Learning model generation device, clinical department determination device, learning model generation method, and clinical department determination method, and program

Abstract

To reduce the burden on a person in charge when clinical department selection is automated.SOLUTION: A learning model generation device 10 is provided, comprising a training data acquisition unit 11 for acquiring subjective symptom data for identifying symptoms felt by a patient and clinical department data for identifying a clinical department visited by the patient as training data, and a learning model generation unit 12 configured to perform machine learning using the acquired training data to generate a learning model.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a learning model generating device and a learning model generating method for generating a learning model for determining a medical department according to a patient's symptoms, and further relates to a program for realizing these. The present disclosure also relates to a medical department determination device and a medical department determination method for determining a medical department according to a patient's symptoms, and further relates to a program for realizing these. [Background technology]

[0002] General hospitals have many medical departments and many doctors and medical staff, so patients who want to receive treatment there feel at ease. When visiting such a general hospital, patients must first select the medical department they should visit based on their symptoms. Then, the patient checks in at the selected department and receives a diagnosis from a doctor.

[0003] However, for ordinary people without medical knowledge, choosing a medical department is difficult, and they may choose the wrong department. In such a case, the patient must choose a different medical department and visit the hospital again, which places a heavy burden on the patient.

[0004] To solve such problems, for example, Non-Patent Document 1 discloses a system that presents the medical department that a patient should visit simply by selecting the part and symptoms on a screen. The system disclosed in Non-Patent Document 1 is believed to make it extremely unlikely that a patient will select the wrong medical department.

[0005] Patent Document 1 also discloses a system for determining the medical department that will handle an emergency patient. In the system disclosed in Patent Document 1, the ambulance crew transporting the patient, not the patient, inputs information about the patient's condition. When the ambulance crew inputs the information, the system disclosed in Patent Document 1 selects the most appropriate medical department and also selects a medical institution that can handle the patient. The system disclosed in Patent Document 1 then transmits the information to the selected medical institution. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2020-197887 A [Non-patent literature]

[0007] [Non-Patent Document 1] “FACILITIES: Find a medical department by the location of symptoms”, [online], 2019, Juntendo University School of Medicine Urayasu Hospital, [Retrieved June 1, 2023], Internet<URL:https: / / www.hosp-urayasu.juntendo.ac.jp / facilities / > Summary of the Invention [Problem to be solved by the invention]

[0008] However, the location of medical departments and the scope of each medical department are different for each medical institution. Therefore, in order to introduce the system disclosed in Non-Patent Document 1, the person in charge at the medical institution needs to set the conditions for determining the medical department. In addition, after the conditions are set, each time a new disease becomes prevalent, the person in charge needs to reset the conditions for determining the medical department. Thus, the system disclosed in Non-Patent Document 1 has the problem that it places a heavy burden on the person in charge at the medical institution.

[0009] Furthermore, the system disclosed in Patent Document 1 was developed on the assumption that it would be used by emergency personnel, and it is difficult for patients to use it to select a medical department.

[0010] One example of an objective of the present disclosure is to reduce the burden on a person in charge when the selection of a medical department is automated. [Means for solving the problem]

[0011] In order to achieve the above object, a learning model generation device according to one aspect of the present disclosure includes: A training data acquisition unit that acquires, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation unit that performs machine learning using the acquired training data to generate a learning model; The present invention is characterized in that it is equipped with:

[0012] In order to achieve the above object, a medical department determination device according to one aspect of the present disclosure includes: An input receiving unit that receives an input of symptoms that a patient is aware of; A medical department determination unit that inputs subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department, and determines the medical department that the patient should visit; The present invention is characterized in that it is equipped with:

[0013] In order to achieve the above object, a learning model generation method according to one aspect of the present disclosure includes: a training data acquisition step of acquiring, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation step of performing machine learning using the acquired training data to generate a learning model; The present invention is characterized in that it has the following features:

[0014] In order to achieve the above object, a medical department determination method according to one aspect of the present disclosure includes: An input receiving step of receiving an input of symptoms recognized by the patient; A medical department determination step of inputting the subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department to determine the medical department that the patient should visit; The present invention is characterized in that it has the following features:

[0015] Furthermore, in order to achieve the above object, a first program according to one aspect of the present disclosure includes: On the computer, a training data acquisition step of acquiring, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation step of performing machine learning using the acquired training data to generate a learning model; The present invention is characterized in that:

[0016] Furthermore, in order to achieve the above object, a second program according to one aspect of the present disclosure includes: On the computer, An input receiving step of receiving an input of symptoms recognized by the patient; A medical department determination step of inputting the subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department to determine the medical department that the patient should visit; The present invention is characterized in that: Effect of the Invention

[0017] As described above, according to the present disclosure, it is possible to reduce the burden on a person in charge when the selection of a medical department is automated. [Brief description of the drawings]

[0018] [Figure 1] FIG. 1 is a diagram showing a schematic configuration of an example of a learning model generating device. [Diagram 2] FIG. 2 is a configuration diagram showing a more specific configuration of an example of a learning model generating device. [Diagram 3] Figure 3 shows an example of training data used to train a machine learning model. [Figure 4] FIG. 4 shows an example of pre-processing performed on the training data. [Diagram 5] FIG. 5 is a flow diagram showing an example of the operation of the learning model generating device. [Figure 6] FIG. 6 is a diagram showing a schematic configuration of an example of a medical department determination device. [Figure 7] FIG. 7 is a configuration diagram specifically illustrating the configuration of an example of a medical department determination device. [Figure 8] FIG. 8 is a diagram showing an example of a screen displayed by the medical department determination device. [Figure 9] FIG. 9 is a flow diagram showing an example of the operation of the medical department determination device. [Figure 10] FIG. 10 is a block diagram showing an example of a computer that realizes the learning model generating device and the medical department determining device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] (Embodiment 1) Hereinafter, in the first embodiment, a learning model generating device, a learning model generating method, and a program will be described with reference to FIGS. 1 to 5. FIG.

[0020] [Device configuration] First, a schematic configuration of an example of a learning model generating device will be described with reference to Fig. 1. Fig. 1 is a configuration diagram showing a schematic configuration of an example of a learning model generating device.

[0021] The learning model generating device 10 shown in Fig. 1 is a device that generates a learning model for determining a medical department according to the symptoms of a patient. As shown in Fig. 1, the learning model generating device 10 includes a training data acquiring unit 11 and a learning model generating unit 12.

[0022] The training data acquisition unit 11 acquires, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies the medical department that the patient has visited. The learning model generation unit 12 executes machine learning using the acquired training data to generate a learning model.

[0023] In this way, the learning model generating device 10 can generate a learning model that has learned the relationship between the patient's subjective symptoms and the corresponding medical department. Therefore, by using this learning model, it is possible to create a device that can determine the medical department without the person in charge setting conditions in advance. The learning model generating device 10 can reduce the burden on the person in charge when the selection of the medical department is automated.

[0024] Next, the configuration and functions of the learning model generating device will be specifically described with reference to Figures 2 to 4. Figure 2 is a configuration diagram showing in more detail the configuration of an example of the learning model generating device.

[0025] As shown in Fig. 2, the learning model generation device 10 is connected to a database 21 via a network or the like so as to be able to communicate data. The database 21 stores training data. Fig. 3 shows an example of the training data used for learning the machine learning model.

[0026] As shown in Figure 3, the training data consists of symptom data and medical department data. The symptom data is data that identifies the subjective symptoms that patients described before treatment. The medical department data consists of the names of medical departments that patients who described their symptoms actually visited.

[0027] 2, the learning model generation device 10 includes a storage unit 13 in addition to the training data acquisition unit 11 and the learning model generation unit 12. The storage unit 13 stores parameters of the learning model, which will be described later.

[0028] In the example of Fig. 2, the training data acquisition unit 11 acquires training data from the database 21 and passes the acquired training data to the learning model generation unit 12. Specifically, when the training data acquisition unit 11 acquires the training data, it divides text data indicating subjective symptoms constituting the subjective symptom data into words, as shown in Fig. 4. Then, the training data acquisition unit 11 converts each word obtained by the division into an identifier previously assigned to each word, and sets the obtained set of identifiers as subjective symptom data for input. Fig. 4 shows an example of pre-processing performed on the training data.

[0029] The learning model generation unit 12 first uses parameters stored in the storage unit 13 to execute a machine learning program to construct a learning model 20. The learning model 20 is, for example, a neural network represented by a DNN (Deep Neural Network) or the like. In this case, the learning model 20 has an input layer, a hidden layer (intermediate layer), and an output layer. The learning model 20 may be constructed on a device (computer) other than the learning model generation device 10.

[0030] Next, the learning model generation unit 12 executes machine learning by inputting the training data to the learning model 20. Specifically, the learning model generation unit 12 inputs the subjective symptom data for input to the learning model 20 and receives the output result from the learning model 20. Then, the learning model generation unit 12 calculates the difference between the contents of the medical department data and the output result, and updates the parameters of the neural network that is the learning model 20 so as to reduce the difference. In the first embodiment, the parameters are updated from time to time in this manner, whereby the target learning model 20 is generated.

[0031] [Device operation] Next, an example of the operation of the learning model generating device will be described with reference to Fig. 5. Fig. 5 is a flow diagram showing an example of the operation of the learning model generating device. In the following description, Figs. 1 to 4 will be referred to as appropriate. In addition, in the first embodiment, the learning model generating method is implemented by operating the learning model generating device 10. Therefore, the description of the learning model generating method in the first embodiment will be replaced with the following description of the operation of the learning model generating device 10.

[0032] First, the training data acquisition unit 11 acquires training data from the database 21 (step A1).

[0033] Specifically, as shown in Fig. 4, the training data acquisition unit 11 divides the text data indicating subjective symptoms into words, converts each word obtained by the division into an identifier, and sets the identifiers as subjective symptom data for input. In addition, the training data acquisition unit 11 passes the training data to the learning model generation unit 12.

[0034] Next, the learning model generation unit 12 executes machine learning using the training data to generate the learning model 20 (step A2).

[0035] Specifically, the learning model generation unit 12 inputs the input subjective symptom data into the learning model 20, receives the output result from the learning model 20, calculates the difference between the contents of the medical department data and the output result, and updates the parameters of the learning model 20 so as to reduce the difference.

[0036] By executing the above steps A1 and A2, a learning model 20 is generated that has learned the relationship between the patient's subjective symptoms and the corresponding medical department. By using this learning model 20, it is possible to create a device that can determine the medical department without the person in charge setting conditions in advance. The learning model generation device 10 can reduce the burden on the person in charge when the selection of the medical department is automated.

[0037] [program] In the first embodiment, the program may be a program that causes a computer to execute steps A1 and A2 shown in Fig. 5. By installing and executing this program in a computer, the learning model generation device 10 and the learning model generation method can be realized. In this case, the processor of the computer functions as the training data acquisition unit 11 and the learning model generation unit 12 and performs the processing.

[0038] The storage unit 13 may be realized by storing the data files constituting the storage unit 13 in a storage device such as a hard disk provided in the computer, or may be realized by a storage device of another computer. Examples of the computer include a general-purpose PC, a smartphone, and a tablet terminal device.

[0039] The program may be executed by a computer system constructed by a plurality of computers. In this case, for example, one or more computers may function as the training data acquisition unit 11 or the learning model generation unit 12.

[0040] (Embodiment 2) Next, in the second embodiment, a medical department determination device, a medical department determination method, and a program will be described with reference to FIGS.

[0041] [Device configuration] First, a schematic configuration of an example of a medical department determination device will be described with reference to Fig. 6. Fig. 6 is a configuration diagram showing a schematic configuration of an example of a medical department determination device.

[0042] The medical department determination device 30 shown in Fig. 6 is a device that determines the medical department that a patient should visit based on the patient's symptoms. As shown in Fig. 6, the medical department determination device 30 includes an input receiving unit 31 and a medical department determination unit 32.

[0043] The input receiving unit 31 receives input of symptoms that the patient is aware of. The medical department determining unit 32 inputs subjective symptom data that identifies the symptoms that have been received into a learning model to determine the medical department that the patient should visit. The learning model is a learning model that learns the relationship between symptoms and the corresponding medical departments by machine learning.

[0044] In this way, the medical department determination device 30 uses a learning model that outputs the corresponding medical department when symptoms are input, and the medical institution staff does not need to set conditions for medical department determination. The medical department determination device 30 can reduce the burden on the staff when the selection of the medical department is automated.

[0045] Next, the configuration and functions of the medical department determination device will be specifically described with reference to Fig. 7 and Fig. 8. Fig. 7 is a configuration diagram showing in more detail the configuration of one example of the medical department determination device.

[0046] 7, the medical department determination device 30 includes, in addition to the input receiving unit 31 and medical department determination unit 32 described above, a screen display unit 33 and a storage unit 34. The storage unit 34 stores parameters of a learning model 20, which will be described later. In addition, the medical department determination device 30 is connected to a display device 40 for displaying information, and an input device 50 such as a keyboard or a touch panel.

[0047] The screen display unit 33 displays an input screen on the screen of the display device 40 to prompt the patient to input subjective symptoms, as shown in FIG. 8. FIG. 8 is a diagram showing an example of a screen displayed by the medical department determination device. In the example of FIG. 8, the screen 41 transitions in response to the patient's input, and the patient inputs his / her subjective symptoms. Furthermore, as shown in FIG. 8, when a determination is made by the medical department determination unit 32, the screen display unit 33 also displays the determination result (lower part of FIG. 8) on the screen 41. Note that in FIG. 8, the arrows indicate the transition of the screen. Also, the form of the input screen is not particularly limited. The input screen may be provided with a pull-down menu to simplify input.

[0048] The input receiving unit 31 receives the input of symptoms that the patient is aware of when the patient makes an input on the screen using the input device 50. Specifically, when the patient inputs subjective symptoms on the input screen using the input device 50 as shown in Fig. 8, the input receiving unit 31 receives the text data input as subjective symptoms as subjective symptom data that identifies the subjective symptoms of the patient.

[0049] Furthermore, the input receiving unit 31 divides the text data into words, converts each word obtained by the division into an identifier previously assigned to each word, and sets the obtained set of identifiers as subjective symptom data for input. The conversion process into identifiers is the same as the process performed by the training data acquiring unit 11 described in the first embodiment. Then, the input receiving unit 31 sends the subjective symptom data for input to the medical department determining unit 32.

[0050] First, the medical department determination unit 32 uses parameters stored in the storage unit 34 to execute a machine learning program to construct the learning model 20. The parameters stored in the storage unit 34 are parameters updated by the learning model generation device 10 (see FIG. 2). In other words, the learning model 20 is a learning model similar to the learning model 20 shown in FIG. 2, and is generated by the learning model generation device 10. The learning model 20 may be implemented on a device (computer) other than the medical department determination device 30.

[0051] Next, the medical department determination unit 32 inputs the subjective symptom data for input sent from the input receiving unit 31 to the learning model 20 and receives an output result from the learning model 20. Then, the medical department determination unit 32 sends the output result as a medical department determination result to the screen display unit 33. As a result, the screen display unit 33 displays the determination result on the screen 41 as shown in FIG.

[0052] [Device operation] Next, an example of the operation of the medical department determination device will be described with reference to Fig. 9. Fig. 9 is a flow diagram showing an example of the operation of the medical department determination device. In the following description, Figs. 7 and 8 will be referred to as appropriate. In addition, in the second embodiment, a medical department determination method is performed by operating the medical department determination device 30. Therefore, the description of the medical department determination method in the second embodiment will be replaced by the following description of the operation of the medical department determination device 30.

[0053] 9, first, the screen display unit 33 displays an input screen on the screen 41 of the display device 40 to prompt the patient to input subjective symptoms (step B1). In response to this, the patient inputs subjective symptoms.

[0054] Next, the input receiving unit 31 receives text data of subjective symptoms inputted on the input screen using the input device 50 as subjective symptom data of the patient (step B2). The input receiving unit 31 also divides the text data into words, converts each word into an identifier, and sets of the obtained identifiers as subjective symptom data for input.

[0055] Next, the medical department determination unit 32 inputs the subjective symptom data received in step B2 into the learning model 20, receives the determination result of the learning model 20, and determines the medical department that the patient should visit (step B3). Specifically, the medical department determination unit 32 sends the output result to the screen display unit 33 as the medical department determination result.

[0056] Next, the screen display unit 33 displays the determination result of step B3 on the screen 41 of the display device 40 (step B4). Through the above steps B1 to B4, the patient can learn the medical department that corresponds to his or her subjective symptoms.

[0057] In this way, the medical department determination device 30 allows the medical institution staff to determine the medical department using the learning model 20 without setting conditions for determining the medical department. The medical department determination device 30 can reduce the burden on the staff when the selection of the medical department is automated. In addition, the patient can know the medical department that is best suited for him / her by simply inputting his / her subjective symptoms according to the display screen.

[0058] [program] In the second embodiment, the program may be a program that causes a computer to execute steps B1 to B4 shown in Fig. 9. By installing and executing this program in a computer, the medical department determination device 30 and the medical department determination method can be realized. In this case, the processor of the computer functions as an input receiving unit 31, a medical department determination unit 32, and a screen display unit 33, and performs processing.

[0059] The storage unit 34 may be realized by storing the data files constituting the storage unit 34 in a storage device such as a hard disk provided in the computer, or may be realized by a storage device of another computer. Examples of the computer include a general-purpose PC, a smartphone, and a tablet terminal device.

[0060] The program may be executed by a computer system constructed by a plurality of computers. In this case, for example, one or more computers may function as the input receiving unit 31, the medical department determining unit 32, and the screen display unit 33.

[0061] [Physical configuration] Here, a computer that realizes the learning model generation device by executing the program in the first embodiment and a computer that realizes the medical department determination device by executing the program in the second embodiment will be described with reference to Fig. 10. Fig. 10 is a block diagram showing an example of a computer that realizes the learning model generation device and the medical department determination device.

[0062] 10, a computer 110 includes a CPU (Central Processing Unit) 111, a main memory 112, a storage device 113, an input interface 114, a display controller 115, a data reader / writer 116, and a communication interface 117. These components are connected to each other via a bus 121 so as to be able to communicate data with each other.

[0063] Furthermore, the computer 110 may include a GPU (Graphics Processing Unit) or an FPGA (Field-Programmable Gate Array) in addition to or instead of the CPU 111. In this embodiment, the GPU or FPGA can execute the programs in the embodiments.

[0064] The CPU 111 loads a program in the embodiment, which is composed of a group of codes and is stored in the storage device 113, into the main memory 112, and executes each code in a predetermined order to perform various calculations. The main memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory).

[0065] Moreover, the program in the embodiment is provided in a state stored in a computer-readable recording medium 120. The program in the embodiment may be distributed on the Internet connected via the communication interface 117.

[0066] Specific examples of the storage device 113 include a hard disk drive and a semiconductor storage device such as a flash memory. The input interface 114 mediates data transmission between the CPU 111 and input devices 118 such as a keyboard and a mouse. The display controller 115 is connected to a display device 119 and controls the display on the display device 119.

[0067] Data reader / writer 116 mediates data transmission between CPU 111 and recording medium 120, reads programs from recording medium 120, and writes processing results in computer 110 to recording medium 120. Communication interface 117 mediates data transmission between CPU 111 and other computers.

[0068] Specific examples of the recording medium 120 include general-purpose semiconductor storage devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic recording media such as a flexible disk, or optical recording media such as a CD-ROM (Compact Disk Read Only Memory).

[0069] The learning model generating device and the medical department determining device can be realized not by a computer with a program installed, but by hardware corresponding to each part, for example, an electronic circuit. Furthermore, the learning model generating device and the medical department determining device may be realized in part by a program and the remaining part by hardware. In the embodiment, the computer is not limited to the computer shown in FIG. 9.

[0070] A part or all of the above-described embodiment can be expressed by (Additional Notes 1) to (Additional Notes 12) described below, but is not limited to the following descriptions.

[0071] (Appendix 1) A training data acquisition unit that acquires, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation unit that performs machine learning using the acquired training data to generate a learning model; A learning model generating device comprising:

[0072] (Appendix 2) the training data acquisition unit divides text data indicating symptoms that the patient is aware of into words, converts the words obtained by the division into identifiers that are assigned to each word in advance, and defines a set of the obtained identifiers as the subjective symptom data. A learning model generation device as described in appendix 1.

[0073] (Appendix 3) the learning model is a neural network, The learning model generation unit generates the learning model by updating parameters of the neural network. A learning model generation device as described in appendix 1.

[0074] (Appendix 4) An input receiving unit that receives an input of symptoms that a patient is aware of; A medical department determination unit that inputs subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department, and determines the medical department that the patient should visit; A medical department determination device comprising:

[0075] (Appendix 5) a training data acquisition step of acquiring, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation step of performing machine learning using the acquired training data to generate a learning model; A learning model generation method comprising the steps of:

[0076] (Appendix 6) In the training data acquisition step, the text data indicating the symptoms that the patient is aware of is divided into words, the words obtained by the division are converted into identifiers that are assigned to each word in advance, and a set of the obtained identifiers is defined as the subjective symptom data. A learning model generation method as described in Appendix 5.

[0077] (Appendix 7) the learning model is a neural network, In the learning model generating step, the learning model is generated by updating parameters of the neural network. A learning model generation method as described in Appendix 5.

[0078] (Appendix 8) An input receiving step of receiving an input of symptoms recognized by the patient; A medical department determination step of inputting the subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department to determine the medical department that the patient should visit; A medical department determination method comprising the steps of:

[0079] (Appendix 9) On the computer, a training data acquisition step of acquiring, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation step of performing machine learning using the acquired training data to generate a learning model; A program to execute.

[0080] (Appendix 10) In the training data acquisition step, the text data indicating the symptoms that the patient is aware of is divided into words, the words obtained by the division are converted into identifiers that are assigned to each word in advance, and a set of the obtained identifiers is defined as the subjective symptom data. 9. The program described in Appendix 9.

[0081] (Appendix 11) the learning model is a neural network, In the learning model generating step, the learning model is generated by updating parameters of the neural network. 9. The program described in Appendix 9.

[0082] (Appendix 12) On the computer, An input receiving step of receiving an input of symptoms recognized by the patient; A medical department determination step of inputting the subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department to determine the medical department that the patient should visit; A program to execute. [Industrial Applicability]

[0083] The present disclosure is useful in the reception of medical institutions. [Explanation of symbols]

[0084] 10 Learning model generation device 11 Training data acquisition section 12 Learning model generation unit 13 Storage section 20 Learning Model 21 Database 30 Medical department determination device 31 Input reception section 32 Department Judgment Department 33 Screen display section 34 Storage section 40 Display device 41 screens 110 Computer 111 CPU 112 Main memory 113 Storage device 114 Input Interface 115 Display Controller 116 Data Reader / Writer 117 Communication Interface 118 Input Devices 119 Display device 120 Recording media 121 Bus

Claims

1. A training data acquisition unit that acquires, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation unit that performs machine learning using the acquired training data to generate a learning model; A learning model generating device comprising:

2. the training data acquisition unit divides text data indicating symptoms that the patient is aware of into words, converts the words obtained by the division into identifiers that are assigned to each word in advance, and defines a set of the obtained identifiers as the subjective symptom data. The learning model generating device according to claim 1 .

3. the learning model is a neural network, The learning model generation unit generates the learning model by updating parameters of the neural network. The learning model generating device according to claim 1 .

4. An input receiving unit that receives an input of symptoms that a patient is aware of; A medical department determination unit that inputs subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department, and determines the medical department that the patient should visit; A medical department determination device comprising:

5. a training data acquisition step of acquiring, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation step of performing machine learning using the acquired training data to generate a learning model; A learning model generation method comprising the steps of:

6. In the training data acquisition step, the text data indicating the symptoms that the patient is aware of is divided into words, the words obtained by the division are converted into identifiers that are assigned to each word in advance, and a set of the obtained identifiers is defined as the subjective symptom data. The learning model generating method according to claim 5 .

7. the learning model is a neural network, In the learning model generating step, the learning model is generated by updating parameters of the neural network. The learning model generating method according to claim 5 .

8. An input receiving step of receiving an input of symptoms recognized by the patient; A medical department determination step of inputting the subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department to determine the medical department that the patient should visit; A medical department determination method comprising the steps of:

9. On the computer, a training data acquisition step of acquiring, as training data, subjective symptom data that identifies symptoms that a patient is aware of and medical department data that identifies a medical department that the patient has visited; A learning model generation step of performing machine learning using the acquired training data to generate a learning model; A program to execute.

10. On the computer, An input receiving step of receiving an input of symptoms recognized by the patient; A medical department determination step of inputting the subjective symptom data that identifies the symptom that has been accepted as input into a learning model that performs machine learning on the relationship between the symptom and the corresponding medical department to determine the medical department that the patient should visit; A program to execute.

Images