Support device, support system, support method and program

Abstract

To more appropriately support pharmacists in their business.SOLUTION: A support server 30 includes a target information acquisition section 254, a guidance content inference section 256, and a candidate information generation section 257. The target information acquisition section 254 acquires target information to be considered in pharmaceutical guidance to a patient. The guidance content inference section 256 infers guidance content of the pharmaceutical guidance to the patient on the basis of the target information acquired by the target information acquisition section 254. The candidate information generation section 257 generates candidate information that is a candidate to be included in a pharmaceutical history of the pharmaceutical guidance to the patient on the basis of the guidance content inferred by the guidance content inference section 256.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an assistance device, an assistance system, an assistance method, and a program. [Background technology]

[0002] BACKGROUND ART Conventionally, information processing techniques for supporting the work of pharmacists in pharmacies have been known. For example, Patent Document 1 describes that data on a patient's medication history is managed in a database, and when dispensing medicine to a patient, the database is referenced to provide medication instructions based on the medication history, etc. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-122253 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in order to properly operate the database, pharmacists must sequentially input data related to medication histories based on the content of the medication instructions they have actually provided. The task of inputting data related to medication histories is cumbersome and requires a great deal of effort from the pharmacist. Therefore, in order to reduce this effort, it is desirable to provide more appropriate support for the work of pharmacists.

[0005] An object of the present invention is to more appropriately support the work of pharmacists. [Means for solving the problem]

[0006] In order to solve the above problem, an assistance device according to one aspect of the present invention comprises: a target information acquisition means for acquiring target information to be considered in providing pharmaceutical guidance to a patient; an instruction content inference means for inferring instruction content of pharmaceutical instruction for the patient based on the target information acquired by the target information acquisition means; a candidate information generating means for generating candidate information to be included in a medication history of pharmaceutical guidance for the patient based on the guidance content inferred by the guidance content inferring means; Equipped with. [Effects of the Invention]

[0007] According to the present invention, it is possible to more appropriately support the work of pharmacists. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a schematic diagram showing an overview of a process in which a support system according to the present embodiment supports data registration in a medication history (medication instruction history) in pharmaceutical instruction (medication instruction) for a patient. [Figure 2] 1 is a diagram showing a system configuration of a support system 1 according to an embodiment of the present invention. [Figure 3] FIG. 8 is a diagram showing the hardware configuration of an information processing device 800 that constitutes each device. [Figure 4] 2 is a block diagram showing the functional configuration of a terminal device 10. FIG. [Figure 5] FIG. 10 is a schematic diagram showing an example of a medication instruction selection screen. [Figure 6] FIG. 10 is a schematic diagram illustrating an example of a questionnaire display screen. [Figure 7] FIG. 10 is a schematic diagram showing an example of a medical interview display screen. [Figure 8] FIG. 10 is a schematic diagram showing an example of a medication instruction selection screen. [Figure 9] FIG. 10 is a schematic diagram illustrating an example of an approval reception screen. [Figure 10] FIG. 10 is a schematic diagram showing another example of the approval reception screen. [Figure 11] FIG. 2 is a block diagram showing the functional configuration of a pharmacy computer 20. [Figure 12] FIG. 2 is a block diagram showing the functional configuration of the support server 30. [Figure 13] 10 is a schematic diagram showing data relating to medication instruction statements among data relating to candidate information stored in candidate information DB 277. FIG. [Figure 14] 10 is a flowchart showing the flow of target information acquisition processing executed by the terminal device 10. [Figure 15] 10 is a flowchart showing the flow of information management processing executed by the pharmacy computer 20. [Figure 16] 10 is a flowchart showing the flow of medication history registration support processing executed by the support server 30. [Figure 17] FIG. 8 is a block diagram showing the functional configuration of a stand-alone information processing device 800 having a medication history registration support function. [Figure 18] 10 is a flowchart showing the flow of a modified example of the medication history registration support process executed by the support server 30. [Figure 19] 1 is a schematic diagram showing an example of a medication instruction selection screen 60 displayed on the terminal device 10 or the support server 30. FIG. [Figure 20] 10 is a schematic diagram showing an example of a training home screen 70 displayed on the terminal device 10 or the support server 30. FIG. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0010] [Processing overview] FIG. 1 is a schematic diagram showing an outline of a process in which a support system according to an embodiment of the present invention supports data registration in a medication history (medication instruction history) in pharmaceutical instruction (medication instruction) for a patient. As shown in FIG. 1, the support system uses AI (Artificial Intelligence) to infer medication instruction content based on information to be considered in medication instruction (hereinafter referred to as "target information"), such as data on prescriptions issued to patients who visit the pharmacy and data on questionnaire results answered by the patients. The support system also generates candidate information to be included in the medication history (e.g., medication instruction statements corresponding to the inferred medication instruction content) based on the inferred medication instruction content. The support system then presents the generated candidate information (e.g., by displaying or outputting a sound) to a pharmacist who is the manager of medication instruction. The support system then receives approval for registering the candidate information from the pharmacist and registers the approved candidate information in the medication history.

[0011] In this way, the support system generates candidate information by making inferences based on target information such as prescription data, and presents this candidate information to the pharmacist. Therefore, the pharmacist only needs to confirm the content of the candidate information when inputting all or at least part of the data related to the medication history (e.g., medication instructions) and decide whether or not to approve the registration of the data in the medication history. In other words, the support system can reduce the pharmacist's workload of inputting data related to the medication history. Therefore, the support system according to the embodiment of the present invention can more appropriately support the work of pharmacists.

[0012] As shown by the dashed lines in Figure 1, the support system can also use data other than prescription data and questionnaire result data as target information. For example, the support system can infer the content of medication instructions using, in addition to the prescription data issued to the patient and questionnaire result data, data on the results of the medical interview conducted by the pharmacist with the patient (such as the interview results and the pharmacist's impressions from the patient) as target information. Furthermore, when providing pharmaceutical instructions to a patient at their second or subsequent visits, the support system can infer the content of this medication instruction using, in addition to the prescription data issued to the patient and questionnaire result data, data on the previous medication instruction and the current medical interview result as target information.

[0013] The support system may infer the content of medication instruction while providing the instruction, but it can also infer the content of medication instruction even after the instruction has been completed and a medical fee statement (receipt) has been issued. In this case, as shown by the dashed line in Figure 1, the support system can infer the content of medication instruction by further referring to the data of the medical fee statement (receipt) issued in response to the medication instruction, in addition to the above-mentioned target information. Furthermore, in any of the above cases, the support system can also infer the content of medication instructions on a rule-based basis instead of (or in addition to) inferring the content of medication instructions using AI. The above is an overview of the processing performed by the support system. Next, more specific details of the support system for realizing such processing will be described below.

[0014] [System Configuration] FIG. 2 is a diagram showing the system configuration of the support system 1 according to one embodiment of the present invention. The support system 1 in this embodiment is used to support the work of pharmacists in dispensing pharmacies. For example, as described above with reference to Fig. 1, the support system 1 is used to reduce the work of pharmacists inputting data into medication histories by inferring the content of medication instructions given to patients who bring in prescriptions.

[0015] As shown in FIG. 2, the support system 1 includes a terminal device 10, a pharmacy computer 20, and a support server 30. The terminal device 10, the pharmacy computer 20, the support server 30, and an external server such as a drug information database server that stores drug information including medication instructions are configured to be able to communicate with each other via a network 40 (such as the Internet). The terminal device 10 and the pharmacy computer 20 may be configured to be able to communicate with each other via a private network such as a Virtual Private Network (VPN). Although the figure shows one of each device, this is not limited to this. For example, there may be multiple pharmacy computers 20 corresponding to each of multiple pharmacies. Alternatively, there may be multiple terminal devices 10 corresponding to each of multiple pharmacists working at each of multiple pharmacies.

[0016] The terminal device 10 is operated by a pharmacist and is configured as an information processing device such as a tablet terminal or a PC (Personal Computer). The terminal device 10 displays various information to support the pharmacist's work when the pharmacist interviews a patient, and accepts input of various information from the pharmacist. For example, the terminal device 10 displays the contents of a questionnaire that the pharmacist administers to the patient, and accepts input of questionnaire responses (questionnaire results) from the pharmacist. The terminal device 10 also displays the contents of the interview (interview contents) when the pharmacist interviews (interviews) the patient, and accepts input of the interview results (interview results) from the pharmacist. Furthermore, the terminal device 10 accepts input of impressions (impressions) that the pharmacist receives from the patient when they meet. Furthermore, the terminal device 10 displays candidate information generated in the medication history registration support process described below. Furthermore, the terminal device 10 receives an input of an approval result (including a request to register the approved candidate information in the medication history) for the registration of the displayed candidate information in the medication history from the pharmacist.

[0017] The pharmacy computer 20 is configured with an information processing device such as a server computer that executes processes related to the operations of the dispensing pharmacy. The pharmacy computer 20 also has a function of a prescription computer (receipt computer function) and a function of managing patient medication histories (medical history management function). In connection with these functions, the pharmacy computer 20 also manages various data. For example, the pharmacy computer 20 manages various data such as patient attributes for multiple patients, prescriptions for multiple patients, a medication history that is a history of medication instructions provided by pharmacists to patients and prescribed medications, medical interview results (interview results and impressions, etc.), patient interview content, and information about medications handled at the pharmacy. It is assumed that the medication history managed by the pharmacy computer 20 includes information used as a medication history management record for insurance dispensing. However, the medication history is not limited to this, and may also include other information used at the pharmacy, etc. The pharmacy computer 20 then executes the information management process described below to transmit the various information it manages to the support server 30 and update the various information it manages using the various data transmitted from the support server 30.

[0018] The support server 30 is configured with an information processing device such as a server computer having a function for supporting the work of pharmacists (work support function). The support server 30 receives various data managed by the pharmacy computers 20 installed in multiple pharmacies in order to support the work of pharmacists. The support server 30 also manages the received various data using a group of databases (including a medication history database) similar to those of the pharmacy computers 20. In other words, the support server 30 acquires information (part or all) held by the pharmacy computers 20 installed in multiple pharmacies and stores it in order to execute the medication history registration support process.

[0019] The support server 30 also executes a medication history registration support process. In this medication history registration support process, the support server 30 accepts support requests for medication history registration (such as requests to provide candidate information and requests to register candidate information approved by a pharmacist in the medication history) from terminal devices 10 installed in multiple pharmacies. In response to these support requests, the support server 30 infers medication instruction content by referring to target information such as prescription data, questionnaire data answered by the patient, and medical interview results (such as interview results and impressions given by the patient to the pharmacist), as well as medical fee statement (receipt) data, and generates candidate information based on the inferred medication instruction content. The support server 30 then transmits the generated candidate information to the terminal device 10. When the support server 30 receives approval of the candidate information from the pharmacist who referenced the candidate information from the terminal device 10, it registers the candidate information in the medication history database it manages. By this medication history registration support process, the medication history database managed by the support server 30 is updated to the latest content, and in synchronization with this, the medication history database managed by the pharmacy computer 20 is also updated to the latest content. In other words, the support server 30 and the pharmacy computers 20 (if there are multiple computers, each of them) can share various data including medication history.

[0020] While this sharing of various data can be achieved by any method, the following description assumes, as an example, that the support server 30 and the pharmacy computer 20 comply with a common specification. This common specification is not particularly limited, but may be, for example, NSIPS (New Standard Interface of Pharmacy-system Specifications) (registered trademark). By complying with a common specification (e.g., NSIPS), data sharing between the support server 30 and the existing pharmacy computer 20 can be easily achieved. Furthermore, data sharing can be achieved without relying on specific specifications (e.g., specific specifications established by a certain manufacturer). If an external server also has a medication history database, the medication history database managed by the support server 30 and the pharmacy computer 20 may be synchronized, and the medication history database managed by the external server may also be updated to the latest content. In other words, various data may also be shared with the external server. In this case, it is assumed that the sharing of various data complies with the common specification, as with the pharmacy computer 20.

[0021] [Hardware configuration] Next, the hardware configuration of each device in the support system 1 will be described. As described above, each device included in the support system 1 is configured by an information processing device such as a PC, a server computer, or a tablet terminal, and has the same basic configuration.

[0022] FIG. 3 is a diagram showing the hardware configuration of an information processing device 800 that constitutes each device. As shown in Figure 3, the information processing device 800 that constitutes each device includes a CPU (Central Processing Unit) 811, a ROM (Read Only Memory) 812, a RAM (Random Access Memory) 813, a bus 814, an input unit 815, an output unit 816, a memory unit 817, a communication unit 818, a drive 819, and an imaging unit 820.

[0023] The CPU 811 executes various processes according to a program recorded in the ROM 812 or a program loaded from the storage unit 817 into the RAM 813 . The RAM 813 also stores data and the like necessary for the CPU 811 to execute various processes.

[0024] The CPU 811, ROM 812, and RAM 813 are connected to one another via a bus 814. To the bus 814, an input unit 815, an output unit 816, a storage unit 817, a communication unit 818, a drive 819, and an imaging unit 820 are connected.

[0025] The input unit 815 is made up of various buttons and the like, and various information is input in response to instruction operations. The output unit 816 is composed of a display, a speaker, etc., and outputs images and sounds. The storage unit 817 is configured with a hard disk or a DRAM (Dynamic Random Access Memory), etc., and stores various data managed by each server. The communication unit 818 controls communication with other devices via the network 40 .

[0026] Removable media 831, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is appropriately loaded into the drive 819. A program read from the removable media 831 by the drive 819 is installed in the storage unit 817 as needed. The imaging unit 820 is configured by an imaging device equipped with a lens, an imaging element, etc., and captures a digital image of a subject. When the information processing device 800 is configured as the pharmacy computer 20 or the support server 30, it is possible to omit the imaging unit 820. When the information processing device 800 is configured as a tablet terminal, it is also possible to configure the input unit 815 using a touch sensor and place it over the display of the output unit 816, thereby providing a touch panel.

[0027] [Functional configuration] Next, the functional configuration of each device in the support system 1 will be described.

[0028] [Functional configuration of terminal device 10] FIG. 4 is a block diagram showing the functional configuration of the terminal device 10. As shown in FIG. As shown in FIG. 4, in the CPU 811 of the terminal device 10, a user interface display control unit (UI display control unit) 51, a target information acquisition unit 52, a support request unit 53, a candidate information acquisition unit 54, and an approval receiving unit 55 function.

[0029] The UI display control unit 51 controls the display of various input / output screens (hereinafter referred to as "UI screens") in various processes described later, based on information for displaying a user interface screen (hereinafter referred to as "UI information") received from the support server 30. For example, the UI display control unit 51 presents (for example, outputs and displays on a display) a screen for selecting a patient from whom target information is to be acquired in a target information acquisition process described later (hereinafter referred to as a "patient selection screen"), a screen for displaying the contents of a questionnaire that a pharmacist will administer to a patient in the target information acquisition process (hereinafter referred to as a "questionnaire display screen"), a screen for displaying interview contents (questionnaire items) when a pharmacist interviews a patient in the target information acquisition process (hereinafter referred to as a "medical interview display screen"), a screen for selecting medication instruction for which data such as a medication instruction statement is to be registered in a medication history registration support process (hereinafter referred to as a "medication instruction selection screen"), and a screen for displaying candidate information for receiving approval from a pharmacist in a medication history registration support process (hereinafter referred to as an "approval acceptance screen"), etc. Furthermore, the UI display control unit 51 transmits various pieces of information input on the UI screen to the support server 30. For example, the UI display control unit 51 transmits information identifying the patient selected on the patient selection screen, the questionnaire results input on the questionnaire display screen, the medical interview results input on the medical interview display screen, information identifying the medication instruction selected on the medication instruction selection screen, and the approval results input on the approval reception screen to the support server 30. The UI display control unit 51 may transmit the various pieces of information input on the UI screen (for example, approved candidate information, etc.) to the support server 30 and also to the pharmacy computer 20.

[0030] FIG. 5 is a schematic diagram showing an example of the patient selection screen. 5, the patient selection screen displays a list of patients corresponding to the patient attributes managed by the pharmacy computer 20, and the pharmacist selects a patient to interview (medical interview) from this list. For new patients, new patient attributes are registered on a registration screen (not shown).

[0031] FIG. 6 is a schematic diagram showing an example of a questionnaire display screen. As shown in Figure 6, the questionnaire display screen displays the contents of the questionnaire, including multiple-choice questions, and the patient enters the answers themselves, or the pharmacist enters the answers based on the patient's answers. The questionnaire contents displayed at this time are a series of questions set in common for all patients, and are used to identify patient attributes such as the patient's name, gender, medical history, and illnesses currently being treated.

[0032] Furthermore, FIG. 7 is a schematic diagram showing an example of a medical interview display screen. As shown in FIG. 7 , the medical interview display screen displays interview content (interview items) including multiple-choice questions, and the pharmacist inputs the interview results (interview results) based on the patient's answers. The displayed interview content is a series of questions selected according to patient attributes, and is determined for each patient, each prescription, or the number of interviews (e.g., whether it is the first interview or the second interview), etc. The medical interview display screen also has a free entry field for the pharmacist, allowing the pharmacist to freely enter any information the pharmacist noticed when interviewing the patient (e.g., physical impressions such as "lack of energy" or "pale complexion," or personality impressions such as "nervous personality" or "judgmental personality"). The pharmacist can also register data such as medication instruction statements corresponding to the medication instruction statements in the medical history without using the medication history registration support process. In this case, the data such as medication instruction statements is registered in the medical history using a registration screen (not shown).

[0033] Furthermore, FIG. 8 is a schematic diagram showing an example of the medication instruction selection screen. As shown in Figure 8, the medication instruction selection screen displays a list of each medication instruction included in the medication history managed by the pharmacy computer 20, and the pharmacist selects from this list the medication instruction for which they wish to request the generation of candidate information to be registered in the medication history.

[0034] Furthermore, FIG. 9 is a schematic diagram showing an example of an approval reception screen. As shown in FIG. 9, the approval reception screen displays a list of medication instruction sentences indicating the medication instruction content that a pharmacist (especially an experienced pharmacist) typically provides when providing medication instruction (hereinafter referred to as the "list of inferred medication instruction candidates"), and a list of medication instruction sentences indicating the general medication instruction content for prescribed drugs (hereinafter referred to as the "list of general medication instruction candidates"). Each of the medication instruction sentences included in the inferred medication instruction candidate list and the general medication instruction candidate list corresponds to candidate information generated corresponding to the medication instruction content estimated by the medication history registration support process. For example, each of the medication instruction sentences included in the inferred medication instruction candidate list represents results reflecting the effects, side effects, and drug interactions (contraindications for concomitant use) of dispensed drugs that a pharmacist (especially an experienced pharmacist) should explain to a patient for whom they are providing medication instruction, observation items that the pharmacist recalls for the patient for whom they are providing medication instruction, the guidance policy that the pharmacist anticipates when providing medication instruction, and indicators (points of focus) that the pharmacist recalls in the thought process when providing medication instruction. Each of the medication instruction sentences included in the list of general medication instruction candidates represents a general explanation selected in accordance with the medication prescribed according to the patient's prescription data.

[0035] In addition, a check box is displayed next to each medication instruction sentence, and medication instruction sentences for which the pharmacist has checked a check box are registered in the patient's medication history as a list of medication instruction sentences used in medication instruction (medication instruction results) after the pharmacist approves the registration to the medication history (for example, by pressing the ``Approve Registration to Medication History'' button shown in the figure). That is, in this embodiment, the candidate information includes at least medication instruction sentences corresponding to pharmaceutical instructions for the patient. The pharmacist's approval of registration to the medication history involves selecting medication instruction sentences to be approved from the medication instruction sentences included in the candidate information. In this case, check boxes corresponding to medication instruction sentences that the pharmacist is likely to check based on the likelihood output by inference may be pre-checked. Then, the pharmacist may uncheck medication instruction sentences that he or she does not consider necessary to register. In this way, in this embodiment, by being based on the approval operation of the pharmacist, it is possible to realize registration in the medication history while appropriately reflecting the judgment of the pharmacist who has the authority to register in the medication history.

[0036] FIG. 10 is a schematic diagram showing another example of the approval reception screen. As shown in FIG. 10 , if the candidate information includes a point that a pharmacist should take note of when approving the information, a predetermined warning message is displayed on the approval reception screen as shown in FIG. 9 . Examples of points that should be taken note of when approving the information include, for example, the prescription of a drug that requires the involvement of a specialist in pharmaceutical management for safety management (so-called high-risk drugs) or the patient having a specific chronic illness. When such points are included in the candidate information, a warning message corresponding to the points is displayed. The timing of displaying this predetermined warning message is not particularly limited. For example, it may be displayed when the pharmacist approves registration to the medication history (for example, by pressing the “Approve Registration to Medication History” button shown in the figure), to reconfirm whether or not approval is truly appropriate. Displaying such a predetermined warning message can prompt the pharmacist to take note of the points that should be taken note of when approving the information. In other words, the pharmacist's work can be more appropriately supported. In addition to displaying a warning message, attention may also be drawn to the point by, for example, using a special color for the “Approve Registration to Medication History” button, background display color, or font. Alternatively, attention may be drawn to the point by outputting a warning sound or a voice corresponding to the warning message. In other words, if the candidate information contains content that the pharmacist should take note of when approving, it is advisable to present the candidate information to the pharmacist in various ways (e.g., by displaying or outputting a sound) that differ from when such content is not contained.

[0037] Returning to FIG. 4 , the target information acquisition unit 52 acquires various types of target information that are to be considered in providing medication instructions to patients. As described above, the target information is information that is to be considered in providing pharmaceutical instructions to patients. For example, the target information acquisition unit 52 acquires data representing the contents of the prescription brought by the patient (prescription data), questionnaire result data including patient attribute data for identifying the patient, such as the name, age, medical history, and illness being treated of the patient who brought the prescription, and data on the medical interview results (interview results, impressions, etc.) entered by the pharmacist on the medical interview display screen. Note that the information acquired by the target information acquisition unit 52 is not limited to these, and it is also possible to acquire data on the patient's medication history, data on the contents of medication instructions from the patient's previous visit, data related to medical fees such as a medical fee statement, or data stored in an electronic medicine notebook.

[0038] The support request unit 53 sends a request for candidate information to the support server 30, along with information identifying the medication instructions for the subject for whom the pharmacist is requesting the generation of candidate information, selected by the pharmacist from the list described above with reference to Figure 8. The candidate information acquisition unit 54 acquires candidate information transmitted from the support server 30 in response to a request for candidate information transmitted by the support request unit 53. The candidate information acquired by the candidate information acquisition unit 54 includes data on a list of medication instruction sentences indicating medication instruction contents (list of inferred medication instruction candidates) and data on a list of general medication instruction sentences regarding prescribed drugs (list of general medication instruction candidates), as described above with reference to Fig. 9. In addition, if there is content that the pharmacist should take note of when approving, the candidate information includes this content to take note of in order to display a warning message as described above with reference to Fig. 10.

[0039] The approval receiving unit 55 receives an approval result (including a request to register the approved candidate information in the medication history) from the pharmacist who has received the candidate information, and transmits the received approval result to the support server 30.

[0040] [Functional configuration of pharmacy computer 20] FIG. 11 is a block diagram showing the functional configuration of the pharmacy computer 20. 11, a receipt management unit 151, a medication history management unit 152, and a database management unit (DB management unit) 153 function in CPU 811 of pharmacy computer 20. In addition, a patient attribute database (patient attribute DB) 171, a prescription database (prescription DB) 172, a medication history database (medication history DB) 173, a medical interview result database (medical interview result DB) 174, a hearing content database (hearing content DB) 175, and a medical fee database (medical fee DB) 176 are formed in storage unit 817 of pharmacy computer 20.

[0041] Patient attribute data such as the patient's address, name, age, sex, and various information representing the patient's individual characteristics are stored in the patient attribute DB 171. These patient attributes are composed of information acquired by the pharmacist through conversations with the patient, information provided by the patient in response to questionnaires, etc., and include, for example, the patient's hobbies, work, family structure, favorite foods, etc. The prescription DB 172 stores data on prescriptions issued to patients in association with information identifying each patient and the date on which the prescription was brought. The medication history DB 173 stores data on the history of drugs prescribed to patients (medication history) in association with information identifying each patient and information identifying each pharmacist who prescribed the drug. The medication history also stores data on the history of medication instructions given to patients by pharmacists (medication instruction statements, etc.). As described above, the medication history registration support process can be used to register these medication instruction statements, etc., after reducing the work of pharmacists in inputting data into the medication history.

[0042] The medical interview result DB 174 stores the results of medical interviews conducted with patients in association with information identifying each patient and the date and time of the interview. The medical interview results include the results of interviews entered by pharmacists after interviewing patients, and impressions entered by pharmacists based on the impressions they received from patients they met. The hearing content DB 175 stores data of a list of hearing content (question items) to be asked of patients, such as "Have you forgotten to take your medicine?" or "Have you experienced any changes in your physical condition after taking your medicine?".

[0043] The medical fee DB 176 stores data of medical fee statements (receipts) issued by the receipt computer function realized by the receipt management unit 151 in order for pharmacies to bill health insurance associations and the like for medical expenses.

[0044] The medical receipt management unit 151 acquires information necessary for a patient's medical receipt (patient attributes, prescription contents, medical insurance points, etc.) and performs the process of issuing the medical receipt. The medication history management unit 152 manages the history (medication history) of drugs prescribed to a patient. For example, when a new prescription is given to a patient, the medication history management unit 152 stores data of the currently prescribed drug in the medication history DB 173; when a request to send target information or data of a medical fee statement is received from the terminal device 10 in the medication history registration support process, the medication history management unit 152 acquires the requested target information or data of a medical fee statement from each database formed in the storage unit 817 and transmits it to the terminal device 10; and when a request to register candidate information is made by the support server 30, the medication history management unit 152 stores data such as a medication instruction statement included in the candidate information in the medication history DB 173.

[0045] The DB management unit 153 manages the synchronization of data in the various databases managed by the pharmacy computer 20 with data in the various databases provided in the support server 30. For example, at a preset time (e.g., 3:00 AM), the DB management unit 153 transmits updated data in the various databases managed by the pharmacy computer 20 to the support server 30, and receives updated data in the various databases in the support server 30 from the support server 30, and updates the various databases it manages.

[0046] [Functional configuration of support server 30] FIG. 12 is a block diagram showing the functional configuration of the support server 30. As shown in FIG. 12, a DB management unit 251, a user interface information generation unit (UI information generation unit) 252, a support request reception unit 253, a target information acquisition unit 254, a feature extraction unit 255, a guidance content inference unit 256, a candidate information generation unit 257, a presentation control unit 258, and a medication history registration unit 259 function in the CPU 811 of the support server 30. In addition, a patient attribute database (patient attribute DB) 271, a prescription database (prescription DB) 272, a medication history database (medical history DB) 273, an interview result database (interview result DB) 274, an interview content database (interview content DB) 275, a medical fee database (medical fee DB) 276, and a candidate information database (candidate information DB) 277 are formed in the storage unit 817 of the support server 30. Of these databases, the stored contents of each database other than candidate information DB 277 are synchronized by DB management unit 251 with the stored contents of each corresponding database in pharmacy computer 20 .

[0047] The candidate information DB 277 stores data used by a candidate information generating unit 257 (described later) to generate candidate information in the medication history registration support process. FIG. 13 is a schematic diagram showing data related to medication instruction sentences, which are data for generating candidate information stored in the candidate information DB 277. As shown in FIG. 13, each drug identified by a drug code and a drug name is associated with a plurality of medication instruction sentences provided by a drug manufacturer or a pharmacist. Also, as shown in FIG. 13, each medication instruction sentence is assigned a category corresponding to the medication instruction content so that the pharmacist can easily confirm the content when approving. Furthermore, as shown in FIG. 13, a medication instruction content ID is assigned as information identifying the medication instruction content corresponding to each medication instruction sentence. In this embodiment, the medication instruction content is inferred in the medication history registration support process, and a medication instruction content ID indicating the inferred medication instruction content is output as an inference result. The candidate information generation unit 257 can generate candidate information by extracting, from the candidate information DB 277, the medication instruction sentence corresponding to the medication instruction content ID output as the inference result. The candidate information DB 277 also stores data on the predetermined warning sentence described above with reference to FIG. 10. If the candidate information generation unit 257 infers that there is something that the pharmacist should take note of when approving, it extracts a predetermined warning message corresponding to the something that the pharmacist should take note of from the candidate information DB 277 and includes it in the candidate information.

[0048] Note that candidate information DB277 is a database used exclusively by candidate information generating unit 257, and is therefore assumed to be formed only in support server 30, and not particularly formed in pharmacy computer 20. However, this is not limiting, and a database equivalent to candidate information DB277 may also be formed in pharmacy computer 20. The database in pharmacy computer 20 and candidate information DB277 may also be synchronized. This makes it possible, for example, when a pharmacist adds or modifies the content of a medication instruction statement using pharmacy computer 20, to reflect the added or modified content of the medication instruction statement in candidate information DB277 of support server 30.

[0049] 12, the DB management unit 251 manages the synchronization of data in various databases provided in the support server 30 with data in various databases managed by the pharmacy computer 20. For example, at a preset time (e.g., 3:00 AM), the DB management unit 251 transmits data in various databases updated in the support server 30 to the pharmacy computer 20, and receives updated data in the various databases managed by the pharmacy computer 20 from the pharmacy computer 20, and updates the various databases it manages.

[0050] The UI information generation unit 252 generates UI information for the terminal device 10 to display a UI screen and transmits the generated UI information to the terminal device 10. In this case, the UI information generation unit 252 generates, as UI information, a frame format for displaying the UI screen and substantive content to be inserted into the format. In this embodiment, the substantive content to be inserted into the format includes, for example, patient attributes for the medication instruction selection screen, questionnaire content for the questionnaire display screen, hearing content for the interview display screen, a list of medication instructions to be selected on the medication instruction selection screen, candidate information for the approval reception screen, etc. In addition, in response to transmitting the UI information to the terminal device 10, the UI information generation unit 252 receives various information transmitted from the terminal device 10 (information identifying the patient, questionnaire result data, prescription data, interview result data, information identifying the prescribing pharmacist, information identifying the selected medication instruction, approval results, etc.).

[0051] The support request receiving unit 253 receives from the terminal device 10 a request to provide candidate information together with information identifying the medication instruction for the subject for whom generation of candidate information is requested. The target information acquisition unit 254 acquires, from the pharmacy computer 20, target information and a medical fee statement that correspond to the information that identifies the medication instruction transmitted from the terminal device 10.

[0052] The feature extraction unit 255 references the target information and medical fee statement acquired by the target information acquisition unit 254 and extracts predefined features. At this time, the feature extraction unit 255 performs natural language processing to extract phrases representing features included in the target information and medical fee statement, or to extract feature values ​​calculated or estimated from the target information and medical fee statement. Regarding the features extracted at this time, content (e.g., the patient's age, personality, etc.) that is determined to be a feature in the thought process of a pharmacist providing medication instructions is predefined. For example, when "patient's age" is defined as a feature, the feature extraction unit 255 extracts phrases representing the patient's age included in the target information. Furthermore, when "visit interval" is defined as a feature, the feature extraction unit 255 calculates the visit interval (i.e., the difference between the date of the previous visit and the date of the current visit) from the date of visit included in the target information. Furthermore, when "dispensing fee points" is defined as a feature, the feature extraction unit 255 extracts the content and points of each item included in the medical statement, such as the medication history management instruction fee. In the inference described below, by using both the feature extracted from the target information in this way and the feature extracted from the medical fee statement, more accurate inference can be achieved than when using only one of them.

[0053] In addition, in this embodiment, features can also be extracted from text data expressing a patient's complaint (such as text data obtained by voice recognition of a patient's speech, text data entered by a pharmacist, or text data expressing an option selected by a pharmacist). Therefore, for example, colloquial expressions including onomatopoeia such as "my stomach hurts" or "my stomach feels queasy" are acceptable in text data expressing a patient's complaint. In other words, in this embodiment, the expressions expressed by the patient during an interview can be directly converted into data to generate text data expressing the patient's complaint. However, the pharmacist may also interpret the expressions expressed by the patient and convert them into text data as pharmaceutical expressions expressing the patient's condition.

[0054] The instruction content inference unit 256 uses the feature values ​​extracted by the feature extraction unit 255 as input and infers the medication instruction content of the medication instruction given to the patient based on machine learning. In this embodiment, the instruction content inference unit 256 is equipped with an inference engine constructed by machine learning to determine what medication instruction a pharmacist (especially an experienced pharmacist) would give to a patient when they recognize the feature values. Therefore, the medication instruction content inferred by the instruction content inference unit 256 represents the medication instruction content that a pharmacist would give when given target information for the target patient. Also, as described above, in this embodiment, the feature extraction unit 255 also extracts feature values ​​from the medical fee statement. Therefore, the inference engine equipped in the instruction content inference unit 256 is machine-learned to also learn information such as the content and points of each item, such as the medication history management instruction fee, included in the medical fee statement. Therefore, the medication instruction content inferred by the instruction content inference unit 256 takes into consideration information such as the content and points of each item, such as the medication history management instruction fee, included in the medical fee statement (i.e., it does not contradict the content and points of each item).

[0055] To realize such machine learning-based inference, a learning model constructed by a neural network can be created by performing supervised machine learning using training data in which the feature amounts extracted by the feature extraction unit 255 are used as input data and the medication instruction content given by a pharmacist (especially an experienced pharmacist) in medication instruction for the input data is used as a label (correct answer). However, other methods (deep learning, etc.) can also be used as machine learning to realize machine learning-based inference.

[0056] Furthermore, instead of (or in addition to) inferring medication instruction contents using machine learning, it is also possible to infer medication instruction contents using a rule base. As an example, when rule-based inference is used, table data is used in which medication instruction contents that are desirable to be given when various feature quantities are extracted are defined for the feature quantities. When inference is performed, the table data is referenced, and the medication instruction contents defined for the extracted quantities are output as inference results. Note that the relationship between the feature quantities and the definitions of medication instruction contents may be one-to-one, one-to-many, many-to-one, or many-to-many, or these relationships may be mixed and defined.

[0057] The instruction content inference unit 256 outputs the inference result of the inference thus executed as a medication instruction content ID corresponding to the inferred medication instruction content. Note that, if there are multiple medication instruction sentences corresponding to the inferred medication instruction content, the instruction content inference unit 256 may output multiple medication instruction content IDs corresponding to each of them. In this case, if the instruction content inference unit 256 can infer the likelihood of each of the multiple medication instruction contents, it may also output the likelihood. Alternatively, the instruction content inference unit 256 may output only the medication instruction content with the highest likelihood.

[0058] The candidate information generation unit 257 extracts from the candidate information DB 277 a medication instruction sentence corresponding to the medication instruction content ID output as an inference result by the instruction content inference unit 256. The candidate information generation unit 257 then generates the candidate information by including the extracted medication instruction sentence in the candidate information as data in the inferred medication instruction candidate list and data in the general medication instruction candidate list. The candidate information DB 277 also stores data on the predetermined warning sentences described above with reference to FIG. 10. If the candidate information generation unit 257 infers that there is something that the pharmacist should take note of when approving the request, it extracts from the candidate information DB 277 a predetermined warning sentence corresponding to the something to take note of and includes it in the candidate information. In this case, the candidate information generation unit 257 may also acquire data such as patient questionnaire results and interview results, such as patient interview results and impressions, from each database and include it in the candidate information so that the data can serve as information for the pharmacist to decide whether to approve the request. Furthermore, for example, when the likelihood of each of a plurality of medication instruction contents is also inferred, the candidate information generating unit 257 may generate candidate information so that medication instruction sentences corresponding to medication instruction contents with a high likelihood are presented so that they are more likely to be selected by the pharmacist (for example, so that those with a high likelihood are displayed at the top of the list of inferred medication instruction candidates, or so that those with a high likelihood are displayed with a check mark attached in advance). This allows the pharmacist to recognize and select medication instruction sentences inferred to have a high likelihood more easily than other medication instruction sentences.

[0059] The presentation control unit 258 transmits a request for acceptance of approval from the pharmacist together with the candidate information generated by the candidate information generation unit 257 to the terminal device 10. That is, the presentation control unit 258 performs control for presenting the candidate information to the pharmacist. The presentation control unit 258 may also perform control to present the candidate information to the pharmacist in cases other than when approval is received from the pharmacist. For example, in order to support the pharmacist in providing medication instruction, the presentation control unit 258 may perform control to present the candidate information to the pharmacist while the medication instruction is being provided, or before and after the medication instruction is provided. This allows the pharmacist to regard the medication instruction statement included in the candidate information as recommended medication instruction content and use it as a reference when actually providing medication instruction. For example, by reading out the medication instruction statement included in the candidate information, medication instruction based on the recommended medication instruction content can be realized. In this embodiment, using the candidate information in this manner also makes it possible to more appropriately support the work of the pharmacist.

[0060] The medication history registration unit 259 receives from the terminal device 10 an approval result (including a request to register the approved candidate information in the medication history) regarding the registration of the candidate information in the medication history from the pharmacist who has received the presented candidate information. Furthermore, the medication history registration unit 259 registers the candidate information approved by the pharmacist as a registration target in the medication history included in the medication history DB 273 based on the received approval result. Furthermore, the medication history registration unit 259 transmits to the pharmacy computer 20 a request to register the candidate information approved by the pharmacist as a registration target in the medication history included in the medication history DB 173.

[0061] [Operation] Next, the operation of the support system 1 will be described.

[0062] [Target information acquisition process] FIG. 14 is a flowchart showing the flow of the target information acquisition process executed by the terminal device 10. The target information acquisition process is started in response to an instruction to execute the target information acquisition process being input via the input unit 815 of the terminal device 10. In step S1, the UI display control unit 51 receives UI information from the support server 30 and displays a patient selection screen. In step S2, the UI display control unit 51 receives the selection of the patient to be interviewed, thereby specifying information for identifying the patient.

[0063] In step S3, the UI display control unit 51 receives input of prescription data issued to the selected patient. The patient identification information and prescription data are transmitted to the support server 30. In step S4, the UI display control unit 51 receives UI information from the support server 30 and displays a medical interview display screen corresponding to the selected patient. If the patient to be interviewed visits the clinic for the first time, the UI display control unit 51 receives UI information from the support server 30, displays a questionnaire display screen, and accepts input on the questionnaire display screen. After transmitting the questionnaire results entered on the questionnaire display screen to the support server 30, the UI display control unit 51 again receives UI information for the medical interview display screen and displays a medical interview display screen corresponding to the patient.

[0064] In step S5, UI display control unit 51 receives an input of a response to the medical interview display screen. Data of the response result to the medical interview display screen (medical interview result) is transmitted to pharmacy computer 20.

[0065] In step S6, the UI display control unit 51 determines whether or not a medication instruction statement has been input from the pharmacist along with the answer to the medical interview display screen. As described above, the medication instruction statement may be input by the pharmacist sequentially during medication instruction without using the medication history registration support process. If a medication instruction statement has been input, the determination in step S6 is YES, and the target information acquisition process ends. On the other hand, if no medication instruction has been input, the determination in step S6 is YES, and the process proceeds to step S7. In step S7, UI display control unit 51 accepts input of medication instruction sentences from the pharmacist. Data of the medication instruction sentences from the pharmacist is transmitted to pharmacy computer 20. After step S7, the target information acquisition process ends.

[0066] [Information Management Processing] FIG. 15 is a flowchart showing the flow of the information management process executed by the pharmacy computer 20. The information management process is started in response to an instruction to execute the information management process being input via the input unit 815 of the pharmacy computer 20.

[0067] In step S11, the DB management unit 153 determines whether or not a prescription for the patient has been received. If the patient's prescription has not been received, the determination in step S11 is NO, and the process proceeds to step S13. On the other hand, if the patient's prescription has been accepted, the determination in step S11 is YES, and the process proceeds to step S12. In step S12, the DB management unit 153 updates the patient attribute DB 171 and the prescription DB 172 with the data of the currently accepted prescription.

[0068] In step S13, the DB management unit 153 determines whether or not data of the target information has been received from the terminal device 10. If the data of the target information has not been received, the determination in step S13 is NO, and the process proceeds to step S15. On the other hand, if the target information has been received, the determination in step S13 is YES, and the process proceeds to step S14. In step S14, the DB management unit 153 updates the medical interview result DB 174 and the hearing content DB 175 with the data of the currently received target information.

[0069] In step S15, the DB management unit 153 determines whether or not a medical fee statement has been issued. If a medical fee statement has not been issued, the result of step S15 is NO, and the process proceeds to step S17. On the other hand, if a medical fee statement has been issued, the determination in step S15 is YES, and the process proceeds to step S16. In step S16, the DB management unit 153 updates the medical fee DB 176 with the data from the currently issued medical fee statement.

[0070] In step S17, the DB management unit 153 determines whether or not a request to send the target information and medical fee statement data has been received from the support server 30. If a request to send the target information and medical fee statement data has not been received from the support server 30, the result of step S17 is determined to be NO, and the process proceeds to step S19. On the other hand, if a request to send the target information and medical fee statement data is received from the support server 30, the determination in step S17 is YES, and the process proceeds to step S18. In step S18, the DB management unit 153 acquires the requested target information and medical fee statement data from each database and transmits them to the support server 30.

[0071] In step S19, the DB management unit 153 determines whether or not medication history data (data on medication instruction statements, etc.) has been received from the support server 30 or the terminal device 10. If medication history data has not been received from the support server 30 or the terminal device 10, the result of step S19 is determined to be NO, and the process proceeds to step S21. On the other hand, if medication history data has been received from the support server 30 or the terminal device 10, the result of the determination in step S19 is YES, and the process proceeds to step S20. In step S20, the DB management unit 153 updates the medication history DB 173 with the received medication history data.

[0072] In step S22, the DB management unit 153 determines whether it is the predetermined timing for synchronizing the data of the various databases managed by the pharmacy computer 20 with the data of the various databases provided on the support server 30. If the predetermined timing for synchronizing the data of the various databases managed by the pharmacy computer 20 with the data of the various databases provided on the support server 30 has not arrived, step S21 is judged as NO and the information management process is repeated. On the other hand, if it is the predetermined timing for synchronizing the data of the various databases managed by the pharmacy computer 20 with the data of the various databases provided on the support server 30, the result of step S21 is judged as YES, and processing proceeds to step S22.

[0073] In step S22, the DB management unit 153 updates each database by transmitting and receiving data to and from the support server 30, and synchronizes the data in the various databases managed by the pharmacy computer 20 with the data in the various databases provided in the support server 30. After step S22, the information management process is repeated.

[0074] [Medical history registration support processing] FIG. 16 is a flowchart showing the flow of the medication history registration support process executed by the support server 30. The medication history registration support process is started when the support server 30 receives a request from the terminal device 10 to provide candidate information.

[0075] In step S31, the support request receiving unit 253 receives from the terminal device 10 a request to provide candidate information together with information identifying medication instruction for a subject for whom generation of candidate information is requested. In step S32, the target information acquisition unit 254 transmits to the pharmacy computer 20 a request to transmit target information and medical fee statement data corresponding to the information for identifying medication instruction transmitted from the terminal device 10. In step S33, the target information acquisition unit 254 receives the target information and medical fee statement data from the pharmacy computer 20.

[0076] In step S34, the feature extraction unit 255 performs natural language processing on the received target information and medical fee statement data. In step S35, the feature extraction unit 255 extracts feature amounts from the target information and the medical fee statement. In step S36, the instruction content inference unit 256 receives the feature amount extracted by the feature extraction unit 255 as an input and infers the medication instruction content.

[0077] In step S37, the candidate information generating section 257 generates candidate information by extracting from the candidate information DB 277 a medication instruction sentence corresponding to the medication instruction content ID output by the instruction content inferring section 256 as the inference result. In step S38, the presentation control unit 258 transmits the candidate information generated by the candidate information generating unit 257 together with a request for acceptance of approval from the pharmacist to the terminal device 10 (outputs it to the terminal device 10 via the network 40). In step S39, the medication history registration unit 259 receives from the terminal device 10, from the pharmacist who has received the presented candidate information, an approval result regarding the registration of the candidate information in the medication history (including a request to register the approved candidate information in the medication history).

[0078] In step S40, the medication history registration section 259 determines whether or not the registration of the candidate information has been approved by the pharmacist, based on the received approval result. If the registration of the candidate information has not been approved by the pharmacist, the determination in step S40 is NO, and the medication history registration support process ends. On the other hand, if the pharmacist approves the registration of the candidate information, the determination in step S40 is YES, and the process proceeds to step S41.

[0079] In step S41, medication history registration unit 259 updates the medication history database. Specifically, medication history registration unit 259 registers the candidate information approved by the pharmacist as the registration target in the medication history included in medication history DB 273. Furthermore, medication history registration unit 259 transmits to pharmacy computer 20 a request to register this candidate information approved by the pharmacist as the registration target in the medication history included in medication history DB 173. After step S41, the medication history registration support process ends.

[0080] As described above, the support system 1 according to this embodiment generates candidate information by performing inference based on target information such as prescription data, and presents this candidate information to the pharmacist. Therefore, the pharmacist only needs to confirm the content of the candidate information when inputting all or at least part of the data related to the medication history (e.g., medication instructions) and decide whether or not to approve the registration of the data in the medication history. In other words, the support system can reduce the work of the pharmacist in inputting data related to the medication history. Therefore, the support system 1 according to the embodiment of the present invention can more appropriately support the work of pharmacists.

[0081] [Variation 1] In the above embodiment, a client-server type support system 1 is constructed, and a request for candidate information is made from the terminal device 10 to the support server 30 to obtain support information. In contrast, by providing the support functions of the support server 30 in a single device (e.g., terminal device 10 or pharmacy computer 20, etc.), the functions of the support system 1 can be realized in a single information processing device 800 (i.e., realized as a stand-alone system).

[0082] FIG. 17 is a block diagram showing the functional configuration of a stand-alone information processing device 800 having an assistance function. As shown in FIG. 17, when configured as a standalone type, in a single information processing device 800, the functions of the UI display control unit 51 of the terminal device 10, the UI information generation unit 252 of the support server 30, the support request reception unit 253, the target information acquisition unit 254, the feature extraction unit 255, the instruction content inference unit 256, the candidate information generation unit 257, the presentation control unit 258, and the medication history registration unit 259 are provided in the CPU 811, and each database managed by the support server 30 (or the pharmacy computer 20) is provided in the memory unit 817.

[0083] Furthermore, when the support system 1 is configured as a client-server system, the combination of information processing devices that configure the system is not limited to the examples shown in the above-described embodiments. For example, it is possible to distribute the functions of the pharmacy computer 20 or the support server 30 among more servers (e.g., cloud servers), or to integrate the functions of the pharmacy computer 20 and the support server 30 into one server.In addition, it is possible to integrate the functions of the terminal device 10 and the pharmacy computer 20 into one client.

[0084] [Variation 2] In the above-described embodiment, the candidate information mainly includes medication instructions, and the medication history registration support process is intended to register these medication instructions in the medication history. However, the candidate information may also include other information, and the medication history registration support process may also register this other information. For example, the medication history registration support process may also register various information, such as bibliographic information about the patient (such as name, date of birth, gender, health insurance card number, address, and emergency contact information), information included in the prescription (such as the name of the health insurance medical institution and the name of the health insurance physician who prescribed the medication, the prescription date, and the prescription contents), and information obtainable from the patient's past medication history or medication notebook (such as prescription history, information about the patient's medical history including complications, and whether the patient has visited other departments).

[0085] In this case, the candidate information generation unit 257 extracts information stored in each database based on, for example, the patient ID, and performs processes such as name identification and matching. This allows the candidate information generation unit 257 to include various information about the patient corresponding to the medication instruction that is the target of the medication history registration support process in the candidate information. Then, the medication history registration unit 259 registers various information in the medication history based on the approval of the pharmacist. This will further reduce the work required of pharmacists to input data related to medication history. Therefore, the support system 1 according to this modification can more appropriately support the work of pharmacists.

[0086] [Variation 3] In the medication history registration support process of the above embodiment, it is assumed that a pharmacist first selects medication instructions for which he / she requests the creation of candidate information. Then, for the selected medication instructions, the process involves a series of processes: creation of candidate information, approval of the candidate information, and updating of the medication history database based on the approval result.

[0087] Alternatively, a series of processes may be performed for multiple medication instructions, including generating multiple candidate information items corresponding to each of the multiple medication instructions, collectively approving each of the multiple candidate information items, and updating the medication history database based on the results of this collective approval. This allows the pharmacist to confirm the contents of the multiple candidate information items at once and then collectively approve their registration in the medication history. This further reduces the work of the pharmacist in inputting medication history data.

[0088] The medication history registration support process in this modified example for realizing such collective approval will be described with reference to Fig. 18. Fig. 18 is a flowchart showing the flow of the medication history registration support process executed by the support server 30 in this modified example. The medication history registration support process is started when the support server 30 receives a request from the terminal device 10 to provide candidate information.

[0089] In step S51, the support request receiving unit 253 receives a request for collective provision of candidate information from the terminal device 10. Here, in the step corresponding to step S51 in the above-described embodiment (i.e., step S31 in FIG. 16), information identifying the medication instruction for the subject for whom the generation of candidate information is requested is received together with the request for provision of candidate information. In this modified example, instead, information identifying the pharmacist for whom the generation of candidate information is requested is received together with the request for collective provision of candidate information.

[0090] In step S52, the support request receiving unit 253 refers to the medication history database 273 to identify all information identifying medication instructions corresponding to the information identifying the pharmacist received in step S51 as the target of this process. That is, all medication instructions given by this pharmacist are identified as the target of this process. Note that medication instructions for which candidate information (here, medication instruction statements) have already been registered are excluded from this process. Then, the processes of steps S32 to S37 are performed on any of the medication instructions that are the target of this process. The contents of these processes are the same as those of the processes described above with reference to FIG. 16, and therefore redundant explanations will be omitted here.

[0091] In step S53, the candidate information generating section 257 determines whether or not candidate information has been generated for all medication instructions that are the subject of this process and that were identified in step S52. If candidate information has been generated for all medication instructions, the determination in step S53 is YES, and the process proceeds to step S54. On the other hand, if candidate information has not been generated for all medication instructions, the determination in step S53 is NO, and the process returns to step S32. Then, the process is repeated from step S32 for medication instructions for which candidate information has not yet been generated.

[0092] In step S54, the presentation control unit 258 transmits to the terminal device 10 (outputs to the terminal device 10 via the network 40) a request for acceptance of batch approval from the pharmacist together with all the candidate information generated by the candidate information generating unit 257. In step S55, the medication history registration unit 259 receives from the terminal device 10 the approval result of the collective approval for registering the candidate information in the medication history from the pharmacist who has been presented with all the candidate information generated by the candidate information generation unit 257 (including a request to register the approved candidate information in the medication history).

[0093] In step S56, the medication history registration unit 259 determines whether or not there is any candidate information that has been approved by the pharmacist based on the received batch approval result. That is, it determines whether or not at least one piece of candidate information has been approved by the pharmacist in the batch approval. If there is no candidate information approved by the pharmacist, the determination in step S56 is NO, and the medication history registration support process ends. On the other hand, if there is candidate information that has been approved by the pharmacist, the determination in step S56 is YES, and the process proceeds to step S57.

[0094] In step S57, medication history registration unit 259 updates the medication history database. Specifically, medication history registration unit 259 registers all candidate information approved by the pharmacist as registration targets in the medication history included in medication history DB 273. Furthermore, medication history registration unit 259 transmits to pharmacy computer 20 a request to register all candidate information approved by the pharmacist as registration targets in the medication history included in medication history DB 173. After step S57, the medication history registration support process in this modified example ends.

[0095] The medication history registration support process in this modification allows the pharmacist to confirm the contents of multiple candidate information items at once and approve their registration in the medication history all at once. In other words, the work of the pharmacist inputting data related to the medication history can be further reduced.

[0096] In this modification, the manner in which the pharmacist accepts collective approval of registration to the medication history (for example, the user interface of the approval acceptance screen, etc.) is not particularly limited, and collective approval can be accepted in various manners. For example, the approval acceptance screen for each medication instruction as shown in FIG. 9 may be displayed by scrolling sequentially in response to a scrolling operation by the pharmacist, and approval operations may be accepted sequentially from the pharmacist for each medication instruction. Furthermore, instead of scrolling sequentially, the approval acceptance screen for each of the multiple medication instructions may be displayed in a list, for example, by displaying thumbnails. In this case, the pharmacist may individually approve the registration of each medication instruction to the medication history (for example, by pressing the "Approve registration to medication history" button), or the pharmacist may approve the registration of each medication instruction to the medication history all at once (for example, by pressing the "Approve registration to medication history all at once" button).

[0097] Furthermore, approval may not be accepted in the same manner for all medication instructions, but may be accepted in different manners depending on the medication instruction. For example, if there are no changes to the prescription and the candidate information again contains a medication instruction statement that overlaps with the content of the previous medication instruction statement, it is considered that there is no problem with this candidate information (i.e., this medication instruction statement). Therefore, it is preferable to accept approval operations for such candidate information in a simple manner. For example, it is preferable to automatically switch the scroll display for such candidate information in a short time, without requiring the pharmacist to perform a scrolling operation, and then accept approval operations all at once. Alternatively, it is preferable to display such candidate information in a small list, and then accept approval operations all at once.

[0098] On the other hand, for example, when a drug that requires the involvement of a specialist in pharmaceutical management for safety management (so-called high-risk drug) is prescribed, or when the patient has a specific chronic illness, it is considered necessary to pay attention to whether or not there are any problems with the candidate information (i.e., this medication instruction). Therefore, it is advisable to accept approval operations for such candidate information in a non-simplified manner. For example, it is advisable not to switch the scrolling display for such candidate information unless operated by the pharmacist, and to accept approval operations individually. Alternatively, it is advisable to display such candidate information large on the entire screen and then accept approval operations individually.

[0099] For this reason, when the presentation control unit 258 controls the presentation of candidate information to the pharmacist, it is preferable to control the presentation so as to accept collective approval in various modes as described above. In this way, by using various modes for accepting collective approval of registration to the medication history from the pharmacist, it is possible to appropriately support collective approval by the pharmacist.

[0100] [Variation 4] In the medication history registration support process of the above-described embodiment, the instruction content inference unit 256 infers medication instruction contents by machine learning or rule-based analysis using the feature quantities extracted by the feature extraction unit 255 as input. Then, the candidate information generation unit 257 generates candidate information by extracting, from the candidate information DB 277, medication instruction sentences corresponding to the medication instruction content IDs output by the instruction content inference unit 256 as inference results. That is, the medication instruction contents are inferred one by one, and medication instruction sentences are extracted one by one corresponding to each of these medication instruction contents. That is, there is a one-to-one correspondence between medication instruction contents and medication instruction sentences.

[0101] However, it is also possible to extract one medication instruction sentence corresponding to a plurality of medication instruction contents. To do so, for example, a plurality of medication instruction sentences corresponding to a plurality of instruction contents may be extracted together as one medication instruction sentence.

[0102] As a specific example, assume that multiple side effects (e.g., lower back pain, lower abdominal pain, and diarrhea) are individually inferred as medication instruction content using machine learning or a rule-based approach. In this case, in the above-described embodiment, three medication instruction sentences corresponding to the medication instruction content IDs of these three side effects are individually extracted. For example, three medication instruction sentences are extracted: "Lower back pain may occur as a side effect. Instruct the patient to stop taking the drug and consult a doctor if this occurs.", "Lower abdominal pain may occur as a side effect. Instruct the patient to stop taking the drug and consult a doctor if this occurs.", and "Diarrhea may occur as a side effect. Instruct the patient to stop taking the drug and consult a doctor if this occurs." However, if all three medication instruction sentences with similar wording are included in the candidate information and registered in the medication history, the wording may become redundant and the content of the medication history may become unclear.

[0103] Therefore, in such cases, these three medication instructions are combined and extracted as a single medication instruction. For example, expressions with common or similar content are combined in each medication instruction. In this case, in the above example, a single medication instruction such as "Back pain, lower abdominal pain, or diarrhea may occur as a side effect. Instruct the patient to stop taking the medication and consult a doctor if this occurs" is extracted. This reduces the number of characters while retaining the content of the medication instructions, making the expressions when registered in the medication history concise and the content of the medication history clear. In other words, it further reduces the work required of pharmacists to input data related to the medication history.

[0104] As a method for extracting a single medication instruction sentence by combining multiple medication instruction sentences, for example, one medication instruction sentence may be prepared for each combination of multiple medication instruction contents. That is, when a first medication instruction content and a second medication instruction content are inferred in the same category of side effects, etc., one medication instruction sentence to be extracted may be prepared for each of the various combinations of medication instruction contents. Alternatively, a rule for combining multiple medication instruction sentences (for example, as described above, a rule that combines expressions with common or similar content) may be established, and a single medication instruction sentence may be created based on this rule.

[0105] [Variation 5] Functions applicable to the above-described embodiment and their user interfaces will be described with reference to Figs. 19 and 20. This function can be applied to various situations in which candidate information (here, medication instruction sentences) based on inference by the instruction content inference unit 256 is presented. For example, it can be applied to a situation in which candidate information is presented as a candidate medication instruction content to be registered in a medication history. In addition, it can be applied to a situation in which candidate information is presented as medication instruction content recommended in medication instruction.

[0106] 19 is a schematic diagram showing an example of a medication instruction selection screen 60 displayed in various situations on the terminal device 10 or the support server 30. As shown in FIG. 19, the medication instruction selection screen 60 includes an information display area 61 and a selection operation area 62 as display areas.

[0107] The information display area 61 displays bibliographic information such as the patient's name, buttons for transitioning to other display screens, etc. In addition, the information display area 61 displays information about the drug, such as the name and dosage of the drug to be prescribed (or has been prescribed) for this patient. For example, information such as "Lipitor Tablets 5 mg" and "Bezatol SR Tablets 200 mg" is displayed.

[0108] The selection operation area 62 displays a list of medication instruction contents that may be the subject of medication instruction when these drugs are prescribed. The display order of each medication instruction content in this list can be determined arbitrarily. To determine this display order, for example, a predetermined score is assigned to highly reliable medication instruction contents, such as medication instruction contents with a high likelihood inferred by the instruction content inference unit 256 or medication instruction contents that have been selected multiple times by pharmacists in the past. Then, medication instruction contents with a high assigned score and high reliability are displayed at the top of the list so that they are more likely to be selected by pharmacists. This allows each medication instruction content to be displayed in an order that takes into account the inference results and past selection results.

[0109] Furthermore, medication instruction statements corresponding to each of these medication instruction contents are displayed in the selection operation area 62. Furthermore, a "slide button," a "redisplay next time button," and a "not recommended button" are displayed in the selection operation area 62 corresponding to each of these medication instruction contents. The pharmacist can use these buttons to perform operations related to the selection of medication instruction content. Each of these buttons will be explained below.

[0110] The slide button switches the selection state of the medication instruction content. Each time the pharmacist operates the slide button, the state switches between a state in which that medication instruction content is selected and a state in which that medication instruction content is not selected. As the initial setting of this slide button, the medication instruction content inferred by the instruction content inference unit 256 is pre-selected before the pharmacist operates the slide button. On the other hand, other medication instruction content is pre-selected. As a result, the results of the inference by the instruction content inference unit 256 (i.e., AI or rule-based inference) are already reflected at the initial setting stage before the pharmacist operates the slide button. Then, from this state, the pharmacist operates the slide button based on their own judgment to modify the selection state of each medication instruction content to a more appropriate one. In other words, the pharmacist does not need to select medication instruction content from a completely unpredictable state; they can simply select medication instruction content from a state in which the inference is reflected. By initializing the slide button in this way, the pharmacist's selection of medication instruction content can be semi-automated, reducing the pharmacist's workload.

[0111] The Redisplay Next Time button is a button for setting the medication instruction content to be displayed again next time. When making a selection using the slide button, if the pharmacist thinks that the medication instruction content must be displayed again next time, the pharmacist operates the Redisplay Next Time button. This causes the medication instruction content to be displayed in the list again next time. Note that the medication instruction content may be displayed not only next time, but also the time after that. This prevents the pharmacist from noticing the existence of the medication instruction content next time.

[0112] The "Not Recommended" button is a button for setting the medication instruction content not to be displayed next time. When making a selection using the slide button described above, if the pharmacist thinks that the medication instruction content does not need to be displayed next time, the pharmacist operates the "Not Recommended" button. This prevents the medication instruction content from being displayed in the list next time either. Note that the medication instruction content may be prevented from being displayed not only next time but also the next time and thereafter. This prevents the pharmacist from mistakenly selecting the medication instruction content next time.

[0113] The scope to which the settings of the redisplay next time button and the not recommended button are applied can be determined as appropriate. For example, they may be applied on a patient-by-patient basis. In this case, the settings of each button are applied to the next medication instruction for that patient, but are not applied to medication instructions for other patients. Similarly, they may be applied on a pharmacy-by-pharmacy or pharmacist-by-pharmacist basis. This allows each pharmacist's judgment to be applied to an appropriate scope.

[0114] Furthermore, separate from the settings of the "Re-display next time" button and the "Not recommended" button, for example, medication instruction contents whose predetermined score is below a threshold may not be displayed in the list, and medication instruction contents whose predetermined score is above a threshold may be displayed in the list. Even in this case, the settings of the "Re-display next time" button and the "Not recommended" button may be applied with priority. Furthermore, when the "Not recommended" button is set, it may be configured so that it is less likely to be displayed from the next time onwards by reducing the score, rather than always not being displayed next time.

[0115] Furthermore, the operation details of these various buttons (i.e., the pharmacist's judgment after checking the inference results) may be reflected in the criteria for inferring future medication instruction content by the instruction content inference unit 256. For example, the inference criteria may be changed so that medication instruction content selected using the slide button or medication instruction content for which the "redisplay next time" button is set is more likely to be inferred in the future. On the other hand, the inference criteria may be changed so that medication instruction content not selected using the slide button or medication instruction content for which the "not recommended" button is set is less likely to be inferred in the future. Such a change in the inference criteria can be achieved, for example, by changing the parameters used by the AI ​​for inference or by adding a rule that prevents output even if an inference is made. This allows the instruction content inference unit 256 to perform inferences after adding the pharmacist's judgment criteria in future inferences. Therefore, highly accurate inferences can be achieved using criteria that are more in line with the pharmacist's practical work.

[0116] Fig. 20 is a schematic diagram showing an example of a guidance home screen 70 displayed on the terminal device 10 or the support server 30 in various situations. As shown in Fig. 20, the guidance home screen 70 includes, as display areas, an information display area 71, a prescription content confirmation area 72, and a medication guidance confirmation area 73. Fig. 20 also conceptually illustrates a pharmacist's finger 80 to show an example of operation.

[0117] The information display area 71 displays bibliographic information such as the patient name, buttons for transitioning to other display screens, etc. In addition to this, the information display area 71 displays pharmaceutical judgment factors (problems related to the patient) when making inferences by the instruction content inference unit 256. In this example, with regard to problems related to the patient, the relevance to inferences for each problem (here, percentages indicating the importance) is displayed based on the patient attributes, medication history, questionnaire results, and interview results of the patient who answered the interview.

[0118] Information about the drug, such as the name and dosage of the drug to be prescribed (or that has been prescribed) for this patient, is displayed in the prescription content confirmation area 72. Note that information about the name and dosage of not only the drug that is currently prescribed but also the drug that was previously prescribed may be displayed.

[0119] In the medication instruction confirmation area 73, when these drugs are prescribed, medication instruction contents selected by the pharmacist as medication instruction targets are displayed in a list. For example, as described above with reference to FIG. 19, medication instruction contents selected by the pharmacist are displayed in a list. The display order of each medication instruction content in this list can be determined, for example, based on a predetermined score, similar to the display order in FIG. 19. In this case, if medication instruction has previously been given to this patient regarding a certain medication instruction content, the medication instruction regarding this certain medication instruction content may be postponed and displayed lower even if the predetermined score is high. Alternatively, for example, if medication instruction regarding a certain medication instruction content has previously been given, the certain medication instruction content may be temporarily paused (i.e., snoozed) and hidden. Then, when medication instruction progresses and the number of medication instruction contents displayed in the list decreases, or when a certain time has passed since hiding, the medication instruction content may be displayed again.

[0120] Furthermore, a "slide button" is displayed in medication instruction confirmation area 73. This slide button, like the slide button shown in Fig. 19, is a button for switching the selection state of medication instruction content. For example, when medication instruction for a certain medication instruction content has been completed or when the pharmacist determines that medication instruction for this medication instruction content is not necessary after all, the pharmacist may operate this slide button to switch this medication instruction content to an unselected state so that it is not displayed in the list.

[0121] Furthermore, medication instruction confirmation area 73 accepts a predetermined operation from the pharmacist (for example, a flick operation using pharmacist's finger 80, a touch pen, or the like). For example, when a flick operation is performed off the screen on a certain medication instruction content, a predetermined process is performed on this certain medication instruction content. For example, medication instruction on this certain medication instruction content may be postponed, and even if the certain score is high, it may be displayed lower. Alternatively, for example, when a flick operation is performed off the screen, this certain medication instruction content may be temporarily paused and hidden. Then, when medication instruction progresses and the number of medication instruction contents displayed in the list decreases, or when a certain time has passed since it was hidden, it may be displayed again.

[0122] In this way, the display state in the list can be changed by the pharmacist's operation according to the progress of medication instruction, etc. For example, medication instruction content for which medication instruction has been completed can be hidden from the list, medication instruction content to be postponed can be moved down in the display order in the list, or medication instruction content to be postponed can be temporarily paused and hidden from the list. This allows the pharmacist to easily change the display state to the one he or she intends, simply by performing an intuitive operation. As described above, the functions and user interface provided by this modified example make it possible to more appropriately support the work of pharmacists from various perspectives.

[0123] As described above, the support server 30 according to this embodiment includes the target information acquisition unit 254, the teaching content inference unit 256, and the candidate information generation unit 257. The target information acquisition unit 254 acquires target information that is to be considered in providing pharmaceutical guidance to a patient. The instruction content inference unit 256 infers the instruction content of pharmaceutical instruction for the patient based on the object information acquired by the object information acquisition unit 254. The candidate information generating unit 257 generates candidate information to be included in the medication history of pharmaceutical instruction to the patient based on the instruction content inferred by the instruction content inferring unit 256. In this way, the support server 30 can generate candidate information by making inferences based on target information such as prescription data. By using this candidate information, for example, it is possible to reduce the work of pharmacists in inputting data related to medication history. Therefore, the support server 30 according to the embodiment of the present invention can more appropriately support the work of pharmacists.

[0124] The support server 30 further includes a presentation control unit 258 and a medication history registration unit 259. The presentation control unit 258 performs control to present the candidate information generated by the candidate information generating unit 257 to a manager of pharmaceutical guidance for patients. The medical history registration unit 259 registers candidate information that has been presented and approved by the administrator as a medical history of pharmaceutical guidance for the patient. This allows the pharmacist to simply check the contents of the candidate information for all or at least part of the data related to the medication history (for example, medication instructions) and decide whether or not to approve the registration of the data in the medication history. In other words, the work of the pharmacist in inputting data related to the medication history can be reduced.

[0125] The candidate information includes at least a medication instruction statement corresponding to pharmaceutical instructions for the patient. Approval by the administrator involves selection of a medication instruction statement to be approved from among the medication instruction statements included in the candidate information. This allows the pharmacist to simply select a medication instruction statement included in the candidate information generated by the support server 30, thereby reducing the effort required to create a medication instruction statement.

[0126] When the presentation control unit 258 controls the presentation of candidate information, if the candidate information includes information that the administrator should take note of when approving the candidate information, the presentation control unit 258 controls the presentation of the candidate information in a manner different from that of other candidate information. This will encourage pharmacists to pay attention to important points.

[0127] In the control for presenting candidate information, the presentation control unit 258 performs control for presenting each of a plurality of candidate information corresponding to each of pharmaceutical instructions for a plurality of patients. The medication history registration unit 259 registers each of the plurality of pieces of candidate information that have been presented and approved collectively by the administrator as a registration target for the medication history of pharmaceutical guidance for the patient. This allows the pharmacist to check the contents of multiple candidate information items at once and approve their registration in the medication history all at once, which further reduces the work required for the pharmacist to input data related to the medication history.

[0128] The instruction content inferring unit 256 changes the criteria for inferring instruction content based on instructions from the administrator who has received the candidate information. This allows the instruction content inference unit 256 to make subsequent inferences by adding the pharmacist's judgment criteria, thereby achieving highly accurate inferences based on criteria more in line with the pharmacist's practical work.

[0129] The target information acquisition unit 254 further acquires information regarding medical fees for pharmaceutical guidance to patients. The instruction content inference unit 256 infers the instruction content for pharmaceutical instruction to the patient based on the information related to medical fees acquired by the object information acquisition unit 254 in addition to the object information acquired by the object information acquisition unit 254. This allows for more accurate inference of guidance content, taking into account information related to medical fees (for example, information on medical fee statements).

[0130] The support server 30 further includes a feature extraction unit 255 . The feature extraction unit 255 extracts feature amounts from the target information acquired by the target information acquisition unit 254 based on preset extraction conditions. The instruction content inference unit 256 infers the instruction content in pharmacological instruction for the patient based on at least the feature amount extracted from the target information. This makes it possible to infer teaching content based on at least a clear index, namely, the feature amount.

[0131] As described above, the support system 1 according to this embodiment includes the support server 30 and a plurality of pharmacy computers 20 corresponding to a plurality of pharmacies, respectively. The support server 30 and the multiple pharmacy computers 20 share information including at least the medical history of pharmaceutical instructions for patients in accordance with a common specification. This allows the support server 30 to more appropriately support the work of pharmacists at each of the multiple pharmacies based on the information shared with the multiple pharmacy computers 20.

[0132] The present invention is not limited to the above-described embodiment, and any modifications and improvements that can achieve the object of the present invention are included in the present invention. For example, in the above embodiment, a list of medication instructions is presented as candidate information, but this is not limiting. In other words, the candidate information presented in the present invention includes various types of medical information.

[0133] In the above-described embodiment, after the patient is interviewed, the patient waits while the pharmacist prepares the medication. Therefore, during this waiting time, simple lifestyle advice information identified from the interview results may be presented to the patient (for example, displayed on the patient's smartphone). Furthermore, in the above-described embodiment, a medical interview display screen for conducting a medical interview with a patient and a display screen for a list of medication instruction statements after approval by a pharmacist (a list of inferential medication instruction candidates and a list of general medication instruction candidates) may be displayed on a device carried by the patient (e.g., the patient's smartphone, etc.). In this case, medication instruction statements that are easier to understand for patients (e.g., medication instruction statements in simple language without using technical terms) may be prepared in the form of a database, etc., and a display screen for a list of easier-to-understand medication instruction statements for patients from this database may be displayed on a device carried by the patient.

[0134] The above-described series of processes can be executed by hardware or software. In other words, the functional configurations in the above-described embodiments are merely examples and are not particularly limited. That is, it is sufficient that any of the computers constituting the support system 1 has a function capable of executing the above-described series of processes as a whole, and the functional blocks used to realize this function are not particularly limited to the examples shown. Furthermore, one functional block may be configured as a single piece of hardware, a single piece of software, or a combination thereof.

[0135] Furthermore, the recording medium containing the program for executing the above-mentioned series of processes may be configured not only as a removable medium distributed separately from the device main body in order to provide the program to the user, but also as a recording medium provided to the user in a state where it is pre-installed in the device main body.

[0136] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments. Furthermore, the effects described in the present embodiments are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the present embodiments. [Explanation of symbols]

[0137] 1 Support system, 10 Terminal device, 20 Pharmacy computer, 30 Support server, 40 Network, 51 User interface display control unit (UI display control unit), 52, 254 Target information acquisition unit, 53 Support request unit, 54 Candidate information acquisition unit, 55 Approval reception unit, 151 Receipt management unit, 152 Medication history management unit, 153, 251 DB management unit, 171, 271 Patient attribute database (Patient attribute DB), 172, 272 Prescription database (Prescription DB), 173, 273 Medication history database (Medical history DB), 174, 274 Interview result database (Interview result DB), 175, 275 Hearing content database (Hearing content DB), 176, 276 Medical fee database (Medical fee DB), 277 Candidate information database (Candidate information DB), 252 User interface information generation unit (UI information generation unit), 253 Support request reception unit, 255 feature extraction unit, 256 instruction content inference unit, 257 candidate information generation unit, 258 presentation control unit, 259 medication history registration unit, 800 information processing device, 811 CPU, 812 ROM, 813 RAM, 814 bus, 815 input unit, 816 output unit, 817 storage unit, 818 communication unit, 819 drive, 820 imaging unit, 831 removable media

Claims

1. an instruction content inference means for inferring instruction content of pharmaceutical instruction to a patient based on target information to be considered in pharmaceutical instruction to the patient; a candidate information generating means for generating a plurality of candidate information to be included in a medication history of pharmaceutical guidance for the patient based on the guidance content inferred by the guidance content inferring means; a presentation control means for controlling presentation of the generated plurality of pieces of candidate information to an instructor who provides pharmaceutical guidance to the patient; a medication history registration means for registering the candidate information selected by the instructor after receiving the plurality of candidate information in the medication history of pharmaceutical instruction for the patient; Equipped with The presentation control means performing control to present both first candidate information based on the inference by the teaching content inference means and second candidate information not based on the inference by the teaching content inference means; The first candidate information is treated as a state selected by the instructor at a stage before the instructor performs an operation.

1. A support device comprising:

2. an instruction content inference means for inferring instruction content of pharmaceutical instruction to a patient based on target information to be considered in pharmaceutical instruction to the patient; a candidate information generating means for generating a plurality of candidate information to be included in a medication history of pharmaceutical guidance for the patient based on the guidance content inferred by the guidance content inferring means; a presentation control means for controlling presentation of the generated plurality of pieces of candidate information to an instructor who provides pharmaceutical guidance to the patient; a medication history registration means for registering the candidate information selected by the instructor after receiving the plurality of candidate information in the medication history of pharmaceutical instruction for the patient; Equipped with The instruction content inference means changing a criterion for inferring the content of the instruction based on an operation by the instructor regarding selection of the candidate information to be registered in the medication history; 1. A support device comprising:

3. A support method executed by an information processing device, comprising: an instruction content inference step of inferring instruction content of pharmaceutical instruction for the patient based on target information to be considered in pharmaceutical instruction for the patient; a candidate information generating step of generating a plurality of candidate information to be included in a medication history of pharmaceutical guidance for the patient based on the guidance content inferred in the guidance content inferring step; a presentation control step of performing control to present the generated plurality of pieces of candidate information to an instructor who provides pharmaceutical guidance to the patient; a medication history registration step of registering the candidate information selected by the instructor who has received the plurality of candidate information as a registration target for the medication history of pharmaceutical instruction for the patient; Including, In the presentation control step, performing control to present both first candidate information based on the inference made by the teaching content inference step and second candidate information not based on the inference made by the teaching content inference step; The first candidate information is treated as a state selected by the instructor at a stage before the instructor performs an operation. A support method characterized by:

4. A support method executed by an information processing device, comprising: an instruction content inference step of inferring instruction content of pharmaceutical instruction for the patient based on target information to be considered in pharmaceutical instruction for the patient; a candidate information generating step of generating a plurality of candidate information to be included in a medication history of pharmaceutical guidance for the patient based on the guidance content inferred in the guidance content inferring step; a presentation control step of performing control to present the generated plurality of pieces of candidate information to an instructor who provides pharmaceutical guidance to the patient; a medication history registration step of registering the candidate information selected by the instructor who has received the plurality of candidate information as a registration target for the medication history of pharmaceutical instruction for the patient; Including, In the instruction content inference step, changing a criterion for inferring the content of the instruction based on an operation by the instructor regarding selection of the candidate information to be registered in the medication history; A support method characterized by:

5. A computer, an instruction content inference function for inferring instruction content of pharmaceutical instruction to a patient based on target information to be considered in pharmaceutical instruction to the patient; a candidate information generating function that generates a plurality of candidate information to be included in a medication history of pharmaceutical guidance for the patient based on the guidance content inferred by the guidance content inferring function; a presentation control function for controlling presentation of the generated plurality of pieces of candidate information to an instructor who provides pharmaceutical guidance to the patient; a medication history registration function for registering the candidate information selected by the instructor who has received the plurality of candidate information as a medication history of pharmaceutical instruction for the patient; To achieve this, The presentation control function includes: performing control to present both first candidate information based on inference by the teaching content inference function and second candidate information not based on inference by the teaching content inference function; The first candidate information is treated as a state selected by the instructor at a stage before the instructor performs an operation. A program characterized by:

6. A computer, an instruction content inference function for inferring instruction content of pharmaceutical instruction to a patient based on target information to be considered in pharmaceutical instruction to the patient; a candidate information generating function that generates a plurality of candidate information to be included in a medication history of pharmaceutical guidance for the patient based on the guidance content inferred by the guidance content inferring function; a presentation control function for controlling presentation of the generated plurality of pieces of candidate information to an instructor who provides pharmaceutical guidance to the patient; a medication history registration function for registering the candidate information selected by the instructor who has received the plurality of candidate information as a medication history of pharmaceutical instruction for the patient; To achieve this, The instruction content inference function changing a criterion for inferring the content of the instruction based on an operation by the instructor regarding selection of the candidate information to be registered in the medication history; A program characterized by:

Images