Information provision device, information provision method, and information provision program

Abstract

To enable effective utilization of a language model specialized in a particular field.SOLUTION: An information provision device according to an embodiment is configured to collect texts entered by a user and answers output by multiple language models configured to output answers regarding patient treatment policies in response to entered prompts and set up to have different answer trends. The information provision device presents the collected answers to the user. The information provision device inputs the collected answers and the texts into the multiple language models as prompts to output further answers.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The disclosed embodiments relate to an information providing device, an information providing method, and an information providing program. [Background technology]

[0002] 2. Description of the Related Art Conventionally, there is known a system that uses a language model to generate an answer to a question input by a user (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2022-503838 Summary of the Invention [Problem to be solved by the invention]

[0004] While conventional technology generates answers based on news articles, it does not take into account the use of language models specialized for specific domains.

[0005] The present invention has been made in view of the above, and has an object to effectively utilize a language model specialized for a specific field. [Means for solving the problem]

[0006] An information providing device according to one aspect of an embodiment includes a collection unit that collects answers output by a plurality of language models that output answers regarding a patient's treatment plan based on an input prompt, the answers being set so that the tendencies of the answers differ from one another, and text input by a user, a presentation unit that presents the collected answers to the user, and an output control unit that inputs the collected answers and the text to the plurality of language models as prompts, and further causes the answers to be output. Effect of the Invention

[0007] According to one aspect of the embodiment, a language model specialized for a specific field can be effectively utilized. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an overview of an information providing device according to an embodiment. [Diagram 2] FIG. 2 is a functional block diagram illustrating an example of the configuration of an information providing device according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating the discussion. [Figure 4] FIG. 4 is a flowchart illustrating a processing procedure executed by the information providing device according to the embodiment. [Diagram 5] FIG. 5 is a flowchart illustrating a processing procedure executed by the information providing device according to the embodiment. [Figure 6] FIG. 6 is a flowchart showing the procedure for processing a discussion. [Figure 7] FIG. 7 is a diagram illustrating an example of a computer hardware configuration that functions as an information providing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The present invention will be described below through embodiments, but the following embodiments do not limit the scope of the invention according to the claims. In addition, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0010] A process flow of the information providing device according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining an overview of the information providing device according to the embodiment. Fig. 1 shows a configuration of an information providing system 1 including an information providing device 10 according to the embodiment.

[0011] 1, the information providing system 1 includes an information providing device 10 and a medical case database 20. The medical case database 20 is a database that stores various data related to medical care. For example, the medical case database 20 stores medical papers and knowledge, various medical records, various data related to medicines, various data related to insurance, various data related to medical equipment, and the like.

[0012] The information providing device 10 is a device to which various devices including a medical case database 20 are plugged in. In the information providing system 1, in which the various devices include various servers, vehicles, smartphones, and other devices, the information providing device 10 realizes the highest level of artificial intelligence by being plugged in to each device.

[0013] For example, in the information provision system 1, the information provision device 10 and each device including the medical case database 20 incorporate semiconductor chips manufactured by the same manufacturer. Each of these semiconductor chips may perform machine learning or deep learning by itself.

[0014] In addition, the semiconductor chips used in the information providing device 10 and the medical case database 20 are chips of a size suitable for each housing. For example, assuming that the chip size of the information providing device 10 is XL size, L size is used for servers and vehicles, and S or M size is used for user terminals. For terminals with housing sizes smaller than that of the user terminals, SS size is used and is put into a SoC (System on a chip) to form a single chip. Note that the number of tiles for each size is only an example and is not limited to the above. If it is desired to attach accessories such as a camera or a microphone to the user terminal, a chip dedicated to accessories other than the semiconductor chip may be set in an empty space near the semiconductor chip in the SoC.

[0015] In this way, in the information providing system 1, the use of semiconductor chips made by the same manufacturer in various devices connected to the information providing device 10 makes it possible to keep the information providing system 1 secure. In other words, in the information providing system 1, hacking, virus infection, and deep fakes can be avoided with a high degree of accuracy, and privacy can be ensured between the information providing device 10 and data source providers including the medical case database 20.

[0016] In this embodiment, the information providing device 10 learns a model based on a medical case database 20, which is a data source. The model is a language model. For example, ChatGPT by OpenAI is known as a language model (Reference: https: / / openai.com / blog / chatgpt). The language model may be a language model such as GAN (Generative Adversarial Networks) or VAE (Variational Autoencoder) that uses a neural network.

[0017] In this embodiment, the language model generates a text response to a text of a query (hereinafter, a prompt) input by a user. The language model is trained in advance using a data source. The language model may be trained by known machine learning techniques.

[0018] This enables the language model to generate answers based on the data source. In this embodiment, the information providing device 10 plugs in to the medical case database 20 (step S1), and learns the language model based on the data stored in the medical case database 20 (step S2).

[0019] In this way, the information providing device 10 trains the language model on various data stored in the medical case database 20. As a result, the language model generates a response to an input prompt based on the trained medical data. In other words, the information providing device 10 can generate a language model specialized for the medical field.

[0020] In this embodiment, a language model specialized for the medical field is used to provide advice on the patient's medical policy. Specifically, in this embodiment, accounts (roles) of "Doctor", "Patient", "Family", "Experts A to C" and "Judge System" are set in advance by system prompts of the language model.

[0021] Here, accounts in this embodiment include bot accounts and human accounts. A bot account is a language model in which a system prompt can be set. A bot account outputs a response using a language model. On the other hand, a human account is a human being. In other words, a human account outputs a response according to a human input.

[0022] In Figure 1, "Doctor," "Experts A-C," "Judge System," "Patient," and "Family" are high-level accounts. High-level accounts include at least one of bot accounts and human accounts. White circles in Figure 1 represent bot accounts. Black circles in Figure 1 represent human accounts.

[0023] Hereinafter, bot accounts or human accounts included in a higher-level account may be referred to as lower-level accounts. In addition, when it is clear from the preceding and following explanations or drawings, or when there is no need to distinguish between higher-level accounts and lower-level accounts, the words "higher" and "lower" will be omitted and the term will simply be used as "accounts."

[0024] In the following explanation, we will assume that all accounts are bot accounts. The configuration in Figure 1 can be realized by replacing bot accounts with human accounts as appropriate, or by adding human accounts as subordinate accounts to higher-level accounts.

[0025] "Doctor" is a higher-level account corresponding to, for example, the patient's doctor. In FIG. 1, a case is shown in which "Doctor" is one account, but in reality, multiple accounts are set. Note that the multiple accounts may be, for example, doctors with different specialties (internal medicine, surgery, etc.).

[0026] "Patient" is an account corresponding to a patient. "Family" is an account corresponding to a patient's family. "Experts A to C" are expert accounts involved in the treatment of a patient.

[0027] Specific examples of expert accounts include medical researchers, hospitals, nurses, pharmacists, pharmaceutical manufacturers, and medical device manufacturers. The "judge system" is an account that judges the results of discussions by each account. For example, the judge system judges the merits of each account's arguments and proposes the content to an actual doctor (e.g., the patient's primary care physician).

[0028] In this embodiment, claims made by each of a plurality of doctor accounts are input as prompts into the language model, and the input prompts are set as system prompts so that other doctor accounts can debate the input prompts.

[0029] Such a setting enables each doctor account to hold a spontaneous discussion using the language model. As shown in Fig. 1, the information providing device 10 uses the language model to hold a discussion regarding the treatment plan for the patient by each account (step S3).

[0030] For example, a discussion begins by first entering various data such as the patient's age and gender, and the patient's medical records as prompts. To explain in more detail, the doctor account is further divided into multiple accounts such as Doctor 1, Doctor 2, and Doctor 3, and Doctor 1 is distinguished by personality, such as a conservative personality, Doctor 2 is proactive, and Doctor 3 is data-oriented, and each account debates using a language model. Doctor 1, for example, discusses medical policy in further subdivided lower accounts such as Doctor 1-1, 1-2, and 1-3, and Doctor 2, for example, Doctor 2-1, Doctor 2-2, and Doctor 2-3, and draws a conclusion as Doctor 1 or Doctor 2. The virtual experts debate billions of times per second. This enables verification and problem solving from all angles, and highly accurate diagnoses and treatment proposals based on past medical data can be made instantly. In addition, Doctor 1 performs multimodal data analysis and proposes the results of integrating and analyzing various types of medical data such as genetic data, blood data, MRI and X-ray images, Doctor 2 proposes using a real-time learning model to obtain new data from medical sites around the world in real time, and always incorporates the latest medical information and research results into treatment, and Doctor 3 proposes having advanced simulation functions to virtually simulate the progression of the disease and the effects of treatment, and predict the most appropriate treatment and its results in advance. Then, using the comprehensive judgment based on the output results of Doctor 1, Doctor 2, and Doctor 3, the doctor account may decide on a treatment policy. Other ideas that the doctor account may adopt include proposing individually optimized treatment plans based on the background of each patient's genetic information and lifestyle habits, such as promoting personalized medicine, and by linking with 3D bioprinting, it may propose identifying the structure of organs and tissues that are optimal for the patient and using 3D bioprinting technology to generate individually customized artificial organs and tissues.

[0031] For example, the family account draws a conclusion on the family's medical policy using multiple accounts set up within the family. Each expert account holds discussions with multiple accounts for each field and draws a conclusion on the medical policy for each field. Then, the doctor account holds a discussion on the patient's treatment policy based on the discussions in each field. Note that the final discussion may be held by all accounts including each account.

[0032] For example, the doctor accounts discuss the treatment method, cost, risk, cure rate, and the method and timing of informing the patient and family as a treatment policy for the patient. The "judgment system" then makes a judgment based on the content of the discussion (step S5). For example, the "judgment system" is made up of multiple accounts. The multiple accounts that make up the judgment system discuss the content of the discussions of the doctor accounts, etc., and judge the final medical policy. For example, when the discussion reaches a deadlock, or other specified termination conditions are met, the judgment system compares the claims of each account with the data stored in the medical case database 20 to determine the most appropriate medical policy.

[0033] The "judgment system" then proposes the determined medical policy to, for example, the patient's doctor. In other words, the information provision system 1 uses a language model to simulate a large-scale discussion between doctors and others regarding medical policies. In addition, because the language model is trained in advance with a large amount of data related to medical cases, it is possible to propose medical policies based on various past findings.

[0034] In this manner, the information providing device 10 according to the embodiment generates a language model based on various pieces of knowledge registered in the medical case database 20, and after holding a discussion using the language model, makes a proposal regarding a medical policy.

[0035] Therefore, the information providing device 10 according to the embodiment can effectively utilize a language model specialized for a specific field.

[0036] The configuration of the information providing device 10 will be described with reference to Fig. 2. Fig. 2 is a functional block diagram showing an example of the configuration of the information providing device according to the embodiment.

[0037] As shown in FIG. 2, the information providing device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0038] The communication unit 11 transmits and receives information to and from the medical case database 20 and the like via the network.

[0039] The storage unit 12 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. The storage unit 12 stores various programs and various data. The storage unit 12 stores language model information 121.

[0040] The language model information 121 is information about a language model. For example, the language model information 121 is information about parameters for constructing a language model. Such parameters are, for example, weights and biases of a neural network.

[0041] The control unit 13 is a controller, and includes, for example, a microcomputer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM, an input / output port, and various other circuits. The control unit 13 may also be configured with hardware such as an integrated circuit, for example, an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 13 includes an acquisition unit 31, a generation unit 32, a discussion unit 33, and a proposal unit 34.

[0042] The acquiring unit 31 acquires data from a data source provider. For example, the acquiring unit 31 acquires data related to medical cases from the medical case database 20 (see FIG. 1). For example, the acquiring unit 31 acquires data every time the medical case database 20 is updated.

[0043] The generation unit 32 generates a language model. Specifically, the generation unit 32 learns the language model based on a data source related to a medical case. The generation unit 32 also updates the parameters of the model through learning. The generation unit 32 may regenerate the model at each learning timing, or may reflect a data source difference from the previous learning in the model.

[0044] The discussion unit 33 uses a language model that is generated by learning data stored in a database related to medical cases and generates answers to input prompts, and holds discussions between multiple doctor accounts, each with different claims.

[0045] First, the discussion unit 33 sets accounts for each field according to the system prompts of the language model. For example, the discussion unit 33 sets a doctor account, a patient account, a family account, expert A to C accounts, and a judge system account.

[0046] After setting these accounts, the discussion unit 33 starts a discussion using the language model. For example, the discussion unit 33 holds a discussion for each field, and then holds a discussion using the doctor account based on the discussion results for each field. Specifically, the discussion unit 33 holds a discussion using the language model by the following steps 1 to 5.

[0047] Step 1: Set up a multi-functional virtual expert There will be hundreds of sets of virtual experts in different medical fields, for example, neurology will have specific characters such as "Neuro-Expert A", "Neuro-Expert B", and "Neuro-Expert C", and cardiology will have specific characters such as "Cardiologist A", "Cardiologist B", and "Cardiologist C".

[0048] Step 2: Speed ​​up information exchange These experts debate billions of times per second, exchanging information based on patient data, enabling them to make instantaneous decisions about a patient's condition, symptoms, and treatment options.

[0049] Step 3: Data handling The virtual experts discuss and share various types of information, such as MRI data, genetic data, and blood data, allowing them to quickly arrive at optimal solutions from multiple perspectives.

[0050] Step 4: Self-study and update If new knowledge, information, or treatment methods are discovered during the discussion, they will be immediately added to the database and used in future discussions, allowing doctors to provide diagnoses and treatments based on the latest medical information.

[0051] Step 5: Building consensus Discussion involves the formation of a final "consensus" through the clash of different opinions and perspectives. This allows information and knowledge from multiple sources to be comprehensively incorporated when making a diagnosis or treatment proposal to a patient. There may be multiple treatment proposals.

[0052] The above has been explained about the doctor account, but the patient account, family account, and Experts A to C accounts also have their own characters set, and each account is further divided into various characters. Through discussions between the two accounts, a consensus is formed as a patient, as a family, and as Experts A to C.

[0053] The suggestion unit 34 judges the discussion results by the discussion unit 33 using a judge account set in the language model, and proposes a treatment plan. For example, the suggestion unit 34 makes a judgment when a predetermined end condition is met, such as when the discussion by the discussion unit 33 reaches a deadlock.

[0054] For example, the suggestion unit 34 refers to various data registered in the medical case database 20, judges the medical policy that is estimated to be the most appropriate among the medical policies discussed by each doctor account, and proposes that medical policy. Alternatively, a medical policy may be proposed by adding various consensuses such as a patient's consensus (do not want to be hospitalized as much as possible), a family's consensus (do not want to be left with scars as much as possible), and an expert A's consensus (up to what amount insurance will pay).

[0055] [Discussion on the inclusion of human accounts] Up to this point, we have explained the discussion assuming that the lower-level accounts are bot accounts. Here, we will explain the discussion when the lower-level accounts include human accounts. In this case, the processing contents of steps 1 and 2 above by the discussion unit 33 will change.

[0056] First, in step 1, the discussion unit 33 changes the configuration of at least some of the higher-level accounts so that they include human accounts as lower-level accounts. For example, the discussion unit 33 replaces bot accounts with human accounts or adds new human accounts. A user, i.e., a real person, is associated with a human account.

[0057] Next, in step 2, the discussion unit 33 presents the text output by each account as an answer to the user associated with the human account. Then, the discussion unit 33 accepts text input from the user. The answer text output by each account and the action of outputting text as an answer are called "statements." "Statements" include text input by users.

[0058] A bot account treats utterances from human accounts in the same way as utterances from bot accounts. For example, a bot account inputs utterances from other bot accounts and human accounts as prompts into its language model and then outputs answers.

[0059] The processing of the discussion unit 33 will be described with reference to Fig. 3. Fig. 3 is a diagram for explaining the discussion. As shown in Fig. 3, the discussion unit 33 conducts the discussion according to the progress of the phase. Here, it is assumed that Doctor 1, which is a higher-level account, is composed of three lower-level accounts, Doctor 1-1, Doctor 1-2, and Doctor 1-3.

[0060] Doctor 1-1 is a bot account of a surgeon. For example, the language model of Doctor 1-1 outputs text that prioritizes surgical treatment methods.

[0061] Doctor 1-2 is a bot account of a physician. For example, the language model of Doctor 1-2 outputs text that prioritizes medical treatment methods.

[0062] The substance of the bot account is a language model, and the discussion is realized by the discussion unit 33 repeatedly inputting a prompt to the language model. The prompt is, for example, a statement from the language model in the previous phase. The data to be emphasized in the statement may be set by a system prompt. As a result, each bot account has a different tendency in answering.

[0063] Doctor 1-3 is a human account. A user is associated with Doctor 1-3. Furthermore, Doctor 1-3 may have any personality (what he or she values).

[0064] 3, in phase 1, doctor 1-1 says, "I think it would be better to perform the abdominal surgery early." At this point, the discussion unit 33 advances the phase.

[0065] In Phase 2, Doctor 1-2 inputs the statement made by Doctor 1-1 in Phase 1 into the language model as a prompt and says, "Considering the patient's physical condition, it may be best to first try medication and see how it goes."

[0066] Next, in phase 3, a human account makes a statement such as, "The results of my blood test haven't come out yet." The statement of the human account is the content entered by the user. For example, the discussion unit 33 may display the statements of each account on the user's terminal by a chat UI and accept user input from an input field of the chat UI.

[0067] It is not necessary for each account, including bot accounts and human accounts, to make a statement in every phase. The discussion unit 33 only needs to allow at least one account to make a statement in each phase.

[0068] In addition, if the accounts participating in the discussion include human accounts, it is difficult to have users make comments every time in each of the phases, which may number in the billions. For this reason, for example, the discussion unit 33 may accept user comments only in a specific phase, such as once in 10,000 phases.

[0069] The discussion unit 33 may also accept a user's comment when a certain condition is met. The condition may be when a bot account repeats the same comment a certain number of times. It is expected that a stagnant discussion will start to move toward a conclusion by the bot account using the user's comment as a prompt.

[0070] In this way, the discussion unit 33 presents the answer to the user when the answer satisfies the condition. Then, the discussion unit 33 collects the text entered according to the presented answer.

[0071] In addition, users may have knowledge that was not used to train the language model of the bot accounts. In such cases, the inclusion of human accounts in a discussion may lead to more useful conclusions than the inclusion of only bot accounts.

[0072] Next, a process procedure executed by the information providing device 10 according to the embodiment will be described with reference to Fig. 4 and Fig. 5. Fig. 4 and Fig. 5 are flowcharts showing a process procedure executed by the information providing device 10 according to the embodiment.

[0073] First, the procedure for generating a language model will be described with reference to Fig. 4. As shown in Fig. 4, the information providing device 10 first acquires data related to a legal case from the medical case database 20 (step S101). Next, the information providing device 10 generates a language model based on the data acquired from the medical case database 20 (step S102), and ends the process.

[0074] Next, the discussion process using the language model will be described with reference to Fig. 5. As shown in Fig. 5, the information providing device 10 first holds a discussion on a medical policy in each field (step S111). Next, the information providing device 10 holds a discussion on a medical policy between fields (step S112).

[0075] Next, the information providing device 10 judges the results of the discussion (step S113), and then the information providing device 10 proposes a medical policy (step S114), and ends the process.

[0076] The procedure of the discussion process will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the procedure of the discussion process. The process shown in Fig. 6 corresponds to, for example, the process of S111 in Fig. 5.

[0077] 6, when a phase starts, the information providing device 10 determines whether to allow a human account to make a statement (step S201). The conditions for allowing a human account to make a statement include that a prescribed number of phases have passed, that a bot account has repeated the same statement a certain number of times, etc.

[0078] If the information providing device 10 does not allow a human account to make a statement (step S202, No), the information providing device 10 proceeds to step S204. On the other hand, if the information providing device 10 allows a human account to make a statement (step S202, Yes), the information providing device 10 collects the statements of the human account (step S203). For example, the information providing device 10 collects text entered by the user in an input field of the chat UI as the statements of the human account. Also, the information providing device 10 may present the statements of each account to the user immediately before step S203.

[0079] Next, the information providing device 10 collects comments from the bot account (step S204). Here, when the discussion ends (step S205, Yes), the information providing device 10 performs discussion end processing (step S208). For example, the information providing device 10 may determine that the discussion has ended when a prescribed number of phases have passed or when judging is performed by a judge account. The discussion end processing is to transition to a discussion between higher-level accounts (for example, step S3 in FIG. 1).

[0080] If the discussion has not ended (step S205, No), the information providing device 10 advances the phase (step S206). Then, based on the collected comments, the information providing device 10 inputs a prompt into the language model of each bot account (step S207), returns to step S201, and performs processing in the phase after the advance.

[0081] The information providing device 10 functions as a collection unit, a presentation unit, and an output control unit. The collection unit collects answers output by a plurality of language models (corresponding to bot accounts) that output answers regarding a patient's treatment plan based on an input prompt and are set so that the answer tendencies are different from each other, and text input by a user (corresponding to a human account) (steps S203, S204). The presentation unit presents the collected answers to the user. The output control unit inputs the collected answers and text to the plurality of language models as prompts, and further causes them to output answers (step S207).

[0082] According to this embodiment, a medical policy can be proposed after discussing the medical policy using a language model trained based on data stored in the medical case database 20, so that a language model specialized for a specific field can be effectively utilized.

[0083] 7 is a diagram showing an example of a computer hardware configuration functioning as an information providing device. A program installed in the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to the present embodiment, or cause the computer 1200 to execute operations or one or more "parts" associated with the device according to the present embodiment, and / or cause the computer 1200 to execute a process or steps of the process according to the present embodiment. Such a program can be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0084] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphic controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive, a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive, a solid state drive, etc. The computer 1200 also includes input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0085] The CPU 1212 operates according to a program stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphic controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.

[0086] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0087] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or a program that depends on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, and the like.

[0088] The programs are provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, the RAM 1214, or the ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by implementing operations or processing of information according to the use of the computer 1200.

[0089] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded in the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in the RAM 1214, the storage device 1224, a DVD-ROM, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer area or the like provided on the recording medium.

[0090] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), an IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0091] Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the plurality of entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0092] The above-mentioned programs or software modules may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0093] The blocks in the flowcharts and block diagrams in the present embodiment may represent stages of a process in which an operation is performed or "parts" of an apparatus responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer readable instructions stored on a computer readable storage medium, and / or a processor provided with computer readable instructions stored on a computer readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as, for example, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like, including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0094] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.

[0095] The computer readable instructions may include either assembler instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0096] Computer readable instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, either locally or over a local area network (LAN), a wide area network (WAN), such as the Internet, etc., to cause the processor of the general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, to execute the computer readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0097] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is clear to those skilled in the art that various modifications or improvements can be made to the above embodiments. It is clear from the claims that such modifications or improvements can also be included in the technical scope of the present invention.

[0098] It should be noted that the order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and may be realized in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is explained using "first," "next," etc. for convenience, it does not mean that it is essential to perform the process in this order. [Explanation of symbols]

[0099] 1 Information provision system 10 Information provision device 11 Communications Department 12 Storage section 13 Control section 20 Medical Case Database 31 Acquisition Department 32 Generation part 33 Discussion Department 34 Proposal Department 121 Language Model Information

Claims

1. a collection unit that collects answers output by a plurality of language models that output answers regarding a treatment plan for a patient based on an input prompt, the plurality of language models being set so that the answer tendencies are different from each other, and text input by a user; a presentation unit that presents the collected answers to the user; an output control unit that inputs the collected answers and the text as prompts to the plurality of language models and outputs the answers; An information providing device comprising:

2. The presentation unit presents the answer to the user when the answer satisfies a condition; The collection unit collects the text input in response to the answer presented by the presentation unit.

2. The information providing device according to claim 1.

3. An information providing method executed by an information providing device, comprising: a collection step of collecting answers output by a plurality of language models that output answers regarding a treatment plan for a patient based on an input prompt, the plurality of language models being set so that the answer tendencies are different from each other, and a text input by a user; a presentation step of presenting the collected answers to the user; an output control step of inputting the collected answers and the text as prompts to the plurality of language models and outputting the answers; 13. An information providing method comprising:

4. a collection step of collecting answers output by a plurality of language models that output answers regarding a treatment plan for a patient based on an input prompt, the plurality of language models being set so that the answer tendencies are different from each other, and a text input by a user; a presentation step of presenting the collected answers to the user; an output control step of inputting the collected answers and the text as prompts to the plurality of language models and outputting the answers; An information providing program that causes a computer to execute the above steps.

Images