memo of random thoughts, a memo of a conference, etc. A natural language generation model 3023 or the like can automatically create a medical note. However, in order to save it as a medical record, the medical note must be approved by a doctor. In actual medical settings, the contents of paper medical questionnaires and progress records brought by patients are often treated as medical notes, and once approved by a doctor, they become electronic medical record data 3022.

[0082] The RPA data 3026 is RPA data for a module in the server 30 or the external server 40 .

[0083] The search database (DB) 3027 is a database showing the correspondence between words or strings of words included in the medical information, or search tags created by natural language processing based on the medical information, and execution instruction data corresponding to the search tags for instructing modules in the server 30 and the external server 40 to execute specific operations, or natural sentences to be input to the natural language generation model 3023 and the execution instruction data generation model 3024. Details will be described later.

[0084] The electronic medical questionnaire data 3028 includes data that is the basis of the electronic medical questionnaire that the patient inputs via the terminal device 10, and data on the content that the patient inputs based on this data.

[0085] Preferably, the electronic questionnaire data 3028 is execution instruction data that specifies the medical interview items, the medical interview questions associated with these medical interview items, the medical interview question types, and the medical interview option options. There are no particular limitations on the data format of the electronic questionnaire data 3028, but like the electronic medical record data 3022, it is data written in XAML that has been converted into JSON format. Like the electronic medical record data 3022, the electronic questionnaire data 3028 preferably has identifiers such as numeric strings assigned to its input items, and these identifiers also constitute the electronic questionnaire data 3028.

[0086] The determination model 3029 is a model for determining whether or not execution instruction data that instructs modules in the server 30 and the external server 40 to perform a predetermined operation should be generated for medical information accepted by a various information input acceptance module 3035 (described later). The determination model 3029 is, for example, a so-called machine learning model. A method for generating the determination model 3029 will be described later.

[0087] The machine learning model according to this embodiment is, for example, a parameterized composite function obtained by combining multiple functions. The parameterized composite function is defined by a combination of multiple adjustable functions and parameters. The predictive model according to this embodiment may be any parameterized composite function that satisfies the above requirements, but is assumed to be a multi-layer network model (hereinafter referred to as a multi-layer network). A predictive model using a multi-layer network has an input layer, an output layer, and at least one intermediate layer or hidden layer disposed between the input layer and the output layer. The predictive model is intended to be used as a program module that is part of artificial intelligence software.

[0088] The multi-layer network according to the present embodiment may be, for example, a deep neural network (DNN), which is a multi-layer neural network that is the subject of deep learning. As the DNN, for example, a convolution neural network (CNN) that targets images may be used.

[0089] Furthermore, the above is merely an example of a prediction model, and the prediction model may have other configurations. For example, the prediction model may be a rule-based model described by a function in which hunting information and environmental information are variables and coefficients derived from past performance are assigned to each variable.

[0090] The control unit 303 is realized by the processor 29 reading an application program 3021 stored in the storage unit 302 and executing instructions included in the application program 3021. By operating in accordance with the application program 3021, the control unit 303 performs functions shown as a reception control module 3031, a transmission control module 3032, a generative model generation module 3033, a search database data generation module 3034, a various information input acceptance module 3035, a search DB search module 3036, a generative model input / output module 3037, a presentation control unit 3038, an execution instruction information output module 3039, and an electronic medical record data generation module 3040.

[0091] The reception control module 3031 controls the process by which the server 30 receives signals from external devices in accordance with a communication protocol.

[0092] The transmission control module 3032 controls the process in which the server 30 transmits signals to external devices in accordance with a communication protocol.

[0093] The generative model generation module 3033 generates the execution instruction data generation model 3024 and the judgment model 3029 stored in the storage unit 302 of the server 30. A specific method for generating the execution instruction data generation model 3024 and the judgment model 3029 by the generative model generation module 3033 will be described later.

[0094] The search database data generation module 3034 generates data for the search database 3027 stored in the storage unit 302 of the server 30 .

[0095] More specifically, the search database data generation module 3034 extracts at least one of the following information: medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical notes (hereinafter simply referred to as "medical information" and "medical history information") contained in the electronic medical record data 3022 and the medical information data 3025, and records this medical history information in pairs with execution instruction data for a machine that was performed on the same day or at the same time as the medical history information or that is intentionally linked to the medical history. Furthermore, the search database data generation module 3034 sets, as search tags, words or word strings contained in the medical history information or expressions obtained by converting the medical history information using natural language processing. While any word or word string can be set as a search tag, one example is to set the medical history, disease name, or symptom name contained in the medical information as a search tag or display title. Such search tags or display titles may be extracted from the disease name, symptom name, or problem in the problem list contained in the medical history information of the electronic medical record data 3022. Furthermore, problems may be extracted from medical history information based on factors such as the length of a line, the presence or absence of an identifier, the presence or absence of a disease name or symptom name, and the presence or absence of a tenioha. Furthermore, when registering disease names, symptom names, and problem lists as search tags or titles, disease names and symptom names may be collated and normalized to standard disease names and standard symptom names, or typos may be corrected. Furthermore, date information such as March 1st may be converted to hospitalization or examination type or relative date, such as the first day of hospitalization, the first day of outpatient treatment, or the third day after surgery, and used as a search tag or display title.

[0096] The search database 3027 stores past medical history information and its input date and time, as well as past execution instruction data and its generation unit generated by the search database data generation module 3034 based on this past medical history information. The search database data generation module 3034 may generate execution instruction data and store it in the search database 3027 based on execution instruction data that is temporally related to the generation of the search tag (for example, on the same day or the same month) or that is instructed to be executed in association with the generation of the search tag.

[0097] Here, the problem list is a list that shows what treatment is being given to the patient and what is being solved, and it needs to be updated as problems are solved or new problems emerge.

[0098] When a medical professional describes a problem in a problem list as a medical history in the electronic medical record data 3022, he or she may place a specific symbol (for example, a # or a line feed symbol) before the medical history, disease name, symptom name, etc. The search database data generation module 3034 extracts this specific symbol from the electronic medical record data 3022, etc., determines that the word or string of words following the specific symbol is a problem, and sets this word, etc. as a search tag.

[0099] Then, the search database data generation module 3034 generates execution instruction data for each search tag from the electronic medical record data or medical information data to instruct modules in the server 30 and external server 40 to perform specific operations, links it to medical history information, and stores it as data in the search database 3027.

[0100] Linking search tags to execution instruction data, etc., may be performed manually by a medical professional, or the search database data generation module 3034 may analyze electronic medical record data 3022, etc., and learn the search tags and the instructions given by medical professionals when these search tags appear, and then link them. Furthermore, if execution instruction data is linked to multiple tags, such as #high blood pressure and #constipation, the execution instruction data may be subdivided, and each tag may be determined to be linked to #high blood pressure or #constipation based on information such as drug efficacy, electronic textbook information, and data linked to other tags. An algorithm may then be executed to link the subdivided execution instruction data to each tag, and the data may then be stored. Specifically, if an antihypertensive drug and a laxative are linked as examples of prescriptions linked to #high blood pressure and #constipation, the antihypertensive drug may be linked to #high blood pressure, and the laxative may be linked to #constipation. Furthermore, drugs linked to #hypertension through other linking may be determined as antihypertensive drugs, and drugs excluding these may be determined as remaining laxatives. Alternatively, electronic medical record log information, medical professional search behavior logs, and sensor log information may be stored in the medical information data 3025, and tags may be generated based on search words entered in logs of searches for electronic textbooks, etc. Alternatively, execution instruction data may be automatically generated from electronic medical record log information and recorded in the search database 3027.

[0101] The execution instruction data linked to a search tag may include a specific operation to be executed by the execution instruction data instructing a module in the server 30 or the external server 40. In other words, when it is desired to execute a series of operations for one search tag, individual execution instruction data instructing the execution of each operation may be collected into one execution instruction data, which may be associated and stored in the search database 3027. The series of operations here may be operations executed simultaneously, or may be operations executed sequentially within a predetermined time period.

[0102] Furthermore, the search database data generation module 3034 presents the search tags generated by this search database data generation module 3034 via the display 241 of the terminal device 20, and accepts instructions to correct the search tags from the user via the input device 23 and voice processing unit 27 of the terminal device 20. The search tags for which a correction instruction has been given are corrected by the search database data generation module 3034 based on the correction instruction, and the correction details are stored in the search database 3027.

[0103] Furthermore, if a medical-related standard glossary is stored in the memory unit 302, the search database data generation module 3034 may search for synonyms based on words contained in the medical history information or words obtained by natural language processing of the medical history information, or may search for the cosine similarity of such medical history information, etc., to obtain words from the standard glossary, and set the words as new search tags in the search database 3027.

[0104] Furthermore, the search database data generation module 3034 stores comments about the search tag and / or information in a deprecated state in the search database 3027, linked to the tag, and the presentation control unit 3038, when the search DB search module 3036 searches the search database 3027 based on the search tag, presents the comment if one is linked to the search tag, and, if information in a deprecated state is linked to the tag, displays the presentation mode of the execution instruction data linked to this tag if it is different from the presentation mode of other execution instruction data.

[0105] Furthermore, the search database data generation module 3034 associates the flag entered for the search tag and / or information indicating the number of positive and negative feedbacks with this tag and stores it in the search database 3027, and when the search DB search module 3036 searches the search database 3027, if a flag is associated with the search tag, the presentation control unit 3038 filters or preferentially displays the execution instruction data based on the flag, and if information indicating either positive or negative feedback is associated with the tag, if the number of negative feedbacks is greater than the positive feedbacks, the presentation control unit 3038 preferentially displays the execution instruction data.

[0106] Furthermore, the search database data generation module 3034 stores in the search database 3027 the number of operation instructions given in the execution instruction data for each user, the number of operation instructions given in the execution instruction data for each medical department to which the user belongs, the name of the patient related to the execution instruction data, the patient's age, the creator of the execution instruction data, the creator's job title, or the medical department to which the creator belongs, linked to the execution instruction data.When the presentation control unit 3038 searches the search database 3027 using the search DB search module 3036, it changes the display mode of the execution instruction data based on the user's past number of operation instructions, the number of operation instructions by medical department, the number of operation instructions at the medical institution, the patient's name, the patient's age, the creator of the execution instruction data, the job title of the creator of the execution instruction data, the medical department to which the creator belongs, the number of execution instructions given in the execution instruction data based on the execution instruction data for each medical department to which the user belongs, a ranking of the number of execution instructions based on the execution instruction data for each job title, and a ranking of the number of individual execution instruction data linked to the execution instruction data.

[0107] The various information input accepting module 3035 accepts various information including medical information input from the terminal devices 10, 20, the external server 40, etc., and stores it in the memory unit 302. Preferably, the various information input accepting module 3035 has an input device such as a keyboard, a pointing device, a scanner, etc., and accepts various information input via the input device and stores it in the memory unit 302. The various information input accepting module 3035 also accepts various information input via the input devices 13, 23 and voice processing units 17, 27 of the terminal devices 10, 20, and stores it in the memory unit 302.

[0108] Furthermore, the various information input acceptance module 3035 accepts the result of an instruction from the execution instruction information output module 3039 to a module in the server 30 or the external server 40 to execute a specific operation based on the execution instruction data, and updates the medical information data 3025 based on this result. The updated medical information becomes input to the search DB search module 3036 and also serves as the source of search tags generated by the search database data generation module 3034. When the various information input acceptance module 3035 updates the medical information, the presentation control unit 3038 presents the updated correction content and accepts approval for the update via the terminal device 20. If this approval for the update is received, the various information input acceptance module 3035 may update the medical information.

[0109] The search DB search module 3036 searches the search database 3027 using the natural language included in the medical history information or a search tag generated from natural language, based on the various information accepted by the various information input acceptance module 3035, and obtains the search results, which correspond to the search tag, and are execution instructions for modules in the server 30 or external server 40, or medical history information to be input to the natural language generation model 3023 or execution instruction data generation model 3024. The search of the search DB search module may also be based on a vector expression based on natural language or the vector expression itself.

[0110] The generation model input / output module 3037 inputs various information including medical history information accepted by the various information input accepting module 3035, as well as instructions acquired by the search DB search module 3036, to the natural language generation model 3023 and the execution instruction data generation model 3024, and acquires natural language or execution instruction data output from the natural language generation model 3023 and the execution instruction data generation model 3024. The generation model input / output module 3037 also inputs various information including medical history information accepted by the various information input accepting module 3035 to the determination model 3029, and acquires the determination result from the determination model 3029. Then, based on the judgment results from the judgment model 3029, the generation model input / output module 3037 inputs various information including medical information accepted by the various information input acceptance module 3035, as well as instructions acquired by the search DB search module 3036, into the natural language generation model 3023 and the execution instruction data generation model 3024, and acquires natural language or execution instruction data output from the natural language generation model 3023 and the execution instruction data generation model 3024.

[0111] The presentation control unit 3038 cooperates with the transmission control module 3032 to transmit various information including medical history information accepted by the various information input acceptance module 3035, and execution instruction data that is output from the natural language generation model 3023 and the execution instruction data generation model 3024 and acquired by the generation model input / output module 3037, to the terminal device 20 operated by the medical professional, and displays it on the display 241 of the terminal device 20. The medical professional operating the terminal device 20 inputs characters (including corrections, additions, and deletions) based on the various information displayed by the presentation control unit 3038 via the display 241 of the terminal device 20, and the content of the selected input is acquired by the various information input acceptance module 3035 in cooperation with the reception control module 3031.

[0112] Furthermore, when the execution instruction information output module 3039 (described later) outputs instruction information to modules in the server 30 and the external server 40, the presentation control unit 3038 displays a user interface on the display 241 of the terminal device 20, requesting approval of the instruction information from the medical professional. As described above, the instruction input and selection input made by the medical professional via this interface are acquired by the various information input acceptance module 3035 in cooperation with the reception control module 3031. At this time, the presentation control unit 3038 displays information summarizing the execution instruction data that is the source of the instruction information on the display 241 of the terminal device 20, and requests approval of the instruction information. This information summarizing the execution instruction data may be generated by the natural language generation model 3023 or the execution instruction data generation model 3034.

[0113] Furthermore, if the medical information is a specific patient's medical history, the presentation control unit 3038 generates and updates a problem list based on this medical history, sets search terms based on this problem list, and uses these search terms to search a search database for execution instruction data. The execution instruction information output module 3039 then searches a search database for past execution instruction data for machines within the medical institution or for the patient based on medical history information or tags, and obtains execution instruction data such as test execution instruction candidates, prescription execution instruction candidates, and disease name registration execution instructions for the patient whose medical history is recorded. The presentation control unit 3038 then displays a user interface on the display 241 of the terminal device 20 that displays tags for the test execution instruction candidates, prescription execution instruction candidates, and disease name registration execution instruction candidates and presents them to a medical professional for approval. Additionally, the presentation control unit 3038 displays the frequency of test instructions and prescription instructions in the past medical information data 3025. This frequency display can be implemented in various ways, such as changing the display order, color, or font density.

[0114] The presentation control unit 3038 receives pathological information as input, outputs the input to the determination model 3029, and also has the function of determining whether to generate, search for, or display execution instruction data as a result of the determination model.

[0115] Furthermore, the presentation control unit 3038 presents at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical care notes that are the basis for generating the search tag, via the display 241 of the terminal device 20, when the search DB search module 3036 searches for execution instruction data based on the tag. At this time, the search database data generation module 3034 records the link with the medical history information and the position of the disease name included in the medical history information in the search database 3027, and when presenting the medical history information that is the basis for generating the tag, if the medical history information that is the basis for generating the tag is presented first, the presentation control unit 3038 presents that it is presented first, and if there are multiple pieces of medical history information that are the basis for generating the tag, it presents the medical history information that is the basis for generating the tag with the oldest date information.

[0116] The execution instruction information output module 3039 generates instruction information for modules in the server 30 and the external server 40 based on the natural language output from the natural language generation model 3023, the execution instruction data output from the execution instruction data generation model 3024, and the results of operation input performed by the medical professional via the terminal device 20, and outputs the information to this module.

[0117] The electronic medical record data generation module 3040 acquires a log of information exchanged between each module of the control unit 303 of the server 30 and the natural language generation model 3023 and the execution instruction data generation model 3024, and stores this log in the memory unit 302 as electronic medical record data 3022.

[0118] 5 and 6 are diagrams showing the data structure of the database stored in the server 30. Note that Fig. 5 and Fig. 6 are merely examples and do not exclude data not shown.

[0119] The databases shown in Figures 5 and 6 are relational databases, which are used to manage data sets called tables in a tabular format that are structurally defined by rows and columns, by associating them with one another. In a database, a table is called a table, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables can be set and associated.

[0120] Typically, each table has a column set as a primary key for uniquely identifying a record, but setting a primary key to a column is not essential. The control unit 303 of the server 30 can cause the processor 29 to add, delete, or update records in a specific table stored in the storage unit 302 according to various programs.

[0121] 5 is a diagram showing an example of the data structure of search DB 3027. As shown in FIG. 5, each record of search DB 3027 includes, for example, an item "Type," an item "Structure Data," an item "Hospital Standard Approval Flag," an item "Department Standard Approval Flag," an item "Number of Uses," an item "Patient Name," and an item "Search Tag or Natural Sentence." Each item of search DB 3027 is input by search database data generation module 3034. The information stored in search DB 3027 can be changed or updated as appropriate.

[0122] The item "type" is information indicating the type of medical information.

[0123] The item "structured data" is structured data linked to the item "search tag or natural sentence" and is an example of execution instruction data that instructs a module in the server 30 or external server 40 to perform a specific operation.

[0124] The items "Hospital standard approval flag" and "Department standard approval flag" are set by the execution instruction information output module 3039. When the execution instruction data output module 3039 outputs execution instruction data to a module in the server 30 or external server 40 to instruct the module to perform a specific operation, the presentation control unit 3038 displays buttons or the like on the display 241 of the terminal device 20 for inputting whether or not to approve the execution instruction data as the hospital standard or whether or not to approve it as the department standard, and if the input indicating approval is accepted, the execution instruction information output module 3039 sets a flag (enters 1 into the item).

[0125] The "number of uses" item is an item incremented by the execution instruction information output module 3039 each time the execution instruction information output module 3039 outputs execution instruction data specified by the "structure data" item to a module within the server 30 or external server 40.

[0126] The item "patient name" is information about the patient's name that was included in the medical information that was the source of generating the data when the data in the row in the search DB 3027 was generated.

[0127] "Search tag or natural sentence" is information indicating a search tag included in the medical information identified by the item "type."

[0128] 6 is a diagram showing another example of the data structure of search DB 3027. As shown in FIG. 6, each record of search DB 3027 includes, for example, an item "Type," an item "Structure Data," an item "Hospital Standard Approval Flag," an item "Department Standard Approval Flag," an item "Number of Uses," an item "Patient Name," and an item "Search Tag or Natural Sentence." Each item of search DB 3027 is input by search database data generation module 3034. The information stored in search DB 3027 can be changed or updated as appropriate.

[0129] The data structure shown in FIG. 6 is almost the same as the data structure shown in FIG. 5, so a detailed description will be omitted, but in FIG. 6, natural sentences are entered in the item "search tag or natural sentences."

[0130] <3. Operation Example> An example of the operation of the server 30 will now be described.

[0131] Fig. 7 is a flowchart showing an example of the operation of the server 30. Fig. 7 shows an example of the operation of generating execution instruction data for an electronic medical questionnaire based on the medical history information written on a referral letter brought by a patient from another hospital or extracting it from a search database, and adding the patient's response to the electronic medical questionnaire to the medical history information, if any.

[0132] The flowchart shown on the right side of Figure 7 shows the operation of generating a search database 3027 and a judgment model 3029 to realize the operation shown in the flowchart on the left side of Figure 7, and the flowchart shown on the left side of Figure 7 shows the operation based on the search database 3027 and the judgment model 3029 generated by the operation shown in the flowchart on the right side of Figure 7.

[0133] First, the flowchart shown on the right side of Figure 7 will be described. In step S700, the control unit 303 references the electronic medical record data 3022, etc., and extracts medical history information written in natural language or search tags linked to the medical history, and instructions for displaying an electronic questionnaire from a medical professional, which are included in the electronic medical record data 3022, to create an electronic medical questionnaire display instruction search database, which is an example of the search database 3027. Specifically, for example, the control unit 303 references the electronic medical record data 3022, etc., and extracts the natural language of the medical history or search tags linked to the medical history and instructions for creating an electronic medical questionnaire, using the search database data generation module 3034, to create an electronic medical questionnaire display instruction search database, which is an example of the search database 3027. The electronic medical questionnaire display instruction search database created in step S700 is stored in the search database 3027 of the storage unit 302.

[0134] Next, in step S701, the control unit 303 refers to the electronic medical record data 3022, etc., and extracts the natural language of the medical history or search tags linked to the medical history, and the determination result of whether an additional medical interview is necessary, which is included in the medical information, to create a determination model of whether an additional medical interview is necessary, which is an example of the determination model 3029. Specifically, for example, the control unit 303 refers to the electronic medical record data 3022, etc., and extracts the natural language of the medical history or search tags linked to the medical history, and the determination result of whether an additional medical interview is necessary, which is included in the medical information, using the generative model generation module 3033, to create a determination model of whether an additional medical interview is necessary, which is an example of the determination model 3029. The determination model of whether an additional medical interview is necessary, which is generated in step S701, is stored in the determination model 3029 in the storage unit 302.

[0135] Next, the flowchart shown on the left side of Figure 7 will be described. In step S750, the control unit 303 obtains medical history information, particularly the natural language of the medical history, by scanning a referral letter from another hospital brought by the patient. Specifically, for example, the control unit 303 scans the referral letter using a scanner provided in the various information input acceptance module 3035, and obtains medical history information, particularly the natural language of the medical history, from the referral letter. Then, the various information input acceptance module 3035 stores the obtained natural language of the medical history in the storage unit 302 as medical information data 3025.

[0136] In step S751, the control unit 303 inputs the natural language of the medical history obtained in step S750 into the determination model 3029 and obtains a determination result. The determination result of the determination model 3029 in FIG. 7 is a determination result of whether or not an additional medical interview is necessary for the patient, based on the natural language of the medical history obtained in step S750. Specifically, for example, the control unit 303 inputs the natural language of the medical history obtained in step S750 into the determination model 3029 using the generative model input / output module 3037 and obtains the determination result. Then, if the determination result by the determination model 3029 is that an additional medical interview is necessary for the patient, the program proceeds to step S752, and if it is determined that an additional medical interview is not necessary, the program terminates the operation according to the flowchart on the left of FIG. 7.

[0137] In step S752, the control unit 303 searches the electronic questionnaire instruction search database, which is an example of the search database 3027, using the medical history or a search tag generated from the medical history as a search key, transmits execution instruction data as the search result to an electronic questionnaire generation module, which is an example of a module in the server 30 or external server 40, and instructs the electronic questionnaire generation module to create electronic questionnaire data. Specifically, for example, the control unit 303 uses the search DB search module 3036 to search the electronic questionnaire instruction search database, which is an example of the search database 3027, using the medical history or a search tag generated from the medical history as a search key, and transmits the execution instruction data as the search result to the electronic questionnaire generation module, which is an example of a module in the server 30 or external server 40, using the execution instruction information output module 3039, and instructs the electronic questionnaire generation module to create electronic questionnaire data.

[0138] In step S753, the control unit 190 of the terminal device 10 carried by the patient displays the electronic medical questionnaire on the display 141 based on the electronic medical questionnaire data sent from the electronic medical questionnaire creation module of the server 30. Next, in step S754, the patient inputs data into the electronic medical questionnaire using the terminal device 10. The input data is transmitted to the server 30 via the control unit 190 of the terminal device 10.

[0139] In step S755, the control unit 303 adds the electronic medical questionnaire data input and transmitted in step S754 to the medical history information, thereby generating new (updated) medical history information. Specifically, for example, the control unit 303 uses the various information input acceptance module 3035 to add the electronic medical questionnaire data input and transmitted in step S754 to the medical history information, thereby generating new (updated) medical history information. Note that a medication notebook scanner may be used instead of the referral letter scanner. As an example, in guiding medical treatment, when considering prescribing a drug called Paquilobit, which is expected to cause COVID-19 infection and has many drug interactions, a function may be provided to highlight drugs that interact with Paquilobit when displaying the OCR results data from the medication notebook, thereby indicating whether the patient is at high risk for prescribing that drug.

[0140] Fig. 8 is a flowchart showing an example of the operation of the server 30. The operation shown in the flowchart of Fig. 8 is similar to the operation shown in the flowchart of Fig. 7, except that while data for the search database 3027 is generated in Fig. 7, an execution instruction data generation model 3024 is generated in Fig. 8. Therefore, a description of steps common to those in Fig. 7 will be omitted, and the following description will focus on steps that differ from those in Fig. 7.

[0141] In step S800 of the flowchart shown on the right of Fig. 8 , the control unit 303 references the electronic medical record data 3022, etc., and extracts the natural language of the medical history or search tags linked to the medical history, and electronic questionnaire creation instructions for medical professionals included in the medical information, to create an electronic questionnaire display instruction generation model, which is an example of the execution instruction data generation model 3024. Specifically, for example, the control unit 303 references the electronic medical record data 3022, etc., and extracts the natural language of the medical history or search tags linked to the medical history, and electronic questionnaire creation instructions, using the generation model generation module 3033, to create an electronic questionnaire display instruction generation model, which is an example of the execution instruction data generation model 3024. The electronic questionnaire display instruction generation model generated in step S800 is stored in the execution instruction data generation model 3024 in the storage unit 302.

[0142] 8 , the control unit 303 inputs the medical history or tags generated from the medical history into an electronic questionnaire display instruction generation model, which is an example of the execution instruction data generation model 3024, and uses the execution instruction data, which is an output result of the electronic questionnaire display instruction generation model, to instruct an electronic questionnaire generation module, which is an example of a module in the server 30 or the external server 40, to create electronic questionnaire data. Specifically, for example, the control unit 303 inputs the medical history or tags generated from the medical history into an electronic questionnaire display instruction generation model, which is an example of a module in the server 30 or the external server 40, using the generation model input / output module 3037, and uses the execution instruction data, which is an output result of the electronic questionnaire display instruction generation model, to instruct the electronic questionnaire generation module, which is an example of a module in the server 30 or the external server 40, to create electronic questionnaire data.

[0143] Fig. 9 is a flowchart showing an example of the operation of the server 30. Fig. 9 is a diagram showing an example of the operation of starting from medical history information, which is an example of medical information included in the electronic medical record data 3022, etc., issuing operation instructions to modules in the server 30 and the external server 40 based on this medical history, and updating the medical history based on the processing results from this module.

[0144] The flowchart shown on the right side of Figure 9 shows the operation of generating a search database 3027 and a judgment model 3029 to realize the operation shown in the flowchart on the left side of Figure 9, and the flowchart shown on the left side of Figure 9 shows the operation based on the search database 3027 and the judgment model 3029 generated by the operation shown in the flowchart on the right side of Figure 9.

[0145] First, the flowchart shown on the right side of Fig. 9 will be described. In step S900, the control unit 303 references the electronic medical record data 3022, etc., and creates a machine-instruction search database, which is an example of the search database 3027, from medical history information written in natural language or search tags linked to the medical history information, and execution instruction data related to the medical history information in the electronic medical record data 3022 (electronic questionnaire generation execution instruction data, test order execution instruction data, prescription order execution instruction data, disease name registration execution instruction data, message sending execution instruction data, RPA execution instruction data, and natural language append execution instruction data). That is, the control unit 303, through the search database data generation module 3034, references the electronic medical record data 3022, etc., and creates a machine-instruction search database using pairs of natural language medical history information or search tags linked to the medical history information, and execution instruction data (electronic questionnaire generation execution instruction data, test order execution instruction data, prescription order execution instruction data, disease name registration execution instruction data, message sending execution instruction data, RPA execution instruction data, natural language append execution instruction data) that are issued to the same patient and at the same time (same year, same month, same time, same second, etc.) as the medical history information in the electronic medical record data 3022, or that are intentionally linked by a medical professional. The machine-instruction search database created in step S900 is stored in the search database 3027 of the storage unit 302.

[0146] Next, in step S901, the control unit 303 references the electronic medical record data 3022, etc., and creates a determination model that uses the natural language of the medical history or search tags linked to the medical history as input to determine whether additional machine instructions are necessary. Specifically, for example, the control unit 303 references the electronic medical record data 3022, etc., and extracts the natural language of the medical history or search tags linked to the medical history and the results of whether additional machine instructions have been issued, which are included in the electronic medical record data 3022, etc., or collects the results of medical professionals' determinations of whether additional machine instructions are necessary, and performs machine learning on the data to create the determination model. The determination model for whether additional machine instructions are necessary, generated in step S701, is stored in the determination model 3029 of the storage unit 302.

[0147] Next, the flowchart shown on the left side of Fig. 9 will be described. In step S950, the control unit 303 obtains a medical history from medical information such as the electronic medical record data 3022. Specifically, for example, the control unit 303 obtains a medical history from medical information such as the electronic medical record data 3022 using the various information input acceptance module 3035.

[0148] In step S951, the control unit 303 inputs the medical history obtained in step S950 into the determination model 3029 and obtains a determination result. The determination result of the determination model 3029 in FIG. 9 is a determination result of whether or not additional machine instructions are necessary based on the medical history obtained in step S950. Specifically, for example, the control unit 303 inputs the medical history obtained in step S950 into the determination model 3029 using the generation model input / output module 3037 and obtains the determination result. If the determination result by the determination model 3029 is that additional machine instructions are necessary, the program proceeds to step S952, and if it is determined that additional machine instructions are not included, the operation according to the flowchart on the left of FIG. 9 is terminated.

[0149] In step S952, the control unit 303 uses the natural language of the medical history or a search tag generated from the medical history as a search key to search a machine-instruction search database, which is an example of the search database 3027. Specifically, for example, the control unit 303 uses the natural language of the medical history or a search tag generated from the medical history as a search key to search a machine-instruction search database, which is an example of the search database 3027, using the search DB search module 3036, to search a machine-instruction search database, which is an example of the search database 3027, and obtains execution instruction data as a search result.

[0150] In step S953, the control unit 303 transmits the execution instruction data acquired in step S952 to the terminal device 20 carried by the medical professional, and the presentation control unit 294 of the control unit 290 of the terminal device 20 presents this execution instruction data on the display 241 based on the execution instruction data sent from the server 30, and the instruction information input instruction unit 295 of the terminal device 20 requests the medical professional to input approval as to whether or not to instruct the server 30 and the external server 40 to perform a specific operation based on this execution instruction data. Then, if approval is input in step S953, in step S954, the control unit 290 of the terminal device 20 transmits to the server 30 a notification that approval has been input, and the control unit 303 transmits the execution instruction data for which approval has been input to the modules in the server 30 and the external server 40, and instructs the medical professional to perform a specific operation based on this execution instruction data. Specifically, for example, the control unit 303 transmits the execution instruction data for which approval has been input via the execution instruction information output module 3039 to a module within the server 30 or the external server 40, and instructs a specific operation based on this execution instruction data.

[0151] In step S955, the control unit 303 accepts the results of the specific operation based on the execution instruction data transmitted to the modules in the server 30 and the external server 40 in step S954, and updates the medical history based on these results and input from the modules in the server 30 and the external server 40. Specifically, for example, the control unit 303 accepts the results of the specific operation based on the execution instruction data transmitted to the modules in the server 30 and the external server 40 in step S954 using the various information input acceptance module 3035, and updates the medical history based on these results and input from the modules in the server 30 and the external server 40.

[0152] Fig. 10 is a flowchart showing an example of the operation of the server 30. The operation shown in the flowchart of Fig. 10 is similar to the operation shown in the flowchart of Fig. 9, except that a search database 3027 is generated in Fig. 9, whereas an execution instruction data generation model 3024 is generated in Fig. 10. Therefore, a description of steps common to the description of Fig. 9 will be omitted, and the following description will focus on steps that differ from the steps of Fig. 7.

[0153] In step S1000 of the flowchart shown on the right side of Figure 10, the control unit 303 refers to the electronic medical record data 3022, etc., and creates a machine instruction generation model, which is an example of an execution instruction data generation model 3024, from the natural language of the medical history or search tags linked to the medical history, and instructions to modules in the server 30 and external server 40 (electronic questionnaire generation execution instruction data, test order execution instruction data, prescription order execution instruction data, disease name registration execution instruction data, message sending execution instruction data, RPA execution instruction data, natural language append execution instruction data). That is, the control unit 303, using the generation model generation module 3033, references the electronic medical record data 3022, etc., and creates a machine instruction generation model, which is an example of the execution instruction data generation model 3024, from the natural language of the medical history or search tags linked to the medical history, and instructions (electronic questionnaire generation execution instruction data, test order execution instruction data, prescription order execution instruction data, disease name registration execution instruction data, message sending execution instruction data, RPA execution instruction data, and natural language append execution instruction data) for the modules in the server 30 and external server 40. The machine instruction generation model generated in step S1000 is stored in the execution instruction data generation model 3024 in the memory unit 302.

[0154] 10 , the control unit 303 inputs the medical history or tags generated from the medical history into a machine instruction generation model, which is an example of the execution instruction data generation model 3024, and uses the execution instruction data, which is an output result of the machine instruction generation model, to instruct an electronic questionnaire generation module, which is an example of a module in the server 30 or the external server 40, to create electronic questionnaire data. Specifically, for example, the control unit 303 inputs the medical history or tags generated from the medical history into a machine display instruction generation model, which is an example of a module in the server 30 or the external server 40, using the generation model input / output module 3037, and uses the execution instruction data, which is an output result of the electronic questionnaire display instruction generation model, to instruct the electronic questionnaire generation module, which is an example of a module in the server 30 or the external server 40, to create electronic questionnaire data, using the execution instruction information output module 3039.

[0155] <4 Screen Examples> Examples of screens output to the terminal device 20 will be described below with reference to FIGS.

[0156] 10 to 19 are diagrams showing updates to medical history information in the system 1 of this embodiment. In these figures, the term "item" refers to information indicating what operation was performed in the system 1, the term "date" refers to information indicating the date on which the operation was performed, and the term "content" refers to medical history information, information exchanged in natural language with the natural language generation model 3023 and the execution instruction data generation model 3024, and information indicating instruction information given to modules in the server 30 and the external server 40 and the results thereof. The information listed in the item, date, and content is execution instruction data, and at least a portion of it becomes a log for generating electronic medical record data.

[0157] An outline of the flow of updating medical history information shown in Figures 10 to 19 will be described. A patient comes to the hospital with a referral letter from another hospital, and the referral letter is scanned to obtain medical history information. After deleting items and content that do not need to be recorded in the electronic medical record from the obtained medical history information, this medical history information is input into the natural language generation model 3023 and the execution instruction data generation model 3024. The natural language generation model 3023 and the execution instruction data generation model 3024 then create a draft of the medical record, as well as create execution instruction data for creating an electronic medical questionnaire for the patient, and request permission from the doctor.

[0158] If permission is given by the doctor, the medical record is updated, and the execution instruction data is output to a module in the server 30 and the external server 40 to generate an electronic medical questionnaire, which is displayed on the patient's terminal device 10. The electronic medical questionnaire data input by the patient using the terminal device 10 is sent to the server 30, and the medical record is updated with the doctor's permission.

[0159] Furthermore, the natural language generation model 3023 and the execution instruction data generation model 3024 recommend that the patient be tested for COVID-19, and based on the doctor's instructions, a test instruction is sent to the server 30 and the module in the external server 40. At the same time, a voice instruction instructing the patient to head to the examination room is sent to the module in the server 30 and the external server 40.

[0160] Furthermore, when the test results are sent to the server 30, the doctor is advised to update the medical record and create an additional electronic medical questionnaire based on the test results, and the medical record is updated and the electronic medical questionnaire is sent with the doctor's permission.

[0161] When a patient fills out an electronic medical questionnaire and requests additional prescription medication, the natural language generation model 3023 and the execution instruction data generation model 3024 update the medical record, send a voice message to the patient, and ask the doctor whether additional prescription medication is permitted. With the doctor's permission, a prescription is issued and a voice message is sent to the patient allowing them to go home.

[0162] 10 to 19, the shaded areas indicate the contents entered by the doctor using the terminal device 20.

[0163] Next, Figures 20 to 26 are figures showing an example in which the output from the system 1 of this embodiment, particularly the server 30 (including the natural language generation model 3023 and the execution instruction data generation model 3024) and the input content by the medical professional are displayed on the display 241 of the terminal device 20 carried by the medical professional.

[0164] A feature of the screen examples shown in Figures 20 to 26 is that the input / output log of information between the server 30 and the terminal device 20 and a summary of the log extracted from this input / output log (this summary also becomes part of the electronic medical record data) are displayed on the same screen of the display 241.

[0165] On the right side of the screen of the display 241, natural language output by the chat functions of the natural language generation model 3023 and the execution instruction data generation model 3024, and candidate instructions for input to modules in the server 30 and the external server 40 recommended to medical professionals, which are similarly output by the natural language generation model 3023 and the execution instruction data generation model 3024, are displayed. Meanwhile, on the left side of the screen of the display 241, a summary of the content displayed on the right side of the screen is generated and displayed by the server 30. This summary is the medical record for the medical professional and also electronic medical record data. The summary is generated by the natural language generation model 3023, the execution instruction data generation model 3024, or a machine learning model trained for summarization.

[0166] 20 to 26, the shaded areas indicate the options selected and input by the doctor using the terminal device 20.

[0167] 27 and 28 are diagrams showing the input results of the electronic medical questionnaire displayed on the display 241 of the terminal device 20 carried by the medical professional. In Fig. 27 and Fig. 28, the shaded areas indicate the options selected and input by the doctor using the terminal device 20.

[0168] <5. Effects of the embodiment> As described above in detail, the system 1 of the present embodiment can automate the processing of medical information by medical professionals.

[0169] <6. Modification> As a modification, there is a case where a system has both Function 1, which automatically executes execution instruction data in response to input, and Function 2, which confirms a doctor's approval before execution, and a function that sets a flag indicating whether confirmation is required or not for specific input, and selects between Function 1 and Function 2. This function makes it possible to skip user approval of execution instructions for specific input data and execute them automatically. This enables effective input when rapid processing is required.

[0170] Specifically, suppose a doctor orders a minimally invasive "routine blood draw for side effect evaluation" performed approximately once a year, for example, by recording "high blood pressure, routine blood draw performed" as medical history in the patient's chart during the patient's first visit and issuing an instruction to perform the test that day. In response, the AI ​​tags the test execution instruction as "high blood pressure: routine blood draw" to make it searchable. At subsequent visits, when the doctor records "high blood pressure, routine blood draw performed today" as medical history in the patient's chart, the system can automatically enter the previous execution instruction tagged as "high blood pressure routine blood draw" for that day. At this time, the user can input that approval is no longer required, and from then on, the execution instruction can be automatically registered the next time the doctor records "high blood pressure, routine blood draw performed today" as medical history in the patient's chart.

[0171] As another example, when a doctor writes "high blood pressure, next routine blood test" in a patient's chart, the next time the doctor makes a reservation for that day, the order can be automatically registered as an order to be performed on that scheduled date. In this case, a check function can be implemented to check whether a similar test has been scheduled just before the appointment, preventing similar orders from being automatically ordered multiple times.

[0172] Another example of a variation is a function for integrating multiple execution instruction data obtained from search results and deleting duplicates when integrating them. A specific example includes a function for integrating execution instruction data for drug prescriptions obtained as search results and deleting duplicates.

[0173] For example, if a doctor writes in the medical record of a patient receiving outpatient treatment for high blood pressure, "Continue regular high blood pressure treatment, prescribe the same hay fever medication as last year," prescription execution instruction A, which prescribes the current high blood pressure medication, can be combined with execution instruction data B, which prescribes both high blood pressure medication and hay fever medication from one year ago, and by deleting the prescription execution instruction data for the high blood pressure medication from one year ago, it becomes possible to add the same execution instruction data for the hay fever medication as last time to the prescription execution instruction data for the current high blood pressure medication.This makes it possible to prescribe the latest dosage and administration even if the dosage and administration of the high blood pressure medication has changed over the past year.

[0174] This function can also be linked to an electronic medical questionnaire. This function can be realized by adding a function to tag prescription execution instruction data in more detail for each drug, and by preparing the contents of the medical record and a list of tags that may be assigned to drugs in a separately prepared database.

[0175] In one example, the disease names "hay fever" for Claritin and "high blood pressure" for Amlodipine are registered in advance in the database as tagging candidates, and if a doctor writes "prescribed medication for hay fever and high blood pressure" in the patient's chart and simultaneously creates execution instruction data prescribing "Claritin and amlodipine," the execution instruction data for the entire prescription will be tagged with "high blood pressure + hay fever," and at the same time, "Claritin" will be tagged with hay fever and Amlodipine with "high blood pressure."

[0176] By tagging in this way in advance, if you write "continue normal hypertension treatment, prescribe the same hay fever medication as last year" one year from now, you will be able to search for and obtain last year's hay fever medication and create new execution instruction data.

[0177] In another example, patients can enter their desired hay fever medication prescriptions on an electronic medical questionnaire, and if the patient requests a prescription, the patient's hay fever prescription from one year ago can be duplicated and integrated to create new prescription data. These methods allow doctors to reflect the patient's wishes directly in the electronic medical record. When integrating and deleting duplicates, the most recent information among drugs with the same tag is prioritized for duplicate deletion, ensuring that the most recent dosage and administration are prescribed.

[0178] Another example is a modified version where, when execution instruction data is obtained from the search results, additional execution instruction data for another patient is searched for and the results are integrated, with duplicates deleted during integration. Specifically, this is a prescription for a patient with high blood pressure and renal dysfunction who has developed pneumonia.

[0179] In one example, if a doctor writes in the medical record as follows in the medical history: "Continue normal hypertension treatment, and prescribe a pneumonia set based on the pneumonia medication prescribed when another patient was diagnosed with renal dysfunction," it is necessary to integrate prescription execution instruction A, which prescribes hypertension medication, with prescription execution instruction B, which prescribes pneumonia medication for a patient with renal dysfunction.

[0180] For such a prescription set, the disease names "pneumonia, cough" for Mezicom, "pneumonia" for Azithromycin, "pneumonia, fever" for Calonal, and "pneumonia, phlegm" for Mucosolvan are registered in advance as tagging candidates in the database. For example, if a patient's medical record states "treated for pneumonia" and blood test results show renal dysfunction, and the prescription contains "Azithromycin, Calonal, Mucosolvan, Mezicom," the entire prescription can be tagged as "pneumonia, renal dysfunction," and each prescription for Azithromycin, Calonal, Mucosolvan, and Mezicom can also be tagged as "pneumonia, renal dysfunction." From the next time onward, for patients with pneumonia whose test results show renal dysfunction, it will be possible to obtain and issue instructions for pneumonia treatment at the dosage for patients with renal dysfunction.

[0181] <6. Supplementary Note> The above-described embodiments have been described in detail to clearly explain the present disclosure, and are not necessarily limited to those including all of the described configurations. Furthermore, some of the configurations of each embodiment can be added to, deleted from, or replaced with other configurations.

[0182] As an example, in the embodiment described above, electronic questionnaire data was corrected / added using voice recognition, but electronic questionnaires, electronic medical record templates, and electronic medical record data may also be corrected / added using voice recognition.

[0183] Furthermore, some or all of the above-described configurations, functions, processing units, processing means, etc. may be implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that implements the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for providing such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tape, non-volatile memory cards, and ROMs.

[0184] Furthermore, the program code that realizes the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, perl, Shell, PHP, and Java (registered trademark).

[0185] Furthermore, the program code of the software that realizes the functions of the embodiments may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read and execute the program code stored in the storage means or the storage medium.

[0186] The matters described in the above embodiments are supplemented below. (Supplementary Note 1) A program for operating a computer (30) having a processor (39) and a memory (35), wherein the memory (35) stores a search database (3027) in which execution instruction data used to instruct the computer (30) and / or other computers to execute specific operations, or a program or machine learning model (3023, 3024) for generating execution instruction data, and the program receives input of at least one of medical history information, information entered by a patient, a disease name, a symptom name, a problem in a problem list, and a medical note in the processor (39). and a second step (S852) of searching a search database (3027) using the input received in the first step (S750) to obtain execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation, or inputting the input received in the first step (S750) into a program or machine learning model (3023, 3024) to obtain execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation. (Supplementary Note 2) The program according to Supplementary Note 1, wherein the execution instruction data includes a plurality of individual execution instruction data used to instruct the computer (30) and / or other computers to perform a specific operation. (Appendix 3) A program as described in Appendix 1, in which at least one of the medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical notes is written in natural language, or natural language processing is performed when searching the search database (3027), or the program or machine learning model (3023, 3024) performs natural language processing to generate execution instruction data.(Supplementary Note 4) The program according to Supplementary Note 1, wherein the execution instruction data includes at least one of test order execution instruction data, prescription order execution instruction data, disease name registration execution instruction data, message sending execution instruction data, RPA execution instruction data, natural language append execution instruction data, template display execution instruction data, template data input execution instruction data, test result filtered display execution instruction data, prescription information filtered display execution instruction data, and consultation reservation execution instruction data. (Supplementary Note 5) The program according to Supplementary Note 1, wherein at least one of a referral letter or a medicine notebook, OCR result information of a scanner of test results, an electronic referral letter, an electronic medicine notebook and electronic test results, information in natural language input by the patient, information resulting from speech recognition of speech input by the patient, and a medical note generated by a program or a machine learning model (3023, 3024) is used as input to a first step (S750) of accepting input of at least one of medical history information, information entered by a patient, a disease name, a symptom name, a problem in a problem list, and a medical note. (Supplementary Note 6) The program according to Supplementary Note 1, further causing the processor (39) to execute a third step (S954) of outputting the execution instruction data acquired in the second step (S852) to the computer (30) and / or another computer, and instructing the computer (30) and / or another computer to execute a specific operation. (Supplementary Note 7) The program according to Supplementary Note 6, wherein the execution instruction data includes a plurality of individual execution instruction data used to instruct the computer (30) and / or another computer to execute a specific operation, and wherein in the third step (S954), the execution instruction data including the plurality of individual execution instruction data acquired in the second step (S852) is output to the computer (30) and / or another computer, and instructs the computer (30) and / or another computer to execute a series of specific operations based on the plurality of individual execution instruction data.(Supplementary Note 8) The program further causes the processor (39) to execute the following steps: a fourth step (S955) of instructing the computer (30) and / or another computer to perform a specific operation in the third step (S954) and accepting output obtained from the computer (30) and / or another computer; a fifth step of updating and correcting the medical history information or the clinical note using the output accepted in the fourth step (S955); and a sixth step of searching a database using the medical history information or the clinical note updated in the fifth step as input to obtain execution instruction data for instructing the computer (30) and / or another computer to perform the specific operation, or inputting the medical history information or the clinical note updated in the fourth step (S955) into a program or a machine learning model (3023, 3024) to again obtain execution instruction data for instructing the computer (30) and / or another computer to perform the specific operation. The program according to Supplementary Note 6. (Supplementary Note 9) The program according to Supplementary Note 1, further causing the processor (39) to execute a seventh step (S953) of accepting an approval input as to whether or not to instruct the computer (30) and / or other computers to execute a specific operation based on the execution instruction data acquired in the second step (S852). (Supplementary Note 10) The program according to Supplementary Note 9, further causing the processor (39) to execute an eighth step (S954) of presenting the update correction content and accepting approval for the update when updating the medical history information or medical notes based on the output acquired in the fourth step (S955). (Supplementary Note 12) The program according to Supplementary Note 7, wherein in the seventh step (S953), if the acquired execution instruction data includes a plurality of options, a selection input of at least one of the plurality of options is accepted.(Supplementary Note 13) The program according to Supplementary Note 11, wherein in an eighth step (S954), if the update or correction of the medical history information or the medical note includes multiple options, the program accepts input of a selection of at least one of the multiple options. (Supplementary Note 14) The program according to Supplementary Note 9, further causing the processor (39) to output the execution instruction data for which approval was input in the seventh step (S953) to the computer (30) and / or another computer, and execute a ninth step of instructing the computer (30) and / or another computer to execute a specific operation. (Supplementary Note 15) The program according to Supplementary Note 1, wherein the search database (3027) is set with search keys consisting of words contained in at least one of the medical history information, the information input by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, or tags created by natural language processing based on at least one of the medical history information, the information input by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, and wherein the tags are associated with execution instruction data for instructing the computer (30) and / or other computers to execute specific operations. (Supplementary Note 16) The program according to Supplementary Note 15, wherein the search database (3027) includes tags obtained by converting date information such as the start date of hospitalization, the date of surgery, and the date of first outpatient visit, which are contained in the medical history information, the information input by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, into relative dates and times from a predetermined date and time by natural language processing.(Supplementary Note 17) The program further causes the processor (39) to execute a tenth step of generating tags from words contained in at least one of the medical history information, the information input by the patient, the disease name, the symptom name, the problem in the problem list, and the medical care note, or generating tags by performing natural language processing based on the medical history information, the information input by the patient, the disease name, the symptom name, the problem in the problem list, and the medical care note, and an eleventh step of presenting at least one of the medical history information, the information input by the patient, the disease name, the symptom name, the problem in the problem list, and the medical care note, which are the basis for generating the tags, when searching for execution instruction data based on the tags, and in the tenth step, recording the link with the medical history information and the position of the disease name contained in the medical history information in the search database (3027), and In step 11, when at least one of the medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical note that is the basis for generating the tag is presented, if at least one of the medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical note that is the basis for generating the tag is presented first, it is indicated that it is presented first, and if there are multiple pieces of medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical note that are the basis for generating the tag, the medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical note that is the basis for generating the tag with the oldest date information is presented. (Supplementary Note 18) The program according to Supplementary Note 15, wherein the memory (35) stores a medical standard glossary, and the program further causes the processor (39) to execute a twelfth step of searching for synonyms or searching for cosine similarities of the medical history information, etc., based on words contained in at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, or words obtained by natural language processing of at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, to obtain words from the standard glossary and set the words as new tags in the search database (3027).(Supplementary Note 19) The program according to Supplementary Note 1, further causing the processor (39) to execute a thirteenth step of accepting a correction input for a search tag in the search database (3027) from a user and correcting the search tag based on the correction input. (Supplementary Note 20) The program according to Supplementary Note 1, wherein the search database (3027) stores comments and / or deprecated information about the search tag linked to the tag, and in the second step (S852), when the search database (3027) is searched based on the tag, if a comment is linked to the tag, the comment is presented, and if deprecated information is linked to the tag, the presentation mode of the execution instruction data linked to the tag is made different from the presentation mode of other execution instruction data. (Appendix 21) A program as described in Appendix 15, in which the search database (3027) associates a flag entered for a tag and / or information indicating the number of positive and negative feedbacks with this tag, and in a second step (S852), when searching the search database (3027), if a flag is associated with the tag, the program filters or preferentially displays the execution instruction data based on the flag, and if information indicating either positive or negative feedback is associated with the tag, the program preferentially displays the execution instruction data if the number of negative feedbacks is greater than the positive feedbacks.(Appendix 22) The search database (3027) stores, linked to the execution instruction data, the number of operation instructions of the execution instruction data for each user, the number of operation instructions of the execution instruction data for each medical department to which the user belongs, the name of the patient related to the execution instruction data, the patient's age, the creator of the execution instruction data, the creator's job title, or the medical department to which the creator belongs, and in a second step (S852), the program described in Appendix 7 changes the display mode of the execution instruction data based on the user's past number of operation instructions, the number of operation instructions by medical department, the number of operation instructions at the medical institution, the patient's name, the patient's age, the creator of the execution instruction data, the job title of the creator of the execution instruction data, the medical department to which the creator belongs, the number of execution instructions of the execution instruction data based on the execution instruction data for each job title, and the ranking of the number of individual execution instruction data linked to the execution instruction data. (Supplementary Note 23) The program according to Supplementary Note 1, which in a second step (S852) accepts a speech input from a user and searches a search database (3027) based on the speech input to acquire execution instruction data. (Supplementary Note 24) The program according to Supplementary Note 1, which in a second step (S852) accepts a speech input from a user and modifies the acquired execution instruction data based on the speech input. (Supplementary Note 25) The program according to Supplementary Note 19, which in a second step (S852) accepts a speech input from a user regarding execution instruction data obtained by searching a search database (3027) using the search tag modified in step 13, and modifies the execution instruction data based on the speech input. (Supplementary Note 26) The program according to Supplementary Note 1, in which the machine learning models (3023, 3024) are created by machine learning or front-end engineering based on the tags and the execution instruction data.(Appendix 27) A program as described in Appendix 15, in which a plurality of tags are provided in the search database (3027), and in the second step (S852), when searching the search database (3027), a search is performed to determine whether a tag is included in at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, and as a search result of the search database (3027), execution instruction data corresponding to the tag is obtained for instructing the computer (30) and / or other computers to perform a specific operation. (Supplementary Note 28) The program according to Supplementary Note 1, wherein the memory (35) stores at least one of past medical history information, information entered by the patient, a disease name, a symptom name, a problem in the problem list, and a problem in the medical notes, as well as input dates and times of the medical history information, and past execution instruction data and generation dates and times of the execution instruction data, and the program further causes the processor (39) to execute a fourteenth step of generating execution instruction data for the search database (3027) based on execution instruction data given simultaneously with, on the same day, the same month, or in association with the input or tag generation of at least one of the past medical history information, information entered by the patient, a disease name, a symptom name, a problem in the problem list, and the medical notes. (Supplementary Note 29) The program according to Supplementary Note 28, wherein in the fourteenth step, an identifier and a word following this identifier included in at least one of the past medical history information, information entered by the patient, a disease name, a symptom name, a problem in the problem list, and the medical notes, and the extracted word is set as a tag. (Supplementary Note 30) The program according to Supplementary Note 29, wherein the identifier is an identifier included in a past problem list, and in step 14, the disease name and symptom name included in the problem list are set as tags. (Supplementary Note 31) The program according to Supplementary Note 28, wherein past test information is included in at least one of the past medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, and in step 2 (S852), test order execution instruction data is obtained as execution instruction data, and test execution instruction data that is the same as or has the same meaning as the past test information is displayed.(Supplementary Note 32) The program according to Supplementary Note 28, wherein at least one of the past medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes includes past prescription information, and in a second step (S852), obtains prescription order execution instruction data as execution instruction data, and among them, narrows down and displays, or highlights, or displays at a higher rank, drugs with the same ingredients as the past prescription information. (Supplementary Note 33) The program according to Supplementary Note 28, wherein at least one of the past medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes includes a disease name such as a medical history, and in a second step (S852), obtains disease name registration execution instruction data as execution instruction data, checks for disease name registration execution instruction data that is the same as or synonymous with the disease name, and narrows down and displays, or highlights, or displays at a higher rank, disease names that are not registered as a disease name. (Supplementary Note 34) The program according to Supplementary Note 28, wherein at least one of past medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical care notes includes a disease name such as a medical history, and in a second step (S852), acquires disease name registration execution instruction data as execution instruction data and accepts input of a sub-disease name of the disease. (Supplementary Note 35) The program according to Supplementary Note 1, wherein the program executes a fifteenth step of accepting instruction input using natural language or option buttons, and acquires execution instruction data using at least one of medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical care notes, and the instruction input, as input in the second step (S852). (Supplementary Note 36) The program according to Supplementary Note 1, further causing the processor (39) to execute a sixteenth step of simultaneously and visually presenting search results from a search database (3027) or output results from a program or machine learning model (3023, 3024) that generates execution instruction data, and execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation.(Appendix 37) The program further causes the processor (39) to execute a seventeenth step of generating information summarizing at least one of the medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical notes, and natural language indicating the reason for searching for execution instruction data for the computer (30) and / or another computer, and presenting the medical history information, etc., the information summarizing the medical history information, etc., and the natural language, and simultaneously presenting an approval button or selection button for the execution instruction data in a visible state. (Appendix 37) The program described in Appendix 1. (Supplementary Note 38) A program for operating a computer (30) having a processor (39) and a memory (35), wherein the memory (35) stores data in which at least a medical history or data generated from the medical history and medical instruction information or medical history addition instruction information are stored in pairs, and the program causes the processor (39) to execute an 18th step of accepting input of the medical history, a 19th step of generating search words based on the medical history accepted in step 18, and a 20th step of searching for medical instruction information based on the search words generated in step 19 and presenting it to a user. (Supplementary Note 39) The program according to Supplementary Note 37, wherein the program further causes the processor (39) to execute a 21st step of displaying the frequency of medical instruction information or the names or titles of users who have previously given medical instructions.(Supplementary Note 40) An information processing device including a processor (39) and a memory (35), wherein the memory (35) stores a search database (3027) in which execution instruction data used to instruct a computer (30) and / or another computer to perform a specific operation, or a program or machine learning model (3023, 3024) for generating execution instruction data, and the processor (39) receives at least one input of medical history information, information input by a patient, a disease name, a symptom name, a problem in a problem list, and a medical care note in a first step (S75). 0), and a second step (S852) of searching a search database (3027) using the input accepted in the first step (S750) to obtain execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation, or inputting the input accepted in the first step (S750) into a program or machine learning model (3023, 3024) to obtain execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation. (Supplementary Note 41) An information processing device comprising a processor (39) and a memory (35), wherein the memory (35) stores data in which at least a medical history or data generated from the medical history and medical instruction information or medical history addition instruction information are stored in pairs, and the processor (39) executes an 18th step of accepting input of the medical history, a 19th step of generating search words based on the medical history accepted in the 18th step, and a 20th step of searching for medical instruction information based on the search words generated in the 19th step and presenting it to a user.(Supplementary Note 42) A method executed by a computer (30) having a processor (39) and a memory (35), wherein the memory (35) stores a search database (3027) storing execution instruction data used to instruct the computer (30) and / or other computers to perform a specific operation, or a program or machine learning model (3023, 3024) for generating the execution instruction data, and the processor (39) receives input of at least one of medical history information, information entered by a patient, a disease name, a symptom name, a problem in a problem list, and a medical note. A method comprising: a first step (S750); and a second step (S852) of searching a search database (3027) using the input received in the first step (S750) to obtain execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation; or inputting the input received in the first step (S750) into a program or machine learning model (3023, 3024) to obtain execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation. (Supplementary Note 43) A method executed by a computer (30) having a processor (39) and a memory (35), wherein the memory (35) stores data in which at least a medical history or data generated from the medical history and medical instruction information or medical history addition instruction information are stored in pairs, and the processor (39) executes an 18th step of accepting input of the medical history, a 19th step of generating search words based on the medical history accepted in the 18th step, and a 20th step of searching for medical instruction information based on the search words generated in the 19th step and presenting it to a user.(Supplementary Note 44) A system comprising: a search database (3027) storing execution instruction data used to instruct a computer (30) and / or other computers to perform a specific operation; or a memory (35) storing a program or machine learning model (3023, 3024) for generating execution instruction data; means for accepting input of at least one of medical history information, information entered by a patient, a disease name, a symptom name, a problem in a problem list, and a medical note; and means for searching the search database (3027) using the input accepted by the means for accepting input of medical history information to obtain execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation, or means for inputting the input accepted in the first step (S750) into the program or machine learning model (3023, 3024) to obtain execution instruction data for instructing the computer (30) and / or other computers to perform a specific operation. (Appendix 45) A system having a memory (35) storing data in which at least a medical history or data generated from the medical history and medical instruction information or medical history addition instruction information are stored in pairs, a means for accepting input of the medical history, a means for generating search words based on the medical history accepted by the means for accepting input of the medical history, and a means for searching for medical instruction information based on the search words generated by the means for generating search words and presenting it to a user.

[0187] DESCRIPTION OF SYMBOLS 1...System 10...Terminal device 20...Terminal device 30...Server 35...Memory 36...Storage 39...Processor 40...External server 301...Communication unit 302...Storage unit 303...Control unit 3021...Application program 3022...Electronic medical record data 3023...Natural language generation model 3024...Execution instruction data generation model 3025...Medical information data 3026...RPA data 3027...Search database 3028...Electronic questionnaire data 3029...Decision model 3031...Reception control module 3032...Transmission control module 3033...Generation model generation module 3034...Search database data generation module 3035...Information input acceptance module 3036...Search DB search module 3037...Generation model input / output module 3038...Presentation control unit 3039...Execution instruction information output module 3040...Electronic medical record data generation module

Claims

1. A program for operating a computer having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the computer and / or other computers to execute a specific operation is stored, and the search database stores the execution instruction data for instructing the computer and / or other computers to execute a specific operation in association with words or sentences contained in at least one of medical history information, information input by the patient, the disease name, the symptom name, and a problem in a problem list, or stores search words or search sentences used to search the execution instruction data in association with words or sentences contained in at least one of the medical history information, information input by the patient, the disease name, the symptom name, and a problem in the problem list, and the program causes the processor to perform a first step of accepting an input of at least one of the medical history information, information input by the patient, the disease name, the symptom name, and a problem in the problem list; and a second step of searching the search database using the input received in the first step to obtain the execution instruction data corresponding to the word or sentence included in the input.

2. A program for operating a computer having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the computer and / or other computers to execute a specific operation is stored, and the search database stores, as search keys for the search database, words contained in at least one of medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in a problem list, or tags created by natural language processing based on at least one of the medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list, and the search keys are stored in association with the execution instruction data for instructing the computer and / or the other computers to execute a specific operation, and the program causes the processor to perform a first step of accepting an input of at least one of the medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; and a twenty-second step of searching the search database using the input received in the first step to obtain the execution instruction data corresponding to the word or tag based on the input.

3. A program for operating a computer having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the computer and / or other computers to execute a specific operation is stored, and the search database stores natural language contained in at least one of medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in a problem list, or a tag created by natural language processing based on at least one of the medical history information, the information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list, as search keys for the search database, and the execution instruction data for instructing the computer and / or the other computers to execute a specific operation is stored in association with the search keys, and the program causes the processor to perform a first step of accepting an input of at least one of the medical history information, the information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; and a 23rd step of searching the search database using the input accepted in the first step to obtain the execution instruction data corresponding to the natural sentence or the tag based on the input.

4. A program for operating a computer having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the computer and / or other computers to perform a specific operation is stored, and in the search database, words or sentences contained in medical notes, or tags created by natural language processing based on the medical notes, are set as search keys for the search database, and the execution instruction data for instructing the computer and / or the other computers to perform a specific operation is stored in correspondence with the search keys, and the program causes the processor to execute a 24th step of accepting input of the medical notes, and a 25th step of searching the search database using the input accepted in the 24th step to obtain the execution instruction data corresponding to the words, sentences or tags based on the input.

5. A program for operating a computer having a processor and a memory, wherein the memory stores another program for generating execution instruction data used to instruct the computer and / or another computer to perform a specific operation based on words or sentences contained in at least one of medical history information, information entered by the patient, the disease name, the symptom name, a problem in the problem list, and medical care notes, and the program causes the processor to execute a first step of accepting input of at least one of the medical history information, information entered by the patient, the disease name, the symptom name, a problem in the problem list, and the medical care notes, and an eighteenth step of inputting the input accepted in the first step into the other program to generate the execution instruction data.

6. A program according to any one of claims 1 to 5, wherein the execution instruction data includes a plurality of individual execution instruction data used to instruct the computer and / or the other computer to execute a specific operation.

7. The program according to claim 1, wherein at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list are written in natural language, or natural language processing is performed when searching the search database.

8. The program according to claim 5, wherein at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, the problems in the problem list, and the medical notes are written in natural language, or the other program performs natural language processing to generate the execution instruction data.

9. The program according to claim 1 or 5, wherein the execution instruction data includes at least one of test order execution instruction data, prescription order execution instruction data, disease name registration execution instruction data, message sending execution instruction data, RPA execution instruction data, natural language addition execution instruction data, template display execution instruction data, template data input execution instruction data, test result filtered display execution instruction data, prescription information filtered display execution instruction data, and appointment reservation execution instruction data.

10. The program according to claim 1 or 5, wherein the execution instruction data includes an instruction to send a medical questionnaire.

11. The program according to claim 10, further causing the processor to execute a 26th step of obtaining a response to the medical questionnaire from the patient, suggesting an addition to the medical record, and / or recording the addition as a result of the computer and / or the other computer executing the medical questionnaire sending execution instruction based on the medical questionnaire sending execution instruction.

12. The program according to claim 11, further comprising causing the processor to execute a 27th step of linking the additional entry with the response to the questionnaire.

13. The program according to claim 1, wherein at least one of the following information is used as input for the first step of accepting input of at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and the problem in the problem list: a referral letter or a medicine book, OCR result information of a scanner of test results, an electronic referral letter, an electronic medicine book and electronic test results, the information in natural language entered by the patient, and the information that is the result of speech recognition of the voice entered by the patient.

14. The program according to claim 5, wherein as input to the first step of accepting input of at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, a problem in the problem list, and the medical care notes, at least one of a referral letter or a medicine book, OCR result information of a scanner of test results, an electronic referral letter, an electronic medicine book, and electronic test results, the information in natural language entered by the patient, the information resulting from speech recognition of the voice entered by the patient, and the medical care notes generated by the other program is used.

15. The program of claim 1, further causing the processor to execute a third step of outputting the execution instruction data acquired in the second step to the computer and / or the other computer, and instructing the computer and / or the other computer to execute a specific operation.

16. The program described in claim 15, wherein the execution instruction data includes a plurality of individual execution instruction data used to instruct the computer and / or other computers to perform specific operations, and in the third step, the execution instruction data obtained in the second step, including the plurality of individual execution instruction data, is output to the computer and / or the other computers, and a series of specific operations are instructed to be performed by the computer and / or the other computers based on the plurality of individual execution instruction data.

17. The program according to claim 15, further causing the processor to execute a fourth step of instructing the computer and / or the other computer to perform a specific operation in the third step and accepting output obtained from the computer and / or the other computer; a fifth step of updating and correcting the medical history information using the output accepted in the fourth step; and a sixth step of searching the search database using the medical history information updated in the fifth step as an input to obtain the execution instruction data for instructing the computer and / or the other computer to perform a specific operation.

18. The program of claim 5, further causing the processor to execute a 28th step of outputting the execution instruction data acquired in the 18th step to the computer and / or the other computer, and instructing the computer and / or the other computer to execute a specific operation.

19. The program described in claim 18, wherein the execution instruction data includes a plurality of individual execution instruction data used to instruct the computer and / or other computers to perform specific operations, and in the 28th step, the execution instruction data obtained in the 18th step, including the plurality of individual execution instruction data, is output to the computer and / or the other computers, and the computer and / or the other computers are instructed to perform a series of specific operations based on the plurality of individual execution instruction data.

20. The program according to claim 18, further comprising: a 29th step of instructing the computer and / or the other computer to perform a specific operation in the 28th step and accepting output obtained from the computer and / or the other computer; a 30th step of updating and correcting the medical history information or the medical care note using the output accepted in the 29th step; and a 31st step of inputting the medical history information or the medical care note updated in the 30th step into the other program and re-acquiring the execution instruction data for instructing the computer and / or the other computer to perform a specific operation.

21. The program of claim 1, further comprising causing the processor to execute a seventh step of accepting an approval input as to whether or not to instruct the computer and / or the other computer to perform a specific operation based on the execution instruction data acquired in the second step.

22. A program as described in claim 21, wherein in the seventh step, information indicating an overview of the execution instruction data obtained in the second step is generated and presented, and after presenting the information, an approval input is accepted as to whether or not to instruct the computer and / or the other computer to perform a specific operation using the execution instruction data.

23. The program according to claim 5, further causing the processor to execute a 20th step of accepting an approval input as to whether or not to instruct the computer and / or the other computer to execute a specific operation using the execution instruction data generated in the 18th step.

24. A program as described in claim 23, wherein in the 20th step, information indicating an outline of the execution instruction data generated in the 18th step is generated and presented, and after presenting the information, an approval input is accepted as to whether or not to instruct the computer and / or the other computer to perform a specific operation using the execution instruction data.

25. The program of claim 17, further comprising causing the processor to execute an eighth step of presenting the update correction content and accepting approval for the update when updating the medical history information using the output obtained in the fourth step.

26. The program according to claim 21, wherein in the seventh step, if the acquired execution instruction data includes a plurality of options, a selection input of at least one of the plurality of options is accepted.

27. The program according to claim 23, wherein in said twentieth step, if the acquired execution instruction data includes a plurality of options, a selection input of at least one of said plurality of options is accepted.

28. The program according to claim 25, wherein in the eighth step, when the update or correction of the medical history information includes a plurality of options, a selection input of at least one of the plurality of options is accepted.

29. The program of claim 21, further causing the processor to execute a ninth step of outputting the execution instruction data for which the approval input was received in the seventh step to the computer and / or the other computer, and instructing the computer and / or the other computer to execute a specific operation.

30. The program of claim 23, further causing the processor to execute a ninth step of outputting the execution instruction data for which the approval input was received in the twentieth step to the computer and / or the other computer, and instructing the computer and / or the other computer to execute a specific operation.

31. The program according to claim 2, wherein the search database includes tags obtained by converting the medical history information, the information entered by the patient, the disease name, the symptom name, and date information, including the start date of hospitalization, the date of surgery, and the date of first outpatient visit, contained in the problems in the problem list, into relative dates and times from a specified date and time using natural language processing.

32. The program according to claim 4, wherein the search database includes tags that are generated by converting date information, including the start date of hospitalization, date of surgery, and date of first outpatient visit, contained in the medical notes into relative dates and times from a specified date and time using natural language processing.

33. The program further causes the processor to execute a tenth step of generating the tag from words contained in at least one of the medical history information, the information input by the patient, the disease name, the symptom name, and the problem in the problem list, and an eleventh step of presenting at least one of the medical history information, the information input by the patient, the disease name, the symptom name, and the problem in the problem list, which are the basis for generating the tag, when searching the execution instruction data based on the tag, and in the tenth step, recording the link with the medical history information and the position of the disease name contained in the medical history information in the search database, 32. The program according to claim 31, wherein in the eleventh step, when presenting at least one of the medical history information, the information input by the patient, the disease name, the symptom name, and the problem in the problem list that are the basis for generating the tag, if at least one of the medical history information, the information input by the patient, the disease name, the symptom name, and the problem in the problem list that are the basis for generating the tag are presented first, a notification is presented that the at least one of the medical history information, the information input by the patient, the disease name, the symptom name, and the problem in the problem list that are the basis for generating the tag are presented first, and when there are a plurality of the medical history information, the information input by the patient, the disease name, the symptom name, and the problem in the problem list that are the basis for generating the tag, the medical history information, the information input by the patient, the disease name, the symptom name, and the problem in the problem list that have the oldest date information are presented.

34. The program according to claim 2, wherein the memory stores a standard medical glossary, and the program further causes the processor to execute a twelfth step of searching for synonyms based on the words contained in at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list, or words obtained by natural language processing of at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list, or searching for cosine similarity of at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list, to obtain words in the standard glossary, and to set the words as new tags in the search database.

35. The program of claim 2, further comprising causing the processor to execute a thirteenth step of: accepting modification input for the tags in the search database from a user, and modifying the tags based on the modification input.

36. The program of claim 2, wherein the search database stores comments about the tag and / or information on a non-recommended state linked to the tag, and in step 22, when searching the search database based on the tag, if a comment is linked to the tag, the comment is presented, and if information on a non-recommended state is linked to the tag, the presentation manner of the execution instruction data linked to the tag is made different from the presentation manner of other execution instruction data.

37. The program of claim 2, wherein the search database stores a flag input for the tag and / or information indicating the number of positive feedbacks and negative feedbacks linked to the tag, and in the 22nd step, when searching the search database, if the flag is linked to the tag, the execution instruction data is filtered or preferentially displayed based on the flag, and if the tag is linked to information indicating either the positive feedback or the negative feedback, and the number of negative feedbacks is greater than the positive feedbacks, the execution instruction data is preferentially displayed.

38. The program according to claim 16, wherein the search database stores, linked to the execution instruction data, the number of operation instructions of the execution instruction data for each user, the number of operation instructions of the execution instruction data for each medical department to which the user belongs, the name of the patient related to the execution instruction data, the age of the patient, the creator of the execution instruction data, the job title of the creator, or the medical department to which the creator belongs, and wherein, in the second step, the display manner of the execution instruction data is changed based on at least one of the following: the user's past number of operation instructions, the number of operation instructions by medical department, the number of operation instructions at a medical institution, the name of the patient, the age of the patient, the creator of the execution instruction data, the job title of the creator of the execution instruction data, the medical department to which the creator belongs, the number of execution instructions of the execution instruction data based on the execution instruction data in the medical department to which the user belongs, a ranking of the number of execution instructions based on the execution instruction data for each job title, and a ranking of the number of individual execution instruction data linked to the execution instruction data.

39. The program according to claim 1, wherein in the second step, a speech input from a user is accepted, and the execution instruction data is obtained by searching the search database based on the speech input.

40. The program according to claim 1, wherein in the second step, speech input from a user is accepted, and the acquired execution instruction data is modified based on the speech input.

41. The program described in claim 35, wherein in the 22nd step, speech input from the user is accepted for the execution instruction data obtained by searching the search database using the tag modified in the 13th step, and the execution instruction data is modified based on the speech input.

42. The program according to claim 5, wherein the other program is a machine learning model, and the machine learning model is created by machine learning or prompt engineering based on words contained in at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, or tags created by natural language processing based on at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, the problem in the problem list, and the medical notes, and the execution instruction data.

43. The program according to claim 2, wherein a plurality of tags are provided in the search database, and in the 22nd step, when searching the search database, a search is made to see whether the tag is included in at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list, and the execution instruction data corresponding to the tag is obtained as a search result of the search database.

44. The program as described in claim 2, wherein the memory stores the past medical history information, the information input by the patient, the disease name, the symptom name, and at least one of the problems in the problem list, as well as input dates and times of the medical history information, the information input by the patient, the disease name, the symptom name, and at least one of the problems in the problem list, and the past execution instruction data and generation dates and times of the execution instruction data, and the program further causes the processor to execute a fourteenth step of generating the execution instruction data in the search database based on the execution instruction data instructed to be executed simultaneously, on the same day, the same month, or in association with the input of the past medical history information, the information input by the patient, the disease name, the symptom name, and at least one of the problems in the problem list or the generation of the tag.

45. The program according to claim 44, wherein in the fourteenth step, an identifier and a word following this identifier contained in at least one of the past medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list are extracted, and the extracted word is set as the tag.

46. ​​The program according to claim 45, wherein the identifier is the identifier included in the past problem list, and in the fourteenth step, the disease name and symptom name included in the problem list are set in the tag.

47. The program described in claim 44, wherein at least one of the past medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list includes past examination information, and in the 22nd step, test order execution instruction data is obtained as the execution instruction data, and among them, test order execution instruction data that is the same as or has the same meaning as the past examination information is displayed.

48. The program described in claim 44, wherein at least one of the past medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list includes past prescription information, and in the 22nd step, prescription order execution instruction data is obtained as the execution instruction data, and among those, drugs with the same ingredients as those in the past prescription information are narrowed down and displayed, highlighted, or displayed at the top of the ranking.

49. The program described in claim 44, wherein at least one of the past medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list includes a disease name in the current medical history, and in the 22nd step, disease name registration execution instruction data is obtained as the execution instruction data, disease name registration execution instruction data that is the same as or synonymous with the disease name is confirmed, and disease names that are not registered are narrowed down and displayed, highlighted, or displayed at the top of the ranking.

50. The program described in claim 44, wherein at least one of the past medical history information, the information entered by the patient, the disease name, the symptom name, and the problems in the problem list includes a disease name in the current medical history, and in the 22nd step, disease name registration execution instruction data is obtained as the execution instruction data, and input of a sub-disease name of the disease name is accepted.

51. The program according to claim 1, further comprising: executing a fifteenth step of accepting instruction input in natural language or by using option buttons; and obtaining the execution instruction data by using the instruction input and at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and a problem in the problem list as the input in the second step.

52. The program of claim 1, further causing the processor to execute a sixteenth step of simultaneously and visually presenting the search results of the search database, or the output result of the program or machine learning model that generates the execution instruction data, and the execution instruction data for instructing the computer and / or the other computer to perform a specific operation.

53. The program according to claim 1, further causing the processor to execute a seventeenth step of generating information summarizing at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and the problem in the problem list, and natural language indicating a reason for retrieving the execution instruction data to the computer and / or the other computer, presenting the information summarizing at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, and the problem in the problem list, the medical history information, the information entered by the patient, the disease name, the symptom name, and the problem in the problem list, and the natural language, and presenting an approval button or selection button for the execution instruction data in a state where it is simultaneously visible.

54. An information processing device having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the information processing device and / or another information processing device to perform a specific operation is stored, and the search database stores the execution instruction data for instructing the information processing device and / or the other information processing device to perform a specific operation in association with words or sentences included in at least one of medical history information, information input by the patient, the disease name, the symptom name, and a problem in a problem list, or stores search words or search sentences used to search the execution instruction data in association with words or sentences included in at least one of the medical history information, information input by the patient, the disease name, the symptom name, and a problem in the problem list, and the processor performs the following steps: a first step of accepting an input of at least one of the medical history information, information input by the patient, the disease name, the symptom name, and a problem in the problem list; and a second step of searching the search database using the input received in the first step to obtain the execution instruction data corresponding to the word or the sentence included in the input.

55. An information processing device having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the information processing device and / or another information processing device to execute a specific operation is stored, and the search database stores, as search keys for the search database, words contained in at least one of medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in a problem list, or tags created by natural language processing based on at least one of the medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list, and the search keys are stored in association with the execution instruction data for instructing the information processing device and / or the other information processing device to execute a specific operation, and the processor performs the following steps: a first step of accepting an input of at least one of the medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; and a twenty-second step of searching the search database using the input received in the first step to obtain the execution instruction data corresponding to the word or tag based on the input.

56. An information processing device having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the information processing device and / or another information processing device to execute a specific operation is stored, and the search database stores natural language contained in at least one of medical history information, information input by the patient, disease name, symptom name, and problem in a problem list, or a tag created by natural language processing based on at least one of the medical history information, information input by the patient, disease name, symptom name, and problem in the problem list, as a search key of the search database, and the execution instruction data for instructing the information processing device and / or another information processing device to execute a specific operation is stored in association with the search key, and the processor performs the following steps: a first step of accepting an input of at least one of the medical history information, information input by the patient, disease name, symptom name, and problem in the problem list; and a twenty-third step of searching the search database using the input received in the first step to obtain the execution instruction data corresponding to the tag based on the input.

57. An information processing device having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the information processing device and / or other information processing devices to perform a specific operation is stored, and in the search database, words or sentences contained in medical notes, or tags created by natural language processing based on the medical notes, are set as search keys for the search database, and the execution instruction data for instructing the information processing device and / or the other information processing devices to perform a specific operation is stored in correspondence with the search keys, and the processor executes a 24th step of accepting input of the medical notes, and a 25th step of searching the search database using the input accepted in the 24th step to obtain the execution instruction data corresponding to the words, sentences or tags based on the input.

58. An information processing device having a processor and a memory, wherein the memory stores another program for generating execution instruction data used to instruct the information processing device and / or other information processing devices to perform a specific operation based on words or sentences contained in at least one of medical history information, information entered by the patient, the disease name, the symptom name, a problem in the problem list, and medical care notes, and the processor executes a first step of accepting input of at least one of the medical history information, information entered by the patient, the disease name, the symptom name, a problem in the problem list, and the medical care notes, and an eighteenth step of inputting the input accepted in the first step into the other program to generate the execution instruction data.

59. A method executed by a computer having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the computer and / or other computers to perform a specific operation is stored, and the search database stores the execution instruction data for instructing the computer and / or other computers to perform a specific operation in association with words or sentences contained in at least one of medical history information, information input by the patient, the disease name, the symptom name, and a problem in a problem list, or stores search words or search sentences used to search the execution instruction data in association with words or sentences contained in at least one of the medical history information, information input by the patient, the disease name, the symptom name, and a problem in the problem list, and the processor performs the following steps: a first step of accepting an input of at least one of the medical history information, information input by the patient, the disease name, the symptom name, and a problem in the problem list; and a second step of searching the search database using the input received in the first step to obtain the execution instruction data corresponding to the word or sentence contained in the input.

60. A method executed by a computer having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the computer and / or another computer to execute a specific operation is stored, and the search database stores, as search keys for the search database, words contained in at least one of medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in a problem list, or tags created by natural language processing based on at least one of the medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list, and the search keys are associated with the execution instruction data for instructing the computer and / or the other computer to execute a specific operation, and the processor performs the following steps: a first step of accepting an input of at least one of the medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; and a twenty-second step of searching the search database using the input received in the first step to obtain the execution instruction data corresponding to the words or tags based on the input.

61. A method executed by a computer having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the computer and / or another computer to execute a specific operation is stored, and the search database stores natural language contained in at least one of medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in a problem list, or a tag created by natural language processing based on at least one of the medical history information, the information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list, as search keys of the search database, and the execution instruction data for instructing the computer and / or the other computer to execute a specific operation is stored in association with the search keys, and the processor performs the following steps: a first step of accepting an input of at least one of the medical history information, the information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; and a twenty-third step of searching the search database using the input received in the first step to obtain the execution instruction data corresponding to the natural sentence or the tag based on the input.

62. A method executed by a computer having a processor and a memory, wherein the memory stores a search database in which execution instruction data used to instruct the computer and / or other computers to perform a specific operation is stored, and in the search database, words or sentences contained in medical notes, or tags created by natural language processing based on the medical notes, are set as search keys for the search database, and the execution instruction data for instructing the computer and / or the other computers to perform a specific operation is stored in correspondence with the search keys, and the processor executes a 24th step of accepting input of the medical notes, and a 25th step of searching the search database using the input accepted in the 24th step to obtain the execution instruction data corresponding to the words, sentences or tags based on the input.

63. A method executed by a computer having a processor and a memory, wherein the memory stores another program for generating execution instruction data used to instruct the computer and / or another computer to execute a specific operation based on words or sentences contained in at least one of medical history information, information entered by the patient, the disease name, the symptom name, a problem in the problem list, and a medical care note, and the processor executes a first step of accepting input of at least one of the medical history information, the information entered by the patient, the disease name, the symptom name, a problem in the problem list, and the medical care note, and an eighteenth step of inputting the input accepted in the first step into the other program to generate the execution instruction data.

64. A system comprising: a search database storing execution instruction data used to instruct a system and / or other systems to execute a specific operation, said search database storing the execution instruction data for instructing said system and / or other systems to execute a specific operation in association with words or sentences contained in at least one of medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in a problem list; a memory storing search words or search sentences used to search for the execution instruction data in association with words or sentences contained in at least one of the medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; means for accepting input of at least one of the medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; and means for searching the search database using the input accepted by the input accepting means to obtain the execution instruction data corresponding to the words or sentences contained in the input.

65. A system comprising: a search database storing execution instruction data used to instruct a system and / or other systems to execute a specific operation, said search database storing search keys of said search database that are words contained in at least one of medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in a problem list, or tags created by natural language processing based on at least one of said medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list, and said search keys are associated with and stored in said execution instruction data for instructing said system and / or said other systems to execute a specific operation; a means for accepting input of at least one of said medical history information, information input by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; and a means for searching the search database using the input accepted by the input accepting means to obtain the execution instruction data corresponding to the word or tag based on the input.

66. A system comprising: a search database storing execution instruction data used to instruct a system and / or other systems to execute a specific operation, said search database storing natural sentences contained in at least one of medical history information, information entered by the patient, the name of a disease, the name of a symptom, and a problem in a problem list, or tags created by natural language processing based on at least one of the medical history information, the information entered by the patient, the name of a disease, the name of a symptom, and a problem in the problem list, as search keys for said search database, and a memory storing said search keys in association with the execution instruction data for instructing said system and / or the other systems to execute a specific operation; a means for accepting input of at least one of the medical history information, information entered by the patient, the name of a disease, the name of a symptom, and a problem in the problem list; and a means for searching the search database using the input accepted by the input accepting means, and acquiring the execution instruction data corresponding to the natural sentences or the tags based on the input.

67. A system comprising: a search database storing execution instruction data used to instruct a system and / or other systems to perform a specific operation, said search database having words or sentences contained in medical notes, or tags created by natural language processing based on said medical notes, set as search keys for said search database, said search keys being associated with the execution instruction data for instructing said system and / or said other systems to perform a specific operation, said system comprising: a memory storing said execution instruction data; a means for accepting input of said medical notes; and a means for searching the search database using the input accepted by said input accepting means, and obtaining the execution instruction data corresponding to the words, sentences or tags based on the input.

68. A system comprising: a memory storing another program that generates execution instruction data used to instruct the system and / or other systems to perform a specific operation based on words or sentences contained in at least one of medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical care notes; a means for accepting input of at least one of the medical history information, information entered by the patient, disease name, symptom name, problem in the problem list, and medical care notes; and a means for inputting the input accepted by the input accepting means into the other program to generate the execution instruction data.

Images