Oral advisor system and recall information generation method

Abstract

To enable a doctor to conduct an appropriate medical interview according to the condition of a patient after the examination. [Solution] A server 1 according to one embodiment of the present invention comprises a recall AI 42 including a learning model that has learned cases of dental patients, a prompt creation unit 412 that generates a recall prompt d34 to the recall AI 42 to generate recall information d35 that encourages the patient to make an appointment for a visit based on information that includes at least the patient's attribute information and information about the examinations performed on the patient, and outputs the generated recall prompt d34 to the recall AI 42, and a data input / output unit 311 that transmits the recall information d35 generated in the recall AI 42 based on the recall prompt d34 to a mobile terminal 2 operated by the patient.

Description

[Technical Field]

[0001] The present invention relates to an oral advisor system and a method for generating recall information. [Background technology]

[0002] Conventionally, there is known a medical consultation management system that encourages patients who have visited a medical institution to visit again. For example, Patent Document 1 discloses a medical consultation management system that includes a storage unit and a control device that stores, in the storage unit, second data indicating the date of the patient's visit, associated with first data that identifies the patient, and third data indicating either the period until the next visit, the scheduled date of the next visit, or the appointment date determined by the doctor. The control device described in Patent Document 1 executes a process to send a reminder to encourage a patient to visit the hospital when the scheduled date of the next visit, calculated from the period until the next visit indicated by the third data, is approaching within a predetermined number of days. The technology described in Patent Document 1 makes it possible to send a timely reminder to a patient even if a definite appointment date has not been determined in advance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2024-38401 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 notifies patients who request a reminder of the date of their next appointment, but does not mention recalling patients who do not request a reminder. Conventionally, patients have been sent reminders, such as standardized messages, to encourage them to come for their next appointment. However, the content of these reminder messages is generalized and does not reflect the details of the treatment provided by the dentist or other professional. Therefore, patients who receive such messages tend to simply read the message and dismiss it without taking it personally. In other words, this often does not lead to the patient making an appointment for their next appointment. For this reason, patients often make appointments for follow-up appointments only when they experience problems such as pain or odor, or visit the hospital without an appointment if their symptoms are severe.

[0005] The present invention has been made in consideration of the above situation, and an object of the present invention is to enable automatic generation of recall text according to a patient's treatment history. [Means for solving the problem]

[0006] An oral advisor system according to one aspect of the present invention is a dental Symptoms of The system comprises a recall AI including a learning model that has learned examples, a recall information creation instruction unit that generates a recall information creation instruction to generate recall information that encourages patients to make an appointment to visit the hospital based on information that includes at least the patient's attribute information and information about the examinations performed on the patient, and outputs the recall information creation instruction to the recall AI, and a recall information input / output unit that transmits the recall information generated in the recall AI based on the recall information creation instruction to a patient-operated terminal device operated by the patient. [Effects of the Invention]

[0007] According to at least one aspect of the present invention, recall text can be automatically generated based on the patient's treatment history. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram showing a schematic configuration example of an oral advisor system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a block diagram showing an example of the configuration of a server, a mobile terminal, a tablet terminal, and a computer, which are hardware components of a terminal device, according to an embodiment of the present invention. [Figure 3] 1 is a diagram showing the correspondence between the processing flow at a dental clinic and the processing by each functional unit of an oral advisor system according to one embodiment of the present invention. FIG. [Figure 4] 10 is a flowchart illustrating an example of a procedure for a medical interview process at the time of reservation by a medical interview function unit at the time of reservation according to one embodiment of the present invention. [Figure 5] FIG. 2 is a diagram showing an example of the configuration of reservation information according to an embodiment of the present invention. [Figure 6] FIG. 10 is a diagram illustrating an example of a configuration of a medical appointment prompt according to an embodiment of the present invention. [Figure 7] FIG. 2 is a diagram showing an example of the configuration of appointment inquiry information according to one embodiment of the present invention. [Figure 8] FIG. 10 is a diagram showing an example of the configuration of a reservation screen displayed on a mobile terminal according to an embodiment of the present invention. [Figure 9] FIG. 2 is a diagram illustrating an example of the configuration of a reservation DB according to an embodiment of the present invention. [Figure 10] 10 is a flowchart illustrating an example of a procedure for training support processing by a training support function unit according to an embodiment of the present invention. [Figure 11] FIG. 10 is a diagram showing an example of the configuration of visual inspection result information according to one embodiment of the present invention. [Figure 12] FIG. 2 is a diagram showing an example of the configuration of medical record DB registration information according to one embodiment of the present invention. [Figure 13] FIG. 10 is a diagram illustrating an example of the configuration of a training support prompt according to an embodiment of the present invention. [Figure 14]FIG. 2 is a diagram showing an example of the configuration of training support information according to an embodiment of the present invention. [Figure 15] FIG. 2 is a diagram showing an example of the configuration of medical record information according to one embodiment of the present invention. [Figure 16] FIG. 10 is a diagram showing an example of the configuration of a business record screen according to an embodiment of the present invention. [Figure 17] FIG. 10 is a diagram showing an example of the configuration of an SNS screen displayed on a mobile terminal according to an embodiment of the present invention. [Figure 18] 10 is a flowchart illustrating an example of a procedure for an aftercare process by an aftercare function unit according to an embodiment of the present invention. [Figure 19] FIG. 2 is a diagram showing an example of the configuration of medical record information according to one embodiment of the present invention. [Figure 20] FIG. 10 illustrates an example configuration of an aftercare prompt according to an embodiment of the present invention. [Figure 21] FIG. 2 is a diagram showing an example of the configuration of aftercare questionnaire information according to one embodiment of the present invention. [Figure 22] FIG. 2 is a diagram showing an example of the configuration of aftercare questionnaire response information according to one embodiment of the present invention. [Figure 23] FIG. 10 is a diagram showing an example of the configuration of aftercare information according to an embodiment of the present invention. [Figure 24] FIG. 10 is a diagram showing an example of the configuration of an aftercare questionnaire screen in a case where an aftercare message is composed of an email according to one embodiment of the present invention. [Figure 25] FIG. 10 is a diagram showing an example of the configuration of an aftercare questionnaire screen when an aftercare message according to one embodiment of the present invention is sent via SNS. [Figure 26] 10 is a flowchart illustrating an example of a procedure for recall processing by a recall function unit according to an embodiment of the present invention. [Figure 27] FIG. 2 is a diagram showing an example of the configuration of medical record information according to one embodiment of the present invention. [Figure 28] FIG. 10 is a diagram showing an example of the configuration of aftercare information according to an embodiment of the present invention. [Figure 29]FIG. 10 is a diagram illustrating an example of a configuration of a recall prompt according to an embodiment of the present invention. [Figure 30] FIG. 2 is a diagram showing an example of the configuration of recall information according to an embodiment of the present invention. [Figure 31] FIG. 10 is a diagram showing an example of the configuration of a recall screen when a recall message is sent via SNS according to one embodiment of the present invention. [Figure 32] FIG. 10 is a diagram showing a schematic configuration example of an oral advisor system according to a modified example of the present invention. [Figure 33] FIG. 10 is a diagram showing an example of the configuration of an appointment inquiry AI resume DB according to a modified example of the present invention. [Figure 34] FIG. 10 is a diagram showing an example of the configuration of a training support AI resume DB according to a modified example of the present invention. [Figure 35] FIG. 10 is a diagram showing an example of the configuration of an aftercare AI resume DB according to a modified example of the present invention. [Figure 36] FIG. 10 is a diagram showing an example of the configuration of a recall AI resume DB according to a modified example of the present invention. [Figure 37] 10 is a flowchart showing an example of a procedure for storing appointment medical interview information by an appointment medical interview function unit according to a modified example of the present invention. [Figure 38] 10 is a flowchart showing an example of a procedure for a process of reading out appointment medical interview information by an appointment medical interview function unit according to a modified example of the present invention. [Figure 39] 10 is a flowchart illustrating an example of a procedure for saving training support information by a training support function unit according to a modified example of the present invention. [Figure 40] 10 is a flowchart illustrating an example of a procedure for a process of reading out training support information by a training support function unit according to a modification of the present invention. [Figure 41] 10 is a flowchart illustrating an example of a procedure for a process of storing aftercare information by an aftercare function unit according to a modified example of the present invention. [Figure 42] 10 is a flowchart illustrating an example of a procedure for a process of reading out aftercare information by an aftercare function unit according to a modified example of the present invention. [Figure 43]10 is a flowchart showing an example of a procedure for a process of saving recall information by a recall function unit according to a modified example of the present invention. [Figure 44] 10 is a flowchart illustrating an example of a procedure for a recall information read process performed by a recall function unit according to a modified example of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, examples of modes for carrying out the present invention (hereinafter referred to as "embodiments") will be described with reference to the accompanying drawings. Various numerical values ​​in the embodiments of the present invention are merely examples, and the present invention is not limited to the embodiments described below. Furthermore, in this specification and drawings, identical components or components having substantially the same functions will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] <Outline of Oral Advisor System> First, the configuration of an oral advisor system 100 according to one embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of a schematic configuration of the oral advisor system 100.

[0011] As shown in FIG. 1, the oral advisor system 100 includes a server 1, a mobile terminal 2, a tablet terminal 3, and a terminal device 4. The mobile terminal 2 (an example of a patient-operated terminal device) is a terminal device that is configured, for example, by a smartphone, a mobile phone terminal, or the like, and is operated by a patient U1 who visits the dental clinic. Note that the terminal device operated by the patient U1 is not limited to a mobile terminal. Instead of a mobile terminal, a tablet terminal, a PC (Personal Computer), or other terminal device may be used.

[0012] The tablet terminal 3 is a tablet-type terminal device, and is operated by a dental hygienist U2, etc. The terminal device operated by the dental hygienist U2 is not limited to a tablet terminal, and may be a mobile terminal, etc. The terminal device 4 (an example of a dentist-operated terminal device) is configured by, for example, a PC or the like, and is operated by a dentist U3 or the like. The server 1, the mobile terminal 2, the tablet terminal 3, and the terminal device 4 are connected to each other so as to be able to communicate with each other via a network (not shown).

[0013] [server] The server 1 is installed in, for example, a cloud environment, and has an appointment interview function unit 10, a training support function unit 20, an aftercare function unit 30, and a recall function unit 40. The server 1 also has a reservation DB (Database) 51, a medical record DB 52, and an aftercare DB 53.

[0014] The appointment time medical interview function unit 10 performs appointment time (pre-appointment) medical interview processing. The appointment time medical interview processing is a process of registering answers to questions posed to the patient when the patient U1 makes an appointment for a medical consultation in the appointment DB 51. The medical interview for the patient U1 is provided to the mobile terminal 2 of the patient U1 as appointment time medical interview information d3 via a website screen, email, SNS, etc. The answer from the patient U1 is sent from the mobile terminal 2 of the patient U1 to the server 1 as appointment time medical interview response information d4 via a website screen, email, SNS, etc. An example of the configuration of the appointment inquiry information d3 will be described later with reference to FIG.

[0015] The training support function unit 20 performs training support processing. The training support processing is processing for generating training support information d13 based on appointment interview information d3. The training support information d13 is information regarding the training content referenced by a dental hygienist U2 who provides training to a patient U1 who visits the clinic. The training support function unit 20 then provides the generated training support information d13 to a tablet terminal 3 operated by the dental hygienist U2 via a website screen, email, SNS, or the like. An example of the configuration of the training support information d13 will be described later with reference to FIG. 14. Furthermore, when the content of the treatment by the dentist U3 is transmitted from the terminal device 4, the training support function unit 20 registers the training support information d13 and the content of the treatment in the medical record DB 52. Furthermore, the training support function unit 20 also transmits the training support information d13 to the mobile terminal 2 of the patient U1.

[0016] The aftercare function unit 30 performs aftercare processing. The aftercare processing is a process of registering answers to a post-examination interview (hereinafter also referred to as a "post-examination interview") conducted based on the examination details of patient U1 stored in the medical record DB 52 in the aftercare DB 53. "Post-examination" specifically refers to both a post-examination period in which only an examination is conducted without treatment (procedure) and a post-treatment period in which treatment is conducted after the examination. The interviews conducted for patient U1 are periodically provided to the mobile terminal 2 of patient U1 as aftercare interview information d23 via a website screen, email, social media, or the like. The timing of providing the aftercare interview information d23 is set by the aftercare AI 32, which will be described later. The aftercare AI 32 determines the optimal timing within the period from after the examination until before the next examination and sets that timing as the timing for providing the aftercare interview information d23. Answers from patient U1 are transmitted as aftercare interview answer information d24 from the mobile terminal 2 of patient U1 to the server 1 via a website screen, email, social media, or the like. An example of the structure of the aftercare questionnaire information d23 will be described later with reference to FIG. 21, and an example of the structure of the aftercare questionnaire answer information d24 will be described later with reference to FIG.

[0017] The recall function unit 40 performs recall processing. The recall processing is processing in which recall information d35, which is generated by the recall function unit 40 and prompts the patient U1 to make an appointment for the next consultation, is sent to the mobile terminal 2 operated by the patient U1. An example of the configuration of the recall information d35 will be described later with reference to FIG. 30.

[0018] (Reservation interview function section) The appointment inquiry function unit 10 includes an appointment creation unit 11 and an appointment inquiry AI (Artificial Intelligence) 12. The reservation creation unit 11 includes a data input / output unit 111 , a prompt creation unit 112 , and a DB writing unit 113 .

[0019] The data input / output unit 111 controls the operation of transmitting and receiving various data to and from the mobile terminal 2 of the patient U1. Specifically, the data input / output unit 111 receives appointment information d1 transmitted from the mobile terminal 2 and outputs it to the prompt creation unit 112. The appointment information d1 is information composed of attribute information such as the name and date of birth of the patient U1, the date and time of visit, the reason for visit, etc. An example of the configuration of the appointment information d1 will be described later with reference to FIG. 5. In addition, the data input / output unit 111 transmits appointment interview information d3 generated by the appointment interview AI 12 to the mobile terminal 2 of the patient U1.

[0020] The prompt creation unit 112 (an example of a reservation medical interview creation instruction unit) generates a reservation medical interview prompt d2 based on the reservation information d1 transmitted from the mobile terminal 2 and received by the data input / output unit 111. The prompt creation unit 112 then outputs the generated reservation medical interview prompt d2 to the reservation medical interview AI 12. An example of the configuration of the reservation medical interview prompt d2 will be described later with reference to FIG. 6.

[0021] The appointment interview AI 12 is composed of, for example, large-scale language models (LLMs). LLMs are a type of text generation AI, and are language models (learning models) that have learned from patient cases. LLMs are capable of performing advanced natural language processing tasks (text generation, translation, summarization, question answering, etc.).

[0022] The appointment interview AI12 creates appointment interview information d3 corresponding to patient U1 based on the appointment interview prompt d2 input from the prompt creation unit 112, and outputs the created appointment interview information d3 to the appointment creation unit 11.

[0023] The appointment interview AI 12 may be configured using a deep learning model (hereinafter simply referred to as a "learning model") that has learned from past medical examination cases (clinical data). The learning model that has learned from past medical examination cases may be configured using, for example, a neural network of a multi-class classification model, a learning model that employs a random forest algorithm, or a fine-tuned LLM.

[0024] The DB writing unit 113 writes the reservation information based on the reservation information d1 and the reservation questionnaire response information d4 into the reservation DB 51. The reservation DB 51 is a database that stores reservation information d1 and reservation questionnaire response information d4 of the patient U1. The configuration of the reservation DB 51 will be described later with reference to FIG.

[0025] (Instruction Support Function Department) The training support function unit 20 includes a medical record creation unit 21 and a training support AI 22. The medical record creation unit 21 includes a data input / output unit 211 , a prompt creation unit 212 , and a DB writing unit 213 .

[0026] The data input / output unit 211 controls the transmission and reception of various data between the mobile terminal 2 of the patient U1 and the tablet terminal 3 of the dental hygienist U2. Specifically, the data input / output unit 211 outputs the visual examination result information d11 transmitted from the tablet terminal 3 to the prompt creation unit 212. The visual examination result information d11 is information indicating the content of the visual examination performed by the dental hygienist U2 based on the training support information d13. Furthermore, the data input / output unit 211 transmits the training support information d13 generated by the training support AI 22 to the tablet terminal 3 of the dental hygienist U2. Furthermore, after the dental hygienist U2 provides training based on the training support information d13, the data input / output unit 211 transmits the training support information d13 to the mobile terminal 2 of the patient U1.

[0027] The prompt creating unit 212 (an example of a training support information creation instructing unit) creates a training support prompt d12 based on the visual examination result information d11 transmitted from the tablet terminal 3 of the dental hygienist U2. An example of the configuration of the visual examination result information d11 will be described later with reference to Fig. 11, and an example of the configuration of the training support prompt d12 will be described later with reference to Fig. 13. Then, the created training support prompt d12 is input to the training support AI 22.

[0028] The training support AI 22 is configured by, for example, a large-scale language model, etc. The training support AI 22 creates training support information d13 corresponding to each patient U1 based on the training support prompt d12 input from the prompt creation unit 212, and outputs the created training support information d13 to the medical record creation unit 21. An example of the configuration of the training support information d13 will be described later with reference to FIG. 14.

[0029] The training support AI 22 may be configured by a deep learning model (learning model) that has learned from past medical examination cases. The learning model that has learned from past medical examination cases may be configured by, for example, a neural network of a multi-class classification model, a learning model that employs a random forest algorithm, or a fine-tuned LLM. The DB writing unit 213 writes the training support information d13 generated by the training support AI 22 into the medical record DB 52. Although not shown in FIG. 1, the contents of the examination and treatment performed by the dentist U3 are also written into the medical record DB 52.

[0030] The medical record DB52 is a database in which medical record information d21 is stored. The medical record information d21 includes appointment information d1, visual examination result information d11, instruction support information d13, and the details of the examination and treatment by dentist U3. The medical record indicated by the medical record information d21 is an electronic medical record. This electronic medical record is an insurance medical record that records the interview conducted with patient U1, the details of the examination and treatment by dentist U3 and dental hygienist U2, and the insurance points related to them.

[0031] (Aftercare Function Department) The aftercare function unit 30 includes an aftercare execution unit 31 and an aftercare AI 32 . The aftercare execution unit 31 includes a data input / output unit 311 , a prompt creation unit 312 , and a DB writing unit 313 .

[0032] The data input / output unit 311 (an example of a post-examination interview information input / output unit) controls the operation of transmitting and receiving various data to and from the mobile terminal 2 of the patient U1. Specifically, the data input / output unit 311 transmits the aftercare interview information d23 generated by the aftercare AI 32 to the mobile terminal 2 of the patient U1.

[0033] The prompt creation unit 312 (an example of a post-examination interview creation instruction unit) acquires medical record information d21 from the medical record DB 52 at a predetermined timing, and generates an aftercare prompt d22 (an example of a post-examination interview information creation instruction) based on the acquired medical record information d21. An example of the configuration of the medical record information d21 will be described later with reference to Fig. 19, and an example of the configuration of the aftercare prompt d22 will be described later with reference to Fig. 20. The prompt generator 312 then outputs the generated aftercare prompt d22 to the aftercare AI 32.

[0034] The aftercare AI 32 (an example of a post-examination interview AI) is configured, for example, by a large-scale language model, etc. The aftercare AI 32 creates aftercare interview information d23 (an example of post-examination interview information) corresponding to the patient U1 based on the aftercare prompt d22 input from the prompt creation unit 312, and outputs the created aftercare interview information d23 to the aftercare execution unit 31. An example of the configuration of the aftercare interview information d23 will be described later with reference to FIG. 21.

[0035] The aftercare AI 32 may be configured by a deep learning model (learning model) that has learned from past medical examination cases. The learning model that has learned from past medical examination cases may be configured by, for example, a neural network of a multi-class classification model, a learning model that employs a random forest algorithm, or a fine-tuned LLM.

[0036] The DB writing unit 313 writes the aftercare questionnaire information d23 generated by the aftercare AI 32 and the aftercare questionnaire response information d24 transmitted from the mobile terminal 2 of the patient U1 into the aftercare DB 53. The aftercare DB 53 is a database in which aftercare questionnaire information d23 and aftercare questionnaire response information d24 are stored.

[0037] (Recall function section) The recall function unit 40 includes a recall execution unit 41 and a recall AI 42 . The recall execution unit 41 includes a data input / output unit 411 and a prompt creation unit 412 .

[0038] The data input / output unit 411 (an example of a recall information input / output unit) controls the transmission and reception of various data between the portable terminal 2 of the patient U1 and the terminal device 4 of the dentist U3. Specifically, the data input / output unit 411 receives recall transmission target patient information d31 transmitted from the terminal device 4 of the dentist U3 and outputs it to the prompt creation unit 412. The recall transmission target patient information d31 is information on patients to whom recall information is to be transmitted, selected by the dentist U3 via the terminal device 4. The data input / output unit 411 also transmits recall information d35 generated by the recall AI 42 to the terminal device 4 of the dentist U3. When confirmation information on the contents of the recall information d35 is transmitted from the terminal device 4 operated by the dentist U3, the data input / output unit 411 transmits the recall information d35 determined to be without problem in the confirmation information to the portable terminal 2 of the patient U1.

[0039] The prompt creation unit 412 (an example of a recall information creation instruction unit) generates a recall prompt d34 based on the recall transmission target patient information d31. An example of the configuration of the recall prompt d34 will be described later with reference to Fig. 29. The prompt creation unit 312 then outputs the generated recall prompt d34 to the recall AI 42.

[0040] The recall AI 42 is configured, for example, by a large-scale language model, etc. The recall AI 42 creates recall information d35 corresponding to each patient U1 based on the recall prompt d34 input from the prompt creation unit 312, and transmits the created recall information d35 to the recall execution unit 41. An example of the configuration of the recall information d35 will be described later with reference to FIG. 30.

[0041] The recall AI 42 may be configured by a deep learning model (learning model) that has learned from past medical examination cases. The learning model that has learned from past medical examination cases may be configured by, for example, a neural network of a multi-class classification model, a learning model that employs a random forest algorithm, or a fine-tuned LLM.

[0042] <Configuration of the control system of the Oral Advisor System> Next, the hardware configurations of the server 1, the mobile terminal 2, the tablet terminal 3, and the terminal device 4 that constitute the oral advisor system 100 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the configuration of a computer 500 that is the hardware of the server 1, the mobile terminal 2, the tablet terminal 3, and the terminal device 4.

[0043] As shown in FIG. 2, the computer 500 includes a control unit 510, a storage unit 520, an operation input unit 530, an output unit 540, and a communication I / F (Interface) unit 550, which are all connected to a bus B. The control unit 510 is an arithmetic unit including a central processing unit (CPU) 511, a read only memory (ROM) 512, and a random access memory (RAM) 513.

[0044] The CPU 511 reads out program code of software that realizes each function of the server 1 according to this embodiment from the ROM 512, expands it into the RAM 513, and executes it. The server 1 may include a processing device such as an MPU (Micro-Processing Unit) instead of the CPU 511. Variables, parameters, and the like that are generated during the calculation processing by the CPU 511 are temporarily written to the RAM 513.

[0045] The storage unit 520 may be, for example, a hard disk drive (HDD), a solid state drive (SSD), a flexible disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a non-volatile memory card, etc. The storage unit 520 stores an operating system (OS), various parameters, and programs for operating the server 1.

[0046] The program for causing the server 1 to function may be stored in the ROM 512. The program is stored in the form of a computer-readable program code. The CPU 511 sequentially executes operations in accordance with the program code. In other words, the ROM 512 or the storage unit 520 is an example of a computer-readable non-transitory recording medium that stores a program to be executed by a computer.

[0047] The operation input unit 530 is configured by, for example, a mouse, a keyboard, and the like, and generates an operation signal according to an operation by the user and supplies it to the CPU 511. The output unit 540 is, for example, a monitor configured with an LCD (Liquid Crystal Display) or the like. The operation input unit 530 and the output unit 540 may be integrated into a touch panel. The communication I / F 550 is configured by a communication device or the like that controls communication between the device and an external device.

[0048] <Example of processing flow at a dental clinic> Next, the correspondence between the processing flow at a dental clinic and the processing by each functional unit of the oral advisor system 100 according to this embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram showing the correspondence between the processing flow at a dental clinic and the processing by each functional unit of the oral advisor system 100 according to this embodiment.

[0049] First, patient U1 recognizes a dental clinic based on an internet search or word of mouth from people around them, and makes an appointment at the recognized dental clinic (step S1). After step S1, the first consultation takes place (step S3). If the appointment in step S1 is made after a predetermined period has elapsed since the previous appointment, the consultation in step S3 will be a second first consultation. Then, at the time of the first visit or follow-up visit in step S3, a medical interview is conducted (step S4).

[0050] In conventional technology, medical interviews are templated and are not suitable for identifying problems specific to a patient. Furthermore, templated medical interviews may include questions that do not need to be answered depending on the patient's gender, age, etc., such as questions about drinking, smoking, pregnancy, etc. In such cases, patients may have doubts about whether they need to answer the questions.

[0051] Furthermore, in conventional technology, the medical interview is conducted after the patient arrives at the hospital, so the consultation does not begin while the patient is answering the interview. In other words, the start time of the consultation is delayed by the time it takes the patient to answer the interview. Therefore, for example, if there is a patient who takes a long time to answer the medical interview, the consultation time of all patients who have appointments after that time will be delayed.

[0052] Furthermore, by conducting the medical interview at the time of the visit, the condition of the patient who will be visiting that day can only be grasped on the same day. As a result, depending on the patient's symptoms, it may happen that the dental clinic does not have the materials or equipment necessary to treat that symptom in stock. In such a situation, it is not possible to provide the patient with appropriate treatment, and so only emergency measures may be given, or treatment may not be possible at all.

[0053] In order to solve the above problem, in the oral advisor system 100 according to this embodiment, the appointment inquiry function unit 10 conducts an appointment inquiry (step S2) between the appointment in step S1 and the first or subsequent first visit in step S3. Details of the appointment inquiry process by the appointment inquiry function unit 10 will be described later with reference to Figs. 4 to 9.

[0054] After the medical interview in step S4, the dentist U3 performs an examination and diagnosis based on the information obtained from the medical interview (step S5). Note that when the oral advisor system 100 according to this embodiment is used, the medical interview is performed after the appointment in step S1, so the medical interview before the medical examination and diagnosis in step S4 is not performed.

[0055] After the examination and diagnosis in step S5, dental hygienist U2 explains the contents of the examination to patient U1 and provides guidance regarding future care, etc. (step S6). Dental hygienist U2 then records the explanations and guidance provided to patient U1 in a dental hygienist work record (not shown). Note that the quality of guidance provided by dental hygienist U2 and the speed at which it is recorded in the dental hygienist work record depend on the experience, skills, verbalization ability, memory, etc. of dental hygienist U2.

[0056] Furthermore, the task of dental hygienist U2 recording information in the dental hygienist work record itself is time-consuming. Even an experienced dental hygienist U2 finds it difficult to always provide optimal guidance tailored to the condition of each patient. In addition, if attempting to record all the necessary information without any omissions or excesses, the recording process can take more than 10 minutes per patient.

[0057] Medical record systems designed to reduce recording time often provide templates for dental hygienist work records. However, when templates are used, dental hygienists U2 must choose from the templates that are closest to the explanations or instructions they provided, which can result in records that do not reflect the actual situation. Furthermore, many dental clinics use paper for dental hygienist work records. Furthermore, when dental hygienist work records are recorded on paper, it becomes difficult to centrally manage and utilize the information.

[0058] In other words, regardless of the dental hygienist U2's experience, skills, verbalization ability, memory, etc., they are required to be able to provide appropriate explanations and guidance according to the condition of patient U1, and to be able to keep appropriate records in a form that allows information to be shared easily. In the oral advisor system 100 according to this embodiment, the training support function unit 20 performs training support processing for the purpose of solving the above-mentioned problems. The training support processing by the training support function unit 20 will be described later with reference to Figs. 10 to 17.

[0059] After dental hygienist U2 provides explanations and guidance in step S6, dentist U3 performs treatment (step S7) and records the treatment details (step S8). Then, payment is made at the reception desk (step S9), and if necessary, an appointment for the next consultation is made (step S10). If an appointment for the next consultation is made, a follow-up consultation is performed based on that appointment (step S11).

[0060] In conventional systems, when a follow-up visit in step S11 is performed and a series of treatments are completed at that point, the next appointment is scheduled at a timing determined by the patient. Alternatively, a reminder to schedule the next appointment is sent via paper media such as a postcard, email, or social media (step S13).

[0061] In contrast, in the oral advisor system 100 according to this embodiment, the aftercare function unit 30 performs aftercare processing between the appointment in step S10 and the follow-up visit in step S11, or between the follow-up visit in step S11 and the recall in step S13. The aftercare process by the aftercare function section 30 will be described later with reference to FIGS.

[0062] In the conventional system, the recall performed in step S13 involves sending a standard email or message via social media at a predetermined timing, such as several months after the consultation or follow-up visit, encouraging the patient to come for the next consultation. However, the content of the recall message at this time is generalized and does not reflect the details of the treatment performed in step S7.

[0063] In order to solve the above problem, in the oral advisor system 100 according to this embodiment, the recall function unit 40 performs recall processing. Note that the recall processing by the recall function unit 40 will be described later with reference to Figs. 26 to 31.

[0064] <Inquiry processing at the time of reservation> [Procedure for processing medical interviews at the time of reservation] Next, the medical interview process at the time of reservation by the medical interview function unit 10 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of the procedure of the medical interview process at the time of reservation by the medical interview function unit 10.

[0065] First, the data input / output unit 111 (see FIG. 1) of the appointment creation unit 11 in the appointment interview function unit 10 accepts appointment information d1 input from the mobile terminal 2 of the patient U1 (step S21). Next, the prompt creation unit 112 of the appointment creation unit 11 generates an appointment interview prompt d2 based on the appointment information d1 and outputs it to the appointment interview AI 12 (step S22). Next, the appointment interview AI 12 creates appointment interview information d3 based on the appointment interview prompt d2 and outputs it to the appointment creation unit 11 (step S23).

[0066] Next, the data input / output unit 111 of the appointment making unit 11 transmits appointment inquiry information d3 to the mobile terminal 2 (step S24). Then, the data input / output unit 111 receives appointment inquiry response information d4, which is a response to the appointment inquiry transmitted from the mobile terminal 2 (step S25). Next, the data input / output unit 111 confirms the appointment for the medical examination managed by a medical record system (not shown) based on the appointment inquiry response information d4 (step S26). Then, the DB writing unit 113 of the appointment making unit 11 writes the appointment inquiry response information d4 to the appointment DB 51 (step S27). After processing step S27, the appointment inquiry processing by the appointment inquiry function unit 10 is terminated.

[0067] [Reservation information configuration example] Next, the reservation information d1 that the data input / output unit 111 of the reservation creation unit 11 receives from the mobile terminal 2 of the patient U1 in step S21 of the flowchart in Fig. 4 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the configuration of the reservation information d1.

[0068] As shown in FIG. 5, appointment information d1 has the following fields: "Name," "Visit Date and Time," "Gender," "Date of Birth," "Email Address," and "Reason for Visit." The "Name" field stores the patient's name, and the "Visit Date and Time" field stores information about the date and time the patient wishes to make an appointment for an examination. The "Gender" field stores information about the patient's gender, and the "Date of Birth" field stores information about the patient's date of birth. The "Email Address" field stores information about the patient's email address. Note that the information that makes up appointment information d1 is not limited to these pieces of information, and other information may be added.

[0069] [Example of prompt configuration for appointment inquiries] Next, the appointment-time medical interview prompt d2 will be described with reference to Fig. 6. The appointment-time medical interview prompt d2 is generated by the prompt generation unit 112 of the appointment creation unit 11 in step S22 of the flowchart in Fig. 4. Fig. 6 is a diagram showing an example of the configuration of the appointment-time medical interview prompt d2.

[0070] As shown in Figure 6, the first line of the appointment interview prompt d2 contains the following sentence, assigning a role to the appointment interview AI 12: "You are one of Japan's top dentists. You will now interview the patient." The next sentence, assigning a task to the appointment interview AI 12, reads: "Consider the patient's age, gender, and reason for visit, and generate 15 questions to fully understand the patient's wishes." The next sentence specifies constraints: "The output must be in XML format and must be in Japanese. Also, include items that are particularly likely to be overlooked by humans during an interview." Finally, the patient's date of birth, gender, and reason for visit are listed as attribute information for the patient for whom appointment interview information d3 is created.

[0071] By inputting such appointment-time medical interview prompt d2, appointment-time medical interview AI12 can create and output appointment-time medical interview information d3 according to the patient's attribute information specified in the prompt. Note that appointment-time medical interview prompt d2 shown in Figure 6 is an example, and appointment-time medical interview prompt d2 may have a different sentence structure than that shown in Figure 6 and may contain different information.

[0072] [Example of medical interview information at time of reservation] Next, with reference to FIG. 7, the appointment interview information d3 created by the appointment interview AI 12 will be described. FIG. 7 is a diagram showing an example of the configuration of the appointment interview information d3. As shown in FIG. 7, the appointment interview information d3 contains, in XML format, multiple-choice questions and free-form questions. The single-choice questions include, "How long have you been experiencing toothache or sensitivity due to tooth decay?" and the options "more than two months ago," "one month ago," "about two weeks ago," and "a few days ago." The free-form questions include, "What kind of tooth brushing and oral care do you usually do? Also, do you use an interdental brush or dental floss?"

[0073] In this way, the appointment interview information d3 created by the appointment interview AI12 reflects the patient's attribute information and the information "treatment for tooth decay" written in the "reason for visit" section of the appointment information d1.

[0074] [Reservation screen configuration example] Next, the appointment screen Sc1 on which appointment interview information d3 is displayed will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example of the configuration of the appointment screen Sc1 displayed on the mobile terminal 2. The appointment screen Sc1 shown in Fig. 8 is a screen that is displayed when patient information is entered on a screen (not shown) that is displayed after accessing a website provided by a dental clinic, for example.

[0075] 8, the appointment screen Sc1 has a patient information display area Ar1, a medical interview information display area Ar2, and an appointment confirmation button Bn1. The patient information display area Ar1 displays the patient information entered on the previously displayed screen. Of the information displayed in the patient information display area Ar1, information on the patient's date of birth, gender, date and time of visit, and reason for visit is sent to the appointment creation unit 11 of the appointment interview function unit 10 as appointment information d1.

[0076] The appointment interview information display area Ar2 displays appointment interview information d3 created by the appointment interview AI 12. Patients can easily answer Question 1 (Q1) by selecting the radio button corresponding to the answer that best suits their situation. For Question 2 (Q2), patients can write their answer in free text format, allowing them to communicate their symptoms to the dental clinic.

[0077] The reservation confirmation button Bn1 is a button for confirming the reservation. When pressing of the reservation confirmation button Bn1 is detected, the patient's appointment for the consultation is confirmed, and the information entered on the reservation screen Sc1 is sent to the server 1 as patient information d1. Note that the configuration of the reservation screen Sc1 is not limited to the example shown in FIG. 8, and the question format may be other formats, and other information may be included.

[0078] [Reservation DB configuration example] Next, the configuration of the reservation DB 51 in which the reservation response information d4 is stored in step S26 of the flowchart in Fig. 4 will be described with reference to Fig. 9. Fig. 9 is a diagram showing an example of the configuration of the reservation DB 51.

[0079] As shown in FIG. 9, the reservation DB 51 has the following fields: "Name," "Visit Date and Time," "Gender," "Date of Birth," "Email Address," "Reason for Visit," and "Results of Medical Interview." In the example shown in FIG. 9, the patient's (scheduled) visit date and time is "October 1, 2024, 2:00 PM," the patient's gender is "Male," and the date of birth is "January 2, 1990." The patient's email address is also shown to be taro@xxxx.com, and the reason for the visit is "tooth decay treatment." Furthermore, the answer to question Q1 is "about two weeks ago," and the answer to question Q2 is "I brush my teeth and floss three times a day after meals."

[0080] According to this embodiment, the information stored in the reservation DB 51 can be obtained at the time the patient makes a reservation for a consultation, so even if the materials or equipment required for treatment are in short supply, the dental clinic can replenish them by the time of the consultation. Therefore, according to this embodiment, it is possible to prevent situations where only emergency treatment is performed or where treatment cannot be performed at all.

[0081] Furthermore, in this embodiment, the appointment interview AI 12 creates appointment interview information d3 tailored to each patient based on the appointment information d1, so inappropriate questions that do not match the patient's attribute information are not included. Specifically, questions about pregnancy are not included for male patients, and questions about smoking are not included for pediatric patients. Therefore, patients can smoothly answer the interview without having any doubts or hesitation about whether or not to answer the questions.

[0082] Furthermore, in this embodiment, the appointment interview processing is performed by the appointment interview function unit 10 between the appointment and the initial or subsequent initial visit, so the patient does not need to answer the interview when they visit the hospital. Therefore, this embodiment can prevent delays in consultation time due to the time it takes to answer the interview. Furthermore, this embodiment eliminates the need to incorporate the time it takes to answer the interview into the consultation time for each patient, which can improve patient turnover.

[0083] In the above-described embodiment, the appointment interview information d3 is used to secure stock of materials and equipment necessary for treating a patient's symptoms, for examinations, and the like, but the present invention is not limited to this. The appointment interview information d3 may also be used for campaigns to motivate patients to visit the clinic. For example, suppose that the appointment interview reveals that a patient has a symptom of "sensitiveness to cold foods." In this case, the dental clinic can plan a campaign to gift a sample of toothpaste that is effective against tooth sensitivity when the patient visits the clinic.

[0084] In this case, the reservation creation unit 11 displays a message such as "We will give you a sample of toothpaste that is effective against tooth sensitivity on the day!" on the reservation screen Sc1 in Fig. 8, etc. Displaying such a message is expected to increase the patient's motivation to visit the clinic, preventing the patient from canceling the reservation at the last minute. Furthermore, by offering such a campaign, it is also expected that the dental clinic will attract more customers.

[0085] <Instruction support processing> [Procedure for Guidance Support Processing] Next, the training support process performed by the training support function unit 20 will be described with reference to FIG. FIG. 10 is a flowchart showing an example of the procedure of training support processing by the training support function unit 20.

[0086] First, the data input / output unit 211 (see FIG. 1) of the medical record creation unit 21 of the training support function unit 20 receives input of the visual examination result information d11 from the tablet terminal 3 (step S31). Next, the medical record creation unit 21 detects pressing of the training AI button Bn2 on the business record screen Sc2 (see FIG. 16) (step S32). Next, the prompt creation unit 212 of the medical record creation unit 21 generates a training support prompt d12 based on the appointment DB registration information d6 and the medical record DB registration information d16, and outputs it to the training support AI 22 (step S33). The appointment DB registration information d6 is information read from the appointment DB 51, and the medical record DB registration information d16 is information read from the medical record DB 52.

[0087] Next, the training support AI 22 creates training support information d13 based on the training support prompt d12 and outputs it to the medical record creating unit 21 (step S34).

[0088] Next, the data input / output unit 211 of the medical record creation unit 21 transmits the training support information d13 to the tablet terminal 3 (step S35). The training support information d13 is transmitted to the tablet terminal 3 at a predetermined timing after the patient's examination is completed. The transmission process of step S35 may be performed at the same timing as step S37, or after step S37 is executed. Alternatively, for example, a transmission button or the like may be provided on the business record screen Sc2 to indicate the timing of transmitting the training support information, and the process of step S35 may be performed when pressing of the button is detected.

[0089] Next, the data input / output unit 211 receives input of the examination and treatment by the dentist from the tablet terminal 3 (step S36). Then, the data input / output unit 211 transcribes the training support information d13 and the contents of the examination and treatment into a medical record managed by a medical record system (not shown) (step S37).

[0090] Next, the DB writing unit 213 creates medical record information d15 based on the reservation information d1, reservation DB registration information d6, medical record DB registration information d16, and training support information d13, and stores it in the medical record DB 52 (step S38). An example of the configuration of the medical record information d15 will be described later with reference to Fig. 15. After the processing of step S38, the training support processing by the training support function unit 20 ends.

[0091] [Example of visual examination result information configuration] Next, the visual inspection result information d11 will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of the configuration of the visual inspection result information d11. The visual examination result information d11 is information indicating the content of the visual examination performed by the dental hygienist U2 based on the training support information d13, and is transmitted from the tablet terminal 3 to the server 1 in step S31 of FIG.

[0092] As shown in FIG. 11, the visual examination result information d11 has the following items: "Examination Date," "Visual Examination," "Plaque," and "Pocket." The "Examination Date" item stores information about the examination date when the visual examination was performed by dental hygienist U2. The "Visual Examination" item stores information about the correspondence between the position of each tooth in the oral cavity and the condition of the tooth.

[0093] The "plaque" item stores information relating to the position of each tooth in the oral cavity and the state of plaque. The "pocket" item stores information on the correspondence between the position of each tooth in the oral cavity and the depth of the pocket. The visual inspection result information d11 is not limited to the example shown in FIG. 11, and may include other information.

[0094] [Example of medical record DB registration information configuration] Next, the medical record DB registration information d16 will be described with reference to Fig. 12. Fig. 12 is a diagram showing an example of the configuration of the medical record DB registration information d16. The medical record DB registration information d16 is information that is read from the medical record DB 52 in order for the DB writing unit 213 to generate the medical record information d15 in step S38 of FIG.

[0095] As shown in FIG. 12, the medical record DB registration information d16 has the items "examination history" and "treatment history." The examination history item stores information on the history of examinations that have been performed on the patient. The treatment history item stores information on the history of examinations that have been performed on the patient. In the example shown in FIG. 12, the treatment history information is composed of information on the treatment date, chief complaint, location, and procedure. Note that in the example shown in FIG. 12, the medical record DB registration information d16 is composed of the most recent examination history and treatment history, but the present invention is not limited to this. The medical record DB registration information d16 may also be composed of a predetermined number of past examination histories and treatment histories.

[0096] [Example of instructional support prompt configuration] Next, the training support prompt d12 will be described with reference to Fig. 13. Fig. 13 is a diagram showing an example of the configuration of the training support prompt d12.

[0097] As shown in Figure 13, the first line of the instruction support prompt d12 contains the following sentence to assign a role to the instruction support AI 22: "You are one of Japan's top dentists. You will now instruct the patient on oral care." Next, the following sentence to assign a task to the instruction support AI 22 is included: "Taking into consideration the patient's date of birth, gender, reason for visit, interview results, test results, test history, and treatment history, point out any changes in the patient's oral condition and devise instruction content to improve the patient's oral health."

[0098] Furthermore, although not shown in Figure 13 due to space limitations, the text specifying the restrictions includes a sentence such as, "Please avoid technical terms as much as possible and use words that patients can understand. If technical terms or names of instruments are used, please attach a URL of content that explains them (such as the dental clinic's blog or video site)." Finally, the patient's date of birth, gender, reason for visit, interview results, test results, test history, and treatment history are listed as information about the patient for whom the instruction support information d13 is created. The information from the date of birth to the interview results is information contained in the reservation DB registration information d6, the test results are information contained in the visual examination result information d11, and the test history and treatment history are information contained in the medical record DB registration information d16.

[0099] By inputting such a training support prompt d12, the training support AI 22 can create and output training support information d13 according to the patient information specified in the prompt. As shown in the example of FIG. 13, there are cases where instructions are given to the training support AI 22 such as, "When using technical terms or names of instruments, please attach a URL of content explaining them (such as a dental clinic blog or video site)." In such cases, the prompt creation unit 212 may add correspondence information between the term and the URL for explaining that term to the training support prompt d12. Furthermore, the training support prompt d12 shown in FIG. 13 is an example, and the training support prompt d12 may have a different sentence structure from that shown in FIG. 12 and may include different information.

[0100] [Example of configuration of instruction support information] Next, the training support information d13 created by the training support AI 22 will be described with reference to Fig. 14. Fig. 14 is a diagram showing an example of the configuration of the training support information d13. As shown in FIG. 14, the instruction support information d13 includes instruction content according to the patient's condition, such as "strengthening plaque control," "reviewing diet," and "regular dental visits."

[0101] For example, the item "Strengthening plaque control" states, "I brush my teeth three times a day and also use floss." This statement was generated based on the answer "I brush my teeth and floss three times a day after meals" included in the appointment interview response information d4.

[0102] Also, in the "Strengthening Plaque Control" section, it says, "Pay attention to the tooth marked ┘2, which has had a lot of plaque buildup in the past. Brushing your teeth after meals is good, but there may be areas that are not brushed properly." This statement was generated based on the plaque-related information in the visual examination result information d11.

[0103] Although not shown in FIG. 14 due to space limitations, the "Review your diet" item may include, for example, the following sentence: "You started feeling pain from a cavity two weeks ago, so consuming sugary drinks and acidic drinks may be contributing to this. Try to reduce snacking as much as possible and eat foods that are gentle on your teeth. -We recommend reducing the frequency of sweets intake. Avoid acidic drinks (carbonated drinks, juice, etc.) and use a straw when drinking to avoid direct contact with your teeth.

[0104] Although not shown in FIG. 14 due to space limitations, the following sentences, for example, are written in the "regular dental visits" section. To prevent and detect cavities and periodontal disease early, have regular checkups every 3-4 months. It is especially important to manage the risk in areas where plaque is likely to accumulate by having regular cleanings at the dentist and having your plaque score checked."

[0105] Furthermore, in the training support information d13, terms that are not generally familiar or technical terms such as "plaque score," "residual root tooth," and "tact brush" are associated with URL information for explanation.

[0106] In this way, since the training support information d13 includes appropriate training content suited to the patient's current condition, even an inexperienced dental hygienist can provide appropriate training to the patient by referring to the training support information d13. Moreover, since the training support information d13 is written into the medical record DB 52 by the data input / output unit 211, the dental hygienist U2 can save the trouble of recording the training content. Furthermore, since the content of the training and treatment by the dental hygienist U2 is written into the medical record DB 52, it becomes possible to easily share information with other dental hygienists U2, dentists U3, etc.

[0107] [Example of medical record information configuration] Next, the medical record information d15 will be described with reference to Fig. 15. Fig. 15 is a diagram showing an example of the configuration of the medical record information d15. The medical record information d15 is information that is written into the medical record DB 52 by the DB writing unit 213 of the medical record creation unit 21 in step S38 of Fig. 10. As shown in FIG. 15, the medical record information d15 has the following fields: "Name," "Sex," "Date of Birth," "Email Address," "Date of Visit," "Reason for Visit," "Questionnaire Results," "Visual Examination," "Plaque," "Pocket," and "Instruction Content." Information from the name to the questionnaire results is information contained in the reservation DB registration information d6. Information on inspection, plaque, and pocket is information contained in the visual examination result information d11, and information on instruction content is information contained in the instruction support information d13.

[0108] The prompt creation unit 212 of the medical record creation unit 21 may write an instruction to refer to the AI's extended learning data in the training support prompt d12 shown in Fig. 13. The AI's extended learning data includes, for example, learning data in which the state of the patient's oral cavity obtained by visual examination is associated with sentences predefined in a medical record system (not shown).

[0109] For example, in the extended learning data, the visual examination result "There is a lot of plaque between the teeth" is associated with the instruction content "Brush the adjacent surfaces thoroughly." In this case, the instruction support AI 22 can generate appropriate instruction content corresponding to the condition of the patient's oral cavity as the instruction support information d13. Examples of sentences that can be associated with the condition of the patient's oral cavity and learned by the extended learning data include the following:

[0110] We will introduce you to the Bass method of tooth brushing. · We will introduce you to the scrubbing method of brushing your teeth. · We will introduce you to the Stillman method of tooth brushing. · We will introduce you to the Charters method of tooth brushing. Brush the transitional tooth area thoroughly. Brush the angled teeth thoroughly. -Brush crowded teeth thoroughly. Brush your wisdom teeth thoroughly. · Brush erupting teeth thoroughly. Thoroughly brush the area where the prosthesis is placed. Thoroughly polish the adjacent surfaces. Polish the root surface thoroughly. Brush the occlusal surfaces thoroughly. Brush the cervical area thoroughly.

[0111] [Example of business record screen configuration] Next, the configuration of the business record screen Sc2 will be described with reference to Fig. 16. Fig. 16 is a diagram showing an example of the configuration of the business record screen Sc2. The business record screen Sc2 is a screen displayed on the tablet terminal 3, and is a screen on which dental hygienist U2 records the results of the visual examination, the contents of the instructions, etc.

[0112] As shown in FIG. 16, a training AI button Bn2 is provided in the upper right corner of the business record screen Sc2. When pressing of the training AI button Bn2 is detected, a training support information display screen Sc21 is displayed on the tablet terminal 3. The training support information display screen Sc21 is a screen that displays training support information d13. In the example shown in FIG. 16, a sentence is displayed at the top of the training support information display screen Sc21: "Based on the information of 'Test Taro,' we have generated the content of the training you should provide. We recommend that you focus on the following points in particular." By displaying this sentence, dental hygienist U2 can understand that information to support training for the patient named "Test Taro" is displayed in the area below.

[0113] The content of the training support information d13 is displayed in the area below. In FIG. 16, due to space limitations, some of the information in the training support information d13 is omitted from the illustration, but all of the content of the training support information d13 is displayed on the training support information display screen Sc21. By checking the content of the training support information d13, dental hygienist U2 can provide appropriate guidance to the patient. Therefore, even dental hygienist U2 with little experience or knowledge can provide patient U1 with guidance at the same high level as a dental hygienist with extensive experience.

[0114] Below the display area of ​​the training support information d13, a button Bn3 with the words "Transfer to medical record" is provided. When pressing of this button Bn3 is detected, the contents of the training support information d13 displayed on the training support information display screen Sc21 are transcribed into the medical record. Therefore, the dental hygienist U2 does not need to record the contents of the instruction given to the patient by handwriting or manual input. Furthermore, when pressing of the "Transfer to medical record" button Bn3 is detected, the training support information d13 is transmitted from the data input / output unit 211 to the mobile terminal 2 operated by the patient.

[0115] [SNS screen configuration example] Next, the SNS screen Sc3 on which the training support information d13 is displayed will be described with reference to Fig. 17. Fig. 17 is a diagram showing an example of the configuration of the SNS screen Sc3 displayed on the mobile terminal 2. As shown in Figure 17, a message from "Chuo Dental Clinic" is displayed on the SNS screen Sc3. This message is based on the instruction support information d13. This message includes advice based on the patient's current condition, predictions of how the condition in the oral cavity will change if proper care is not provided, and specific care information to prevent the condition from worsening.

[0116] Specifically, the following sentences are written as comments that are in line with the patient's current situation. 1. Strengthening plaque control I brush my teeth three times a day and also floss, but I need to be careful about tooth ┘2, which had a lot of plaque in the past. I brush my teeth well after meals, but there is a possibility that some areas may not have been brushed properly. Therefore, I recommend the following: Proper brushing technique: Be sure to brush carefully, especially in areas where plaque tends to accumulate, such as the gum line and between the teeth.

[0117] Furthermore, although not shown in FIG. 17 due to space limitations, the following sentences are written as comments that are in line with the patient's current condition. "· Consider using an electric toothbrush, as it can remove plaque more effectively. · Use floss and interdental brushes together: If you are already using floss, consider using interdental brushes in areas with high plaque scores. It seems you have a residual root, so please take good care of it with a tact brush.

[0118] When patients see these messages, they understand that the instructions are tailored to them and feel more responsible for the care outlined in the instructions.

[0119] Additionally, in the instruction messages displayed on the SNS screen Sc3, URL links are attached to terms such as "plaque score," "residual root teeth," and "tact brush," so that if patients come across a term they do not understand, they can check the meaning of the term on the linked website.

[0120] <Aftercare treatment> [Aftercare procedure] Next, the aftercare processing by the aftercare function section 30 will be described with reference to Fig. 18. Fig. 18 is a flowchart showing an example of the procedure of the aftercare processing by the aftercare function section 30.

[0121] First, the data input / output unit 311 of the aftercare execution unit 31 of the aftercare function unit 30 acquires medical record information d21 related to all patients from the medical record DB 52 at a predetermined timing, such as daily or weekly (step S41). The medical record information d21 acquired by the data input / output unit 311 from the medical record DB 52 in step S41 is information in which the details of treatment have been added to the information written into the medical record DB 52 by the DB writing unit 213 of the medical record creation unit 21 in step S38 of Fig. 10. An example of the configuration of the medical record information d21 will be described later with reference to Fig. 19.

[0122] Next, the prompt creation unit 312 creates an aftercare prompt d22 based on the medical record information d21 acquired in step S41, and outputs the aftercare prompt d22 to the aftercare AI 32 (step S42). Then, the aftercare AI 32 generates aftercare interview information d23 based on the aftercare prompt d22, and outputs the information to the aftercare execution unit 31 (step S43).

[0123] Next, the data input / output unit 311 transmits an aftercare message based on the aftercare questionnaire information d23 to the mobile terminal 2 of the patient U1 for whom "questionnaire not required" has not been specified in the aftercare questionnaire information d23 (step S44). Then, the data input / output unit 311 receives input of aftercare questionnaire answer information d24, which is an answer to the aftercare message, from the mobile terminal 2 of the patient U1 (step S45). Next, the DB writing unit 313 writes the aftercare question answer information d24 received in step S45 into the aftercare DB 53 (step S46). After the process of step S46, the aftercare process by the aftercare function unit 30 ends.

[0124] [Example of medical record information configuration] Next, the medical record information d21 acquired by the data input / output unit 311 of the aftercare implementation unit 31 from the medical record DB 52 will be described with reference to Fig. 19. Fig. 19 is a diagram showing an example of the configuration of the medical record information d21.

[0125] As shown in FIG. 19, the medical record information d21 has the following fields: "Name," "Gender," "Date of Birth," "Email Address," and "Medical Record Content." The "Medical Record Content" field includes the following fields: patient visit date, reason for visit, interview results, visual examination, plaque, pockets, instruction content, and treatment. Items other than treatment are the same as those in the medical record information d15 described with reference to FIG. 15, so duplicate explanations will be omitted. The "Treatment" field describes the content of the treatment performed on the patient by dentist U3.

[0126] [Example of aftercare prompt structure] Next, the aftercare prompt d22 will be described with reference to Fig. 20. Fig. 20 is a diagram showing an example of the configuration of the aftercare prompt d22.

[0127] As shown in Figure 20, the first line of the aftercare prompt d22 contains the following sentence to assign a role to the aftercare AI32: "You are one of Japan's top dental advisors. You will now send the patient a medical interview for aftercare after their last visit. The interview should contain a maximum of five questions."Then, the sentence to assign a task to the aftercare AI32 is "Consider the patient's name, date of birth, gender, date of visit, reason for visit, interview results, visual examination, plaque, pockets, instructions, and treatment, and then come up with a medical interview to inquire about their condition afterwards and check whether any abnormalities have occurred over time."

[0128] Next, as a sentence specifying restrictions, there is written, "Also, at the end of the medical interview, please be sure to add a sentence encouraging the patient to 'feel free to come to the hospital immediately if they notice anything abnormal.'" Next, although not shown in Fig. 20 due to space limitations, there is written, as an instruction for the aftercare AI 32 to select patients to whom the aftercare interview information d23 is to be sent, "Furthermore, after fully considering the trends in the vast amount of dental treatment that you have learned, if you determine that today is not the optimal time to conduct an interview, counting from the date of the visit, output 'No interview necessary.'"

[0129] Furthermore, although not shown in FIG. 20 due to space limitations, the following sentence is written regarding the "optimal timing for medical interview" in the sentence defining the above constraints: "For example, after a tooth extraction, bleeding tends to stop within three days at the latest, so the best time to interview is three days later. Or, after orthodontic appliance removal, patients' teeth tend to return to their original position one year later, so the best time to interview is one year later."

[0130] Below this text, the patient's name, date of birth, sex, date of visit, reason for visit, interview results, visual examination, plaque, pocket, instruction content, and treatment information are written.

[0131] By providing such an instruction in the aftercare prompt d22, the aftercare AI 32 can set, for example, a patient who has not visited the clinic for several years after the first visit, or a patient who has recently visited the clinic, as "no medical interview required." In other words, patients who are set as "no medical interview required" can be excluded from the recipients of aftercare messages. This prevents aftercare messages from being sent to patients who are not expected to receive aftercare messages. Furthermore, since dentists, dental hygienists, dental assistants, etc. do not need to determine or set whether or not to send aftercare messages, this saves the dentist, etc., time, and also prevents missed aftercare messages from being sent.

[0132] It is also possible that even if a patient desires to receive an aftercare message, the "unanswered" state may continue without receiving a response. To prevent such a patient from being determined to be "unnecessary for medical interview," the prompt generation unit 312 may add an instruction to the aftercare prompt d22 to "resend all to patients who have not responded." Alternatively, the data input / output unit 311 of the aftercare execution unit 31 may extract patients who have not responded at a predetermined interval and transmit the aftercare interview information d23 to the mobile terminal 2 of the extracted patient.

[0133] [Example of aftercare interview information] Next, the aftercare questionnaire information d23 created by the aftercare AI 32 will be described with reference to Fig. 21. Fig. 21 is a diagram showing an example of the configuration of the aftercare questionnaire information d23. As shown in Figure 21, the first line of the aftercare interview information d23 contains the message, "Dear Test Taro, you last visited us on 2024-10-10. How are you doing since then?" This section identifies the patient's name and the date and time of the visit.

[0134] Next, the following text informs the patient that an aftercare consultation will be conducted: "We would like to confirm your progress in implementing the 'oral self-care method' that our hygienist explained to you at your last visit, so please take the time to answer the following questions." This is followed by a detailed consultation tailored to each patient, based on their symptoms and the details of the procedure.

[0135] The specific contents of the medical interview include, for example, the following sentences: "1. Do you experience any pain or sensitivity after tooth decay treatment? Yes, I still have it (please tell me the area and symptoms) No, nothing in particular 2. Regarding brushing your teeth, flossing, and using interdental brushes, do you continue to brush your teeth and use floss and interdental brushes after meals? Yes, I continue to do it every day Sometimes I forget It hasn't been done at all."

[0136] Furthermore, although it is omitted from FIG. 21 due to space limitations, the following sentence is also included: 3. Regarding improving your diet, have you reduced your intake of sweet foods and acidic drinks? Yes, it is reducing No, not much has changed 4. Have you tried to reduce snacking or change the way you drink beverages (e.g., using a straw)? 5. Regarding plaque and periodontal pocket care, are there any symptoms that concern you, such as swollen or bleeding gums or bad breath? Yes, there is (please be specific) No, nothing in particular If pain or discomfort persists or new symptoms appear, Please don't hesitate to come to us right away. We will do our best to support you."

[0137] [Example of aftercare questionnaire response information] Next, the aftercare medical questionnaire answer information d24 will be described with reference to FIG. 22. The aftercare medical questionnaire answer information d24 is a patient's answer to the aftercare message, and is transmitted from the patient's mobile terminal 2 to the server 1. FIG. 22 is a diagram showing an example of the configuration of the aftercare medical questionnaire answer information d24. As shown in FIG. 22, the aftercare medical questionnaire answer information d24 includes the answer "No, nothing in particular" to the question "1. Do you experience pain or sensitivity after caries treatment?". Also, the answer "I sometimes forget" to the question "2. Regarding tooth brushing, flossing, and interdental brushing, do you continue to brush your teeth and use floss and interdental brushes after meals?" is included.

[0138] Furthermore, although not shown in FIG. 22 due to space limitations, the aftercare medical interview response information d24 also includes the following information: 3. Regarding improving your diet, have you reduced your intake of sweets and acidic drinks? →Yes, it has been reduced. > 4. Have you tried to reduce snacking or change the way you drink beverages (e.g., using a straw)? → The number of times I eat snacks remains the same, but I try to eat snacks with less sugar, such as dried squid. > 5. Are you experiencing any symptoms such as swollen or bleeding gums or bad breath? → I still feel a little swollen. My bad breath may be worse than before.

[0139] [Example of aftercare information structure] Next, the aftercare information d25 will be described with reference to Fig. 23. Fig. 23 is a diagram showing an example of the configuration of the aftercare information d25. The aftercare information d25 is information that the DB writing unit 313 of the aftercare implementation unit 31 writes into the aftercare DB 53 in step S46 of Fig. 18. As shown in Fig. 23, the aftercare information d25 is composed of the following items: "Name," "Gender," "Date of Birth," "Destination," "Sent Date and Time," "Questionnaire Content," "Answer Date and Time," and "Answer."

[0140] The "Destination" field stores information about the patient's email address to which the aftercare questionnaire information d23 was sent. The "Sent Date and Time" field stores information about the date and time when the aftercare questionnaire information d23 was sent to the patient's mobile terminal 2. The "Questionnaire Content" field stores the content of the aftercare questionnaire information d23. The "Answer Date and Time" field stores information about the date and time when the aftercare questionnaire answer information d24 was sent from the patient's mobile terminal 2. The "Answer" field stores the content of the aftercare questionnaire answer information d24.

[0141] [Example of aftercare interview screen configuration] Next, an aftercare inquiry screen displayed on the mobile terminal 2 of patient U1 will be described with reference to Fig. 24 and Fig. 25. Fig. 24 is a diagram showing an example of the configuration of an aftercare inquiry screen Sc41 when an aftercare message is sent by email. Fig. 25 is a diagram showing an example of the configuration of an aftercare inquiry screen Sc42 when an aftercare message is sent via SNS.

[0142] The aftercare questionnaire screen Sc41 shown in Figure 24 shows the state in which the patient has entered answers to each question in the aftercare message. The aftercare questionnaire information d23 that forms the basis of the aftercare message is created based on the aftercare prompt d22, which includes information on the patient's answers to the appointment questionnaire, instructions given to the patient, and details of treatment. Therefore, since the aftercare message does not include general content that is of little relevance to the patient, the patient can perceive the message as something that concerns them, and feel the need to write a reply, and can reply.

[0143] Specifically, the aftercare interview screen Sc41 contains the following text as aftercare interview information d23: Subject: Re: Aftercare after visit Thank you for contacting us after your treatment. The answers are below. > 1. Do you experience any pain or sensitivity after tooth decay treatment? →No, nothing in particular > 2. Regarding brushing, flossing, and using interdental brushes, Brushing your teeth after meals and using floss and interdental brushes Are you continuing? → Sometimes I forget > 3. Regarding improving your diet, try reducing sweets and acidic drinks. Have you reduced the frequency of your intake? →Yes, it has been reduced.

[0144] Furthermore, although not shown in FIG. 24 due to space limitations, the following sentence is also written as the aftercare interview information d23: 4. Have you tried to reduce snacking or change the way you drink beverages (e.g., using a straw)? → The number of times I eat snacks remains the same, but I try to eat snacks with less sugar, such as dried squid. > 5. Are you experiencing any symptoms such as swollen or bleeding gums or bad breath? → I still feel like it's swollen. My bad breath may be worse than before.

[0145] Furthermore, by sending the aftercare message in email format and receiving the response in the form of a reply, patient U1 can freely write without any restrictions about his / her symptoms, the status of aftercare, etc. Therefore, the amount of responses that patient U1 can include in the aftercare questionnaire response information d24 can be increased.

[0146] The aftercare questionnaire screen Sc42 shown in FIG. 25 shows an example in which aftercare messages are displayed in the form of a social networking service chat. In the example shown in FIG. 25, multiple-choice answers such as "Yes, I still have questions" or "No, nothing in particular" are displayed after the message corresponding to the aftercare questionnaire. Therefore, patient U1 can easily answer questions about his or her condition by selecting one of the answer buttons. Note that while the example shown in FIG. 25 shows an example in which an answer is selected by pressing a button, the present invention is not limited to this. For example, after detecting the pressing of a button, a free text field may be displayed in which a detailed answer regarding the content of the answer indicated by the button press can be entered.

[0147] By acquiring the aftercare questionnaire answer information d24 via an interface such as the aftercare questionnaire screens Sc41 and Sc42, the dental clinic can grasp information on symptoms that the patient has experienced between now and the next diagnosis, without waiting for the next visit. Therefore, dentist U3, who views the aftercare questionnaire answer information d24, can use it as a reference for formulating a treatment plan for the next visit, or identify the pathology causing the symptoms and take measures. Furthermore, if patient U1 experiences any worrisome symptoms, he or she can report the symptoms to the dental clinic via the aftercare questionnaire screens Sc41 and Sc42, etc., which gives him or her peace of mind.

[0148] In addition, the aftercare questionnaire answer information d24 may be utilized for gamification in order to improve and maintain the patient's motivation for treatment. Gamification refers to the application of game elements to services that do not primarily have the purpose of being games, thereby improving the motivation of users and strengthening their loyalty. For example, an answer content evaluation AI or the like may be provided that evaluates the content of the aftercare questionnaire answer information d24 and outputs an evaluation result. The answer content evaluation AI can output a better evaluation result the higher the proportion of answers indicating that the patient is taking positive measures among the number of answers in the aftercare questionnaire answer information d24.

[0149] Let's take a closer look at gamification. For example, if an aftercare questionnaire contains five questions and three are answered positively, the response evaluation AI generates a message such as, "You're 3 out of 5! Work hard to get two more points before your next treatment! In particular, don't forget to floss, as plaque tends to accumulate between your teeth." By displaying such a report card-like message on the aftercare questionnaire screen Sc42, etc., regarding the patient's efforts, it is expected that the patient's motivation to engage in care will be improved or maintained. Alternatively, by providing an achievement such as "Achieved a silver medal! (3 / 5 points)," patients can approach care with a game-like feeling and be more proactive in answering the aftercare questionnaire.

[0150] <Recall processing> [Recall processing procedure] Next, the recall process by the recall function unit 40 will be described with reference to FIG. FIG. 26 is a flowchart showing an example of the procedure of the recall process by the recall function unit 40.

[0151] First, the terminal device 4 receives a selection of the patient U1 to be recalled from the dentist U3 (step S51). The dentist U3 selects, for example, a patient who has been in the recall for 3 months, 6 months, or 12 months since the last visit as the patient U1 to be recalled. Based on the selection in step S51, the terminal device 4 transmits the recall transmission target patient information d31 to the server 1. The processing of step S51 may be performed automatically by the recall execution unit 41 based on the number of days that have passed since the last visit.

[0152] Next, the data input / output unit 411 of the recall execution unit 41 acquires the medical record information d32 corresponding to the selected patient U1 from the medical record DB 52, and acquires the aftercare information d33 from the aftercare DB 53 (step S52). The medical record information d32 acquired by the data input / output unit 411 in step S52 will be described in detail with reference to Fig. 28, and the aftercare information d33 will be described in detail with reference to Fig. 30.

[0153] Next, the prompt creation unit 412 creates a recall prompt d34 based on the medical record information d32 and aftercare information d33, and outputs it to the recall AI 42 (step S53). Then, the recall AI 42 generates recall information d35 based on the recall prompt d34, and outputs it to the recall execution unit 41 (step S54). Next, the data input / output unit 411 of the recall execution unit 41 transmits the recall information d35 to the patient's mobile terminal 2 (step S55). After the processing of step S55, the recall processing by the recall function unit 40 ends.

[0154] [Example of medical record information configuration] Next, the medical record information d32 will be described with reference to Fig. 27. Fig. 27 is a diagram showing an example of the configuration of the medical record information d32. As shown in Fig. 27, the medical record information d32 has the following items: "Email address," "Date of visit," "Reason for visit," "Questionnaire results," "Visual examination," "Plaque," "Pocket," "Instruction content," and "Treatment." Each of these items has already been explained, so duplicate explanations will be omitted here.

[0155] [Example of aftercare information structure] Next, the aftercare information d33 will be described with reference to Fig. 28. Fig. 28 is a diagram showing an example of the configuration of the aftercare information d33. As shown in Fig. 28, the aftercare information d33 has the following fields: "Name," "Sex," "Date of Birth," "Answer Date and Time," and "Answer." The "Answer Date and Time" field stores information on the date and time when the aftercare questionnaire answer information d24 (see Fig. 22) was transmitted from the patient's mobile terminal 2. The "Answer" field stores the aftercare questionnaire answer information d24.

[0156] [Example of recall prompt configuration] Next, the recall prompt d34 will be described with reference to Fig. 29. Fig. 29 is a diagram showing an example of the configuration of the recall prompt d34.

[0157] As shown in Figure 29, the first line of the recall prompt d34 contains the following sentence to assign a role to the recall AI 42: "You are one of Japan's top dentists. We will now send you a direct message to encourage the patient to return (become a repeat patient)." The following sentence is also included to assign a task to the recall AI 42: "Consider the patient's name, gender, date of birth, responses from the most recent patient, and the contents of the most recent medical record, and then create a message that will encourage the patient to visit, such as by explaining that the condition of their oral cavity may have changed due to a long gap between visits and that leaving it untreated poses a risk to their health."

[0158] Next, the following sentence specifies the restrictions: "The output must be in Japanese, and a greeting using a seasonal word must be included at the beginning. Dental terminology must be replaced with words that even a layman can understand. The main text must be as concise as possible, at around 150 characters."

[0159] Next, the patient's name, date of birth, and gender are listed as information about the patient for whom the recall AI 42 is generating the recall information d35. Next, the "Latest Response" and "Latest Medical Record" information are listed. The "Latest Response" item contains the information listed in the aftercare information d33, and the "Latest Medical Record" item contains the information listed in the medical record information d32.

[0160] By inputting such a recall prompt d34, the recall AI 42 can generate recall information d35 that is appropriate for the patient and encourages them to visit the hospital, based on the patient's attributes, the answers to the aftercare questionnaire, and the examination information.

[0161] [Example of recall information structure] Next, the recall information d35 will be described with reference to Fig. 30. Fig. 30 is a diagram showing an example of the configuration of the recall information d35. As shown in Fig. 30, the recall information d35 is composed of the text of a recall message. Specifically, following the greeting "Autumn is deepening and the number of chilly days is increasing, isn't it?", the text states how many days have passed since the last visit and asks how the patient is doing, saying "You last came to the clinic for treatment for a cavity, but it's been about three months since then. Have you had any pain since then?"

[0162] Next, there is a sentence written based on the answers to the aftercare questionnaire, stressing the importance of regular care: "In the aftercare questionnaire sent after treatment, you mentioned concerns about swollen gums and bad breath. Leaving these for a long period of time can lead to the progression of periodontal disease." Next, there is a sentence written based on the contents of the consultation, stressing the importance of care: "During your last examination, you were found to have some plaque buildup, so please make sure to take good care of your teeth on a daily basis."

[0163] Finally, the message reads, "Periodontal bacteria can lead to systemic diseases, so although we understand you are busy, it is important that you come to our clinic early to check your condition and receive appropriate care. Please feel free to make an appointment." This informs customers of the benefits that can be obtained by visiting our clinic and encourages them to visit.

[0164] [Example of recall screen configuration] Next, the recall screen Sc5 displayed on the patient's mobile terminal 2 will be described with reference to FIG. 31. FIG. 31 is a diagram showing an example of the configuration of the recall screen Sc5 when a recall message is sent via SNS. As shown in FIG. 31, the recall screen Sc5 displays recall information d35 (recall message). Due to space limitations, some of the recall information d35 is not shown in FIG. 31, but the recall screen Sc5 in FIG. 31 also displays content similar to the content of the recall information d35 shown in FIG. 30.

[0165] By checking the message displayed on the recall screen Sc5, patients can learn that three months have passed since their last visit, that leaving any symptoms of concern untreated could lead to the progression of periodontal disease, that plaque buildup was detected during the examination, and that their current condition will be checked by visiting the clinic. This message is not a generalized message, but is tailored to the patient's own condition. Therefore, by reading this message, patients will realize the need to make an appointment and can make one.

[0166] Note that the recall prompt d34 may include an instruction to include the URL (Uniform Resource Locator) of the screen for making an appointment in the recall information d35, thereby including a link to the URL of the screen for making an appointment in the recall information d35. By performing such processing, the patient U1 can easily make an appointment by selecting the link included in the recall message and opening the screen for making an appointment.

[0167] <Oral advisor system according to modified example> The oral advisor system 100A according to the modified example has a resume function. The resume function temporarily stores the information generated by the appointment interview AI 12, the instruction support AI 22, the aftercare AI 32, and the recall AI 42, as well as the information required for generating information by these AIs, in a resume database, and reads and outputs the information on the screen when work is resumed.

[0168] Here, the background to why the resume function is needed will be explained. In dental clinics, work is frequently interrupted to attend to patients. For example, while dental hygienist U2 is providing instruction to a patient, an emergency patient may be required, causing dental hygienist U2 to stop the instruction midway. In such cases, dental hygienist U2 may hand over the input work of the instruction content to another person while in the middle of inputting the instruction content into tablet terminal 3. The handover of input work can occur not only when attending to an emergency patient, but also in other situations.

[0169] If work is interrupted midway and the information before the interruption is not saved anywhere, it may result in missing information that needs to be entered, or duplicated information that has already been entered. Dental treatment requires accurate recording of detailed information, but if problems like the ones mentioned above occur, the accuracy of recording information will decrease.

[0170] Furthermore, if the answers generated by the appointment interview AI 12, the instruction support AI 22, the aftercare AI 32, and the recall AI 42 are lost due to an interruption in the process, each AI must generate an answer again. For example, if a patient interrupts the process of inputting answers to the appointment interview AI 12 while the answers generated by the appointment interview AI 12 are not retained, the appointment interview AI 12 must generate an answer again. Furthermore, the time it takes for the appointment interview AI 12 to generate an answer becomes waiting time for patient U1. In this case, patient U1 may stop answering the appointment interview or aftercare interview altogether.

[0171] In order to improve the "patient experience (customer experience)," it is extremely important to minimize the amount of time patients are required to spend in a clinic. However, when resuming a suspended task, the data entered before the interruption must be reconfirmed, when a different staff member takes over, the data entered by the previous staff member must be confirmed, or responses must be regenerated using AI, causing patients to wait. This increases the time between treatment and payment within the clinic, and the time required to create responses to appointment and aftercare inquiries outside the clinic. The occurrence of such situations can lead to increased patient turnover.

[0172] To solve these problems, the oral advisor system 100A according to the modified example provides a resume function.

[0173] [Outline of Oral Advisor System] First, the configuration of an oral advisor system 100A according to a modified example of the present invention will be described with reference to Fig. 32. Fig. 32 is a diagram showing an example of a schematic configuration of the oral advisor system 100A.

[0174] The oral advisor system 100A shown in Figure 32 differs from the oral advisor system 100 shown in Figure 1 in that the oral advisor system 100A includes a reservation interview AI resume DB 61, a training support AI resume DB 62, an aftercare AI resume DB 63, and a recall AI resume DB 64.

[0175] 32, the DB writing unit 113 of the reservation creation unit 11 saves the reservation information d1 sent from the mobile terminal 2 and the reservation inquiry information d3 generated by the reservation inquiry AI 12 in the reservation inquiry AI resume DB 61, which is a DB that temporarily holds this information. The timing of saving the reservation information d1 to the reservation inquiry AI resume DB 61 is each time character input is detected, and the timing of saving the reservation inquiry information d3 is after generation by the reservation inquiry AI 12 is completed.

[0176] The DB writing unit 213 of the medical record creation unit 21 saves the reservation DB registration information d6, the visual examination result information d11 transmitted from the tablet terminal 3, the training support information d13 generated by the training support AI 22, and the medical record DB registration information d16 stored in the medical record DB 52 in the training support AI resume DB 62. The training support AI resume DB 62 is a DB that temporarily holds this information. The timing of saving the visual examination result information d11 in the training support AI resume DB 62 is each time character input is detected, and the timing of saving the training support information d13 and the medical record DB registration information d16 is after the training support AI 22 has completed generating the training support information d13.

[0177] The DB writing unit 313 of the aftercare execution unit 31 stores the medical record information d21 acquired from the medical record DB 52, the aftercare questionnaire information d23 generated by the aftercare AI 32, and the aftercare questionnaire answer information d24 sent from the mobile terminal 2 in the aftercare AI resume DB 63. The aftercare AI resume DB 63 is a DB (an example of a post-examination questionnaire information resume database) that temporarily holds this information. The aftercare questionnaire answer information d24 is stored each time character input is detected, and the aftercare questionnaire information d23 and medical record information d21 are stored after the aftercare AI 32 has completed generating the aftercare questionnaire information d23.

[0178] The DB writing unit 413 of the recall execution unit 41 saves the medical record information d32 corresponding to patient U1 obtained from the medical record DB 52, the aftercare information d33 obtained from the aftercare DB 53, and the recall information d35 generated by the recall AI 42 in the recall AI resume DB 64. The recall AI resume DB 64 is a DB that temporarily holds this information. The timing for saving each piece of information in the recall AI resume DB 64 is after the recall AI 42 has completed generating the recall information d35.

[0179] Other functions of the advisor system 100A according to the modified example are the same as those of the oral advisor system 100 shown in FIG. 1, so a duplicated description will be omitted.

[0180] [Configuration of AI resume database for appointment interviews] Next, the configuration of the appointment inquiry AI resume DB 61 will be described with reference to Fig. 33. Fig. 33 is a diagram showing an example of the configuration of the appointment inquiry AI resume DB 61. The appointment inquiry AI resume DB 61 is made up of appointment information d1 (see Fig. 5) and appointment inquiry information d3 (see Fig. 7).

[0181] Of the items constituting the appointment interview AI resume DB61 shown in Figure 33, the items "Name," "Visit Date and Time," "Gender," "Date of Birth," "Email Address," and "Reason for Visit" are items included in appointment information d1. The "Appointment Interview Information" item is an item shown in appointment interview information d3. The specific contents of each of these items have already been explained with reference to Figures 5 and 7, respectively, so duplicate explanations will be omitted.

[0182] [Structure of the AI ​​resume database for teaching support] Next, the configuration of the training support AI resume DB 62 will be described with reference to FIG. Fig. 34 is a diagram showing an example of the configuration of the training support AI resume DB 62. The training support AI resume DB 62 is composed of reservation DB registration information d6, visual examination result information d11 (see Fig. 11), medical record DB registration information d16 (see Fig. 12), and training support information d13 (see Fig. 14), which are stored in the reservation DB 51 (see Fig. 9).

[0183] Of the items constituting the training support AI resume DB62 shown in Figure 34, the items "Name," "Visit Date and Time," "Gender," "Date of Birth," "Email Address," "Reason for Visit," and "Interview Results" are items included in the reservation DB registration information d6. The items "Examination Date," "Visual Examination," "Plaque," and "Pocket" are items shown in the visual examination result information d11. The items "Examination History" and "Treatment History" are items included in the medical record DB registration information d16. The item "Training Support Information" is an item shown in the training support information d13. The specific contents of each of these items have been explained with reference to Figures 9, 11, 12, and 14, respectively, so duplicate explanations will be omitted.

[0184] [Aftercare AI Resume DB Configuration] Next, the configuration of the aftercare AI resume DB 63 will be described with reference to Fig. 35. Fig. 35 is a diagram showing an example of the configuration of the aftercare AI resume DB 63. The aftercare AI resume DB 63 is made up of medical record information d21 (see Fig. 19), aftercare interview information d23 (see Fig. 21), and aftercare interview answer information d24 (see Fig. 22).

[0185] Of the items constituting the aftercare AI resume DB63 shown in Figure 35, the items "Name," "Date and time of visit," "Gender," "Date of birth," "Email address," and "Reason for medical record" are items included in the medical record information d21. The item "Aftercare interview information" is an item shown in the aftercare interview information d23. The item "Aftercare interview answer information" is an item shown in the aftercare interview answer information d24. The specific contents of each of these items have already been explained with reference to Figures 19, 21, and 22, respectively, so duplicate explanations will be omitted.

[0186] [Configuration of Recall AI Resume DB] Next, the configuration of the recall AI resume DB 64 will be described with reference to FIG. Fig. 36 is a diagram showing an example of the configuration of the recall AI resume DB 64. The recall AI resume DB 64 is made up of aftercare information d33 (see Fig. 28), medical record information d32 (see Fig. 27), and recall information d35 (see Fig. 30).

[0187] Of the items constituting the recall AI resume DB64 shown in FIG. 36, the items "Name," "Gender," "Date of Birth," "Response Date and Time," and "Response" are items included in the aftercare information d33. The items "Email Address," "Date of Visit," "Reason for Visit," "Questionnaire Results," "Visual Examination," "Plaque," "Pocket," "Instruction Content," and "Treatment" are items included in the medical record information d32. The "Recall Information" item is an item shown in the recall information d35. The specific contents of each of these items have been explained with reference to FIGS. 28, 27, and 30, respectively, and therefore will not be explained again.

[0188] [Resume processing by appointment inquiry function] Next, the resume processing by the appointment inquiry function unit 10 will be described with reference to Fig. 37 and Fig. 38. Fig. 37 is a flowchart showing an example of the procedure for saving appointment inquiry information by the appointment inquiry function unit 10, and Fig. 38 is a flowchart showing an example of the procedure for reading appointment inquiry information by the appointment inquiry function unit 10.

[0189] (Storage process of medical interview information at the time of reservation) First, the process of storing the appointment medical interview information by the appointment medical interview function unit 10 will be described with reference to FIG. First, the appointment inquiry AI 12 of the appointment inquiry function unit 10 creates appointment inquiry information d3 and outputs it to the appointment creation unit 11 (step S61). This process is the same as the process of step S23 in Figure 4. Next, the DB writing unit 113 of the appointment creation unit 11 saves the appointment inquiry information d3 and appointment information d1 output from the appointment inquiry AI 12 in step S61 in the appointment inquiry AI resume DB 61 (step S62). After processing step S62, the appointment inquiry information saving process by the appointment inquiry function unit 10 ends. In this way, by storing all information related to the appointment inquiry function in the appointment inquiry AI resume DB 61, the necessary information can be retrieved immediately when work is resumed, thereby speeding up the processing response. Furthermore, even if the work is interrupted during the generation of the appointment consultation information d3 and it becomes necessary to regenerate the appointment consultation information d3, the appointment consultation AI 12 can generate the appointment consultation information d3 quickly and without missing any information using the information stored in the appointment consultation AI resume DB 61. In the process of saving each piece of information to each resume DB described below, similar effects can be obtained because all information related to each function is similarly stored in the resume DB.

[0190] (Reading process of medical interview information at the time of reservation) Next, the process of reading out the appointment inquiry information by the appointment inquiry function unit 10 will be described with reference to FIG. First, the appointment creation unit 11 of the appointment interview function unit 10 determines whether the visit date and time and email address entered on the appointment screen Sc1 (see FIG. 8) have been sent from the mobile terminal 2 (step S71). By entering the visit date and time and email address on the appointment screen Sc1 of the mobile terminal 2, the patient U1 can resume answering the appointment interview that was interrupted.

[0191] If it is determined in step S71 that the visit date and time and email address have not been sent (step S71: NO), the appointment creation unit 11 repeats the determination in step S71. On the other hand, if it is determined in step S71 that the visit date and time and email address have been sent (step S71: YES), the data input / output unit 111 of the appointment creation unit 11 reads out appointment information d1 and appointment interview information d3 from the appointment interview AI resume DB 61, and displays the appointment interview information d3 on the appointment screen Sc1 (step S72). After processing step S72, the appointment interview function unit 10 ends the process of reading out the appointment interview information.

[0192] [Resume processing by the instruction support function unit] Next, the resume processing by the training support function unit 20 will be described with reference to Fig. 39 and Fig. 40. Fig. 39 is a flowchart showing an example of the procedure for saving training support information by the training support function unit 20, and Fig. 40 is a flowchart showing an example of the procedure for reading training support information by the training support function unit 20.

[0193] (Storage processing of instruction support information) First, the process of saving training support information by the training support function unit 20 will be described with reference to FIG. First, the training support AI 22 of the training support function unit 20 creates training support information d13 and outputs it to the medical record creation unit 21 (step S81). This process is the same as the process of step S34 in Fig. 10. Next, the DB writing unit 213 of the medical record creation unit 21 saves the training support information d13 output from the training support AI 22 in step S81, the reservation DB registration information d6, the visual examination result information d11, and the medical record DB registration information d16 in the training support AI resume DB 62 (step S82). After the process of step S82, the training support information saving process by the training support function unit 20 ends.

[0194] (Reading process of training support information) Next, the process of reading out training support information by the training support function unit 20 will be described with reference to FIG. First, the medical record creation unit 21 of the training support function unit 20 determines whether or not the patient's name information has been sent from the tablet terminal 3 (step S91). By inputting the name of the patient U1 into the business record screen Sc2 or the like displayed on the tablet terminal 3, the dental hygienist U2 can resume the interrupted input work of the training support information, treatment details, etc.

[0195] If it is determined in step S91 that the name of patient U1 has not been transmitted (step S91: NO), the medical record creation unit 21 repeats the determination of step S91. On the other hand, if it is determined in step S91 that the name of patient U1 has been transmitted (step S91: YES), the data input / output unit 211 of the medical record creation unit 21 reads out the reservation DB registration information d6, the visual examination result information d11, the medical record DB registration information d16, and the training support information d13 from the training support AI resume DB 62, and transmits the training support information d13 to the tablet terminal 3 to display it on the screen (step S92). After the processing of step S92, the training support information reading process by the training support function unit 20 ends.

[0196] [Resume processing by aftercare function unit] Next, the resume processing by the aftercare function unit 30 will be described with reference to Fig. 41 and Fig. 42. Fig. 41 is a flowchart showing an example of the procedure for the aftercare information saving processing by the aftercare function unit 30, and Fig. 42 is a flowchart showing an example of the procedure for the aftercare information reading processing by the aftercare function unit 30.

[0197] (Storage and processing of aftercare information) First, the process of storing aftercare information by the aftercare function unit 30 will be described with reference to FIG. First, the aftercare AI 32 of the aftercare function unit 30 creates aftercare questionnaire information d23 and outputs it to the aftercare execution unit 31 (step S101). This process is the same as the process of step S43 in FIG. 18. Next, the DB writing unit 313 of the aftercare execution unit 31 saves the aftercare questionnaire information d23, medical record information d21, and aftercare questionnaire answer information d24 output from the aftercare AI 32 in step S101 in the aftercare AI resume DB 63 (step S102). After the process of step S102, the aftercare information saving process by the aftercare function unit 30 ends.

[0198] (Aftercare information reading process) Next, the process of reading out aftercare information by the aftercare function unit 30 will be described with reference to FIG. First, the aftercare execution unit 31 of the aftercare function unit 30 determines whether or not information regarding access to the aftercare questionnaire screen Sc41 by the patient U1 has been transmitted from the mobile terminal 2 (step S111). By redisplaying the aftercare questionnaire screen Sc41 on the mobile terminal 2, the patient U1 can resume answering the interrupted aftercare questionnaire.

[0199] If it is determined in step S111 that the information for accessing the aftercare questionnaire screen Sc41 has not been transmitted (NO in step S111), the aftercare execution unit 31 repeats the determination in step S111. On the other hand, if it is determined in step S111 that the information for accessing the aftercare questionnaire screen Sc41 has been transmitted (YES in step S111), the data input / output unit 311 of the aftercare execution unit 31 reads out the medical record information d21, the aftercare information d23, and the aftercare questionnaire answer information d24 from the aftercare AI resume DB 63, and displays this aftercare information on the aftercare questionnaire screen Sc41 of the mobile terminal 2 (step S112).

[0200] Next, the aftercare execution unit 31 determines whether or not answers to all the aftercare questions displayed on the aftercare question screen Sc41 have been entered (step S113). If it is determined in step S113 that there are any blank answers (NO in step S113), the DB writing unit 313 of the aftercare execution unit 31 saves the medical record information d21, the aftercare interview information d23, and the aftercare interview answer information d24 in the aftercare AI resume DB 63 (step S114). After processing step S114, the aftercare execution unit 31 returns to step S113 and makes another determination.

[0201] On the other hand, if it is determined in step S113 that all answers have been entered (YES in step S113), the DB writing unit 313 of the aftercare execution unit 31 saves the medical record information d21, the aftercare questionnaire information d23, and the aftercare questionnaire answer information d24 in the aftercare DB 53 as aftercare information (step S115). After the processing of step S115, the aftercare information reading process by the aftercare function unit 30 ends.

[0202] [Resume processing by the recall function] Next, the resume processing by the recall function unit 40 will be described with reference to Figures 43 and 44. Figure 43 is a flowchart showing an example of the procedure for the processing of saving recall information by the recall function unit 40, and Figure 44 is a flowchart showing an example of the procedure for the processing of reading recall information by the recall function unit 40.

[0203] (Storage process of recall information) First, the process of saving recall information by the recall function unit 40 will be described with reference to FIG. First, the recall AI 42 of the recall function unit 40 creates recall information d35 based on the recall prompt d34 and outputs it to the recall execution unit 41 (step S121). This process is the same as the process of step S54 in Figure 26. Next, the recall execution unit 41 saves the recall information d35, the medical record information d32, and the aftercare information d33 output from the recall AI 42 in step S121 in the recall AI resume DB 64 (step S122). After the process of step S122, the recall information saving process by the recall function unit 40 ends.

[0204] (Reading recall information) Next, the process of reading out recall information by the recall function unit 40 will be described with reference to FIG. First, the recall execution unit 41 of the recall function unit 40 determines whether the name of the patient U1 has been transmitted from the terminal device 4 (step S131). The dentist U3 can resume the interrupted work of creating the recall information by inputting the name of the patient U1 to whom the recall information is to be transmitted on the screen displayed on the terminal device 4.

[0205] If it is determined in step S131 that the name of patient U1 has not been transmitted (NO in step S131), the recall execution unit 41 repeats the determination in step S131. On the other hand, if it is determined in step S131 that the name of patient U1 has been transmitted (YES in step S131), the data input / output unit 411 of the recall execution unit 41 reads out the medical record information d32, aftercare information d33, and recall information d35 from the recall AI resume DB 64, and transmits the recall information d35 to the terminal device 4 to display it on the screen (step S132). After the processing of step S132, the recall information reading process by the recall function unit 40 ends.

[0206] In the above-described modified example, the appointment interview function unit 11 stores the appointment interview information d3 generated by the appointment interview AI 12 in the appointment interview AI resume DB 61 together with the appointment information d1. Then, when patient U1 resumes answering the appointment interview that was interrupted and patient information (visit date and time, email address) is sent from the mobile terminal 2, the appointment interview information d3 is read from the appointment interview AI resume DB 61 and sent to the mobile terminal 2, where it is displayed on the appointment screen Sc1. Therefore, according to the modified example, even if patient U1 interrupts the appointment work, the appointment interview AI 12 does not need to recreate the appointment interview information d3, so it is possible to prevent patient U1 from having to wait due to the appointment interview information d3 being recreated.

[0207] Furthermore, according to the resume function of the aftercare function unit 30, the aftercare questionnaire information d23 generated by the aftercare AI 32 is saved in the aftercare AI resume DB 63 at the time of creation. Then, when the patient U1 resumes answering the interrupted aftercare questionnaire, the aftercare questionnaire information d23 is read from the aftercare AI resume DB 63 and sent to the mobile terminal 2, and is displayed on the SNS screen Sc3. Therefore, according to the modified example, even if the patient U1 interrupts answering the aftercare questionnaire, the aftercare AI 32 does not need to recreate the aftercare questionnaire information d23, and therefore it is possible to prevent the patient U1 from having to wait due to the aftercare questionnaire information d23 being recreated.

[0208] Therefore, according to the modified example of the present invention, the time that patient U1 is confined by answering medical questionnaires when making an appointment or aftercare outside the clinic can be shortened. If the patient's confinement time or waiting time is prolonged, it is predicted that the patient's "patient experience (customer experience)" will also be reduced, and such an experience will increase the patient dropout rate. According to the modified example of the present invention, it is also possible to prevent an increase in the patient dropout rate from dental clinics.

[0209] Furthermore, according to the resume function of the training support function unit 30, the training support information d13 generated by the training support AI 22 is saved in the training support AI resume DB 62 at the time of creation. Then, when the dental hygienist U2 resumes the interrupted recording of the training support information on the task record screen Sc2, the training support information d13 is read from the training support AI resume DB 62 and sent to the tablet terminal 3, where it is displayed on the task record screen Sc2. Therefore, according to the modified example, even if the dental hygienist U2 interrupts the recording of the training support information, the training support AI 22 does not need to re-create the training support information d15, and therefore it is possible to prevent the dental hygienist U2 from having to wait while the training support information d13 is re-created.

[0210] Furthermore, according to the resume function of the recall function unit 40, the recall information d35 generated by the recall AI 42 is saved in the recall AI resume DB 64 at the time of its creation. Then, when the dentist U3 resumes the interrupted selection of the patient U1 to whom the aftercare questionnaire is to be sent, the recall information d35 is read from the recall AI resume DB 64, sent to the terminal device 4, and displayed on the screen of the terminal device 4. Therefore, according to the modified example, even if the dentist U3 interrupts the selection of the patient U1 to whom the aftercare questionnaire is to be sent, the recall AI 42 does not need to recreate the recall information d35, and therefore it is possible to prevent the dentist U3 from having to wait due to the recall information d35 being recreated.

[0211] The dentist U3 and dental hygienist U2 are often interrupted by the need to treat patients. In such cases, the resume function according to the modified example allows them to quickly return to the interrupted work.

[0212] Furthermore, when dentist U3 or dental hygienist U2 handles an emergency or performs an unscheduled procedure, the dentist U3 or dental hygienist U2 may hand over the work to another dentist or dental hygienist. In this case, too, the modified example can prevent the person who took over from starting the work over again from the beginning or resuming the work from the wrong point. Therefore, it is possible to prevent errors or omissions in recording instruction support information, or the wrong patient selection to send recall information due to insufficient communication or insufficient interpretation during the handover.

[0213] Furthermore, in clinics, dentist U3 and dental hygienist U2 may enter only the "items" into the patient chart or business record screen Sc2 to first determine the billing amount, and then enter the details later. In this case, without a resume function, there is a possibility that the information entered before the interruption and the information entered after the interruption will not be consistent. However, according to a modified example of the present invention, interruption of work prevents the AI, such as the training support information d13, from being recreated by the training support AI 22. The information before the interruption is reliably displayed after the work is resumed. This allows dentist U3 and dental hygienist U2 to easily and safely interrupt their work to determine the billing amount. This further reduces the waiting time for the patient U1 to pay.

[0214] In the above-described modified example, the appointment information d1, the visual examination result information d11, and the aftercare questionnaire answer information d24 are automatically recorded in the appointment interview AI resume DB 61, the training support AI resume DB 62, and the aftercare AI resume DB 63, respectively, when character input is detected. However, the present invention is not limited to this. For example, a "resume button" for instructing a user to suspend work may be provided on the appointment screen Sc1 (see FIG. 8) on which the appointment information d1 is input, the business record screen Sc2 (see FIG. 16) on which the visual examination result information d11 is input, the aftercare questionnaire screen Sc41 (see FIG. 24), or the aftercare questionnaire screen Sc42 (see FIG. 25). Then, when pressing the resume button is detected, the appointment information d1, the visual examination result information d11, or the aftercare questionnaire answer information d24 may be saved in the respective resume DBs.

[0215] In the above-described embodiment, an example was given in which the appointment inquiry AI 12, the training support AI 22, the aftercare AI 32, and the recall AI 42 are provided in the server 1, but the present invention is not limited to this. AIs provided by a service provider or the like may be used as each of these AIs. In this case, a single AI may be used that does not separate the functions of the appointment inquiry AI 12, the training support AI 22, the aftercare AI 32, and the recall AI 42.

[0216] In the above-described embodiment, the medical record transcribed by the medical record creation unit 21 is an example of a dental medical record (electronic medical record), but the present invention is not limited to this. The medical record according to the present invention may be applied to medical records for medical treatment by doctors, nurses, physical therapists, chiropractors, etc. Furthermore, the oral advisor system according to the present invention can be applied not only to dentistry but also to various medical departments such as medicine, pharmacy, and veterinary medicine.

[0217] In the above embodiment, the appointment interview AI 12, the training support AI 22, the aftercare AI 32, and the recall AI 42 are all implemented by AI, but the present invention is not limited to this. Some or all of these functional units may be implemented by methods other than AI, such as programming.

[0218] Furthermore, the oral advisor system 100 according to this embodiment is configured so that the aftercare function unit 30 can provide appropriate aftercare to the patient. For this reason, the oral advisor system 100 according to this embodiment is configured to include all of the components of the appointment interview function unit 10, the training support function unit 20, and the aftercare function unit 30. However, from the perspective of being able to appropriately create appointment interviews, training support for dental hygienists, and recalls for patients, the oral advisor system according to the present invention may also adopt the following configuration.

[0219] (1) A reservation interview creation instruction unit that generates and outputs a reservation interview creation instruction that includes at least the patient's attribute information and information on the reason for the patient's visit to a learning model that has learned examples of examination details and treatment details for patient cases, and that is an instruction to create a reservation interview; and and an input / output unit that transmits the appointment interview generated in the learning model based on the appointment interview creation instruction to a terminal device operated by the patient. Oral Advisor System.

[0220] (2) a training support information creation instruction unit that generates and outputs a training support information creation instruction for creating training support information, which is information that supports instruction for patients, based on information including at least patient attribute information and information on the reason for the patient's visit, for a learning model that has learned examples of examination details and treatment details for patient cases; an input / output unit that transmits the training support information generated in the learning model based on the training support generation instruction to a patient-operated terminal device operated by the patient; Oral Advisor System.

[0221] Furthermore, the above-described embodiments provide detailed and specific descriptions of the configurations of the devices (server, tablet terminal, terminal device) and systems (oral advisor system) in order to clearly explain the present invention, and are not necessarily limited to those having all of the configurations described.

[0222] 1 and 2, the control lines or information lines indicated by solid lines or arrows are those considered necessary for explanation, and do not necessarily show all control lines or information lines in the product. In reality, it can be considered that almost all components are interconnected. [Explanation of symbols]

[0223] 1...server, 2...mobile terminal, 3...tablet terminal, 4...terminal device, 10...reservation interview function unit, 11...reservation creation unit, 12...reservation interview AI, 13...DB writing unit, 20...instruction support function unit, 21...medical record creation unit, 22...instruction support AI, 23...DB writing unit, 30...aftercare function unit, 31...aftercare execution unit, 32...aftercare AI, 33...DB writing unit, 40...recall function unit, 41...recall execution unit, 42...recall AI, 51...reservation DB, 52...medical record DB, 53...aftercare DB , 61... Reservation interview AI resume DB, 62... Guidance support AI resume DB, 63... Aftercare AI resume DB, 64... Recall AI resume DB, 100... Oral advisor system, 111... Data input / output unit, 112... Prompt creation unit, 113... DB writing unit, 211... Data input / output unit, 212... Prompt creation unit, 213... DB writing unit, 311... Data input / output unit, 312... Prompt creation unit, 313... DB writing unit, 411... Data input / output unit, 412... Prompt creation unit

Claims

1. A recall AI that includes a learning model that has learned dental cases; a recall information creation instruction unit that generates a recall information creation instruction for creating recall information that encourages patients to make appointments for hospital visits based on information including at least patient attribute information and information on medical examinations performed on the patients, and outputs the recall information creation instruction to the recall AI; a recall information input / output unit that transmits the recall information generated in the recall AI based on the recall information generation instruction to a patient-operated terminal device operated by the patient. Oral Advisor System.

2. The recall information creation instruction unit includes, in the recall information creation instruction, information on the patient's medical record and an instruction to generate a message encouraging the patient to visit a hospital based on the content of the medical record. The oral advisor system of claim 1 .

3. The recall information creation instruction unit instructs the generation of a sentence to encourage the patient to visit the hospital, the sentence informing the patient that the state of the oral cavity of the patient may have changed due to a long interval between consultations. The oral advisor system of claim 2 .

4. The recall information creation instruction unit instructs the generation of a message to encourage the patient to visit a hospital, informing the patient that leaving symptoms untreated will result in a risk of harm to their health. The oral advisor system of claim 2 .

5. The learning model is a large-scale language model, and the recall information creation instruction is configured by a prompt. The oral advisor system of claim 2 .

6. The recall information creation instruction unit includes, in the recall information creation instruction, information on a post-examination interview, which is an interview conducted after the patient's examination, and an instruction to generate a sentence based on the content of the post-examination interview. The oral advisor system of claim 2 .

7. A post-examination interview AI that includes a learning model that has learned dental cases, a post-examination interview creation instruction unit that generates and outputs a post-examination interview creation instruction for generating the post-examination interview based on the attribute information of the patient; and a post-examination interview information input / output unit that transmits the post-examination interview generated by the post-examination interview AI based on the post-examination interview generation instruction to the patient operation terminal device. The oral advisor system of claim 6.

8. The learning model is a large-scale language model, and the post-examination questionnaire creation instructions are configured by prompts. The oral advisor system of claim 7.

9. The system further includes a recall information resume database that temporarily stores the recall information generated by the recall AI, When the interrupted work for generating recall information in the dentist-operated terminal device is resumed, the recall information input / output unit reads the recall information from the recall information resume database and transmits the recall information to the dentist-operated terminal device. The oral advisor system of claim 2 .

10. A recall AI including a learning model that has learned dental cases, and a recall information creation instruction unit; A recall information generating method by an oral advisor system having a recall information input / output unit, the recall information creation instruction unit generates a recall information creation instruction for generating recall information that prompts patients to make an appointment for a hospital visit based on information including at least patient attribute information and information on examinations performed on the patients, and outputs the recall information creation instruction to the recall AI; and a procedure in which the recall information input / output unit transmits the recall information generated in the recall AI based on the recall information generation instruction to a patient-operated terminal device operated by the patient. Methods for generating recall information.

Images