Information processing system, information processing method, and program

Abstract

To suppress a work burden for creating a medical sentence of a medical worker.SOLUTION: In the display step, a chat room for a medical worker to chat is displayed, and in the chat room, both an input of the medical worker and a response to the input are displayed in time series, in the reception step, a selection step is included, in the selection step, the input for specifying the patient related to the creation of the medical sentence is received via the chat room, and in the acquisition step, conversation data including content related to a conversation between the patient specified in the reception step and the medical worker is acquired, wherein the conversation data is data used for creating the medical sentence.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] In addition to dispensing medicines prescribed by doctors, medical professionals (for example, pharmacists at pharmacies) also have the task of acquiring and managing patient data through conversations with patients. Conventionally, technologies to support the work of medical professionals have been proposed, and Patent Document 1 discloses a system for improving the quality of medication instruction work. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-047624 Summary of the Invention [Problem to be solved by the invention]

[0004] The work of medical professionals involves creating medical documents to record interactions with patients. For example, creating medical documents is a burden for medical professionals when they have other tasks that require their attention, such as dispensing medicines and providing medication advice, but it is a necessary task that cannot be omitted.

[0005] The present invention aims to reduce the workload of medical professionals in creating medical documents. [Means for solving the problem]

[0006] According to the present invention, there is provided an information processing method for assisting patients in creating medical documents, the information processing method comprising a display step, a reception step, and a conversation acquisition step, wherein the display step displays a chat room for medical professionals to chat, and the chat room displays both the medical professional's input and responses to the input in chronological order, the reception step includes a selection step, and the selection step receives the input to identify the patient involved in the creation of the medical document via the chat room, and the conversation acquisition step includes an acquisition step, and the acquisition step acquires conversation data including content related to the conversation between the patient identified in the reception step and the medical professional, and the conversation data is data used in creating the medical document.

[0007] According to the present invention, when acquiring conversation data between patients and medical professionals to be used in creating medical documents, input relating to the identification of the patient is accepted by displaying a chat room, making it easy for medical professionals to use and reducing the workload of medical professionals. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 shows an example of a system configuration of an information processing system 100 according to an embodiment. [Figure 2] FIG. 2A is a block diagram showing the hardware configuration of the medical information server 1, FIG. 2B is a block diagram showing the hardware configuration of the reception terminal 4, and FIG. 2C is a block diagram showing the hardware configuration of the conversation data acquisition terminal 5. [Figure 3] FIG. 3A is a functional block diagram of the control unit 12 shown in FIG. 2A, and FIG. 3B is a functional block diagram of the control unit 52 shown in FIG. 2C. [Figure 4] FIG. 4 is an example of a screen displayed on conversation data acquisition terminal 5. [Figure 5]FIG. 5 shows a screen on which an object se is displayed for specifying a patient for whom conversation data is to be acquired (for whom medication instruction is to be started). [Figure 6] FIG. 6 shows a screen on which an object sf for selecting whether or not to proceed to the process of acquiring conversation data (starting medication instruction) is displayed. [Figure 7] FIG. 7 shows a screen on which an object ob1 for acquiring conversation data is displayed. [Figure 8] FIG. 8 shows the screen in the state where conversation data is being acquired. [Figure 9] FIG. 9 shows a screen on which an object sg for selecting whether or not to terminate acquisition of conversation data is displayed. [Figure 10] FIG. 10 shows a screen on which an object si for selecting whether or not to create a medical document is displayed. [Figure 11] FIG. 11 is a flowchart showing the flow of an information processing method before starting to create a medical document in the information processing system 100 according to the embodiment. [Figure 12] Fig. 12A is an explanatory diagram of data output from the pharmacy to the medical information server 1. Fig. 12B is an explanatory diagram schematically showing an example of the type of stored data DT0 as a database stored in the memory unit 11 of the medical information server 1 shown in Fig. 12A. [Figure 13] FIG. 13 is an explanatory diagram of data exchanged between the medical information server 1, the large-scale language model server 2, and the speech-to-text server 3. [Figure 14] FIG. 14 is an explanatory diagram of data exchanged between the medical information server 1 and the large-scale language model server 2 after the data exchange shown in FIG. [Figure 15]Figure 15A shows an example of medical data that is later in time series than the data shown in Figure 15B. Figure 15B shows an example of medical data that is earlier in time series than the data shown in Figure 15A. In Figures 15A and 15B, data shown in gray is non-output medical data (data that is not output to the large-scale language model server 2). [Figure 16] Fig. 16A shows an example of pre-processed character data d2, and Fig. 16B shows an example of processed character data d3. [Figure 17] FIG. 17 is an example of medical text MT1. [Figure 18] FIG. 18 is a flowchart showing the flow of an information processing method when the information processing system 100 according to the embodiment creates a medical document. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. Various features shown in the following embodiments can be combined with each other. Furthermore, each feature can be an invention independently.

[0010] 1. Description of the configuration of the embodiment 1-1. Overview of each configuration The information processing system 100 can support the creation of medical documents (see FIG. 17) that medical professionals, such as pharmacists, need to create. The information processing system 100 employs chat in at least a portion of the interface of the information processing device used by medical professionals, making it easy to understand the various operations required to receive support for creating medical documents from the information processing system 100, and is configured to enable medical professionals to smoothly obtain medical documents.

[0011] As shown in Fig. 1, the information processing system 100 includes a medical information server 1, a large-scale language model server 2 (an example of a large-scale language model), a speech-to-text server 3, a reception terminal 4, and a conversation data acquisition terminal 5. These are connected to each other so as to enable the exchange of information via a communication network 6 (e.g., the Internet, etc.). Note that the communication network 6 may be a closed network, partly or entirely separated from the Internet.

[0012] The information processing system 100 is capable of executing a first information processing (corresponding to the flowchart in FIG. 11) that is executed mainly on the pharmacy side terminal (conversation data acquisition terminal 5), and a second information processing (corresponding to the flowchart in FIG. 18) that is executed mainly on the medical information server 1 side. When the first information processing is executed, the second information processing is executed, and as a result, a medical document is generated. The first information processing (first information processing method) is, for example, information processing executed when acquiring conversation data, and various user interfaces are utilized. The conversation data is data used to create medical documents. In one embodiment, this conversation data corresponds to the voice conversation data d1 (see FIG. 12A), is sent to the medical information server 1, and is processed by the second information processing. The second information processing (second information processing method) is, for example, information processing for generating medical text using the conversation data generated in the first information processing. These information processes will be explained later in "4. Flow of information processing in the information processing system 100."

[0013] Each component of the information processing system 100, such as the medical information server 1, the reception terminal 4, and the conversation data acquisition terminal 5, has one or more functions (functional units). Here, each component may be configured as a single information processing device as shown in FIG. 1, or may be configured as multiple independent devices configured to be able to exchange information. The same applies to each functional unit, such as the control unit described below. Each component included in the information processing system 100 will be further described below.

[0014] The medical information server 1 is communicatively connected to the pharmacy's information processing device (in this embodiment, a reception terminal 4 and a conversation data acquisition terminal 5), the large-scale language model server 2, and the speech-to-text server 3 via a communication network 6. The medical information server 1 functions as a database, and therefore all data exchanged in the information processing system 100 is accumulated in the memory section of the medical information server 1. The medical information server 1 has the function of automatically generating medical documents in cooperation with the pharmacy's information processing device, the large-scale language model server 2, and the speech-to-text server 3. The medical documents generated by the medical information server 1 are sent to the pharmacy's information processing device and used by medical professionals. This reduces the burden on medical professionals of creating medical documents.

[0015] The large-scale language model server 2 has a sentence generation unit 21. This sentence generation unit 21 has, for example, a neural network trained using a large amount of training data, and has the function of generating responses to data (prompts) output from the medical information server 1 and outputting them to the medical information server 1. The large-scale language model server 2 is not particularly limited, but it is possible to adopt, for example, ChatGPT by OpenAI, Inc.

[0016] The speech-to-text server 3 includes a transcription unit 31. The transcription unit 31 is configured to generate text conversation data by converting the content of a conversation into text using audio conversation data. The transcription unit 31 includes, for example, a neural network trained using a large amount of training data (audio training data). The transcription unit 31 has a function of receiving data (audio data) output from the medical information server 1 and outputting the data as text data to the medical information server 1. In the embodiment, the transcription unit 31 is described as being configured as a trained neural network, but this is not limited thereto. For example, the transcription unit 31 may be configured to analyze and convert audio data into text according to a predetermined algorithm. The speech-to-text server 3 is not particularly limited, but may include, for example, Whisper (registered trademark) by OpenAI, Inc.

[0017] The reception terminal 4 is an information processing device (for example, a personal computer) located in, for example, a pharmacy. The reception terminal 4 is configured to allow a medical professional to input patient data. In other words, the reception terminal 4 is configured to be able to receive various data input by a medical professional. Furthermore, the reception terminal 4 is configured to display the patient data on a display unit (not shown) so that the medical professional can obtain the patient data using the reception terminal 4.

[0018] The conversation data acquisition terminal 5 is an information processing device that has a device such as a microphone and is configured to acquire conversation data. In the embodiment, the conversation data acquisition terminal 5 is described as being separate from the reception terminal 4, but the conversation data acquisition terminal 5 may be integrated with the reception terminal 4. The conversation data acquisition terminal 5 can be configured, for example, as a dedicated voice recorder or a mobile terminal on which a voice acquisition application is implemented. Note that conversation data may be acquired from a microphone connected to the conversation data acquisition terminal 5 via a communication unit (described later) in a wired or wireless manner (for example, Bluetooth (registered trademark)). The mobile terminal can be, for example, a smartphone terminal or a tablet terminal.

[0019] In one example of the embodiment, when the conversation data acquisition terminal 5 acquires conversation data (voice data), the conversation data (voice data in the embodiment) is transmitted from the conversation data acquisition terminal 5 to the reception terminal 4. Then, the reception terminal 4 outputs the patient data and the conversation data together to the medical information server 1. This prevents the patient data related to the current prescription and the conversation data related to the current prescription from being separated, and allows the medical information server 1 to process them appropriately. The data transmission configuration is not limited to this, and when the conversation data acquisition terminal 5 acquires conversation data (voice data in this embodiment), it can output the data from the conversation data acquisition terminal 5 to the medical information server 1 via the communication network 6, and the information can be compiled on the medical information server 1 side.

[0020] 1-2. Functional Block Description As shown in Fig. 2A, the medical information server 1 has a communication unit 10, a memory unit 11, a control unit 12, an output unit 13, and an input unit 14, and these components are electrically connected within the medical information server 1 via a communication bus 15. Also, as shown in Fig. 3A, the control unit 12 has a data acquisition unit 121, a medical text generation unit 122, and an encoding unit 123. Furthermore, the medical text generation unit 122 has an output generation unit 122a and an adjustment unit 122b. As shown in Figure 2B, the reception terminal 4 has a communication unit 40, a memory unit 41, a control unit 42, an output unit 43, and an input unit 44, and these components are electrically connected within the reception terminal 4 via a communication bus 45. 2C, conversation data acquisition terminal 5 has communication unit 50, storage unit 51, control unit 52, output unit 53, and input unit 54, and these components are electrically connected via communication bus 55 inside conversation data acquisition terminal 5. Also, as shown in FIG. 3B, control unit 52 has status acquisition unit 521, reception unit 522, conversation acquisition unit 523, display control unit 524, and creation instruction reception unit 525.

[0021] Each of the above components may be implemented by software or hardware. When implemented by software, various functions can be realized by a CPU executing a computer program. The program may be stored on a non-transitory computer-readable recording medium, provided as a downloadable file from an external server, or implemented by so-called cloud computing, in which a program stored in an external storage unit is read and functions are realized. When implemented by hardware, various circuits such as an ASIC, FPGA, or DRP can be used. The embodiments deal with various information and concepts encompassing such information. These are represented by high and low signal values ​​or quantum bits as a binary bit set consisting of 0s or 1s, and communication and calculations can be performed by the above software or hardware aspects. The software may be a general-purpose OS or a dedicated OS.

[0022] Next, we will explain examples of basic functions and basic configurations of the components of the medical information server 1, the reception terminal 4, and the conversation data acquisition terminal 5. In this explanation, the communication unit corresponds to the communication units 10, 40, and 50, the memory unit corresponds to the memory units 11, 41, and 51, the control unit corresponds to the control units 12, 42, and 52, the output unit corresponds to the output units 13, 43, and 53, and the input unit corresponds to the input units 14, 44, and 54.

[0023] The communication unit may employ a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc. The communication unit may also employ a configuration in which it is connected to the communication network 6 via a wireless communication means such as wireless LAN network communication, mobile communication such as 3G / LTE / 5G, or Bluetooth (registered trademark) communication. The communication unit may also be configured to use both the wired communication means and wireless communication means described above.

[0024] The storage unit stores various values ​​such as various programs executed by the control unit, constants, variables, and setting values. The storage unit 11 can be a storage device such as a solid state drive (SSD), or a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to program calculations. In addition to the storage unit, an external storage unit (for example, an external storage medium, cloud, etc.) may also be used.

[0025] The control unit is configured to execute various information processing (information processing methods). The control unit can be configured, for example, by a central processing unit (CPU). The control unit is also an example of a processor capable of executing desired programs. The control unit 12 realizes various information processing, for example, by reading out programs stored in the storage unit. Furthermore, information processing by the software of the medical information server 1, the reception terminal 4, or the conversation data acquisition terminal 5 is realized, for example, by processing various programs stored in the storage unit by the control unit as hardware.

[0026] The output unit is, for example, a display unit that displays images. The output unit is, for example, an audio output unit (e.g., a speaker) that displays audio. The output unit may be included in the housing of the medical information server 1, the reception terminal 4, or the conversation data acquisition terminal 5, or may be externally attached. The output unit as a display unit displays a graphical user interface (GUI) screen that can be operated by the user. The output unit may be, for example, a CRT display, a liquid crystal display, an organic light emitting diode (EL) display, a plasma display, an electronic paper display, or a display device such as a light that can be turned on or a projector.

[0027] The input unit is configured to accept, for example, operation inputs made by a user. The input unit is, for example, a microphone that acquires voice. The input unit may be included in the housing of the medical information server 1, the reception terminal 4, or the conversation data acquisition terminal 5, or may be attached externally. Regarding the function of accepting operation inputs, the input unit may employ, for example, a touch panel, a switch button, a mouse, a keyboard, etc.

[0028] 2. Functional configuration The functional configuration of the medical information server 1 and the conversation data acquisition terminal 5 according to this embodiment will be described with reference to Fig. 3. Information processing by software stored in the storage unit is specifically realized by a control unit, which is an example of hardware, and each functional unit included in the control unit is executed.

[0029] 2-1. Medical Information Server 1 The data acquisition unit 121 is configured to be able to acquire various data from the pharmacy terminals (the reception terminal 4 and the conversation data acquisition terminal 5), the large-scale language model server 2, the speech-to-text server 3, etc. In the embodiment, the data acquisition unit 121 is configured to be able to acquire conversation data and medical data. The data acquisition unit 121 is also configured to be able to acquire text conversation data from the transcription unit 31. These data will be described in detail later.

[0030] The medical text generation unit 122 is configured to generate medical text based on conversation data (text conversation data) and pharmaceutical data. The output generation unit 122a of the medical text generation unit 122 has a function of generating various prompts (for example, text generation prompts and accuracy improvement prompts, which will be described later). The adjustment unit 122b of the medical text generation unit 122 has a post-processing function. In other words, the adjustment unit 122b has a function of adjusting the content of the medical text MT1 by adding information to the medical text MT1 generated by the large-scale language model server 2 (for example, adding information such as a name that can identify an individual to the medical text MT1). Note that it is optional whether the medical information server 1 has the adjustment unit 122b.

[0031] The encoding unit 123 has a function of encoding part or all of the non-output medical data among the patient-related data. In other words, the encoding unit 123 has a function of encoding the non-output medical data so that the content of the non-output medical data is anonymized or abstracted. The non-output medical data is the patient data that is not output to the large-scale language model server 2. The medical information server 1 prevents individuals from being identified by outputting the encoded data. In other words, since the patient-related data includes, for example, data that could be personal information, in the embodiment, data that is not output to the large-scale language model server 2 (non-output medical data) is predetermined, but the medical information server 1 can encode the non-output medical data and include it in the output medical data.

[0032] 2-2. Conversation data acquisition terminal 5 The status acquisition unit 521 is configured to acquire status data of the patient. This status data may be acquired from the reception terminal 4, from the medical information server 1 that manages various types of information, or from both. The status data includes data such as the patient's name, as will be explained later.

[0033] The reception unit 522 is capable of receiving input for identifying a patient for whom medical documentation is being created. This input is received when a medical professional selects (e.g., taps) an object se (see FIG. 5) displayed on the display unit. Patient data is displayed in the object se. An example of patient data is the patient's name, such as "Mr. A," "Mr. B," "Mr. C," etc., displayed in the object se. The object se will be explained in detail later. By receiving the patient data, the reception unit 522 can subsequently identify (link) which patient's conversation data (audio data) belongs to.

[0034] The conversation acquisition unit 523 is configured to acquire conversation data (voice data in this embodiment). In this embodiment, a medical professional taps an object ob1 (see FIG. 7) displayed on the display unit of the conversation data acquisition terminal 5, whereby recording is performed to acquire the conversation data. The object ob1 will be described in detail later.

[0035] The display control unit 524 has a function of displaying a chat room. Specifically, for example, the display control unit 524 has a function of displaying chats in the chat room, and objects used when the reception unit 522 receives data or when the conversation acquisition unit 523 acquires data. For example, the display control unit 524 can display on the display unit (in the embodiment, the display unit of the conversation data acquisition terminal 5) an object sd (see Figure 4) for selecting (classifying) patients who can accept input, and patient data (corresponding to object se in Figure 5) for identifying patients based on status data. In addition, the display control unit 524 can also display on the display unit an object sf (see Figure 6) for deciding whether to proceed to recording, an object ob1 (see Figure 7) for starting recording, various objects ob2 etc. (see Figure 8) that are displayed during recording, an object sg (see Figure 9) for deciding whether to end the recording operation, and an object si (see Figure 10) for deciding whether to create medical documentation.

[0036] The creation instruction receiving unit 525 receives a selection of whether or not to start creating a medical document via an object si (see FIG. 10).

[0037] 3. Data exchanged in the information processing system 100 In the information processing system 100 according to the embodiment, various data are exchanged between the medical information server 1, the large-scale language model server 2, the speech-to-text server 3, and the terminal on the pharmacy side, and this data will be described below.

[0038] 3-1. Conversation data The conversation data includes the content of the conversation between the medical professional and the patient. In the embodiment, the conversation data is voice data. Here, the voice data may be composed of data corresponding to the voice of the medical professional. In other words, the voice data may be generated by the medical professional speaking the content of the conversation between the medical professional and the patient into the microphone of the conversation data acquisition terminal 5. In this case, the voice data will include only the voice of the medical professional. The voice data may also be composed of data corresponding to the voice of a conversation between a medical professional and a patient. That is, the microphone of the conversation data acquisition terminal 5 may be placed where the medical professional and the patient are conversing, and the conversation between them may be recorded as voice data. In this case, the voice data will be composed of data corresponding to the voice of the medical professional and the voice of the patient.

[0039] The types of conversation data include voice conversation data d1 shown in FIGS. 12A and 13, and text conversation data. The former voice conversation data d1 corresponds to the voice data acquired by the conversation data acquisition terminal 5. This voice conversation data d1 corresponds to the data acquired in the first information processing (described in the following section 4-1). The latter type of character conversation data includes pre-processed character data d2 shown in Fig. 13 and processed character data d3 shown in Fig. 13 and Fig. 14. The character conversation data corresponds to the data obtained in the second information processing described above (described in Section 4-2 below).

[0040] The unprocessed character data d2 is data obtained by transcribing the voice conversation data by the transcription unit 31. The processed character data d3 is character conversation data used when the medical text generation unit 122 generates medical text. In the embodiment, the processed character data d3 is character data obtained after the text generation unit 21 processes the unprocessed character data d2 so as to improve the accuracy of the content.

[0041] Specifically, as shown in the example of FIG. 16A, the pre-processed character data d2 may contain errors in the name of a drug, etc. (see the underlined portion). However, as shown in the example of FIG. 16B, the errors have been corrected in the processed character data d3 (see the underlined portion), improving the accuracy of the text. In addition, the processed character data d3 distinguishes between what was said by the medical professional and what was said by the patient. Because this type of processed character data d3 is output to the large-scale language model server 2, the output from the large-scale language model server 2 (medical text MT1) is optimized and its accuracy is improved.

[0042] 3-2.Status Data In this embodiment, before generating the medical text MT1, it is necessary to generate conversation data (the voice conversation data d1 described in Section 3-1 above). Therefore, status data is used to associate the conversation data to be generated with the patient. It is preferable that the status data include at least one of the following: name, date of birth, age, generation, health insurance card information, and ID. In the embodiment, the status data includes classification data for classifying patients received at the pharmacy. The classification data includes data corresponding to the order in which patients were received at the pharmacy (order of visit), data indicating whether an operation is in progress, data indicating whether recording of conversation data is paused, and data indicating whether recording of conversation data is being skipped. In the embodiment, the data is described as including all four types of data, but it is not necessary to include all of them.

[0043] Although the example has been described in which the perspective of the order in which patients were admitted to the pharmacy (the order in which they visited the pharmacy) is used as the classification data, the present invention is not limited to this. Various perspectives can be used as the classification data, such as the number of visits to the pharmacy, gender, or patients who visited on a specific date. Furthermore, the classification data may be based on a perspective in which all patients admitted to the pharmacy are displayed in a predetermined order (for example, alphabetical order of name).

[0044] 3-3.Medical Data As shown in FIG. 12B, in an embodiment, the medical data includes items such as ID (data D1), name (data D2), gender (data D3), date of birth (data D4), age (data D5), generation (data D5t), health insurance card information (data D6), allergy history (data D7), current illness history (data D8), medical history (data D9), history of drug side effects (data D10), history of concomitant drug use (data D11), information related to medication problems (data D12), pharmacy name (data D13), prescribing doctor name (data D14), hospital name (data D15), prescription date (data D16), drug name (data D17), drug quantity, usage, and dosage (data D18), and medication history (data D19).

[0045] In one embodiment, the types of medical data include items shown in data D1 to data D19 in Fig. 12B, but the numbers of data D1 to data D19 are assigned for convenience to distinguish these items. Also, not all of data D1 to data D19 are necessarily required items.

[0046] The ID (data D1) is a unique symbol assigned to each individual, and is represented by, for example, numbers or letters. The generation (data D5t) may be acquired from the reception terminal 4 at the pharmacy, or may be acquired by the medical information server 1 having a function of calculating the generation based on age and using this function. This function can be realized by the encoding unit 123, for example. The health insurance card information (data D6) includes the insurer number, symbol, and number. Information relating to medication problems (data D12) includes, for example, information that is different from allergies, such as circumstances such as an individual not agreeing with the taste or body (for example, wanting to avoid herbal medicine because it does not agree with the taste).

[0047] The drug name (data D17) is an example of drug data. This drug name may be the exact name of the drug, or an abbreviated name. Name (data D2), sex (data D3), date of birth (data D4), age (data D5), and health insurance card information (data D6) are examples of basic patient data. Medication history (data D19) is an example of medication history data.

[0048] <Stored data DT0 and medical data DT1> In one example of the embodiment, all of these 20 items of data are stored as a database in the storage unit 11 of the medical information server 1. Then, when a patient visits a pharmacy and a medical professional receives, for example, a prescription, the medical professional inputs the prescription data into the reception terminal 4. As a result, the prescription data (medical data DT1) is output to the medical information server 1, as shown in FIG. 12A. For example, if the medical data DT1 is prescription data, it includes at least data such as the name of the pharmacy (data D13), the name of the medicine (data D17), and the quantity, usage, and dosage of the medicine (data D18).

[0049] Furthermore, for example, if the medical data DT1 is dispensing data, it includes data such as the name of the medicine (data D17) and the quantity, usage, and dosage of the medicine (data D18). Furthermore, for example, if the medical data DT1 is pharmaceutical data, data such as the name of the pharmaceutical (data D17) is included. The types of data included in the medical data DT1 are not limited to prescription data, dispensing data, and drug data, and various modifications are possible. In other words, the medical data DT1 may include all or some of the 20 items of data described above, and various settings are possible. The information processing system 100 is preferably configured to be able to change the type of data included in the medical data.

[0050] When the medical data DT1 is output to the medical information server 1, the contents of the stored data DT0 as a database are updated each time. Also, for example, if there is a change in the patient's status (e.g., name), data related to the change is input to the reception terminal 4, and the stored data DT0 is updated. Note that the storage unit 11 also holds data before the update (old data). In this way, the storage unit 11 comprehensively stores data exchanged in the information processing system 100, and the data accumulates.

[0051] Incidentally, medical data can be divided into the above-mentioned non-output medical data and output medical data. The non-output data is data that is not output to the large-scale language model server 2 because it contains personal information, while the output data is data that is output to the large-scale language model server 2. These types of data are explained below.

[0052] 3-3-1. Non-printed medical data The non-output medical data will be described with reference to Fig. 15A. In the embodiment, the non-output medical data may include, for example, name (data D2), date of birth (data D4), age (data D5), health insurance card information (data D6), pharmacy name (data D13), prescribing doctor name (data D14), hospital name (data D15), and prescription date (data D16). The data is not limited to the examples shown here, and for example, information that is considered to be relatively more anonymous than name, etc. (date of birth and age) may be included in the output medical data, and this can be changed as appropriate.

[0053] 3-3-2. Output medical data The output medical data will be described with reference to FIG. 15A. In this embodiment, the output medical data may include, for example, ID (data D1), gender (data D3), age (data D5), allergy history (data D7), current illness history (data D8), medical history (data D9), history of side effects from medication (data D10), history of concomitant medication (data D11), information related to medication problems (data D12), drug name (data D17), drug quantity, dosage, and administration (data D18), and medication history (data D19). The data is not limited to those exemplified here, and other information may be added or removed as necessary.

[0054] <Medical Data DT2> Here, the medical data DT2 shown in FIG. 13 and the medical data DT3 shown in FIG. 14 will be described. 13 shows how medical data DT2 is output to the large-scale language model server 2 in order to improve the accuracy (precision) of the sentences in the raw character data d2 (described later). The medical data DT2 may include all or part of the output medical data described above. The medical data DT2 includes drug names (data D17). This is because drug names are often long and not commonly used, making them difficult to transcribe properly. Preferably, the medical data DT2 includes at least one of the quantity, dosage, and administration of the medicine (data D18) and the medication history (data D19). Furthermore, the medical data DT2 may include not only the content related to the current prescription (see FIG. 15A) but also the content related to past prescriptions (see FIG. 15B). The content related to past prescriptions may include those from multiple times (for example, the previous time and the time before that).

[0055] <Medical Data DT3> 14 shows how medical data DT3 is output to the large-scale language model server 2 together with processed character data d3, which will be described later, to generate medical text MT1, which will be described later. The medical data DT3 may include all or part of the output medical data described above. The medical data DT3 includes drug data. In other words, the medical data DT3 includes drug names (data D17), which are an example of drug data, for appropriately generating the medical text MT1 output from the large-scale language model server 2. Preferably, the medical data DT3 includes at least one of the quantity, usage, and dosage of the medicine (data D18) and the medication history (data D19). More preferably, the medical data DT3 includes at least one of ID (data D1), gender (data D3), age (data D5t), allergy history (data D7), current illness history (data D8), medical history (data D9), history of drug side effects (data D10), and history of concomitant drug use (data D11).

[0056] Furthermore, similar to the medical data DT3, the medical data DT3 may include not only the content related to the current prescription (see FIG. 15A) but also the content related to past prescriptions (see FIG. 15B). The content related to past prescriptions may include those from multiple times (for example, the previous time and the time before that). Specifically, a drug name (an example of drug data) may have new drug data and old drug data. The new drug data corresponds to the conversation in the conversation data. In other words, the new drug data is data on the drug name written on, for example, a prescription submitted by the patient this time. The old drug data is data that predates the new drug data. In other words, the old drug data is data on drugs written on, for example, a prescription submitted by the patient earlier than this time. "Earlier than this time" may be data related to the prescription one prescription before the prescription in the new drug data, or data related to the prescription two prescriptions before, or even earlier than that. Furthermore, the old drug data may have multiple pieces of data that predate this time.

[0057] 3-4. Medical Writing In the embodiment, the medical text is divided into medical text MT1 output from the large-scale language model server 2 to the medical information server 1 and medical text MT2 output from the medical information server 1 to the pharmacy. The medical text MT1 has a predetermined format, as shown in Figure 17. One example of this predetermined format is SOAP. Here, SOAP refers to a recording method (recording format) used in medical settings, etc., in which subjective information (Subject), objective information (Object), assessment, and plan are distinguished. In other words, the medical text MT1 is a text in which subjective information, objective information, assessment, and plan are distinguished.

[0058] The medical document MT2 is data configured to identify an individual by adding at least one of the following data to the medical document MT1: name (data D2), gender (data D3), date of birth (data D4), age (data D5), and health insurance card information (data D6). In other words, the medical document MT2 is data to which basic data elements have also been added. Note that the medical information server 1 may not generate the medical document MT2, and the medical document MT1 itself may be output to the pharmacy. In this case, for example, the process of identifying the individual may be performed at the reception terminal 4 on the pharmacy side.

[0059] 4. Information Processing Flow of Information Processing System 100 The program according to the embodiment causes a computer to execute each step (information processing method) described below. Furthermore, the information processing system 100 according to the embodiment includes at least one information processing device that executes each step (information processing method) described below. The information processing method according to the present embodiment is a process for supporting the creation of medical documents. As described above, the information processing in the information processing system 100 includes a first information processing and a second information processing.

[0060] 4-1. First information processing: Processing when acquiring conversation data The first information processing (first information processing method) will be described in detail with reference to FIGS. As shown in FIG. 11, the first information processing (first information processing method) according to the embodiment includes a status acquisition step, a display step, a reception step, a conversation acquisition step, and a creation instruction reception step. As shown in FIG. 11, the receiving step includes a sorting step and a selection step, and the conversation acquisition step includes an acquisition decision step and an acquisition step. The first information processing is information processing that is mainly executed by the mobile terminal (conversation data acquisition terminal 5) on the pharmacy side.

[0061] <Start (Step S001)> A medical professional receives a prescription from a patient and begins dispensing medication according to the prescription. Once dispensing is complete, a conversation with the patient begins to hand over the medication to the patient. Prior to this conversation, the medical professional has activated the conversation data acquisition terminal 5. Medical professionals at pharmacies are required to record medical procedures, such as dispensing medication and conversations, as medical documents, which is time-consuming. The information processing system 100 according to the embodiment reduces this time and effort by automatically generating all or part of the medical documents, thereby reducing the burden on medical professionals. This first information processing (first information processing method) is an information processing method for supporting the creation of medical documents for patients, and more specifically, is information processing for acquiring conversation data used to generate medical documents.

[0062] <Step S002 (an example of a status acquisition step)> For example, when a medical professional receives a prescription from a patient, the medical professional inputs information required for reception at the pharmacy (such as the patient's name) into the reception terminal 4. This input may be performed, for example, by the medical professional visually referencing the prescription and using an input unit (such as a keyboard or mouse), or by reading a code such as a barcode or QR code on the prescription using an input unit (such as a reader or camera), or by analyzing and reading prescription information obtained with a scanner or camera, or by a combination of these. In this way, in this step, the reception terminal 4 acquires reception information (patient status data) such as the patient's name as explained here. Note that the data of the reception terminal 4 is also centrally managed by the medical information server 1, so the information of the reception terminal 4 (patient status data) is also sent to the medical information server 1.

[0063] Here, the case where the reception terminal 4 acquires the information (patient status data) is described as an example, but the present invention is not limited to this. For example, the information may be acquired by the conversation data acquisition terminal 5, and the information may be stored in the storage unit 51 of the conversation data acquisition terminal 5.

[0064] <Step S003 (an example of a display step)> In this step, a chat room for medical professionals to chat is displayed. Specifically, as shown in Fig. 4, the display control unit 524 controls the display unit of the conversation data acquisition terminal 5 to display a display screen sa1. Here, the display screen sa1 includes the chat room. In the embodiment, a bot that outputs predetermined information according to the situation and input from the medical professional can be used as the chat partner with the medical professional. A bot control unit (not shown) that controls the output of the bot is preferably provided in, for example, the control unit of the medical information server 1, the reception terminal 4, or the conversation data acquisition terminal 5. Alternatively, the bot may be provided in an external server separate from these.

[0065] 5, a bot icon sb1 and a medical worker icon sb2 are displayed in the chat room. These icons may be changeable by the user or the like as appropriate. Also, as shown in FIG. 4, in the chat room, output information from the bot (e.g., see comment sc1) is displayed in area Rg1, and input information from the medical professional (e.g., see comment sc2) is displayed in area Rg2. In one example of an embodiment, area Rg1 is located on the left side of display screen sa1, and area Rg2 is located on the right side of display screen sa1. Also, as shown in FIG. 4, in the chat room, both inputs from the medical professional and replies to the inputs are displayed in chronological order. The chronological direction of the chat corresponds to the arrow Dr shown in FIG. 4. In other words, the bottom comment is the most recent comment from the bot or medical professional.

[0066] Displaying the chat room in this step is initiated when the medical worker selects (e.g., taps) an icon (not shown) of an application for executing the first information processing that has been pre-installed in the conversation data acquisition terminal 5. In other words, this step is triggered by a display operation from the medical worker on the conversation data acquisition terminal 5. Then, unless the medical worker stops the application, the process moves to this step and the display of the chat room continues. The application relating to this chat room may be realized by a dedicated application alone, or may be realized by linking with an existing chat application via an API (Application Programming Interface).

[0067] Note that the chat partner of the medical professional does not necessarily have to be a bot. In other words, a configuration may be adopted in which when the medical professional makes some input in a chat room, an operator provides a corresponding response. Furthermore, the first information processing according to the embodiment may be configured to allow a chat with a bot and a chat with an operator to be combined. For example, by selecting (e.g., tapping) an object (not shown) that calls an operator, the chat partner switches from the bot to the operator.

[0068] <Step S004 (an example of a selection step in a reception step)> In this step, a selection input (classification input) for selecting (classifying) patients who can receive input is accepted based on predetermined conditions. Specifically, as shown in FIG. 4, the display control unit 524 displays objects sd on the display unit of the conversation data acquisition terminal 5. If the conversation data acquisition terminal 5 is a smartphone terminal or a tablet terminal, the objects sd are configured to be selectable by tapping them by a medical professional. There are multiple types of objects sd (here, objects sd1 to sd5). The objects sd1 to sd4 are each objects for selecting (classifying) patients who can receive input.

[0069] The above-mentioned predetermined conditions correspond to the contents of objects sd1 to sd4. Specifically, the predetermined conditions in this step include the patient's visit order (corresponding to object sd1), whether or not the operation is being processed as being in operation (corresponding to object sd2), whether or not the operation is being processed as being suspended (corresponding to object sd3), and whether or not the operation is being processed as being skipped (corresponding to object sd4). It is preferable that at least one of objects sd1 to sd3 is included. Also, although object sd4 is optional, it is also preferable that it be included.

[0070] The order in which patients related to object sd1 will visit the clinic can be determined using the status data acquired in step S002. Moreover, the objects sd2 to sd4 can also be grasped using the status data acquired in step S002. The processing during operation related to object sd2 corresponds to the processing when, after the selection input corresponding to the patient's visit order has been accepted in this step, no input to identify the patient related to the creation of the medical document has been accepted in this step. The interrupted processing related to object sd3 corresponds to the processing when the acquisition of conversation data is temporarily stopped (interrupted) in step S007 described later. The skip processing relating to object sd4 corresponds to the processing when a selection is made to skip recording (medication instruction) in step S006 in FIG. 6 or FIG. 11, which will be described later.

[0071] The process related to object sd5 is an object for viewing a medication history, and when this object is selected, for example, the name of the patient received at the pharmacy and their medication history can be referenced. When object sd5 is selected, it may be displayed on display screen sa1, or the display screen of another application may be automatically launched. A medical professional can determine the specific patient by looking at the displayed medication history.

[0072] The object sd is placed in the area Rg3 below the comments of the bot and medical staff. The area where the object sd is placed is not limited to this, and the object sd may be placed in any position. The same applies to the objects in Figures 5 to 10 described below.

[0073] <Step S005 (an example of a selection step in a reception step)> In step S004, the reception unit 522 receives the selection of object sd1 shown in FIG. 4. A case where object sd1 shown in FIG. 4 is selected by a medical worker will be described as an example. Based on the medical worker's selection, comment sc2 (order of reception) shown in FIG. 5 is displayed. Then, in this step, patient data for identifying the patient is displayed based on the status data. In other words, the status data is referenced, and patient objects se displayed in order of reception are displayed in area Rg3. Furthermore, comment sc3 (a list of patients in order of reception) is displayed as the bot's response. The status data may be referenced by the conversation data acquisition terminal 5 alone. Alternatively, the conversation data acquisition terminal 5 may cooperate with the reception terminal 4 or the medical information server 1. For example, when information for requesting data in the order of reception is output from the conversation data acquisition terminal 5 to the reception terminal 4 or the medical information server 1, the reception terminal 4 or the medical information server 1 may refer to the storage unit and transmit the corresponding data to the conversation data acquisition terminal 5.

[0074] In this step, an input for identifying a patient for whom medical documentation is to be created is received via the object se in the chat room shown in Figure 5. In this example, the order in which patients are received is such that earlier patients are on the left and later patients are on the right, but this is not limited to this and they may be arranged vertically. Also, each object se may be assigned a number indicating the order in which they will arrive.

[0075] Object se1 for Person A, object se1 for Person B, object se1 for Person C, etc. are arranged in the order of their visits. These objects se1 are objects for identifying patients for whom medical documents are being created. For example, by selecting object se1 for Person A, Person A will be identified as the patient for whom medical documents are being created. Conversation data related to the identified patient will be obtained, as will be explained next.

[0076] In this embodiment, the object se2 related to the cancellation is also displayed in the area Rg3. When the object se2 is selected, the state returns to, for example, the state shown in Fig. 4 (the state in which the selection of the object sd is accepted).

[0077] <Step S006 (an example of an acquisition decision step in a conversation acquisition step)> As an example, a case will be described where a medical professional selects object se1 of person A shown in Fig. 5. As a result of the medical professional's selection, comment sc4 (person A) and comment sc5 (medication instructions...) will be displayed as shown in Fig. 6.

[0078] In this step, the display control unit 524 displays the object sf on the display unit of the conversation data acquisition terminal 5. In other words, the object sf for receiving a decision input is displayed on the display screen sa1.

[0079] The decision input is an input related to the start of medication instruction that a medical professional gives to a patient through conversation. In other words, the decision input is an input for making a decision regarding the transition to the next step S007. In this step, the decision input is received by displaying the object sf.

[0080] Here, the decision inputs include a decision to start recording (corresponding to the selection of object sf1), a decision to restart the acquisition of conversation data in step S007 (corresponding to the selection of object sf2), a decision to resume the acquisition of conversation data that was paused in step S007 (corresponding to the selection of object sf3), a decision to skip step S007 (corresponding to the selection of object sf4), and a decision to cancel the processing of this decision input itself (object sf5). The decision input includes object sf1, and preferably includes at least one of objects sf2 to sf4, and object sf5 is optional but is also preferably included.

[0081] <Step S007 (an example of an acquisition step in the conversation acquisition step)> In step S007, the conversation acquisition unit 523 accepts the selection of object sf. In one example of an embodiment, the conversation acquisition unit 523 can also accept the selection of objects ob1 to ob5, object sg, and the like.

[0082] 7, in this step, an object ob1 for recording to acquire audio data is displayed. Specifically, the object ob1 is displayed on the display screen sa1 according to the selection status of the object sf displayed in step S006. The object ob1 is an example of a start object for starting the recording operation. 7 shows, as an example, a state in which the object sf1 shown in FIG. 6 has been selected by the medical professional. As a result of the medical professional's selection, a comment sc6 (Start) is displayed, as shown in FIG. 7, and a comment sc7 (Tap to start recording) is also displayed. This prompts the medical professional to start recording in this step.

[0083] Specifically, when object sf1 in Fig. 6 is selected, object ob1 is displayed in area Rg4 shown in Fig. 7. The display position of object ob1 is below area Rg1 or area Rg2, but is not limited to this and may be any position. This object ob1 is an object for starting recording, and recording starts when the medical professional selects (e.g., taps) this object ob1.

[0084] Also, when object sf2 in Figure 6 is selected, object ob1 in Figure 7 is displayed. The medical professional can re-record by selecting (e.g., tapping) this object ob1. Previously acquired conversation data is, for example, deleted and replaced with the data being recorded this time. Also, when object sf3 in Fig. 6 is selected, object ob1 in Fig. 7 is displayed. When the medical professional selects (e.g., taps) this object ob1, recording resumes. Note that the conversation data obtained by resuming recording is stored as a continuation of the previously acquired conversation data. Furthermore, when object sf4 in Fig. 6 is selected, for example, the state returns to the state shown in Fig. 4 (state in which selection of object sd is accepted). Note that the status data is updated, and the patient's status becomes skipped. When the object sf5 in FIG. 6 is selected, the state returns to, for example, the state shown in FIG. 4 (the state in which the selection of the object sd is accepted).

[0085] When objects sf1 to sf3 are selected and recording (recording operation) begins, objects ob2 to ob5 are displayed as shown in FIG.

[0086] The object ob2 is an example of a pause object for pausing the recording operation. During the recording operation, an effect may be displayed according to the output (volume) of the sound acquired from the microphone of the conversation data acquisition terminal 5. One example of the effect may be to highlight a predetermined range within the region Rg4 by coloring it. Then, a configuration may be adopted in which the highlighted range expands according to the volume (the higher the volume, the larger the range). The position of the predetermined range may be set around the object ob2, but is not limited to this, as long as it is within the range of the region Rg4. Alternatively, a configuration may be adopted in which a bar indicating the volume is displayed in the region Rg4.

[0087] Object ob3 is an example of an object for completing a recording operation. When object ob3 is selected, the screen transitions from that of Fig. 8 to that of Fig. 9. Object ob4 is an example of a deletion object for deleting recorded data. Object ob5 is an example of a timing object that displays the recording time.

[0088] When object ob3 shown in FIG. 8 is selected, the recording operation ends, and as shown in FIG. 9, comment sc8 is displayed, followed by comment sc9 (Do you want to stop recording?). Comment sc8 can display the total recording time. Note that the recorded audio may be played back by selecting (e.g., tapping) comment sc8. 9, objects sg are displayed in the region Rg3. The objects sg include an object sg1, an object sg2, and an object sg3.

[0089] The object sg1 is an object for ending the recording operation, and when the object sg1 is selected, the screen shown in FIG. 9 transitions to the screen shown in FIG. The object sg2 is an object for suspending the recording operation. The status data is updated and the patient's status becomes suspended. Object sg3 is an object for redoing the recording operation. When object sg3 is selected, the display in area Rg4 in Figure 7 is re-created, allowing the user to redo the recording. Note that any conversation data that has already been acquired may be deleted and replaced with the data to be re-recorded, for example.

[0090] 9 is selected, the storage unit of the conversation data acquisition terminal 5 acquires the conversation data. Also, as shown in FIG. 10, the display screen sa1 displays a comment sc10 (Yes (Exit)) and a comment sc11 (Do you want to create a medical document?).

[0091] By going through this step, the conversation data acquisition terminal 5 acquires conversation data including the content of the conversation between the patient and the medical professional identified in step S005. Note that while the case where the medical professional and the patient actually have a conversation is described here, the present invention is not limited to this. The medical professional may talk to himself in front of the conversation data acquisition terminal 5, and the content of the conversation between the medical professional and the patient may be stored in the conversation data acquisition terminal 5.

[0092] <Step S008 (an example of a creation instruction receiving step)> In step S008, the creation instruction receiving unit 525 receives the selection of an object si. As shown in Fig. 10, the object si is displayed in the area Rg3. The object si includes an object si1 and an object si2. The object si1 is an object for generating a medical document using the acquired conversation data, and when the object si1 is selected, the process proceeds to the second information processing, which will be described later. Object si2 is an object that is selected when medical documents are not to be generated. If medical documents do not need to be created, medical professionals can select this object.

[0093] <End (Step S009)> In step S007, the conversation data acquisition terminal 5 completes acquisition of the conversation data, and thereafter, in step S008, when the medical worker selects object si1 in Fig. 10, the conversation data (voice conversation data d1) is transmitted to the medical information server 1 via the reception terminal 4. Note that this conversation data may also be transmitted directly from the conversation data acquisition terminal 5 to the medical information server 1.

[0094] 4-2. Second information processing: Processing to generate medical text from the conversation data acquired in the first information processing The second information processing (second information processing method) is an example of a document acquisition step. In the second information processing, medical documents are acquired using the conversation data generated in the first information processing.

[0095] <Start (Step T001)> In the second information processing, the conversation data generated by the first information processing is used to automatically generate all or part of the medical text, thereby reducing the workload of medical professionals in creating medical text.

[0096] <Step T002> The conversation data (voice conversation data d1) generated in the first information processing is transmitted from the memory unit of the conversation data acquisition terminal 5 to the memory unit of the reception terminal 4. As a result, the reception terminal 4 acquires the conversation data (voice conversation data d1). In addition, the medical worker inputs the contents of this prescription as medical data DT1 into the reception terminal 4, and the memory unit of the reception terminal 4 acquires this medical data DT1. In this way, the second information processing employs a configuration in which medical text is acquired using medical data DT1 in addition to conversation data. Note that although the system may generate medical text from conversation data alone, in order to improve the accuracy of generating medical text, in this embodiment, the medical data DT1 is also utilized.

[0097] In the explanation given here, the patient has already used one of the pharmacies utilized by the information processing system 100, and the patient's basic data (such as name (data D2)) is already stored in the memory unit 11 of the medical information server 1 serving as a database. Therefore, in the example of medical data DT1 in step T001, it is not necessary to input all of the basic data (for example, age (data D5)).

[0098] <Step T003> The data acquisition unit 121 of the medical information server 1 acquires the voice conversation data d1 and medical data DT1 transmitted from the pharmacy side, and stores them in the storage unit 11.

[0099] <Step T004> The control unit 12 of the medical information server 1 outputs the voice conversation data d1 stored in the memory unit 11 to the speech-to-text server 3. The transcription unit 31 of the speech-to-text server 3 transcribes the voice conversation data d1 to generate raw character data d2, which is character data.

[0100] <Step T005> The speech-to-text server 3 outputs the raw character data d2 to the medical information server 1. The data acquisition unit 121 of the medical information server 1 acquires the raw character data d2 and stores it in the storage unit 11.

[0101] <Step T006> The control unit 12 of the medical information server 1 outputs the raw character data d2 and medical data DT2 stored in the storage unit 11 to the large-scale language model server 2, and in doing so generates an output prompt. Specifically, the output generation unit 122a of the medical text generation unit 122 generates an accuracy improvement prompt to be output to the large-scale language model server 2. The accuracy improvement prompt includes the raw character data d2 and the medical data DT2, and also includes an instruction to generate processed character data d3 by referencing the medical data DT2. The accuracy improvement prompt also includes an instruction to generate processed character data d3 by distinguishing between what was spoken by the medical professional and what was spoken by the patient (see FIG. 8B), which is expected to have the effect of improving the generation accuracy of the medical text MT1.

[0102] The control unit 12 of the medical information server 1 outputs this accuracy improvement prompt to the large-scale language model server 2. The number of characters in the accuracy improvement prompt may be, for example, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1200, 1400, 1600, 1800, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, 10000, 12000, or 14000, or may be within a range between any two of the values ​​exemplified here. The accuracy improvement prompt may also be composed of multiple separate prompts.

[0103] The sentence generation unit 21 of the large-scale language model server 2 refers to the accuracy improvement prompt, generates processed character data d3 by correcting the content of the raw character data d2 so as to improve the accuracy of the raw character data d2, and outputs it to the medical information server 1.

[0104] <Step T007> The data acquisition unit 121 of the medical information server 1 acquires the processed character data d3 as an output from the large-scale language model in response to the accuracy improvement prompt, and stores it in the storage unit 11.

[0105] <Step T008> Subsequently, the control unit 12 of the medical information server 1 outputs the processed character data d3 and medical data DT3 stored in the storage unit 11 to the large-scale language model server 2, and in so doing generates an output prompt. Specifically, the output generation unit 122a of the medical text generation unit 122 generates a text generation prompt to be output to the large-scale language model server 2. The text generation prompt includes the processed character data d3 and the medical data DT3, and also includes an instruction to generate medical text MT1. In this embodiment, this prompt includes an instruction to create the content of the processed character data d3 and the medical data DT3 in a predetermined format (SOAP in this embodiment). The prompt may also include supplemental data, such as a definition of what the SOAP is, or a limit on the number of characters in the medical text MT1 to be generated. Note that the medical data DT3 in this prompt excludes information that could identify an individual (for example, name, which is an example of basic data), but the information may be included as coded data (abstracted data) that has been coded (abstracted) by the coding unit 123.

[0106] The control unit 12 of the medical information server 1 outputs this sentence generation prompt to the large-scale language model server 2. The number of characters in the sentence generation prompt may be, for example, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1200, 1400, 1600, 1800, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, 10000, 12000, or 14000, or may be within a range between any two of the values ​​exemplified here. The sentence generation prompt may also be composed of multiple separate prompts.

[0107] The sentence generation unit 21 of the large-scale language model server 2 references the sentence generation prompt, generates medical sentence MT1, and outputs it to the medical information server 1.

[0108] <Step T009> The data acquisition unit 121 of the medical information server 1 acquires medical text MT1 as output from the large-scale language model in response to a text generation prompt, and stores it in the memory unit 11. Here, the medical data DT3 output to the large-scale language model server 2 is processed so as not to include personal information. For this reason, the adjustment unit 122b of the medical text generation unit 122 generates medical text MT2 by adding basic data (such as name) to the medical text MT1 so that individuals can be identified, and stores it in the memory unit 11. In other words, the medical text generation unit 122 generates medical text MT2 based on conversation data (processed character data), pharmaceutical data (medical data), and the basic data.

[0109] <Step T010> The medical staff acquires the medical text MT2 via the reception terminal 4, and the medical text MT2 is stored in the memory unit of the reception terminal 4. If the information processing system 100 does not have the adjustment unit 122b, the reception terminal 4 acquires the medical text MT1. It should be noted that the conversation data acquisition terminal 5, rather than the reception terminal 4, may acquire the medical text MT2.

[0110] <End (Step T011)> By utilizing Medical Text MT2, medical professionals can reduce the effort required to create medical documents.

[0111] 5. Variations In the embodiment, a configuration has been described in which medical text is generated using servers external to the medical information server 1, such as the large-scale language model server 2 and the speech-to-text server 3, but the present invention is not limited to this. For example, the medical information server 1 may have the functions of the large-scale language model server 2 and the speech-to-text server 3. In other words, the medical information server 1 may have a text generation unit 21 and a transcription unit 31.

[0112] In the embodiment, the information processing system 100 is described as a system in which information is exchanged between a terminal on the medical institution (pharmacy) side and a medical information server 1 located in a location independent of the medical institution, but the present invention is not limited to this. The medical information server 1 having the sentence generation unit 21 and the transcription unit 31 may be located in the medical institution (pharmacy), and the system may be one in which data is handled entirely within the medical institution (pharmacy).

[0113] In the embodiment, the conversation data transmitted from the pharmacy to the medical information server 1 is described as voice data (voice conversation data d1), but this is not limited to this. For example, the conversation data acquisition terminal 5 may have a function for transcribing voice, and the conversation data as text data may be acquired by the medical information server 1. In this case, for example, the conversation data and medical data may be input into the large-scale language model server 2 along with desired prompts to generate medical text. For example, if the accuracy of transcription in the conversation data acquisition terminal 5 is low, it is possible to expect the effect of the large-scale language model server 2 correcting incorrect characters to appropriate content.

[0114] In the embodiment, the medical institution is described as a pharmacy, but the present invention is not limited to this. For example, the present invention can be applied to a place that provides medicines installed in a hospital. The present invention can also be applied to fields where documents in a predetermined format must be created. For example, the present invention can be applied to hospital work, since SOAPs are created not only in places where medicines are prescribed but also in hospitals.

[0115] The sentence generation unit 21 may be configured to have a neural network dedicated to generating medical sentences. "Dedicated" means specialized for a specific field, such as the field of medicine or medical care when applied to a pharmacy as in the embodiment. For example, the sentence generation unit 21 can be configured to perform calculations based on a predetermined learning model. Here, the learning model is a model that is trained using a large amount of training data and makes future output predictable. For example, a large amount of medical data (such as drug names) can be used as input data, and a large amount of medical sentences can be used as output data. This allows the sentence generation unit 21 to generate medical sentences based on a learning model that inputs medical data and outputs medical sentences.

[0116] In the embodiment, the information processing system 100 is described as having the transcription unit 31 within it, but this is not limited to this. In other words, the transcription unit 31 may exist outside the information processing system 100, and the information processing system 100 may be configured to use conversation data that has already been transcribed externally. In this case, the medical information server 1 acquires the conversation data that has been transcribed externally and includes it in the medical data DT3, thereby generating a sentence generation prompt.

[0117] Although the embodiments have been described above, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made. The embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the scope of the invention and its equivalents as defined in the claims.

[0118] Various embodiments are exemplified below, and the embodiments shown below can be combined with each other. [Appendix 1] An information processing method for supporting the creation of medical documents for patients, comprising: The method includes a display step, a reception step, and a conversation acquisition step, In the display step, a chat room for medical staff to chat is displayed, In the chat room, both the inputs of the healthcare professional and the responses to the inputs are displayed in chronological order; The receiving step includes a selecting step, In the selection step, the input for identifying the patient related to the creation of the medical document is accepted via the chat room; The conversation acquisition step includes an acquisition step, In the acquiring step, conversation data including content related to a conversation between the patient and the medical staff identified in the receiving step is acquired, An information processing method, wherein the conversation data is data used to create the medical document. [Appendix 2] 10. The information processing method according to claim 1, An information processing method, wherein the conversation data acquired in the conversation acquisition step is voice data. [Appendix 3] 10. The information processing method according to claim 2, An information processing method, wherein the voice data is composed of data corresponding to the voice of the medical professional, or data corresponding to the voice of a conversation between the medical professional and the patient. [Appendix 4] 1. The information processing method according to claim 2 or 3, In the acquiring step, an object for recording for acquiring the audio data is displayed, The information processing method, wherein the objects include a start object for starting a recording operation. [Appendix 5] 5. The information processing method according to claim 4, The information processing method, wherein the objects include a pause object for pausing the recording operation. [Appendix 6] An information processing method according to any one of Supplementary Note 1 to Supplementary Note 5, Further comprising a status acquisition step, The status acquisition step acquires status data of the patient, An information processing method, wherein in the selection step of the reception step, patient data for identifying the patient is displayed based on the status data. [Appendix 7] An information processing method according to any one of Supplementary Note 1 to Supplementary Note 6, The conversation acquisition step further includes an acquisition determination step, In the acquisition decision step, a decision input for deciding whether to proceed to the acquisition step is accepted. [Appendix 8] 8. The information processing method according to claim 7, further comprising: The decision input includes: A decision to reacquire the conversation data in the acquisition step; A decision to resume acquisition of the conversation data that has been paused in the acquisition step; a decision to skip the obtaining step; The information processing method further includes at least one of the following: [Appendix 9] 10. The information processing method according to claim 7 or 8, In the acquiring and deciding step, an object for receiving the decision input is displayed. [Appendix 10] An information processing method according to any one of Supplementary Note 1 to Supplementary Note 9, The receiving step further includes a selecting step, In the selection step, a selection input is accepted for selecting the patients for whom the input is available in the selection step, based on predetermined conditions. [Appendix 11] 11. The information processing method according to claim 10, further comprising: The predetermined conditions of the selection step are: The patient's visit order includes at least one of whether the patient is being treated as being in operation and whether the patient is being treated as being suspended; The process during the operation is a process when, after the selection input corresponding to the visit order of the patient is accepted in the selection step, the input for identifying the patient related to the creation of the medical document is not accepted in the selection step, The information processing method, wherein the interrupted process is a process performed when acquisition of the conversation data is temporarily stopped in the acquisition step. [Appendix 12] 12. The information processing method according to claim 10 or 11, In the selection step, an object corresponding to the predetermined condition for receiving the selection input is displayed. [Appendix 13] An information processing method according to any one of Supplementary Note 1 to Supplementary Note 12, Further comprising a document acquisition step, In the document acquisition step, the medical document is acquired using the conversation data. [Appendix 14] 14. The information processing method according to claim 13, In the document acquisition step, medical data is used in addition to the conversation data to acquire the medical document; The information processing method, wherein the medical data includes pharmaceutical data. [Appendix 15] An information processing method according to any one of Supplementary Note 1 to Supplementary Note 14, An information processing method in which the medical text is a text in which subjective information, objective information, evaluation, and plan are distinguished. [Appendix 16] An information processing method according to any one of Supplementary Note 1 to Supplementary Note 15, The information processing method is executed on a mobile terminal, The information processing method, wherein the mobile terminal is a smartphone type terminal or a tablet type terminal. [Appendix 17] A program that causes a computer to execute the information processing method according to any one of Supplementary Note 1 to Supplementary Note 16. [Appendix 18] An information processing system comprising at least one information processing device that executes each step of the information processing method according to any one of Supplementary Note 1 to Supplementary Note 16. [Explanation of symbols]

[0119] 100: Information Processing Systems 1: Medical information server 10: Communications Department 11: Storage section 12: Control section 121: Data acquisition section 122: Medical text generation unit 122a: Output generation section 122b: Adjustment section 123: Encoding section 13: Output section 14: Input section 15: Communication bus 2: Large-scale language model server 21: Sentence generation section 3: Speech-to-text server 31: Transcription Department 4: Reception terminal 40: Communications Department 41: Storage section 42: Control unit 43: Output section 44: Input section 45: Communication bus 5: Conversation data acquisition device 50: Communications Department 51: Storage section 52: Control unit 521: Status acquisition section 522: Reception 523: Conversation Acquisition Department 524: Display control unit 525: Creation Instruction Reception Department 53: Output section 54: Input section 55: Communication bus 6: Communication network d1: Voice conversation data d2: raw character data d3: Processed character data ob1 : object ob2 : object ob3 : object ob4 : object ob5 : object sa1:Display screen sb1 : icon sb2 :icon sd :object sd1 : object sd2 : object sd3 : object sd4 :Object sd5 :Object se :object se1 : object se2 :Object sf :object sf1 :object sf2 :object sf3 :object sf4 :object sf5 :object sg :object si :object

Claims

1. An information processing method for supporting the creation of medical documents for patients, comprising: The method includes a display step, a reception step, and a conversation acquisition step, In the display step, a chat room for medical staff to chat is displayed, In the chat room, both the inputs of the healthcare professional and the responses to the inputs are displayed in chronological order; The receiving step includes a selecting step, In the selection step, the input for identifying the patient related to the creation of the medical document is accepted via the chat room; The conversation acquisition step includes an acquisition step, In the acquiring step, conversation data including content related to a conversation between the patient and the medical staff identified in the receiving step is acquired, An information processing method, wherein the conversation data is data used to create the medical document.

2. 2. The information processing method according to claim 1, An information processing method, wherein the conversation data acquired in the conversation acquisition step is voice data.

3. 3. The information processing method according to claim 2, An information processing method, wherein the voice data is composed of data corresponding to the voice of the medical professional, or data corresponding to the voice of a conversation between the medical professional and the patient.

4. 4. The information processing method according to claim 2 or 3, In the acquiring step, an object for recording for acquiring the audio data is displayed, The information processing method, wherein the objects include a start object for starting a recording operation.

5. 5. The information processing method according to claim 4, The information processing method, wherein the objects include a pause object for pausing the recording operation.

6. An information processing method according to any one of claims 1 to 3, Further comprising a status acquisition step, The status acquisition step acquires status data of the patient, An information processing method, wherein in the selection step of the reception step, patient data for identifying the patient is displayed based on the status data.

7. An information processing method according to any one of claims 1 to 3, The conversation acquisition step further includes an acquisition determination step, In the acquisition decision step, a decision input for deciding whether to proceed to the acquisition step is accepted.

8. 8. The information processing method according to claim 7, The decision input includes: A decision to reacquire the conversation data in the acquisition step; A decision to resume acquisition of the conversation data that has been paused in the acquisition step; a decision to skip the obtaining step; The information processing method further includes at least one of the following:

9. 8. The information processing method according to claim 7, In the acquiring and deciding step, an object for receiving the decision input is displayed.

10. An information processing method according to any one of claims 1 to 3, The receiving step further includes a selecting step, In the selection step, a selection input is accepted for selecting the patients for whom the input is available in the selection step, based on predetermined conditions.

11. 11. The information processing method according to claim 10, The predetermined conditions of the selection step are: The patient's visit order includes at least one of whether the patient is being treated as being in operation or not, and whether the patient is being treated as being suspended or not; The process during the operation is a process when, after the selection input corresponding to the visit order of the patient is accepted in the selection step, the input for identifying the patient related to the creation of the medical document is not accepted in the selection step, The information processing method, wherein the interrupted process is a process performed when acquisition of the conversation data is temporarily stopped in the acquisition step.

12. 11. The information processing method according to claim 10, In the selection step, an object corresponding to the predetermined condition for receiving the selection input is displayed.

13. An information processing method according to any one of claims 1 to 3, Further comprising a document acquisition step, In the document acquisition step, the medical document is acquired using the conversation data.

14. 14. The information processing method according to claim 13, In the document acquisition step, medical data is used in addition to the conversation data to acquire the medical document; The information processing method, wherein the medical data includes pharmaceutical data.

15. An information processing method according to any one of claims 1 to 3, An information processing method in which the medical text is a text in which subjective information, objective information, evaluation, and plan are distinguished.

16. An information processing method according to any one of claims 1 to 3, The information processing method is executed on a mobile terminal, The information processing method, wherein the mobile terminal is a smartphone type terminal or a tablet type terminal.

17. A program that causes a computer to execute the information processing method according to any one of claims 1 to 3.

18. An information processing system comprising at least one information processing device that executes each step of the information processing method according to any one of claims 1 to 3.

Images