Information provision method and information provision device

Abstract

By utilizing AI-generated data, we provide an information delivery method that enables objective and efficient evaluation of the quality of pharmacists' medication guidance and supports the improvement of pharmacists' skills. [Solution] The information provision method performed by the information provision device 3 includes: a question reception process that receives question information D1, which is conversation information including recorded data of a conversation between a pharmacist and a patient; a prompt generation process that generates prompt information D3 that instructs the generative artificial intelligence model 20 to output response information D4, which is evaluation information that evaluates the quality of the pharmacist's medication guidance to the patient, based on the question information D1; and a response provision process that provides the response information D4 output from the generative artificial intelligence model 20 by inputting the prompt information D3 to the generative artificial intelligence model 20.

Description

Technical Field

[0001] The present invention relates to an information providing method and an information providing apparatus.

Background Art

[0002] In recent years, generative artificial intelligence models called generative AI and generative AI have been utilized for various purposes and applications (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the system disclosed in Patent Document 1, an efficient reminder is set using generative AI. However, the utilization of generative AI is required in more diverse fields without being limited to the efficiency improvement of general desk work such as the system disclosed in Patent Document 1.

[0005] The present invention has been made in view of the above problems, and an object thereof is to provide an information providing method and an information providing apparatus that can objectively and efficiently evaluate the quality of a pharmacist's medication guidance and support the improvement of the pharmacist's skills by utilizing generative AI.

Means for Solving the Problems

[0006] In order to achieve the above object, an information providing method according to an aspect of the present invention is an information providing method for providing information by a computer, a reception process for receiving question information, A prompt generation process generates prompt information that instructs a generative artificial intelligence model to output answer information based on the aforementioned question information, The process involves inputting the prompt information into the generative artificial intelligence model and then providing the response information output from the generative artificial intelligence model. The aforementioned question information is, This is conversational information, including recorded data of conversations between pharmacists and patients. The aforementioned response information is, This is evaluation information that assesses the quality of medication guidance provided by the aforementioned pharmacist to the aforementioned patient. [Effects of the Invention]

[0007] According to one aspect of the present invention, by utilizing generated AI, it is possible to objectively and efficiently evaluate the quality of pharmacists' medication guidance and support the improvement of pharmacists' skills.

[0008] Other issues, configurations, and effects will be clarified in the embodiments for carrying out the invention described later. [Brief explanation of the drawing]

[0009] [Figure 1] This is an overall diagram showing an example of Information Provision System 1. [Figure 2] This is a block diagram showing an example of an information provision device 3. [Figure 3] This is a hardware configuration diagram showing an example of a computer 900 that makes up each device. [Figure 4] This is a flowchart illustrating an example of the operation (one stage) of Information Provision System 1. [Figure 5] This figure shows an example of a display screen. [Modes for carrying out the invention]

[0010] <Common Embodiment: Generative AI> Before providing a detailed description of the present invention, a general explanation of the common behavior of generation AI, its basic concepts, configuration, and operation will be given with reference to the drawings. This will deepen understanding of the specific embodiments for carrying out the present invention described later. Any parts omitted from the explanation will be based on prior art. Below, the scope necessary for explaining how to achieve the objectives of the present invention will be schematically shown, and the scope necessary for explaining the relevant parts of the present invention will be mainly explained, with any parts omitted from the explanation being based on prior art.

[0011] (System Overview) Figure 1 is an overall diagram showing an example of the information provision system 1. The information provision system 1 comprises, as its main components, a generative AI device 2, an information provision device 3 that operates in cooperation with the generative AI device 2, a user terminal device 4 used by user U, and a database device 5 where various types of information are stored. Each device 2 to 5 is, for example, composed of a general-purpose or dedicated computer (see Figure 3 below) and connected to a wired or wireless network 6, enabling the mutual transmission and reception of various types of data. Note that the number of each device 2 to 5 and the connection configuration of the network 6 are not limited to the example in Figure 1 and may be changed as appropriate.

[0012] The generative AI device 2 is composed of, for example, a server-type computer or a cloud-type computer. The generative AI device 2 includes, for example, a generative artificial intelligence model 20, also known as generative AI or generative AI. The generative artificial intelligence model 20 receives instructions from prompt information D3 and generates response information D4 in response to those instructions.

[0013] The generative artificial intelligence model 20 is a pre-trained model constructed using a vast training dataset and deep learning technology, and may include foundational models (e.g., large-scale language models) or multimodal models. The generative artificial intelligence model 20 may also be provided as a service by an external provider; in this case, the generative AI device 2 may be omitted from the components of the information provision system 1.

[0014] The information providing device 3 is composed of, for example, a server-type computer or a cloud-type computer. When the information providing device 3 receives the question information D1 from the user terminal device 4, it generates prompt information D3 for the generative artificial intelligence model 20 and transmits it to the generative AI device 2. Further, when the information providing device 3 receives the answer information D4 generated by the generative artificial intelligence model 20 from the generative AI device 2, it provides the answer information D4 to the user terminal device 4.

[0015] The user terminal device 4 is composed of, for example, a stationary computer or a portable computer. The user terminal device 4 has programs such as an application or a browser installed, accepts various input operations, and outputs various information via a display screen or voice. The user terminal device 4 displays a display screen for accepting an input operation for inputting the question information D1 or outputting the answer information D4, etc., and transmits and receives various data such as the question information D1 and the answer information D4 to and from the information providing device 3.

[0016] The database device 5 is composed of, for example, a server-type computer or a cloud-type computer. The database device 5 includes a reference information management database 50 (described later). The reference information D2 is stored in the reference information management database 50. The reference information management database 50 is accessible from each of the devices 2 to 4, and is referred to, for example, when the generative artificial intelligence model 20 generates the answer information D4. Further, editing operations such as addition, deletion, and modification are performed on the reference information management database 50 via the information providing device 3 or the user terminal device 4.

[0017] (Overview of each information) The question information D1 is data regarding queries, instructions, or situations related to a specific task or objective for the generative artificial intelligence model 20, and is information used to prompt the generation of the response information D4 by the model. The question information D1 may be text data in natural language, image data, audio data, numerical data, structured data, or a combination thereof, and is not limited thereto as long as it is interpretable by the generative artificial intelligence model 20.

[0018] The reference information D2 is information retrieved from an external database, knowledge base, or other information source and used as part of the prompt information D3 to enhance the accuracy, comprehensiveness, or specificity (specialization) when the generative artificial intelligence model 20 generates the response information D4. The reference information D2 may be dynamically retrieved by a search module within the information providing system 1 or an external database search function based on the question information D1 or the intermediate response information D4 by the generative artificial intelligence model 20 in the retrieval-augmented generation (RAG) mechanism, or may be directly included in and provided with the question information D1. The reference information D2 may be text data in natural language (e.g., documents, articles, papers), structured data (e.g., tabular data, JSON data), or a specific data structure such as a knowledge graph, and is not limited thereto as long as it is usable by the generative artificial intelligence model 20.

[0019] The prompt information D3 is information input to the generative artificial intelligence model 20 in a form that includes the question information D1, instructions, constraints, and / or reference information D2 in order to cause the generative artificial intelligence model 20 to execute a specific task or generate the response information D4 in a specific format. The prompt information D3 may mainly be text data in natural language, and is not limited thereto as long as it can correspond to the input format of the generative artificial intelligence model 20.

[0020] The response information D4 is data generated by the generative artificial intelligence model 20 based on the input question information D1, and is information that contributes to solving the problem indicated by the question information D1 or to achieving the objective, or provides new insights or creative works. The response information D4 can take various forms depending on the function and purpose of use of the generative artificial intelligence model 20, such as natural language text data (e.g., text, summary, code), image data, audio data, video data, or structured data (e.g., JSON data, XML data), but is not limited to these as long as it can be generated by the generative artificial intelligence model 20.

[0021] (Configuration of Information Provisioning Device 3) Figure 2 is a block diagram showing an example of an information providing device 3. The information providing device 3 comprises a control unit 30 composed of a processor, a storage unit 31 composed of an HDD, SSD, memory, etc., a communication unit 32 which is a communication interface with the network 6, an input unit 33 composed of a keyboard, mouse, etc., and a display unit 34 composed of a display, etc. Note that the input unit 33 and the display unit 34 may be omitted.

[0022] The memory unit 31 stores the prompt syntax data 310 and the information processing program 311, as well as the operating system, other programs, various types of data, etc.

[0023] The prompt syntax data 310 is used to generate prompt information D3 from question information D1, and includes multiple syntaxes. Each syntax specifies reference information D2 to be referenced when generating answer information D4, or specifies a task to be imposed on the generative artificial intelligence model 20.

[0024] The control unit 30 functions as a question receiving unit 300, a prompt generation unit 301, and an answer provision unit 302 by executing an information processing program 311 stored in the storage unit 31. Each of the units 300 to 302 of the control unit 30 functions as a user interface with the user U by transmitting display information to the user terminal device 4 to display various display screens on the user terminal device 4 and accepting various input operations through the display screens.

[0025] The question reception unit 300 performs question reception processing to receive question information D1.

[0026] The prompt generation unit 301 performs a prompt generation process that generates prompt information D3, which instructs the generative artificial intelligence model 20 to output answer information D4 while referring to reference information D2, based on the question information D1.

[0027] The response provision unit 302 performs a response provision process that provides response information D4 output from the generative artificial intelligence model 20 by inputting prompt information D3 to the generative artificial intelligence model 20.

[0028] (Hardware configuration of each device) Figure 3 is a hardware configuration diagram showing an example of the computer 900 that constitutes each device. Each device 2 to 5 in the information provision system 1 is composed of a general-purpose or dedicated computer 900.

[0029] As shown in Figure 3, the computer 900 comprises, as its main components, a bus 910, a processor 912, memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication interface unit 922, an external device interface unit 924, an I / O device interface unit 926, and a media input / output unit 928. Note that the above components may be omitted as appropriate depending on the intended use of the computer 900.

[0030] The processor 912 consists of one or more arithmetic processing units (CPU (Central Processing Unit), MPU (Micro-Processing Unit), DSP (Digital Signal Processor), GPU (Graphics Processing Unit), NPU (Neural Processing Unit), etc.) and operates as a control unit that oversees the entire computer 900. The memory 914 stores various data and programs 930 and consists of volatile memory (DRAM, SRAM, etc.) that functions as main memory, and non-volatile memory (ROM), flash memory, etc.

[0031] The input device 916 consists of, for example, a keyboard, mouse, numeric keypad, or electronic pen, and functions as an input unit. The output device 917 consists of, for example, a sound (voice) output device or a vibration device, and functions as an output unit. The display device 918 consists of, for example, a liquid crystal display, an organic EL display, electronic paper, or a projector, and functions as an output unit. The input device 916 and the display device 918 may be configured as an integrated unit, such as a touch panel display. The storage device 920 consists of, for example, an HDD or SSD, and functions as a storage unit. The storage device 920 stores various data necessary for the execution of the operating system and program 930.

[0032] The communication I / F unit 922 is connected by wire or wireless to a network 940 such as the Internet or an intranet (which may be the same as network 6 in Figure 1) and functions as a communication unit that sends and receives data with other computers according to a predetermined communication standard. The external device I / F unit 924 is connected by wire or wireless to external devices 950 such as cameras, printers, scanners, and reader / writers and functions as a communication unit that sends and receives data with external devices 950 according to a predetermined communication standard. The I / O device I / F unit 926 is connected to I / O devices 960 such as various sensors and actuators and functions as a communication unit that sends and receives various signals and data with the I / O devices 960, such as detection signals from sensors and control signals to actuators. The media input / output unit 928 consists of, for example, a drive device such as a DVD drive or CD drive, a memory card slot, and a USB connector, and reads and writes data to media (non-temporary storage media) 970 such as DVDs, CDs, memory cards, and USB memory.

[0033] In the computer 900 having the above configuration, the processor 912 calls and executes the program 930 stored in the storage device 920 in the memory 914, and controls various parts of the computer 900 via the bus 910. The program 930 may also be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded on the media 970 in an installable or executable file format and provided to the computer 900 via the media input / output unit 928. The program 930 may also be provided to the computer 900 by downloading it via the network 940 through the communication interface unit 922. Furthermore, the computer 900 may implement various functions realized by the processor 912 executing the program 930 using hardware such as an FPGA (Field-Programmable Gate Array) or ASIC (Application Specific Integrated Circuit).

[0034] Computer 900 is an electronic device of any form, consisting of, for example, a stationary computer or a portable computer. Computer 900 may be a client computer, a server computer, a cloud computer, or an embedded computer such as a control panel or controller (including microcontrollers, programmable logic controllers, and sequencers).

[0035] (Operation of Information Provision System 1) The following describes a series of operations performed by the information provision system 1. This series of operations is performed through the cooperation of each part 300-302 of the information provision device 3 (each process of the information provision method executed by the information processing program 311), the generative AI device 2, the user terminal device 4, and the database device 5.

[0036] (In the case of a single prompt) Figure 4 is a flowchart illustrating an example of the operation (one stage) of the information provision system 1. The following explanation assumes that reference information D2 is registered in the reference information management database 50.

[0037] First, in step S100, the user terminal device 4 transmits question information D1 based on the user U's input operation on the display screen to the information providing device 3.

[0038] Next, in step S110 (question reception processing), the question reception unit 300 of the information providing device 3 receives the question information D1 transmitted in step S100, thereby accepting the question information D1.

[0039] Next, in step S200 (prompt generation process), the prompt generation unit 301 generates prompt information D3 that instructs the generative artificial intelligence model 20 to output answer information D4 while referring to reference information D2, based on the question information D1 received in step S110.

[0040] Next, in step S210 (answer provision process), the answer provision unit 302 inputs the prompt information D3 generated in step S200 into the generative artificial intelligence model 20, thereby generating answer information D4 as an output result from the generative artificial intelligence model 20.

[0041] Next, in step S220 (answer provision processing), the answer provision unit 302 sends display screen information for displaying the answer information D4 generated in step S210 to the user terminal device 4, which is the source of the question information D1. At this time, the display screen information may also include the prompt information D3 generated in step S200.

[0042] Next, in step S230, when the user terminal device 4 receives the display screen information transmitted in step S220, it displays a display screen containing the response information D4 based on that display screen information.

[0043] Through the above series of processes, the answer information D4 to the question information D1 is provided to user U. The same series of processes will be performed again if user U inputs new question information D1.

[0044] In the following first embodiment, the explanation will focus on a case where, after a pharmacist (user) using the user terminal device 4 provides medication guidance to a patient, the information provision device 3 generates evaluation information that assesses the quality of the pharmacist's medication guidance to the patient based on the conversation between the pharmacist and the patient, and provides this evaluation information to the user.

[0045] <First Embodiment> Next, a first embodiment for carrying out the present invention will be described with reference to the above-mentioned common embodiment drawings. Note that detailed explanations of parts similar to those in the common embodiment regarding the functions and connections of each component in the system, the various data handled by each component, the configuration and operation of each part in each device, the various data handled by each device, and the operation and configuration in the flowchart will be omitted.

[0046] (Overview of the system according to the first embodiment) Information provision system 1 functions as a system for evaluating the quality of medication guidance provided by pharmacists to patients.

[0047] (Summary of each piece of information according to the first embodiment) Question information D1 is conversation information that includes recorded data of a conversation between a pharmacist and a patient. The conversation information may also include text data containing sentences from the user that represent information about the conversation, along with the recorded data. The recorded data may be input as a file in which the recorded data is recorded in any data format, or as a reference file name to access the file in which the recorded data is recorded.

[0048] The recorded data is not limited to audio data of a conversation between a pharmacist and a patient; it may also be text data obtained by transcribing such audio data, or a data format in which arbitrary information is extracted and structured from such text data.

[0049] Furthermore, conversational information may include supplementary information to complement the information about the patient receiving medication guidance. Examples of supplementary information include, but are not limited to, patient personal information, questionnaire information, prescription information, and medication history information; it may also include information about other patients.

[0050] Patient personal information refers to information that indicates the patient's attributes, etc. Examples of patient personal information include the patient's name, telephone number and address, insurer number, gender, age, height, and weight.

[0051] Questionnaire information is information that shows the patient's responses to a questionnaire. Questionnaire information includes, for example, the patient's answers to questions about their diagnosis, medication status, and the occurrence of side effects.

[0052] Prescription information is information that describes the contents of a prescription for a patient. Prescription information includes, for example, the names of each prescribed medication, the quantity, and the instructions for use. It may also include the name of the hospital that issued the prescription and the date of issue.

[0053] Medication history information is a systematic record of all aspects of a patient's drug treatment. This information includes, for example, the history of medications prescribed to the patient, handover information from the previous medication counseling session, a history of past medication counseling sessions, and medication history recorded in SOAP format (a common format used in the medical field for recording patient information).

[0054] Reference information D2 is knowledge information that contributes to the evaluation of medication guidance. The knowledge information may include, for example, scoring data that associates existing conversation examples between pharmacists and patients, scoring criteria corresponding to those conversation examples, and scoring values ​​corresponding to those scoring criteria.

[0055] Existing conversation examples between pharmacists and patients may exist for each evaluation item (described later). If conversation examples exist for each evaluation item, for example, the evaluation item for understanding the patient's situation (described later) may include conversation examples such as, "What do you usually do?", "What do you do when you're hungry?", "Do you consciously exercise?", "Is there anything you pay attention to in your diet?", and "What is your greatest pleasure?". Also, for example, the evaluation item for checking medication adherence (described later) may include conversation examples such as, "Are you taking your usual medication properly?", "Have you forgotten to take your medication recently?", "How many days' worth of each medication do you have left?", and "How much of each medication do you feel you have left?". There may be one or more conversation examples.

[0056] The scoring criteria corresponding to the given conversation example could be, for example, "What do you usually do?" with the scoring criterion "Able to ask the patient about their usual exercise, diet, and other lifestyle habits." Or, for example, "How are you feeling? Anything unusual?" with the scoring criterion "Does the doctor specifically check for any changes in the patient's physical condition or any side effects?" The conversation example and the scoring criteria do not need to correspond one-to-one; there may be common scoring criteria for multiple conversation examples, or there may be multiple scoring criteria for a single conversation example, and these are not the only examples.

[0057] The scoring value corresponding to the scoring criteria may be a numerical value, such as 8 out of 10, or a rank such as A or B. There is no one-to-one correspondence between scoring criteria and scoring values; a single scoring value may be assigned if all of the scoring criteria are met, or there may be multiple scoring values ​​depending on the degree to which a single scoring criterion is satisfied, and this is not limited to these cases.

[0058] Knowledge information may include patient personal information, medical questionnaire information, prescription information, medication history information, etc., registered for each patient. Furthermore, knowledge information may also include publicly available information such as package inserts, interview forms, various treatment guidelines, information on side effects, and general manuals and educational materials regarding medication guidance.

[0059] Response information D4 is evaluation information that assesses the quality of medication guidance provided by pharmacists to patients. The evaluation information may include, for example, at least one of the following: communication skills evaluation information and compliance evaluation information.

[0060] The dialogue skills evaluation information assesses the quality of medication guidance from the perspective of therapeutic conversational skills. Therapeutic conversational skills refer to professional dialogue techniques used by pharmacists to build trust with patients and create an environment where patients feel comfortable discussing their anxieties and questions. The dialogue skills evaluation information includes at least one evaluation item from the following categories: communication skills, understanding the patient's situation, information gathering and transmission, trust building, and presenting the benefits of medication. Each evaluation item is assessed, for example, by assigning points if the conversation content meets specific criteria.

[0061] Communication skills refer to evaluation items related to fundamental methods and operational standards for achieving smooth communication with patients. Examples of communication skills include clarifying and organizing the patient's responses, taking care not to be pushy, using an approach tailored to the patient's personality type, summarizing goals for the next visit at the end, and offering words of encouragement to the patient. However, these are not limited to these, and other technical elements that facilitate communication with patients may also be included.

[0062] Understanding the patient's situation is an evaluation item related to the process of identifying the patient's health status, background, and concerns regarding medication through active listening. Examples of understanding the patient's situation include listening to the patient's feelings about their illness and treatment, listening to the patient's daily habits, not talking unilaterally while waiting for the patient to speak, and not interrupting the patient. However, it is not limited to these and may include other information-gathering actions to understand the patient's overall situation.

[0063] Information gathering and communication is an evaluation item related to methods for obtaining necessary information through effective questioning techniques and providing clear and accurate information to patients. Examples of information gathering and communication include asking open questions to patients, asking questions that encourage patients to think for themselves, using an approach that is appropriate to the readiness (stage), and avoiding technical jargon and explaining things in simple terms, but it is not limited to these, and other methods for effectively gathering and communicating information may also be used.

[0064] Building trust is an evaluation item related to the process of removing psychological barriers between patients and pharmacists and creating a space for dialogue by demonstrating empathy. Examples of building trust include being able to speak to patients based on their medication history and lifestyle, creating a warm and gentle atmosphere, using positive language, being able to rephrase (positive change), and accepting what the patient says positively. However, it is not limited to these, and other actions that build a good relationship with patients may also be included.

[0065] Presenting the benefits of medication is an evaluation item related to means of motivating patients to actively participate in their treatment by specifically showing the effects, efficacy, and advantages of prescribed drugs. Examples of presenting the benefits of medication include providing information after confirming the patient's needs, adequately controlling the amount of information provided, adding benefits to the information provided, confirming the patient's understanding during the explanation, and communicating the specific life benefits of taking the medication. However, it is not limited to these, and other motivational methods to improve patient medication adherence may also be used.

[0066] Compliance assessment information refers to information that evaluates the quality of medication guidance from a pharmaceutical management perspective. Pharmaceutical management refers to the act of a pharmacist systematically managing a patient's drug therapy with the aim of maintaining and improving its effectiveness, safety, and appropriateness. Compliance assessment information includes at least one of the following evaluation items: confirmation of medication adherence, confirmation of changes in physical condition, clinical judgment ability, guidance style, and medication plan. For each evaluation item, a system may be adopted in which points are added if specific confirmation items are included in the conversation, and points are deducted if confirmation is not made when it is necessary.

[0067] Medication adherence checks are evaluation items related to the patient's medication adherence and the confirmation of remaining medication. Examples of medication adherence checks include whether the patient has missed doses, whether the circumstances and reasons for missed doses have been specifically confirmed, whether the type of medication and time of administration have been specifically confirmed, whether regular medications and previously prescribed medications unrelated to the current day's prescription have been included in the check, whether there is any remaining medication, whether the type and amount of remaining medication have been confirmed, and whether the reason for the remaining medication has been specifically confirmed. However, these are not limited to these, and other checks that accurately grasp the patient's medication adherence may also be included.

[0068] The "checking for changes in physical condition" is an evaluation item related to confirming the presence or absence of subjective symptoms related to changes in physical condition (such as symptoms that may indicate side effects). Examples of checking for changes in physical condition include whether the presence or absence of changes in physical condition or side effects has been specifically confirmed, whether the symptoms of side effects and the drugs involved have been specifically confirmed, whether the presence or absence of subjective symptoms has been specifically confirmed for drugs that may cause serious or severe side effects, whether the presence or absence of side effects has been confirmed for regular medications and medications prescribed in the past, and whether the degree of symptom improvement has been confirmed. However, it is not limited to these, and other confirmation items for evaluating the effectiveness and safety of drug therapy may also be used.

[0069] Clinical judgment ability refers to the comprehensive ability to accurately understand patient information and physician explanations, combine them with pharmaceutical knowledge, and determine an appropriate treatment plan. Examples of clinical judgment ability include whether information other than medication adherence and changes in physical condition (treatment objectives, subjective symptoms, disease state, physician's explanation, living situation, status in other departments, etc.) has been specifically confirmed; whether the patient's complaints and explanations have been confirmed to the extent that the disease state and treatment status can be understood; whether the reasons for changes (additions or deletions) to the current prescription or the reason for the visit have been confirmed; whether the effects, side effects, and changes in symptoms have been confirmed if the previous prescription has been changed; whether necessary information has been collected regarding the results of the previous prescription change and the current prescription change (including new prescriptions); whether objective evaluations from a pharmaceutical perspective (useful clinical data, etc.) have been confirmed; and whether the appropriateness of the prescription has been evaluated. However, it is not limited to these examples and may include other abilities for determining the necessity of pharmaceutical intervention.

[0070] The guidance style refers to evaluation items related to the basis, actual content, and quality of medication guidance. Examples of guidance style include whether the pharmacist's thoughts and judgments (assessment) based on patient information and circumstances are explained in conversation during guidance, whether the basis for the guidance content is clearly explained, whether individualized guidance is provided based on information such as the patient's living situation, symptoms, and whether they drive, whether guidance is provided on the correct way to take each prescribed medication and how to maintain safety and effectiveness, whether the reasons and methods of guidance are explained in detail, whether drug side effects and safety measures are explained in detail and appropriately, whether the guidance content is individualized and patient-centered, whether lifestyle guidance is provided to enhance the effectiveness of drug therapy, whether specific and motivating explanations and guidance are provided that patients can actually take action, whether specific behavioral goals and numerical targets that lead to the success of drug treatment are explained, and whether the patient brings their medication record book. However, it is not limited to these, and other elements that ensure the quality of medication guidance may also be included.

[0071] A medication plan is an evaluation item related to confirming the continuity of previously established medication plans and developing new ones. Examples of medication plans include whether the patient has been confirmed with the previous medication plan, whether the patient's medication status has been checked based on the previous plan, whether changes since the last time (improvements and deteriorations) have been confirmed, and whether the next plan has been developed based on the content of the current guidance, outlining items to be checked and points to observe. However, it is not limited to these, and may include other planning elements for practicing continuous pharmaceutical management.

[0072] Furthermore, the evaluation information may include scoring values ​​for each evaluation item calculated based on the scoring criteria included in the aforementioned scoring data. The scoring values ​​may be expressed as, for example, a numerical value out of 10, or as ranks such as S, A, B, C, and D. In addition, the evaluation information may include a total score, which is the sum of the scoring values ​​for each evaluation item, and an overall rank based on that total score.

[0073] Response information D4 may include feedback information that suggests improvements to medication guidance for pharmacists, in addition to evaluation information. Feedback information is information that supports pharmacists' self-reflection and skill improvement by specifically showing the good points and areas for improvement in the pharmacist's medication guidance based on the evaluation information. The areas for improvement may be practical content that pharmacists can use in their next medication guidance, such as providing specific conversation examples or action guidelines. The feedback information may also include quotations of highly rated statements and, conversely, recommended conversation examples for improving items that received low ratings.

[0074] (Operation of the information provision system 1 according to the first embodiment) The information provision system according to the first embodiment operates as shown in the flowchart in Figure 4. In this embodiment, the case in which prompt information D3 is generated based on question information D1 while referring to reference information D2 has been described. However, if it is desired to quickly obtain answer information D4 from the generative artificial intelligence model 20, prompt information D3 may be generated based on question information D1 without referring to reference information D2.

[0075] (User interface according to the first embodiment) Figure 5 shows an example of a display screen. When the user terminal device 4 receives display screen information transmitted from the information providing device 3, it displays a display screen including response information D4 based on that display screen information. In the example in Figure 5, the display screen includes at least a recording button 40, a conversation playback function 41, a conversation information display screen 42, and an evaluation information display screen 43.

[0076] When a pharmacist operating the user terminal device 4 presses the record button 40, the microphone (input device 916 provided by the user terminal device 4) starts recording the conversation between the pharmacist and the patient. Pressing the record button 40 again stops the recording.

[0077] When a pharmacist operating the user terminal device 4 presses the play button 410, the conversation playback function 41 is activated. The conversation playback function 41 has the function of playing the recorded data as audio from the speaker (output device 917 provided by the user terminal device 4) by pressing the play button 410, and adjusting the volume by operating the volume button 411.

[0078] The conversation information display screen 42 displays text data that is a transcription of the recorded conversation between the pharmacist and the patient. The conversation information display screen 42 may also display information that summarizes the conversation between the pharmacist and the patient in a predetermined format (such as SOAP format or SO format).

[0079] The evaluation information display screen 43 displays evaluation information (dialogue technology evaluation information) as response information D4. The evaluation information displayed on the evaluation information display screen 43 may be further selected by the pharmacist. For example, if a portion of the evaluation information is displayed for each predetermined item on the evaluation information display screen 43 in Figure 5, the pharmacist may configure the system to switch the display or hide of each piece of information, or change the layout of the display area, by checking the checkbox 430 for the evaluation information items they deem necessary and unchecking the checkbox 430 for the evaluation information items they deem unnecessary.

[0080] As described above, according to the information provision device 3 and information provision method of the first embodiment, when prompt information D3 generated based on question information D1 while referring to reference information D2 is input to the generative artificial intelligence model 20, response information D4 is output from the generative artificial intelligence model 20. Therefore, the quality of pharmacists' medication guidance can be evaluated objectively and efficiently, and support for improving pharmacists' skills can be provided. Furthermore, when prompt information D3 is generated based on question information D1 without referring to reference information D2, response information D4 can be efficiently obtained from the generative artificial intelligence model 20.

[0081] <Other Embodiments> The present invention is not limited to the embodiments described above, and can be implemented with various modifications without departing from the spirit of the invention. All such modifications are included in the technical concept of the present invention.

[0082] In the above embodiment, the functions of each part of the information providing device 3 were described as being realized in a single device, but the functions of each part may be distributed among multiple devices to be realized in multiple devices. Alternatively, the control unit of the user terminal device 4 or the control unit of the database device 5 may execute the information processing program 311 to function as the information providing device 3.

[0083] In the above embodiment, the case in which the database device 5 includes a reference information management database 50 was described, but part or all of the reference information management database 50 may be stored in an external device (or more) connected to the network 6 or in any storage medium. Alternatively, the reference information management database 50 may be stored in the storage unit 31 of the information providing device 3.

[0084] In the above embodiment, the case in which the information providing device 3 operates according to the flowchart shown in Figure 4 has been described, but the execution order of each step may be changed as appropriate, some steps may be omitted, or other steps may be added. For example, when the prompt generation unit 301 generates prompt information D3 in the prompt generation process (step S200), a step may be added in which the prompt information D3 is provided to the user terminal device 4, and a user U input operation to change the prompt information D3 is received via the display screen of the user terminal device 4, and the prompt information D3 is changed.

[0085] In the above embodiment, the generative artificial intelligence model 20 generates response information D4 by referring to reference information D2 stored in the reference information management database 50 when prompt information D3 is input. In contrast, the generative artificial intelligence model 20 may use a trained model in which reference information D2 has been systematically incorporated by including reference information D2 as part of the training dataset. In that case, the generative artificial intelligence model 20 can generate response information D4 by referring to the reference information D2 incorporated into the generative artificial intelligence model 20 based on the instructions of prompt information D3. Furthermore, some or all of the knowledge information that contributes to the evaluation of medication guidance contained in reference information D2 may be included in question information D1. This allows the generative artificial intelligence model 20 to obtain highly accurate response information D4 using only question information D1 without referring to reference information D2.

[0086] <Example of a prompt> An example of prompt information D3 in the first embodiment described above is shown below. Note that the prompt shown here is merely an example, and the task definition, agent role, and specific instructions can be modified as appropriate without departing from the spirit of the present invention. This prompt provides a specific means for stably obtaining the desired output (dialogue technology evaluation information) by giving the generative artificial intelligence model 20 its role, available tools, and constraints.

[0087] "#role You are a specialist in pharmacist education. You are in charge of a project to improve the quality of medication guidance. #instruction Based on the given conversation between the pharmacist and the patient regarding medication guidance, please evaluate the following items and output the results according to the specified output format. #Premise This conversation is from a pharmacist-patient medication guidance session. Please evaluate it logically according to the scoring criteria, and ensure consistency even when outputting the same voice multiple times. # Scoring Rules Please score all items according to the criteria provided. -Please evaluate the product by referring to the "scoring criteria" and "example conversations" listed in the scoring section. -If there is no clear relevant statement in the conversation, please give it a score of "0". However, it does not need to be exactly the same word for word. -When outputting the breakdown, please clearly indicate which statements or attitudes were evaluated positively. -Please specify the score out of a possible total for each category in the breakdown. -As stated in the scoring criteria, if the standard is met, you will receive X points; if you have achieved even more than this, you will receive X points. # Scoring criteria <Category>: Communication Techniques <Item>: Clarifying and summarizing the patient's responses. <Example conversation>: Is that correct? / So, does that mean...? <Score>: 0-10 points <Scoring Criteria>: - Asking questions about what the patient says: 6 points - In addition to the above, the points were clarified, confirmed, and the intentions were summarized: 10 points <Category>: Understanding Patient Status <Item>: We are able to hear the patient's feelings about their illness and treatment. <Example Conversation>: How do you feel about your HbA1c level this time, [Name]? / What does diabetes mean to you, [Name]? / Isn't it difficult to continue treatment for diabetes? <Score>: 0-5 points <Scoring Criteria>: - You can hear how the patient is feeling: 5 points <Category>: Information gathering and dissemination <Item>: Asking open-ended questions <Example conversation>: How was your day? / What happened? <Score>: 0-5 points <Scoring Criteria>: - Able to ask questions: 3 points - Asking questions in a friendly tone: 5 points <Category>: Building Trust <Item>: We are able to provide support based on medication history records and lifestyle habits. <Content>: The ability to approach and ask questions of patients based on their medication history, lifestyle, and past relationship. <Example conversation>: ○○, you're always so early! / You look a little down, what's wrong? / How did it go? <Score>: 0-10 points <Scoring Criteria>: - Able to proactively reach out to patients: 5 points -In addition to the above, the ability to make relevant comments to patients based on their past memories and medication history: 8 points - In addition to the above two points, the ability to respond to patients with positive remarks and engage in dialogue: 10 points <Category>: Presenting the benefits of taking medication <Item>: Information is provided after confirming the patient's needs. <Content>: Ask the patient questions to find out what they want to know before providing information. Confirm the patient's level of understanding and avoid repeating information. <Example Conversation>: What did your doctor tell you about this medication? / Was there anything unclear? / How was XX explained to you? <Score>: 0-10 points <Scoring Criteria>: -Confirming information from doctors and other medical professionals, as well as the individual's knowledge, before speaking: 6 points -In addition to the above, we have confirmed the patient's wishes and understanding: 10 points #Output format <Score>: {Total points earned} / 100 points (Rank) - Rank the scores and add a short, uplifting phrase for each rank. <Breakdown>: (Category in which points were earned and the points earned (points earned / maximum score are as listed below)) • Communication skills: XX / 25 points (Please specify which statements or attitudes were praised.) • Patient status assessment: XX points / 25 points (Please specify which statements or attitudes were praised.) • Information gathering and communication: XX points / 25 points (Please specify which statements or attitudes were praised.) • Building trust: XX / 25 points (Please specify which statements or attitudes were praised.) • Presentation of medication benefits: XX points / 25 points (Please specify which statements or attitudes were praised.) <Positive points>: -Based on actual statements, briefly list three characteristics of actions or statements that received high marks. -Examples: "-They provided empathetic responses that showed they understood the patient's feelings," "-They were able to ask insightful questions about the patient's lifestyle." <Improvements>: - For items where the score was low or no relevant comments were made, briefly list about three points that should be improved in the future. -Example: "There were few open-ended questions, and information gathering was one-way."

[0088] While several embodiments of this disclosure have been illustrated above, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. Furthermore, the embodiments described above can be implemented in combination with each other. [Explanation of Symbols]

[0089] 1... Information provision system, 2... Generative AI device, 3... Information provision device, 4... User terminal device, 5...Database device, 20...Generative artificial intelligence model, 30...Control unit, 31...Storage unit, 32...Communication unit, 33...Input unit, 34...Display unit, 50...Reference information management database, 300...Question reception unit, 301...Prompt generation unit, 302...Answer provision unit, 310... Prompt syntax data, 311... Information processing program

Claims

1. A method of providing information using a computer, The reception process for receiving question information, A prompt generation process generates prompt information that instructs a generative artificial intelligence model to output answer information based on the aforementioned question information, The process involves inputting the prompt information into the generative artificial intelligence model and then providing the response information output from the generative artificial intelligence model. The aforementioned question information is, This is conversational information, including recorded data of conversations between pharmacists and patients. The aforementioned response information is, This is evaluation information that assesses the quality of medication guidance provided by the aforementioned pharmacist to the aforementioned patient. The aforementioned question information is, It further includes knowledge and information that can be used to evaluate medication guidance, The aforementioned knowledge information is, This includes scoring data that associates existing conversation examples between pharmacists and patients, scoring criteria corresponding to those conversation examples, and scoring values ​​corresponding to those scoring criteria. Information provision method.

2. A method of providing information using a computer, The reception process for receiving question information, A prompt generation process generates prompt information that instructs a generative artificial intelligence model to output answer information based on the aforementioned question information, The process involves inputting the prompt information into the generative artificial intelligence model and then providing the response information output from the generative artificial intelligence model. The aforementioned question information is, This is conversational information, including recorded data of conversations between pharmacists and patients. The aforementioned response information is, This is evaluation information that assesses the quality of medication guidance provided by the aforementioned pharmacist to the aforementioned patient. The prompt generation process described above is: Based on the aforementioned question information, prompt information is generated to output the aforementioned answer information while referring to the reference information. The aforementioned reference information is, Includes knowledge and information that can be used to evaluate medication guidance. The aforementioned knowledge information is, This includes scoring data that associates existing conversation examples between pharmacists and patients, scoring criteria corresponding to those conversation examples, and scoring values ​​corresponding to those scoring criteria. Information provision method.

3. The aforementioned evaluation information is, The evaluation includes at least one of the following: dialogue skills evaluation information that assesses the quality of medication guidance from the perspective of therapeutic conversational techniques, and compliance evaluation information that assesses the quality of medication guidance from the perspective of pharmaceutical management. The method for providing information according to either claim 1 or claim 2.

4. The aforementioned dialogue technology evaluation information is The evaluation criteria include possessing at least one of the following: communication skills, understanding the patient's situation, information gathering and dissemination, building trust, and demonstrating the benefits of medication. The method of providing information as described in claim 3.

5. The aforementioned compliance evaluation information is, The evaluation criteria must include at least one of the following: medication adherence, monitoring of changes in physical condition, clinical judgment ability, guidance style, and medication plan. The method of providing information as described in claim 3.

6. The aforementioned response information is, This further includes feedback information indicating suggestions for improving medication guidance for the aforementioned pharmacist. The method for providing information according to either claim 1 or claim 2.

7. An information providing device that provides information using a computer, The reception desk accepts questions and information, A prompt generation unit generates prompt information that instructs a generative artificial intelligence model to output answer information based on the aforementioned question information, The system includes an answer providing unit that provides the answer information output from the generative artificial intelligence model by inputting the prompt information into the generative artificial intelligence model, The aforementioned question information is, This is conversational information, including recorded data of conversations between pharmacists and patients. The aforementioned response information is, This is evaluation information that assesses the quality of medication guidance provided by the aforementioned pharmacist to the aforementioned patient. The aforementioned question information is, It further includes knowledge and information that can be used to evaluate medication guidance, The aforementioned knowledge information is, This includes scoring data that associates existing conversation examples between pharmacists and patients, scoring criteria corresponding to those conversation examples, and scoring values ​​corresponding to those scoring criteria. Information provision device.

8. An information providing device that provides information using a computer, The reception desk accepts questions and information, A prompt generation unit generates prompt information that instructs a generative artificial intelligence model to output answer information based on the aforementioned question information, The system includes an answer providing unit that provides the answer information output from the generative artificial intelligence model by inputting the prompt information into the generative artificial intelligence model, The aforementioned question information is, This is conversational information, including recorded data of conversations between pharmacists and patients. The aforementioned response information is, This is evaluation information that assesses the quality of medication guidance provided by the aforementioned pharmacist to the aforementioned patient. The prompt generation unit, Based on the aforementioned question information, prompt information is generated to output the aforementioned answer information while referring to the reference information. The aforementioned reference information is, Includes knowledge and information that can be used to evaluate medication guidance. The aforementioned knowledge information is, This includes scoring data that associates existing conversation examples between pharmacists and patients, scoring criteria corresponding to those conversation examples, and scoring values ​​corresponding to those scoring criteria. Information provision device.

Images