Browsing support system, browsing support method and program

Abstract

A browsing support system is provided that enables medical-related information to be entered accurately. [Solution] The information processing terminal 10 included in the browsing support system 1 has an input unit 12 that creates questions for contents to be registered in the electronic medical record displayed on the display unit 11. The medical record management system 3 has a medical record management unit 31 that outputs creation information for creating the electronic medical record, which is input by the information processing terminal 10, to a RAG system 4, receives answers from the RAG system 4, and supports the creation of the electronic medical record. The RAG system 4 has a vector DB 52 that stores knowledge that has been vectorized and embedded in a vector space, and a knowledge search unit 44 that searches the vector DB 52 for knowledge based on the vectorized creation information and outputs answers formed from the searched knowledge to the medical record management unit 31.

Description

[Technical field]

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

[0002] In health insurance treatment, the calculation rules for treatments for dental diagnoses and the insurance points are defined by the Ministry of Health, Labor and Welfare, and are revised periodically. In particular, the insurance points must reflect the fluctuation in the price of gold, which is used in fillings in dental treatment, on the receipt. For this reason, the points are now revised every three months (four times a year) instead of twice a year as in the past.

[0003] Insurance doctors and medical institutions that provide insurance medical care must follow the rules of insurance medical care. The rules of insurance medical care are published, for example, in the Official Gazette published by the Ministry of Health, Labor and Welfare.

[0004] Patent document 1 discloses a technology for improving the quality of medical data as a whole (e.g., all medical data related to a certain patient) by evaluating the consistency between reference data (reference data, first medical data) and other data (subject data, second medical data). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Special Publication No. 2023-504193 Summary of the Invention [Problem to be solved by the invention]

[0006] Traditionally, the writing of medical records was left to the ability of each individual. This caused a lot of stress for dentists who frequently had incomplete medical records and had to repeatedly return them. As mentioned above, the rules for insured medical treatment are frequently revised, so not only medical records but also receipts must be written in accordance with the rules. Insured doctors are not only required to acquire knowledge and techniques related to treatment, but also to be thoroughly familiar with the rules of insured medical treatment and to constantly update their knowledge.

[0007] However, the rules for insurance medical treatment are enormous, and the contents are difficult to understand. For this reason, it is extremely difficult for insurance doctors to keep up with the frequent cycle of updating their knowledge. If an insurance doctor creates an incorrect receipt, it will be returned, and medical institutions with too many returns will be audited in the form of individual guidance. Dentists with little experience in insurance medical treatment have to continue practicing without being able to grasp such situations. Generally, the content taught to students at educational institutions such as dental schools is mainly diagnostic and treatment methods. For this reason, dentists rarely receive sufficient training at educational institutions on how to write medical records and claim for receipts, and in most cases they only encounter these issues when they start clinical practice after graduating.

[0008] The above-mentioned Patent Document 1 describes, for example, a support technology for detecting missing entries in electronic medical records, but does not describe a support technology for filling out electronic medical records in accordance with the rules of insured medical treatment.

[0009] The present invention has been made in view of the above circumstances, and has an object to support the creation of medical-related information. [Means for solving the problem]

[0010] A browsing support system according to the present invention includes an information processing terminal that displays medical-related information, a medical-related information management system that manages the medical-related information, and an input support system that are connected via a network. The information processing terminal has a display unit that displays the medical-related information, and an input unit that creates a question about the content to be registered in the medical-related information displayed on the display unit. The medical-related information management system has a creation support unit that outputs creation information for creating medical-related information input by the information processing terminal to the input support system, receives an answer from the input support system, and supports the creation of the medical-related information. The input support system has a vector database that stores knowledge that has been vectorized and embedded in a vector space, and a knowledge search unit that searches the vector database for knowledge based on the vectorized creation information, and outputs an answer formed from the searched knowledge to the creation support unit. Effect of the Invention

[0011] According to the present invention, it is possible to support the creation of medical-related information. Problems, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0012] [Figure 1] 1 is a functional block diagram showing an example of the overall configuration of a browsing support system according to a first embodiment of the present invention. [Diagram 2] 1 is a diagram showing an example of a data structure of data and information used in a medical record management system according to a first embodiment of the present invention. FIG. [Diagram 3] 2 is a diagram showing an example of a data structure of a medical record DB according to the first embodiment of the present invention; FIG. [Figure 4] 1 is a block diagram showing an example of the internal configuration of a RAG system according to a first embodiment of the present invention. [Diagram 5] FIG. 2 is a diagram showing an example of the configuration of a knowledge DB according to the first embodiment of the present invention. [Figure 6] FIG. 2 is a diagram illustrating an example of a configuration of a vector DB according to the first embodiment of the present invention. [Figure 7] FIG. 2 is a diagram showing an example of the configuration of a prompt DB according to the first embodiment of the present invention. [Figure 8] 1 is a block diagram showing an example of the hardware configuration of a computer according to a first embodiment of the present invention. [Figure 9] FIG. 2 is a diagram showing a first display example of an electronic medical record creation display screen according to the first embodiment of the present invention. [Figure 10] FIG. 11 is a diagram showing a second display example of the electronic medical record creation display screen according to the first embodiment of the present invention. [Figure 11] 4 is a flowchart showing an example of knowledge addition processing in the RAG system according to the first embodiment of the present invention. [Figure 12] 4 is a flowchart showing an example of a knowledge update process in the RAG system according to the first embodiment of the present invention. [Figure 13] 4 is a flowchart showing an example of a process for creating an electronic medical record according to the first embodiment of the present invention. [Figure 14] 4 is a flowchart showing an example of knowledge search processing by the RAG system according to the first embodiment of the present invention. [Figure 15] FIG. 11 is a functional configuration diagram showing an example of the overall configuration of a browsing support system according to a second embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functions or configurations are designated by the same reference numerals, and redundant description will be omitted.

[0014] [First embodiment] <Overall configuration example of a browsing support system> First, a configuration example and a processing example of a browsing support system according to a first embodiment will be described with reference to FIGS.

[0015] 1 is a functional block diagram showing an example of the overall configuration of a browsing support system 1 according to the first embodiment. The staff of a dental clinic who use the browsing support system 1 are assumed to be, for example, dentists, dental hygienists, reception staff, etc.

[0016] 2 is a diagram showing an example of a data structure of data and information used in the medical record management system 3. Below, in addition to the explanation of the browsing support system 1, the data and information used in the medical record management system 3 will also be explained with reference to FIG.

[0017] The main components of the browsing support system 1 are an information processing terminal 10 used in medical institutions such as dental clinics and medical universities, a medical receipt management system 2 operated by a service company, a medical record management system 3, and a RAG (Retrieval-Augmented Generation) system 4. The information processing terminal 10, the medical receipt management system 2, and the medical record management system 3 are connected via a network, and data can be safely transmitted and received using a secure communication method such as encryption and a VPN (Virtual Private Network). The medical receipt management system 2, the medical record management system 3, and the RAG system 4 are connected via an in-house LAN of the service company, etc.

[0018] The browsing support system 1 according to the first embodiment implements a medical record management function and an input support function using RAG in a cloud-based medical record management system 3 provided to dental clinics by a service company. Therefore, the medical record described below is an "electronic medical record" that has been digitized using the medical record management function of the medical record management system 3, and this electronic medical record is an insurance medical record that records the treatment given to the patient and the insurance points.

[0019] The dental clinic staff accesses the medical record management system 3 by inputting a user ID, a password, etc. into the authentication screen of the medical record management system 3 using their own information processing terminal 10. After that, the staff browses the medical record DB 33 and creates an electronic medical record.

[0020] The RAG system 4 is an example of an input support system that presents answers to staff and supports input. For example, when staff create electronic medical records, the RAG system 4 can provide input support. With the viewing support system 1 shown in Figure 1, dental clinics do not need to prepare individual servers, etc., and therefore initial costs can be significantly reduced.

[0021] (Dental clinic staff) The information processing terminal 10 is an example of an information processing terminal such as a desktop PC (Personal Computer), a notebook PC, a smartphone, a tablet, etc. The information processing terminal 10 is connected to a medical receipt management system 2 and a medical record management system 3 via the Internet, and displays medical-related information including medical receipts and medical records (electronic medical records). The medical receipt management system 2 and the medical record management system 3 are examples of medical-related information management systems that manage medical-related information. The information processing terminal 10 displays various screens provided by the medical receipt management system 2, the medical record management system 3, and the RAG system 4 through operation by the staff, and accepts various information inputs by the staff. For this reason, the information processing terminal 10 includes a display unit 11 that displays medical-related information, and an input unit 12 that creates questions regarding the content to be registered in the medical-related information displayed on the display unit 11.

[0022] For example, at a dental clinic, a dentist performs dental treatment for a patient and inputs the details of the treatment and medical fees into the information processing terminal 10. At a dental clinic, a dental hygienist may operate the information processing terminal 10 to refer to the medical records and medical receipts displayed on the screen. At a medical university, a professor or a medical student may operate the information processing terminal 10 to obtain necessary information.

[0023] When a staff member operates the information processing terminal 10 to access the medical receipt management system 2, a medical receipt input screen (not shown) is displayed on the Web browser of the display unit 11 based on the functions provided by the medical receipt management system 2. The information processing terminal 10 can also access the medical record management system 3 and display an electronic medical record creation display screen W1 shown in Figures 9 and 10 (described later) on the Web browser of the display unit 11.

[0024] In addition, the dental clinic staff operates the input unit 12 to input words and phrases into various screens displayed on the display unit 11, and creates medical records and medical receipts. Since the medical records created by the medical record creation work are computerized, they are called "electronic medical records." The words and phrases input from the input unit 12 are sent to the medical receipt management system 2 together with the information in the word and phrase input field.

[0025] Furthermore, when the information processing terminal 10 accesses the medical record management system 3, the display screen of the electronic medical record is displayed on the Web browser of the display unit 11 based on the function provided by the medical record management system 3. The electronic medical record is displayed in a fixed format that matches the layout of an actual book, allowing words on the page to be copied and pasted using the Web browser or a dedicated application. Furthermore, the dental clinic staff can switch to a reflow type display that allows the font size to be changed to any size, a horizontal or vertical display, etc.

[0026] In addition, the dental clinic staff can highlight important points in the displayed electronic medical record, create indexes for pages, and convert the electronic medical record into a portable document format (PDF). The electronic medical record can be displayed on the information processing terminal 10 by turning one page at a time, or by turning multiple pages continuously.

[0027] In addition to the "disease name" and "procedure name (or treatment name)," the electronic medical record records, for example, the "patient's complaint (e.g., there is a tingling pain in the area)" and the "findings of staff such as dentists (e.g., there is bleeding when pressing the affected area with a finger)." For example, in the electronic medical record, keywords such as the patient's complaint and staff findings are recorded as trends in the disease name.

[0028] (Receipt management system) The information entered by the dental clinic staff into the receipt entry field via the information processing terminal 10 is transmitted to the receipt management system 2 as medical treatment data d1 shown in Fig. 2. The receipt management system 2 includes a receipt management section 21 and a receipt DB (Data Base) 22.

[0029] The medical receipt management unit 21 manages data related to medical treatment and data related to the issuance of medical receipts, which are input from the information processing terminal 10. The medical receipt management unit 21 outputs an input screen for data related to medical treatment to the information processing terminal 10. The medical receipt management unit 21 also outputs information to be displayed on the information processing terminal 10 (e.g., html (Hyper Text Markup Language) files, xml (Extensible Markup Language) files, image files, etc.) to the information processing terminal 10. The Web browser of the information processing terminal 10 displays a medical receipt input screen. The medical receipt management unit 21 also displays a screen for inputting data related to medical treatment, in addition to the electronic medical record input screen, on the display unit 11 of the information processing terminal 10 by a program that manages the issuance of medical receipts.

[0030] The medical treatment data d1 is input to the medical treatment receipt management unit 21 from the information processing terminal 10. The medical treatment data d1 is data entered in an electronic medical record and data for creating a medical treatment receipt. The medical treatment receipt management unit 21 imports the medical treatment data d1 from the information processing terminal 10 and stores it in the medical treatment receipt DB 22.

[0031] The receipt DB 22 stores medical treatment log data and basic medical institution information shown in FIG. 2, which will be described later. The receipt management unit 21 creates receipts based on the data acquired from the receipt DB 22. For example, the receipt DB 22 stores medical treatment log data and receipt data created for each patient and for each medical content. Staff at the dental clinic periodically operate the information processing terminal 10 to print receipts. For example, with the receipt data read from the receipt management system 2 displayed, the staff presses a print button displayed on the screen of the information processing terminal 10 to output a receipt printed on paper. This printed receipt is submitted to an examination and processing agency, not shown.

[0032] 2, the medical data d1 stores the date and time, the user ID, and the user name. The date and time item stores the date and time when the dental clinic staff inputs the medical receipt using the information processing terminal 10. In the item of user ID, a user ID that uniquely identifies a staff member as a user of the information processing terminal 10 is stored. The user name field stores the name of the user linked to the user ID, i.e., the name of the dental clinic staff member. The medical receipt information item stores medical receipt information entered by the user.

[0033] (Composition of medical log data) As described above, the medical treatment log data shown in Fig. 2 is stored in the medical treatment receipt DB 22 of the medical treatment receipt management system 2. Each item of the medical treatment log data includes a date and time, a medical staff ID, a patient name, and an event recorded in the medical record. The date and time item stores the date and time when the dental clinic staff filled out the electronic medical record. The medical staff ID item stores a medical staff ID assigned to identify a staff member.

[0034] The patient name field stores the patient's name. The item "Events entered in medical records" stores information about events entered in the electronic medical record by dental clinic staff. Events entered in the electronic medical record include the quoted content (disease name, procedure name, summary, etc.) when the staff quoted the page or phrase information on the electronic medical record, the quoted date and time, the quoted person (medical professional ID), the number of citations, etc.

[0035] (Basic information on medical institutions) The medical institution basic information shown in Fig. 2 is also registered in the receipt DB 22. The medical institution basic information is also known by the service company. Each item of the medical institution basic information stores the name of the clinic, address, telephone number, home page URL (Uniform Resource Locator), and medical staff information.

[0036] The clinic name field stores the name of the dental clinic (or hospital). The address item stores the address of the dental clinic (or hospital). The telephone number field stores the telephone number of the dental clinic (or hospital). The URL of the website managed by the dental clinic (or hospital) is stored in the item of the website URL. The medical staff information item stores information about medical staff working at the dental clinic (or hospital). The medical staff information includes, for example, information about the university from which the medical staff graduated.

[0037] (Service company) The service company not only manages the entire viewing support system 1, but also provides the dental clinic staff with a service of supporting the input of information to be recorded in the electronic medical record using the medical record management system 3. Usually, the staff who can view the electronic medical record include, for example, other staff members of the dental clinic where the staff member who created the electronic medical record works.

[0038] The medical record management system 3 displays the electronic medical record read from the medical record DB 33 on the display unit 11 of the information processing terminal 10 by the dental clinic staff operating the information processing terminal 10. The dental clinic staff operates the information processing terminal 10 connected to the medical record management system 3 to open the electronic medical record at any page, and creates the patient's electronic medical record or medical receipt by referring to the page corresponding to the treatment content. The dental clinic staff can also copy and paste a word or phrase selected from the electronic medical record into the receipt input field or enter a comment in the input field.

[0039] The medical record management system 3 includes a medical record management unit 31, a reference management unit 32, a medical record DB 33, and a reference log DB . The medical record management unit 31 manages electronic medical record information. The medical record management unit 31 also outputs creation information for creating medical-related information, which is input by the information processing terminal 10, to the RAG system 4. The medical record management unit 31 then receives a response from the RAG system 4 and supports the creation of medical-related information. In other words, the medical record management unit 31 can be said to be an example of a creation support unit that supports the creation of medical-related information by staff.

[0040] The creation information for creating medical-related information includes questions to be entered in the display area of ​​the medical-related information creation display screen (see Figures 9 and 10 described below) used for the creation of the medical-related information. The creation information also includes information regarding the items selected by the dental clinic staff on the medical-related information creation display screen. For example, questions that staff ask to create electronic medical records or medical receipts, instructions to create a summary document, etc., are examples of created information. This created information includes at least one of text, audio, and images. In addition, the answer includes the summary document and information on the reference source of the reference information summarized by LLM45 (e.g., page number of the reference information, chapter title, etc.).

[0041] The medical record management unit 31 accepts input to the electronic medical record by the dental clinic staff, and outputs a screen displaying the electronic medical record to the display unit 11 of the information processing terminal 10. The medical record management unit 31 manages the electronic medical records whose creation has been assisted by the RAG system 4. The electronic medical record is generated based on information obtained from the RAG system 4 when the knowledge search unit 44 inputs creation information (a prompt, described later) to the LLM 45.

[0042] The RAG system 4 performs embedding processing by reading past electronic medical records, official gazettes, etc., and mapping vectorized text and images into a vector space. The RAG system 4 also uses large language models (LLMs) to output information appropriate for the input content. A detailed configuration example of the RAG system 4 is shown in Fig. 4, which will be described later, and only a brief explanation will be given here.

[0043] The RAG system 4 includes an LLM 45 (an example of a large-scale language model) shown in FIG. 4, which will be described later. The LLM 45 may use a service provided by a service company other than the service company. The LLM 45 is one of the text generation AIs (Artificial Intelligence), and is a language model that has learned a huge amount of text data. The LLM 45 has the ability to perform advanced natural language processing tasks (text generation, translation, summarization, question answering, etc.). In addition, the LLM 45 can output an appropriate answer according to the created information (e.g., a question) input by the staff of the dental clinic, using the mechanism of Transformer. The created information may be not only text explicitly input by the staff, but also text or images automatically extracted from the information displayed on the screen.

[0044] The reference management unit 32 collects data such as reference log data d2 (see FIG. 2) from the reference log DB 34 in accordance with commands received from the information processing terminal 10, and passes the data to the receipt DB 22 of the receipt management system 2. The receipt management unit 21 manages receipt data stored in the receipt DB 22 for each dental clinic or for each staff member of the dental clinic.

[0045] 2 includes information on the history of electronic medical record access that was referenced by the dental clinic staff when creating an electronic medical record or inputting a medical receipt by operating the information processing terminal 10. The reference log data d2 is stored in the reference log DB 34 of the medical record management system 3.

[0046] The reference log data d2 is data that stores the type of electronic medical record that the staff member referenced, the version of the electronic medical record (date of creation, etc.), the time the electronic medical record was left on the electronic medical record, etc. The reference management unit 32 reads out the version of the electronic medical record specified by the input unit 12 from the medical record DB 33, and displays it on the display unit 11 of the information processing terminal 10. In addition, operations that the dental clinic staff performed while referring to the electronic medical record when entering a receipt (for example, copying and pasting a specific item) are also stored in the reference log DB 34 as reference log data d2.

[0047] (See Log Data Configuration) The reference log DB 34 stores the reference log data d2 shown in FIG. The reference log data d2 stores the chart ID, book name, version, index, page information, and reference page. In the item of medical record ID, a medical record ID that uniquely identifies the electronic medical record being viewed on the information processing terminal 10 is stored. The book name field stores the name of the electronic medical record linked to the medical record ID as the book name. The version item stores the version of the electronic medical record (date of creation, etc.). In the item of page information, page information such as the page number of the electronic medical record is stored.

[0048] In addition, the reference log DB 34 may store the prescription ID and return information indicated by the dashed dotted line as reference log data d2. The Receipt ID field stores the receipt ID for identifying the receipt submitted to the review and processing organization. The receipt ID is a unique identification given to each receipt when the staff creates the receipt. The items of the return information store a return flag indicating whether the receipt submitted to the examination processing agency has been returned, and return information including the phrases and locations where corrections were pointed out by the examination processing agency at the time of return.

[0049] Figure 3 is a diagram showing an example of the data structure of the medical record DB 33. The medical record DB 33 has items for patient ID, book ID, date, location, disease name, and treatment. The patient ID item stores a patient ID that uniquely identifies the patient. The book ID item stores a book ID that uniquely identifies the documented electronic medical record. The date item stores the creation date or update date of the electronic medical record.

[0050] The location item stores information on the treated location. The disease name item stores information on the patient's disease name. The treatment item stores information on the treatment performed on the patient.

[0051] For a first-time visit patient, since a new electronic medical record is created, the creation date of the electronic medical record is stored in the date item. For a revisit patient, since it is appended to the electronic medical record with the existing patient ID, a new record is added to the medical record DB 33, and the treatment details of the revisit are stored in that record.

[0052] <Example of the internal configuration of the RAG system> Figure 4 is a block diagram showing an example of the internal configuration of the RAG system 4. Here, the cooperation between the medical record management system 3 and the RAG system 4 will be described.

[0053] First, let us explain RAG. RAG is a technology that combines a generative model (usually a text generation model) with information search capabilities, and is primarily composed of a search engine (Retriever) and a generative model (Generator). A search engine has the function of searching for related documents and information from a database based on a user's input (query). For this reason, the search engine performs similarity calculations using an embedding model that embeds the user's query and documents in the database in a vector space, and searches for documents related to the query. On the other hand, the generative model generates responses and text for the user based on the information searched by the search engine. For this reason, the generative model generates responses by converting the contents of documents searched by the search engine into language expressions that are easy for humans to recognize.

[0054] The RAG system 4 includes a knowledge upload unit 41, a knowledge update unit 42, an embedding unit 43, a knowledge search unit 44, an LLM 45, a knowledge database (knowledge DB 51), a vector database (vector DB 52), and a prompt database (prompt DB 53).

[0055] A knowledge upload unit 41, a knowledge update unit 42, and a knowledge search unit 44 are connected to the medical record management system 3. The knowledge upload unit 41 is connected to the knowledge DB 51 and uploads knowledge acquired from the medical record management system 3 to the knowledge DB 51. The knowledge includes, for example, official gazettes published by the Ministry of Health, Labor and Welfare, guidelines for filling out medical receipts, past electronic medical records, etc. The knowledge uploaded by the knowledge upload unit 41 is stored in the knowledge DB 51.

[0056] The knowledge update unit 42 is connected to the embedding unit 43 and the knowledge DB 51. The knowledge update unit 42 updates the knowledge stored in the knowledge DB 51. Then, the knowledge update unit 42 acquires knowledge that is instructed to be updated by the medical record management system 3 from the knowledge DB 51, and outputs the acquired knowledge to the embedding unit 43.

[0057] The embedding unit 43 uses the embedding model to vectorize the knowledge input from the knowledge update unit 42 and embed it in a high-dimensional vector space. The knowledge embedding process uses a technique for mapping data such as text and images into a vector space. The embedding unit 43 performs tokenization to divide the knowledge into tokens, and then vectorizes the tokens and generates a vector representation of the entire query.

[0058] A vector representation of the entire query is obtained by integrating token vectors in the query in an appropriate manner (average pooling, max pooling, etc.). Through the embedding process in the embedding unit 43, words, sentences, and entire documents of the text are converted into numerical vectors, and semantically similar words and documents are placed close to each other in the vector space. Using these numerical vectors, machine learning tasks such as similarity calculation and clustering of different texts are made easier. The embedding unit 43 then stores the vectorized knowledge in the vector DB 52.

[0059] The vector DB 52 stores knowledge that is vectorized and embedded in a vector space. For this reason, the vector DB 52 is constructed as a database specialized for vector search. The vector DB 52 stores a group of chunks (e.g., text) obtained by dividing a file stored in the knowledge DB 51 into multiple chunks, information on the chunks expressed as vectors, and the like.

[0060] The text embedded in the vector space is stored in the vector DB 52, for example, in a matrix format. Each row of the matrix represents an individual text vector, and each column represents a dimension of the vector. The vector may also be stored as a numerical array of floating-point numbers or in a binary format. Searchability is improved by storing the vector in the vector DB 52 together with the text corresponding to the vector itself, the document ID of the document from which the text is written, the publication date and time, etc.

[0061] The knowledge search unit 44 is connected to the medical record management system 3, the embedding unit 43, the LLM 45, the vector DB 52, and the prompt DB 53. The knowledge search unit 44 searches the vector DB 52 for knowledge based on the vectorized creation information, and outputs an answer formed from the searched knowledge to the medical record management unit 31.

[0062] Then, when the knowledge search unit 44 receives a question (query) input from the medical record management system 3, it performs tokenization to divide the question into tokens, and then vectorizes the tokens to vectorize the question. Then, the knowledge search unit 44 extracts vectorized knowledge based on the similarity between the vectorized knowledge stored in the vector DB 52 and the vectorized creation information (query vector). At this time, the knowledge search unit 44 extracts one record stored in the vector DB 52.

[0063] In the knowledge search, the knowledge search unit 44 calculates the similarity between the query vector and each vector in the database. The similarity of the vectors is measured using, for example, cosine similarity or Euclidean distance. Cosine similarity is a method for calculating the cosine of the angle between two vectors, and its value ranges from -1 to 1. The closer the value is to 1, the more similar the vectors are judged to be. Euclidean distance is a method for calculating the linear distance between two vectors, and the smaller the value is, the more similar the vectors are judged to be.

[0064] The embedding unit 43 embeds the question text in a vector space and searches the vector DB 52 for a vector that is an answer to the question. The embedding unit 43 then determines the most similar vector as the answer with the highest confidence. The embedding unit 43 returns the text corresponding to the vector searched for in the vector DB 52 to the knowledge search unit 44 as a search result.

[0065] The knowledge search unit 44 also outputs the text of the knowledge found by the vector search to the LLM 45. The LLM 45 receives the text of the knowledge input from the knowledge search unit 44 and a question (prompt) composed of normal characters. The LLM 45 can generate natural sentences based on the prompt and generate an answer based on the prompt. The LLM 45 also reads reference information in advance and summarizes the reference information based on a prompt consisting of text or an image. For example, the LLM 45 can summarize long texts contained in reference information such as the official gazette and information on the Ministry of Health, Labor and Welfare website that have been read in advance, and extract important information.

[0066] The LLM 45 can also translate text from one language to another and classify text into categories. By using the LLM 45, the RAG system 4 can utilize the text generation capabilities of the LLM 45 to provide a response to the staff member that matches the context based on the retrieved information. This allows the RAG system 4 to provide a dialogue function to the medical record management system 3. The knowledge search unit 44 can also output a summary document summarized by the LLM 45 to the medical record management system 3.

[0067] The subject that selects a prompt from the prompt DB 53 is assumed to be one of the first to third forms described below. In the first mode, the knowledge search unit 44 specifies a fixed prompt ID, and a prompt corresponding to the specified prompt ID is obtained from the prompt DB 53 and executed.

[0068] The second form is a derivative of the first form, in which, for example, the knowledge search unit 44 displays a list of prompts acquired from the prompt DB 53 on a screen, and the staff of the dental clinic can select any prompt.

[0069] In the third form, the LLM 45 and the prompt DB 53 are connected as shown by the dashed line in the figure. In other words, in the third form, the LLM 45 directly references the prompt DB 53. In this third form, the dental clinic staff searches for the most appropriate prompt to process the input question. The LLM 45 then uses the searched prompt to execute processes such as creating a summary.

[0070] Next, examples of the configurations of the knowledge DB 51, the vector DB 52, and the prompt DB 53 will be described with reference to FIGS. 5 is a diagram showing an example of the configuration (data structure) of the knowledge DB 51. The knowledge DB 51 has the following items: document ID, file name, file type, and BLOB (Binary Large Object). The document ID field stores a document ID that can identify knowledge as a document. The document ID includes various printed information that can be referenced when creating an electronic medical record.

[0071] The file name item includes the file names of the various printed materials mentioned above. For example, PDF format medical record case collections, insurance revision collections, memos, etc. In addition, file names of files saved in text format, document file format, and presentation file format are also included. The file type item includes the file types (eg, file extensions) of various print files. The BLOB item stores data that has been compiled from a file, i.e., BLOB data. BLOB data includes text data or binary data such as image data.

[0072] 6 is a diagram showing an example of the configuration (data structure) of the vector DB 52. The vector DB 52 has the following items: document ID, chunk ID, text, vector, file name, character position, and page. The document ID field stores a document ID. This document ID is the same as the document ID stored in the knowledge DB 51. The chunk ID item stores chunk IDs that identify chunks obtained by dividing a document into a specified number of characters. Multiple chunk IDs may be included for the same document ID. For example, a document with document ID "1" may contain chunk IDs "1" to "4".

[0073] The text item stores text that has been split into chunks from a document. A chunk is, for example, a group of 500 characters, and is automatically split from the original document. However, chunks identified by consecutive chunk IDs are likely to be out of context. For this reason, consecutive chunks are split from the original document in such a way that some characters overlap each other.

[0074] For example, a chunk with a chunk ID of "1" is the text from 0 to 499 characters of "Medical Record Case Collection", and a chunk with a chunk ID of "2" is the text from 449 to 948 characters, with splitting starting 50 characters back from the end character position of the split of the chunk with a chunk ID of "1". To clarify the context, for example, the character position of the segmentation start character for segmenting the next chunk may be the character position of the text up to the first period, counting backward from the character position of the segmentation end character that segmented the previous chunk. Alternatively, the text of the heading and the main text may be segmented into one chunk.

[0075] The vector field stores the vector calculated for each chunk. Based on the characters contained in the chunk, it is tokenized for each minimum unit of meaning, and the tokens are embedded in a vector space to calculate a numeric vector for the token. The chunk vector calculated by combining the numeric vectors of each token is stored in the vector field. This process results in a vector that retains the meaning of each chunk in a high-dimensional vector space.

[0076] The file name field stores the file name of the file from which the text is stored. The character position field stores the start and end character positions of the chunks split from the original document. For example, the character positions of a chunk with a chunk ID of "1" are the start character position "0" and the end character position "499." The page item stores the number of pages in the file that contained the chunk.

[0077] 7 is a diagram showing an example of the configuration (data structure) of the prompt DB 53. The prompt DB 53 has items such as ID and prompt.

[0078] The ID item stores a prompt ID that identifies the prompt. The prompt item stores the prompt to be entered into LLM45. A prompt is an instruction sentence that the dental clinic staff enters into the RAG system 4 through the medical record management system 3. For example, the prompt for ID1 is as follows. "You" in the prompt refers to LLM45. "You are a Japanese language AI assistant for RAG, and will converse in a friendly tone. The following knowledge has been found in response to the user's question. {"Text": (0 to 499th characters of the text in "Medical Records")} Please explain to the user that you found the above knowledge base article and provide a summary of it."

[0079] <Example of Hardware Configuration of Information Processing Terminal 10 and Each Server> Next, the hardware configuration of the computer 100 constituting the information processing terminal 10 of the browsing support system 1, the medical receipt management system 2, the medical record management system 3, and the RAG system 4 will be described. FIG. 8 is a block diagram showing an example of the hardware configuration of the computer 100. As shown in FIG.

[0080] The calculator 100 is an example of hardware used as a computer capable of operating as the information processing terminal 10, the medical receipt management system 2, the medical record management system 3, and the RAG system 4 according to this embodiment. The computer 100 includes a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, and a RAM (Random Access Memory) 103, each of which is connected to a bus 104. The computer 100 further includes a display device 105, an input device 106, a non-volatile storage 107, and a network interface 108.

[0081] The CPU 101 reads out program code of software for implementing each function according to this embodiment from the ROM 102, loads it into the RAM 103, and executes it. Variables, parameters, etc. generated during the calculation processing of the CPU 101 are temporarily written into the RAM 103, and these variables, parameters, etc. are read out by the CPU 101 as appropriate. However, an MPU (Micro Processing Unit) may be used instead of the CPU 101. Each function of the receipt management system 2, the medical record management system 3, and the RAG system 4 is implemented by the operation of the CPU 101.

[0082] The display device 105 is, for example, a liquid crystal display monitor, and displays the results of processing performed by the computer 100 to the staff. The input device 106 is, for example, a keyboard, a mouse, etc., and allows the staff to input predetermined operations and give instructions. The functions of the display unit 11 and input unit 12 of the information processing terminal 10 are realized by the display device 105 and the input device 106. In addition, the functions of the display unit and input unit of a PC (not shown) connected to the medical record management system 3 are also realized by the display device 105 and the input device 106. The RAG system 4 does not need to be equipped with the display device 105 and the input device 106.

[0083] The non-volatile storage 107 may be, for example, a hard disk drive (HDD), a solid state drive (SSD), a flexible disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a magnetic tape, or a non-volatile memory. In addition to an operating system (OS) and various parameters, programs for operating the computer 100 are recorded in the non-volatile storage 107.

[0084] The ROM 102 and the non-volatile storage 107 record programs, data, etc. necessary for the CPU 101 to operate, and are used as an example of a computer-readable non-transitory storage medium storing a program executed by the calculator 100. Data of the receipt management system 2, the medical record management system 3, and the RAG system 4 are stored in the non-volatile storage 107.

[0085] For example, a network interface card (NIC) is used as the network interface 108, and various data can be transmitted and received between devices via a LAN, a dedicated line, or the like connected to a terminal of the NIC.

[0086] [Screen display example] Next, examples of screens displayed on the information processing terminal 10 will be described with reference to Fig. 9 and Fig. 10. The following screens are all displayed on a general-purpose web browser installed on the information processing terminal 10.

[0087] <First display example of the electronic medical record creation display screen> 9 is a diagram showing a first display example of the electronic medical record creation display screen W1. The display function of the electronic medical record creation display screen W1 is realized by the medical record management unit 31. The electronic medical record creation display screen W1 is used in the medical record management system 3 equipped with a chat-type RAG. This electronic medical record creation display screen W1 has an oral cavity information display area W1a, a medical record information display area W1b, and a chatbot display area W1d.

[0088] In the oral cavity information display area W1a, a schematic diagram of the oral cavity of the patient is displayed. The schematic diagram of the oral cavity shows the arrangement and condition of the patient's teeth. The medical record information display area W1b displays the contents of the electronic medical record as medical record information. The medical record information includes the consultation date and the details of the treatment given to the patient. In addition, the medical record information display area W1b displays a PDF button W1c.

[0089] The dental clinic staff inputs an instruction to convert the medical record information into a PDF file by pressing the PDF button W1c. The PDF medical record information is uploaded to the knowledge DB 51 by the knowledge upload unit 41 and vectorized by the embedding unit 43. The vectorized medical record information is then stored in the vector DB 52. This makes it possible to perform knowledge searches based on past medical record information.

[0090] The chatbot display area W1d displays an answer chat represented by an image of a robot, and a question chat in which a staff member inputs a question. Initially, the answer chat displays "Is there something I can help you with?" When a staff member inputs "What dental crown prostheses are covered by the crown and bridge maintenance fee?" into the question chat, the answer chat displays "We will search for a matching item in the knowledge base."

[0091] In addition, when the staff member clicks on the item "Crown and Bridge Maintenance Fee (Br5 teeth or less)" displayed in the medical record information display area W1b, the question chat may automatically be input with "What crown prostheses are subject to the crown and bridge maintenance fee?". After that, the answer chat displays a summary divided into items such as "The prostheses subject to the crown and bridge maintenance fee include the following: 1. ..., 2. ...". This answer is an explanation summarized by the LLM 45 from the results of a search in the vector DB 52 based on the question vectorized by the embedding unit 43.

[0092] The answer chat also displays the file name on which the answer is based and the relevant part of the file. For example, the answer chat displays both the content and the page on which it is written, such as "The CAD / CAM crowns listed in Insurance Revision 2024.pdf M015-2 are...Page 25." In addition to the file name, the answer may also be based on link information including a URL that allows access to the file. The answer chat may also display multiple answers in order of the confidence of the answer, and staff may select any answer.

[0093] As shown at the bottom of the chatbot display area W1d, information entered by the staff member using the keyboard or voice, such as "What crown prostheses are covered by the crown bridge maintenance fee?" may be displayed. Also, only "Kurabuuri," an abbreviation for "crown bridge maintenance fee," may be entered and displayed in the question chat. Even with such a question, the staff member can press the send button to execute the knowledge search process shown in Figs. 13 and 14, which will be described later. The text of the question is then sent to the RAG system 4 via the medical record management system 3, and an answer can be obtained.

[0094] <Second display example of electronic medical record creation display screen> 10 is a diagram showing a first display example of the electronic medical record creation display screen W2. The display function of the electronic medical record creation display screen W2 is realized by the medical record management unit 31. The electronic medical record creation display screen W2 is used in the medical record management system 3 equipped with a type of RAG that automatically detects input. This electronic medical record creation display screen W2 has an input information display area W2a and a knowledge display area W2b.

[0095] The input information display area W2a displays the items to be input to the electronic medical record. For example, when a staff member selects the item "Crown and bridge maintenance fee (Br5 teeth or less)", this item is highlighted.

[0096] The knowledge display area W2b displays the results of an automatic search for knowledge related to the item selected in the input information display area W2a. For example, the procedure name, disease name, or comment selected by the staff member is automatically adopted as a search word by the medical record management system 3. Knowledge related to this search word is always displayed in the knowledge display area W2b. This allows staff to satisfy their medical practice and communication with patients while reducing the time and effort required for them to look things up themselves.

[0097] Note that the search target of the RAG system 4 is not limited to text. For example, the medical record management system 3 periodically takes a screenshot of the input information display area W2a. By inputting the captured image into the RAG system 4 that supports multimodality, the medical record management system 3 can search for information corresponding to the captured image and display it in the knowledge display area W2b. In this case, information related to the knowledge that is always displayed in the input information display area W2a is displayed in the knowledge display area W2b.

[0098] [Example of operation of the medical record management system and RAG system] Next, an overview of an example of the operation of the medical record management system 3 and the RAG system 4 according to this embodiment will be described with reference to Fig. 11 to Fig. 14. In the following description, the medical record management system 3 and the RAG system 4 shown in Fig. 1 and an example of the internal configuration of the RAG system 4 shown in Fig. 4 will be referred to as appropriate.

[0099] First, an example of the process of adding and updating knowledge in the RAG system 4 will be described with reference to Figures 11 and 12. These processes are performed before the service company provides the service to the dental clinic, but can also be performed at any time after the service is provided. Furthermore, the entity that performs these processes may not only be a person in charge at the service company, but also the staff of the dental clinic that uses the medical record management system 3.

[0100] FIG. 11 is a flowchart showing an example of a knowledge addition process in the RAG system 4. First, the knowledge upload unit 41 selects (S1) a file to be uploaded to the knowledge DB 51. Next, the knowledge upload unit 41 checks whether a file with the same file name as the selected file is stored in the knowledge DB 51 (S2).

[0101] If a file with the same file name is not stored in the knowledge DB 51 (NO in S2), the knowledge upload unit 41 uploads the selected file to the knowledge DB 51 (S3), and ends this process.

[0102] On the other hand, if a file with the same file name is stored in the knowledge DB 51 (YES in S2), the knowledge upload unit 41 ends this process without adding the knowledge. However, if the file has the same file name but is a different version, the knowledge upload unit 41 may upload the file of the different version to the knowledge DB 51 and then end this process.

[0103] FIG. 12 is a flowchart showing an example of a knowledge update process in the RAG system 4. First, the knowledge update unit 42 acquires data including the knowledge to be updated from the knowledge DB 51 (S11). Next, the embedding unit 43 vectorizes the data using the embedding model (S12). This vectorization process includes, for example, a process of dividing a document into chunks, a process of tokenizing words and phrases in the chunks, a process of vectorizing the tokens, and the like.

[0104] Next, the embedding unit 43 stores the vectorized data in the vector DB 52 (S13). Then, the knowledge update unit 42 determines whether or not the vectorized knowledge stored in the vector DB 52 has been updated by all the data acquired from the knowledge DB 51 (S14).

[0105] If the vectorized knowledge has not been updated by all the data (NO in S14), the process returns to step S11 and is repeated. On the other hand, if the vectorized knowledge has been updated by all the data (YES in S14), this process ends.

[0106] Next, an example of the processing of the viewing support system 1 when a staff member creates an electronic medical record will be described with reference to FIGS. 13 is a flowchart showing an example of the process of creating an electronic medical record. Operations on the information processing terminal 10 are performed via a Web screen displayed when a staff member accesses the medical record management system 3. Therefore, each operation on the information processing terminal 10 is executed by each functional unit of the medical record management system 3.

[0107] When the dental clinic staff starts creating an electronic medical record by operating the input unit 12 of the information processing terminal 10, the medical record management unit 31 judges whether the created electronic medical record is stored in the medical record DB 33 or not (S21). This judgment is made based on whether the patient is visiting for the first time or a repeat visit. The dental clinic staff inputs the patient number written on the patient's patient card into the information processing terminal 10 to check whether the patient number is registered in the medical record DB 33.

[0108] If the created electronic medical record is stored in the medical record DB 33 (YES in S21), the medical record management unit 31 acquires the created electronic medical record from the medical record DB 33 (S22) and displays it on the display unit 11. This electronic medical record is displayed on the electronic medical record creation display screen W1 (see FIG. 9) or W2 (see FIG. 10).

[0109] On the other hand, if the electronic medical record already created in step S21 is not stored in the medical record DB 33 (NO in S21), a new electronic medical record is created (S23).

[0110] The dental clinic staff inputs the necessary information while checking the electronic medical record. If there is an item that the staff is unclear about, they select that item and input a question in the question chat. This selected item is input to the medical record management system 3 as a prompt (text or image) (S24). The medical record management unit 31 outputs the input prompt to the RAG system 4 (S25). The RAG system 4 performs a knowledge search process based on the prompt input from the medical record management system 3 (S26).

[0111] Here, the knowledge search process performed by the RAG system 4 will be described with reference to Fig. 14. Fig. 14 is a flowchart showing an example of the knowledge search process performed by the RAG system 4. 4 receives a prompt input from the medical record management system 3, the knowledge search unit 44 inputs the prompt as a search query to the embedding unit 43 (S31). As described above, the prompt includes text or an image.

[0112] Next, the embedding unit 43 vectorizes the search query using the embedding model (S32), and then acquires knowledge that has a high similarity to the vectorized search query from the vector DB 52 (S33).

[0113] Next, the embedding unit 43 determines whether or not knowledge has been acquired from the vector DB 52 (S34). If knowledge has not been acquired from the vector DB 52 in step S34 (NO in S34), the embedding unit 43 ends this process and proceeds to step S27 in FIG.

[0114] On the other hand, if knowledge can be acquired from the vector DB 52 in step S34 (YES in S34), the embedding unit 43 passes the knowledge to the LLM 45. The LLM 45 acquires an arbitrary prompt from the prompt DB 53 based on the knowledge (S35).

[0115] Next, the search query, knowledge, and prompt are input to the LLM 45 (S36). The LLM 45 then generates an explanation of the search results and a summary of the knowledge in accordance with the prompt (S37), and proceeds to step S27 in FIG.

[0116] Returning to the explanation of Figure 13. The medical record management unit 31 acquires an answer including an explanation of the search result and a summary of the knowledge from the RAG system 4 (S27). The medical record management unit 31 displays the acquired answer on the screens W1 and W2. Next, the medical record management unit 31 reflects the answer in the electronic medical record and saves the electronic medical record in the medical record DB 33 (S28), and ends this process.

[0117] The dental clinic staff may use voice input instead of operating the input unit 12 to write the prompt. For example, the input unit 12 may capture a conversation between the staff and the patient via a microphone, and convert the voice information into text, which may then be output as a prompt to the RAG system 4. By using voice input, the staff does not need to hold the information processing terminal 10 and can concentrate on dealing with the patient.

[0118] In the browsing support system 1 according to the first embodiment described above, staff can use the medical receipt management function and the medical record management function simply by preparing the information processing terminal 10 without having to prepare a dedicated server. The medical record management function incorporates a response support function using the RAG system 4, and each time a staff member makes an input when creating an electronic medical record, information related to this input is displayed. Therefore, the dental clinic staff can create an electronic medical record in the correct format while referring to the information displayed on the display unit 11.

[0119] In addition, when dental clinic staff enter a question when creating an electronic medical record, the answer to that question is displayed. The answer is easy for staff to understand because LLM45 summarizes the original long document (reference information). In addition, the reference information of the document on which the answer is based is also displayed, so when staff want to check more detailed information, they can immediately refer to the reference information of the document.

[0120] In addition, the service company manages the medical record management system 3, so there is no need to install a server or the like at the dental clinic. This makes it possible to reduce the introduction costs and ongoing costs of the server and the like required for introducing the browsing support system 1. In addition, the information processing terminal 10 does not need to be installed in a specific location.

[0121] For example, the staff of the dental clinic can access the medical receipt management system 2 and the medical record management system 3 via the Internet using an information processing terminal 10 (e.g., a notebook PC or a tablet terminal) that is taken outside the dental clinic. This makes it easy for the staff of the dental clinic to check the input status of the electronic medical records and medical receipts, and also makes it easy to check the contents of the electronic medical records.

[0122] Answers to questions entered by dental clinic staff are generated using AI technologies such as LLM45, and can include, for example, explanations of search results and knowledge summaries to help staff make sense of complex documents.

[0123] In addition, when a new document is published, the knowledge is uploaded. In addition, when a document is revised, the knowledge is revised. Therefore, the RAG system 4 can output an answer based on the latest knowledge to the medical record management system 3 and reflect the answer in the electronic medical record.

[0124] In the above-mentioned first embodiment, the link between the medical record management system 3 and the RAG system 4 has been described, but the medical receipt management system 2 and the RAG system 4 are also linked in a similar manner. For example, a medical receipt creation display screen similar to the screens W1 and W2 shown in Figs. 9 and 10 is displayed on the display unit 11. Therefore, when the staff specifies an unknown item on the screen displayed when using the medical receipt management system 2, the answer obtained from the RAG system 4 is displayed on the display unit 11. Also, a summary of the appropriate content is displayed from a document that describes the outline of how to fill out the medical receipt. Therefore, the medical receipts created by the staff can be made more accurate, reducing the possibility of them being returned.

[0125] Furthermore, the knowledge upload unit 41 and the knowledge DB 51 may be removed from the RAG system 4 according to the first embodiment. In this case, the document (knowledge) sent from the medical record management unit 31 of the medical record system 3 to the RAG system 4 is sent to the embedding unit 43 by the knowledge update unit 42. The embedding unit 43 vectorizes the document (knowledge) and stores the vectorized knowledge in the vector DB 52. Even in this configuration, the knowledge search unit 44 can display the chunked text in the vector DB 52 on the screens W1 and W2, so that the staff can check the chunked text.

[0126] [Second embodiment] Next, an example of the configuration of a browsing support system according to a second embodiment of the present invention will be described with reference to FIG. 15 is a functional configuration diagram showing an example of the overall configuration of a browsing support system 1A according to the second embodiment. The browsing support system 1A is capable of generating electronic medical records and supporting answers using RAG even in an offline state.

[0127] The browsing support system 1A includes an information processing terminal 10 and a medical record computer 6 for each dental clinic. The medical record computer 6 includes a medical record management system 60 and a RAG system 70. The medical record management system 60 includes a medical record management unit 61, a reference management unit 62, a medical record DB 63, a reference log DB 64, and a medical receipt DB 65.

[0128] The functions of the medical record management unit 61 and the reference management unit 62 are similar to those of the medical record management unit 31 and the reference management unit 32 according to the first embodiment. Therefore, the medical record management unit 61 can generate and manage electronic medical records in an offline state.

[0129] The medical record DB 63 stores information of the electronic medical records created by the medical record computer 6 . Since the electronic medical record information includes the patient's personal information, it remains within the medical record computer 6. Medical care data d1 is sent from the medical record computer 6 to the medical receipt management system 2, and the medical care data d1 is registered in the medical receipt DB 22. In addition, reference log data d2 is sent from the medical record computer 6 to the medical record management system 3, and the reference log data d2 is registered in the reference log DB 34.

[0130] The data configurations of the medical record DB 63 , the reference log DB 64 , and the receipt DB 65 are similar to the data configurations of the medical record DB 33 , the reference log DB 34 , and the receipt DB 22 . The inside of RAG system 70 is configured in the same manner as RAG system 4 shown in Fig. 4. RAG system 70 is installed in a dental clinic, and there is no need to output data such as personal information to the outside of the dental clinic.

[0131] The data in each DB constructed in the medical record computer 6 is limited to information that can be referenced by staff. Even if the medical record computer 6 is offline, staff can operate the information processing terminal 10 to view the information recorded in each DB in the medical record computer 6. Furthermore, of the information written in each DB of the medical record computer 6, information other than the medical record DB 63 is periodically synchronized with each DB provided in the medical receipt management system 2 and the medical record management system 3 and used.

[0132] In the browsing support system 1A according to the second embodiment described above, information in each DB of the medical record computer 6 is synchronized with information in each DB of the medical receipt management system 2 and the medical record management system 3. Therefore, even if the medical record computer 6 goes offline, the staff can check the information recorded in each DB of the medical record computer 6.

[0133] [Variations] In the above-mentioned embodiments, the creation of medical records (electronic medical records) and medical receipts in dental treatment has been described, but the present invention can also be applied when creating medical records (electronic medical records) and medical receipts for treatment by doctors, nurses, physical therapists, judo therapists, etc. For example, not only in dentistry but also in medical, pharmaceutical, and veterinary care departments, staff from each department can check the electronic medical records.

[0134] Furthermore, data that LLM45 has summarized from the electronic medical record may be provided to the patient recorded in the electronic medical record. The patient can confirm the contents of his / her treatment by checking the summarized data. Furthermore, when the patient visits another dental clinic, the patient can continue to receive treatment from the previous dental clinic by bringing the summarized data.

[0135] The present invention is not limited to the above-described embodiments, and it goes without saying that various other applications and modifications are possible without departing from the gist of the present invention as set forth in the claims. For example, the above-mentioned embodiments have described the configuration of the device and system in detail and specifically in order to explain the present invention in an easily understandable manner, and are not necessarily limited to those having all of the configurations described. In addition, it is possible to replace a part of the configuration of the embodiment described here with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. In addition, it is also possible to add, delete, or replace a part of the configuration of each embodiment with another configuration. In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and not all control lines and information lines in the product are necessarily shown. In reality, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0136] 1, 1A...viewing support system, 2...receipt management system, 3...medical record management system, 4...RAG system, 10...information processing terminal, 11...display unit, 12...input unit, 21...receipt management unit, 31...medical record management unit, 41...knowledge upload unit, 42...knowledge update unit, 43...embedding unit, 44...knowledge search unit, 45...LLM

Claims

1. A browsing support system in which an information processing terminal that displays medical-related information, a medical-related information management system that manages the medical-related information, and an input support system are connected via a network, The information processing terminal includes: A display unit that displays the medical information; an input unit for creating a question to be registered in the medical-related information displayed on the display unit, The medical information management system includes: a creation support unit that outputs creation information for creating the medical-related information, which is input by the information processing terminal, to the input support system, receives a response from the input support system, and supports the creation of the medical-related information; The input support system includes: a vector database in which vectorized knowledge embedded in a vector space is stored; a knowledge search unit that searches the vector database for the knowledge based on the vectorized creation information, and outputs the answer formed from the searched knowledge to the creation support unit. Browsing assistance system.

2. The knowledge search unit extracts the vectorized knowledge based on a similarity between the vectorized knowledge stored in the vector database and the vectorized created information. The browsing support system according to claim 1 .

3. The input support system includes: a large-scale language model for reading reference information and summarizing the reference information based on text or image prompts; The knowledge search unit outputs a summary document summarized by the large-scale language model to the medical-related information management system. The browsing support system according to claim 2 .

4. The creation information is information included in a question input into a display area of ​​a medical-related information creation display screen used for creating the medical-related information, or information included in an item selected on the medical-related information creation display screen, and the answer includes the summary document and information on a reference source of the reference information summarized by the large-scale language model. The browsing support system according to claim 3.

5. The production information includes at least one of text, audio, and image. The browsing support system according to claim 4.

6. The input support system includes: a knowledge update unit for updating the knowledge; an embedding unit that vectorizes the knowledge to be updated and embeds it in the vector space, and stores the vectorized knowledge in the vector database. The browsing support system according to claim 5 .

7. The input support system includes: a knowledge database for storing the knowledge; a knowledge upload unit that uploads the knowledge to the knowledge database; 7. The browsing support system according to claim 5 or 6.

8. A browsing support method performed in a browsing support system in which an information processing terminal having a display unit that displays medical-related information and an input unit that edits the medical-related information displayed on the display unit, a medical-related information management system that manages the medical-related information, and an input support system are connected via a network, comprising: a creation support unit of the medical-related information management system outputting creation information for creating the medical-related information, which is input by the information processing terminal, to the input support system; A step of vectorizing the production information by the input support system; A step of searching for the knowledge based on the vectorized creation information from a vector database in which the knowledge that has been vectorized and embedded in a vector space is stored; outputting an answer formed from the searched knowledge to the creation support unit; The creation support unit receives the answer from the input support system and supports the creation of the medical-related information. How to assist with viewing.

9. A step of vectorizing creation information for creating medical-related information, the creation information being inputted by an information processing terminal; A step of searching for the knowledge based on the vectorized creation information from a vector database in which the knowledge that has been vectorized and embedded in a vector space is stored; A procedure for outputting an answer formed from the searched knowledge to the information processing terminal. A program for a computer to execute.

Images