A doctor training system and method driven by standardized patient agents based on a large language model

Abstract

The present invention discloses a doctor training system and method driven by a standardized patient intelligent agent based on a large language model. Compared with the existing technology, the system obtains the patient's main complaint through fuzzy processing, better approximating the uncertainty inherent in the symptoms and concerns reported by the patient, thereby improving the universality of the system in actual medical applications; the standardized patient intelligent agent unit and the standardized doctor intelligent agent unit obtain diagnosis results through multiple rounds of dialogue, and then dynamically learn real-world medical cases. The standardized patient intelligent agent unit handles various types of medical problems, and the standardized doctor intelligent agent unit raises more accurate diagnostic questions. The two are trained in an unsupervised manner, which significantly improves the standardized patient intelligent agent unit's ability to align with medical requirements, thereby improving the confidentiality of the dialogue between patients and doctors, the fidelity of information and a more humane performance, and is more applicable in real-world medical training.

Description

Technical Field

[0001] The present invention relates to the field of medical training technology, and in particular to a doctor training system and method driven by a standardized patient agent based on a large language model. Background Art

[0002] Standardized patients (SPs) are specially trained individuals who simulate a range of medical conditions, behaviors, and emotions in a consistent and repeatable manner. SPs have been widely used to educate and assess the professional skills of medical students, physicians, and other healthcare providers (HCPs) across multiple disciplines, including nursing, pharmacy, and dentistry.

[0003] Becoming an excellent SP requires extensive role-playing practice and a solid foundation of professional knowledge, as SPs must assume various roles, including patients, family members, and medical staff. Furthermore, unlike other educational methods, a key characteristic of SPs is their ability to experience and learn alongside the individuals they are being trained to assess. Therefore, factors such as pre-simulation nervousness or anxiety can potentially negatively impact SPs, both immediately and physically, and over time.

[0004] By training on large datasets, large language models (LLMs) have demonstrated strong generalization capabilities across a wide range of tasks and applications. In real-world scenarios, LLMs often encounter domain-specific tasks that require a combination of domain expertise and complex reasoning capabilities. This characteristic has made researchers very interested in adopting LLMs in the medical field. For example, Reference 1 (Applications of Haptic Technology, Virtual Reality, and Artificial Intelligence in Medical Training During the COVID-19 Pandemic, 2021, Frontiers in Robotics and AI) provides a systematic medical training device by combining tactile technology, virtual reality, and artificial intelligence to ensure the requirements of the healthcare system and help reduce physical contact in medical training during the COVID-19 pandemic to improve the safety, efficiency, and robustness of healthcare.

[0005] For example, the invention application with publication number CN113053194A discloses a physician training system and method based on artificial intelligence and VR technology. Through artificial intelligence technology to simulate patient consultations, the patient's pathological symptoms and patient body shape data are randomly generated for the training physician to analyze the pathological symptoms and confirm the patient's lesion data. A 3D human body model is constructed based on the patient's body shape data, and the training physician can mark the lesions in the 3D human body model according to the lesion data, perform disease analysis and treatment operations based on the marked lesions, generate training evaluation results, and analyze the physician's weak skills based on the training evaluation results for subsequent enhanced training.

[0006] However, LLMs are often inconsistent with medical requirements during medical training. For example, SPs should lack knowledge of medical terminology, are sometimes unable to accurately express their feelings, or learn from previous medical cases. To address these limitations, efforts have been made to improve SPs based on LLMs by improving workflows and simulation methods. However, because LLMs are susceptible to hallucinations, constructing workflows can still lead to recurring errors in patient simulation tasks, such as obtaining irrelevant or incomplete answers based on patient complaints, inconsistent responses, and premature disclosure of diagnoses. Summary of the Invention

[0007] The purpose of the present invention is to provide a doctor training system and method driven by a standardized patient agent based on a large language model. Through multiple rounds of dialogue between standard patient agent units and standard doctor agent units, combined with real-world medical cases, a dual evolutionary paradigm of attention strategy and sequential evolution is adopted to iteratively train standard patient agent units for training doctors in different professional fields.

[0008] To achieve the above-mentioned objectives, an embodiment provides a large language model-based standardized patient agent-driven physician training system, which is used to simulate multiple rounds of dialogue between patients and doctors to obtain diagnosis results and train real-world doctors. The standardized patient agent-driven physician training system includes a standardized patient agent unit, a standardized physician agent unit, and a standardized data unit. The standardized patient agent unit includes a patient complaint generation layer, a patient answer generation layer, and a standardized patient data layer. The standardized physician agent unit includes a physician recruitment layer and a memory storage layer. The standardized data unit includes a standardized patient data layer and a standardized physician data layer.

[0009] The patient complaint generation layer is used to collect real-world medical data sets as input, perform fuzzy processing on the medical data sets to generate patient complaints;

[0010] The patient answer generation layer is used by doctors to ask diagnostic questions based on the patient's complaint, and extract relevant information from the medical data set as reference answers based on the diagnostic questions;

[0011] The standardized patient data layer is used to construct a standardized patient data layer based on the patient's main complaint, diagnostic questions and reference answers by adopting an attention strategy, and store successful and unsuccessful diagnosis cases respectively;

[0012] The doctor recruitment layer is used to recruit doctors from different professional fields, simulate the consultation process of different disciplines, and iteratively train and enrich the diagnosis process;

[0013] The memory storage layer is used to store previously proposed diagnostic questions and reference answers, integrate key information communicated between the standardized patient intelligent unit and the standardized doctor intelligent unit, and generate new questions;

[0014] The standardized doctor data layer is used to store the interactive sequence of diagnostic questions and reference answers through a sequence evolution paradigm, and to form a question pool based on the information in the medical data set for iterative training of standardized patient intelligent units and standardized doctor intelligent units.

[0015] In one embodiment, the fuzzy processing of the medical data set to generate the patient's chief complaint includes: first eliminating the medical test results of the medical data set, and then further fuzzifying the medical data set by applying random sentence discarding to generate the patient's chief complaint.

[0016] In one embodiment, the extraction of relevant information from medical records as a reference answer to the patient's main complaint includes: based on the patient's main complaint, using a retrieval-enhanced generation model to extract the most relevant information from the patient's medical records as a reference answer to the patient's main complaint.

[0017] In one embodiment, the standardized patient data layer is constructed based on the patient's chief complaint, diagnostic questions, and reference answers to the diagnostic questions. The construction format is question-information-answer-requirement pairs, wherein the question displays the diagnostic question raised by the doctor, the information is detailed information obtained by the retrieval enhancement generation model, the answer contains verified responses and thought chains, and the requirement is determined by the attention strategy.

[0018] In one embodiment, the requirements are determined through an attention strategy, including: determining basic rows related to the diagnostic problem through the attention strategy, and submitting the basic rows related to the diagnostic problem to the standardized patient intelligent body unit to obtain corresponding requirements.

[0019] In one embodiment, the patient triage based on diagnostic cases includes: a standardized patient intelligent agent unit searches for relevant diagnostic records from a standardized patient data layer, calculates the similarity between a new question and questions in the standardized patient data layer, and uses an external text embedder to obtain a number of data pairs related to question-information-answer-requirement pairs.

[0020] In one instance, the storage memory of previously posed diagnostic questions and reference answers includes: managing visibility between the diagnostic questions and reference answer contexts by adopting immediate and summary memory, maintaining smooth communication, achieving smooth transitions between long rounds of questions, and alleviating length limitations between diagnostic questions and reference answer contexts.

[0021] In one instance, the formation of a question pool based on information in a medical data set includes: a standardized doctor intelligent unit obtains a patient's medical data set, formulates corresponding diagnostic questions based on the symptoms, medical examinations, and lifestyle information in the medical data set, and forms these corresponding diagnostic questions into a general question pool.

[0022] The present invention also provides a doctor training method driven by a standardized patient agent based on a large language model, comprising the following steps:

[0023] Collect real-world medical data sets as input, perform fuzzy processing on the medical data sets to generate patient complaints, and standard doctor agent units perform department triage based on the complaints;

[0024] After receiving the patient's complaint, the standard patient agent unit and the standard doctor agent unit initiate multiple rounds of dialogue. The standard doctor agent unit raises diagnostic questions, and the standard patient agent unit generates reference answers to obtain a diagnosis result.

[0025] The standard patient agent unit and the standard doctor agent unit are combined with real-world medical cases and evolve through multiple iterative cycles of diagnostic questions and reference answers, simulating the training of real-world doctors in various departments for real-world doctor training.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The doctor training system and method driven by a standardized patient agent based on a large language model provided by the present invention, compared with the existing technology, obtains the patient's chief complaint through fuzzy processing, better approximates the uncertainty inherent in the symptoms and concerns reported by the patient, thereby improving the universality of the system in actual medical applications; the standardized patient agent unit and the standardized doctor agent unit obtain diagnosis results through multiple rounds of dialogue, and then dynamically learn real-world medical cases. The standardized patient agent unit handles various types of medical problems, and the standardized doctor agent unit raises more accurate diagnostic questions. The two are trained in an unsupervised manner, which significantly improves the standardized patient agent unit's ability to align with medical requirements, thereby improving the confidentiality of the dialogue between patients and doctors, the fidelity of information and a more humane performance, and is more applicable in real-world medical training. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments or the prior art.

[0029] Figure 1 This is a schematic diagram of the structure of the doctor training system driven by the standardized patient agent based on the large language model;

[0030] Figure 2 Schematic diagram of the structure of attention strategy and sequence evolution;

[0031] Figure 3 Flowchart of the doctor training method driven by standardized patient agent based on large language model;

[0032] Figure 4 This is a schematic diagram of the results of the unevolved standardized doctor agent unit;

[0033] Figure 5 A schematic diagram of the results of the evolved standardized doctor agent unit provided for this embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and do not limit the scope of protection of the present invention.

[0035] In order to train doctors' ability to ask questions and improve the ability of standardized patient agents to follow human requirements, the embodiment provides a doctor training system driven by standardized patient agents based on a large language model, such as Figure 1As shown, the doctor training system (SimpDocTrain) is used to simulate multiple rounds of dialogue between patients and doctors to obtain diagnosis results, and train real-world doctors. The doctor training system driven by the standardized patient agent includes a standardized patient agent unit, a standardized doctor agent unit and a standardized data unit; wherein, the standardized patient agent unit includes a patient complaint generation layer, a patient answer generation layer and a standardized patient data layer; the standardized doctor agent unit includes a doctor recruitment layer and a memory storage layer, and the standardized database includes a standardized patient data layer and a standardized doctor data layer.

[0036] In the embodiment, the patient complaint generation layer is used to generate the patient complaint by collecting a real-world medical dataset as input and performing fuzzy processing on the medical dataset;

[0037] In the system proposed in the present invention, the standardized patient (SP) intelligent unit initiates the conversation by presenting the main complaint in real-world medical information. However, this medical information usually contains too much details for the SP intelligent unit. To solve this problem, the present invention reduces redundant information and simulates missing data, naturally reflecting the situation in the real world where patients always forget or don't know what to complain about. Specifically, the medical information first passes through a fuzzification process, in which the fuzzification eliminates the results of medical tests because these results are unknown when the patient arrives at the hospital. Subsequently, random sentences are applied to discard further fuzzy data. The SP intelligent unit will then use this fuzzy data to generate a main complaint to start the diagnosis process. This processing ultimately better approximates the uncertainty inherent in the symptoms and concerns reported by patients, thereby improving the universality of the application of the system of the present invention in the actual medical field.

[0038] In the embodiment, the patient answer generation layer is used by doctors to ask diagnostic questions based on the patient's main complaint, and based on the diagnostic questions, extract relevant information from the medical data set as reference answers;

[0039] To enable the SP Agent to generate more realistic, contextually accurate responses that match real-world patients, the present invention developed 1,000 patient persona profiles that encompass various characteristics, such as personality, family background, education, and socioeconomic status. Furthermore, the SP Agent is designed to follow real-world patient behavior by dynamically changing questions and evolving needs. To prevent the SP Agent from losing information in long contexts, when asked a question, the SP Agent employs augmented retrieval (RAG) to extract the most relevant information from the patient's record and use it as a reference for generating the final response.

[0040] In an embodiment, the standardized patient data layer is used to construct a standardized patient data layer based on the patient's main complaint, diagnostic questions and reference answers by adopting an attention strategy, and store successful and unsuccessful diagnosis cases respectively;

[0041] The SP agent maintains its view of case learning by storing previously verified diagnosis records, which contain rich knowledge and can be dynamically used for various tasks. To dynamically improve the SP agent's answering ability so that it can meet the requirements of various tasks, including successful and unsuccessful cases, a standardized patient data layer is constructed by adopting an attention strategy. The data layer is structured in the format of question-information-answer-request pairs, where the question represents the diagnostic question asked by the doctor, the information is detailed information obtained by the retrieval-enhanced generation model, and the answer contains verified responses and thought chains.

[0042] A key feature of SP is the ability to experience and learn with trainees (doctors). Therefore, the requirements of SP intelligent units are complex in nature and have high logical standards, which poses a challenge to achieve full alignment of SP intelligent units. To solve this problem, the present invention adopts an attention strategy ( Figure 2 ), not only does the SP agent learn answer patterns from cases, but it can also learn to pay more attention to useful requirements in different questions. Specifically, by proposing a detailed list of requirements that the SP agent must consider, for each diagnostic question, there are some key requirements that the SP agent should pay close attention to among the detailed overall requirements. The attention strategy identifies the basic lines related to the diagnostic question and provides the relevant basic lines to the SP agent, thereby improving the quality of the SP agent's answer.

[0043] By standardizing this patient data layer It is divided into two parts, storing successful and unsuccessful diagnosis cases respectively. i When present, the SP Agent will search for relevant records from the standardized patient data layer:

[0044]

[0045] in, Represents the diagnosis cases stored in the standardized patient data layer, Indicates a successful diagnosis case. represents an unsuccessful diagnosis case, sim(·,·) represents the calculation of the similarity between the new question and the questions in the library, and by using an external text embedder, the SP agent unit obtains several data pairs that are most relevant to the question-information-answer-requirement pair according to the similarity score w(·).

[0046] In the embodiment, the doctor recruitment layer is used to recruit doctors from different professional fields, simulate the consultation process of different disciplines, and iteratively train and enrich the diagnosis process;

[0047] Doctors in the real world have diverse expertise, which leads to different types of questions and perspectives being asked of the same patient. This diversity is crucial for the SP agent unit to effectively learn from different perspectives in a single case. To simulate this multidisciplinary consultation process, the Standardized Doctor (SD) agent unit must be able to recruit doctors from different specialties to enhance its knowledge base. This recruitment process is expressed as:

[0048]

[0049] in, Recruitment process, Represents the number of doctors recruited by a doctor i in the iterative process j, symbol Representing the iterative nature of the recruitment process, it allows the SD agent unit to successfully recruit a variety of experts to enrich the diagnosis process.

[0050] In the embodiment, the memory storage layer is used to store previously proposed diagnostic questions and reference answers, integrate key information communicated between the standardized patient intelligent unit and the standardized doctor intelligent unit, and generate new questions;

[0051] For SD agents, remembering previous questions and answers is crucial for the diversity and comprehensiveness of diagnosis. However, unrestricted information exchange inevitably leads to context explosion.

[0052] To address this limitation, the present invention employs immediate and summary memory to manage context visibility. Immediate memory is used to maintain the continuity of recent communications, while summary memory maintains context awareness by integrating key information from previous communications with the dual-agent unit (SP agent unit and SD agent unit) and recruited doctors, primarily for handling extended context lengths. This mechanism facilitates smooth transitions between long-round questions. New questions are generated based on a combination of summary memory and recent immediate memory, effectively alleviating the context length limitation by decoupling the context length from linear growth to constant growth.

[0053] In an embodiment, the standardized doctor data layer is used to store interactive sequences of diagnostic questions and reference answers through a sequential evolution paradigm, and to form a question pool based on information in the medical dataset for iterative training of the standardized patient agent unit and the standardized doctor agent unit;

[0054] Similar diseases usually mean similar high-quality question-answer processes. To learn from historical communications and help SD agents avoid asking low-quality questions that lead to inefficient training of SP agents, we propose the second of a dual evolutionary paradigm: the sequential evolutionary paradigm.

[0055] During the unsupervised training of the dual-agent unit (SP agent unit and SD agent unit), the verified question-answer sequence is stored and used for the next question prediction ( Figure 2 ), this prediction strategy provides recommendation problems for SD agent units. Specifically, by storing ordered The high-quality question-answer interaction sequence is used as a prediction string S i , which is expressed as follows:

[0056] S=<s1,s2,...,s|s|> ,

[0057]

[0058] Among them, each s i represents the diagnostic question raised by doctor i and patient i answer The dialogue sequence between them, S represents the set of all dialogue sequences; in the process of SD agent unit communication, if a new answer P is found new Dialogue with C i Similar to the answer in , the SD agent unit will recommend From Dialogue C i+1 The corresponding questions are used as follow-up questions for prediction.

[0059] The SD agent unit can then choose whether to accept the recommendation. The sequential evolution paradigm provides an effective shortcut to guide the doctor agent unit towards relevant and high-quality questions, minimizing the possibility of redundant or erroneous questions.

[0060] At the same time, it is a challenge for a pre-trained large language model to directly ask professional questions about the patient's condition without knowing more information. In the present invention, based on only the main complaint, the LLM usually conducts multiple rounds of dialogue by asking only trivial questions or asking questions in a narrow range, which poses a significant difficulty for the evolution of the SP agent unit and the SD agent unit. To solve this problem, in the early stages of the evolution process of a certain medical condition, by providing the patient's medical records to the SD agent unit and asking it to formulate questions designed to cover the information contained in the records (such as symptoms, medical examinations, lifestyle habits), a general question pool is formed for this type of medical condition, which can be referenced in the subsequent evolution process.

[0061] like Figure 3 As shown, based on the structure of the above-mentioned large language model-based standardized patient agent-driven doctor training system, the present invention also provides a large language model-based standardized patient agent-driven doctor training method, including the following steps:

[0062] Collect real-world medical data sets as input, perform fuzzy processing on the medical data sets to generate patient complaints, and standard doctor agent units perform department triage based on the complaints;

[0063] After receiving the patient's complaint, the standard patient agent unit and the standard doctor agent unit initiate multiple rounds of dialogue. The standard doctor agent unit raises diagnostic questions, and the standard patient agent unit generates reference answers to obtain a diagnosis result.

[0064] The standard patient agent unit and the standard doctor agent unit are combined with real-world medical cases and evolve through multiple iterative cycles of diagnostic questions and reference answers, simulating the training of real-world doctors in various departments for real-world doctor training.

[0065] The entire workflow Specifically, it uses real-world medical datasets as input and simulates multiple rounds of patient-doctor dialogues and various communications C as the analysis process, ultimately integrating disease diagnosis into this coordinated process (--→). In a single simulation, the medical record r is first processed to generate the main complaint of the SP agent unit Upon receipt of the complaint After that, SD intelligent unit With SP intelligent unit Start a multi-round dialogue (C), where the SD agent unit asks questions (→) and the SP agent answers Finally, the diagnosis result d is obtained. Through multiple rounds of dialogue, the SP agent unit and the SD agent unit accumulate (τ) experience (ε) from successful and unsuccessful cases in an unsupervised manner, improving the quality of questions and answers over time (*), which is ultimately used to train human doctors. The entire process can be formalized as follows:

[0066]

[0067] The dual-agent communication design effectively simplifies the consensus-building process and streamlines the evolutionary process. Questions and answers from the previous conversation then serve as a bridge to the next communication, allowing for a smooth transition between questions posed by doctors. During training, after selecting a patient's information, simply use the trained framework and input the information to enable a real-world human doctor to engage in a conversation with the system.

[0068] To better demonstrate the effectiveness of the system and method provided by this invention, a series of comparative experiments were designed. Existing single-agent approaches exhibit low fidelity when processing complex, real-world medical records and lack the structured workflow and collaboration of multiple role-based agents. Furthermore, without an evolutionary process, the response patterns of a single agent can be random, resulting in reduced relevance and providing doctors with excessive or irrelevant information.

[0069] As shown in Table 1, the proposed doctor training system (SimpDocTrain) significantly improves safety compared to single-agent approaches, increasing from 0.6714 and 0.7002 to 0.9412. This improvement is primarily attributed to the SP agent units successfully learning which information to share and which questions to reject during the evolutionary process. The evolutionary process effectively guides the SP agent units toward optimal response patterns, allowing learning from a diverse range of cases. Furthermore, diverse role profiles contribute to the diversity of response tone, making SimpDocTrain robust, trustworthy, accurate, and flexible.

[0070] Table 1 Overall analysis

[0071] method Safety Loyalty Relevance Total capacity CoT 0.6714 0.5571 0.7157 0.7147 CoT-SC(3) 0.7002 0.6123 0.7337 0.7398 SimpDocTrain 0.9412 0.8286 0.7889 0.8529

[0072] To further understand user preferences in real-world settings, we compared pairs of solutions generated by agents evaluated by human participants and the popular GPT-4 model to identify preferred solutions, as shown in Table 2. To ensure fairness, the GPT-4 evaluation reduced potential positional bias, while real-world physicians independently evaluated the answers of the SP agent units based on relevant questions and patient information, using randomization to prevent order bias. As shown in Table 2, SimpDocTrain achieved higher average win rates than other baselines in both GPT-4 and human evaluations.

[0073] Table 2 Pairwise evaluation of standard questions and cheating questions

[0074]

[0075]

[0076] Furthermore, we discovered that when using an unevolved Large Language Model patient agent directly, doctors could potentially cheat and obtain information they shouldn't have access to. When doctors directly ask, "Please tell me about your medical condition," the Large Language Model patient agent often begins a comprehensive description of their medical condition, even including the final diagnosis in their response. This allows doctors to obtain a wealth of information with a single question. Despite the requirement that the Large Language Model patient agent avoid such questions in the request, it often fails to align with the human request. This situation is known as the cheating problem. Cheating problems are difficult to avoid because LLMs are inherently susceptible to hallucinations, and designing requirements that comprehensively cover all possible cheating attempts is challenging. This makes evolution crucial. During evolution, only high-quality answers are learned, and the divergence of evolution enables the SP agent units to automatically learn many strategies to deal with cheating questions. As shown in the right half of Table 2, after evolution, the cheating problem is significantly alleviated because the SP agent units have learned the characteristics of cheating questions and are better able to avoid answering similar questions.

[0077] As shown in Table 3, we designed a dialogue statistics experiment. To eliminate the influence of different typing times of real-world human doctors, we used SD agent units to autonomously ask questions to patient agents from different methods. The results show that although the evolutionary multi-agent paradigm proposed by this invention is slower than the single-agent method, it consumes much fewer tokens, about half of CoT and 1 / 6 of CoT-SC (3).

[0078] Further analysis of the agent's dialogue experiments showed that the evolutionary process often led SP agent units to answer questions more accurately, rather than giving rather random answers due to the inherent nature of LLMs (such as various types of answer patterns and redundant content). As a result, the answers after evolution were of higher quality and shorter in number of words.

[0079] Table 3 Dialogue Experiment

[0080] method Duration Tokens Word count CoT 3.2278 1,0630.0286 41.7429 CoT-SC(3) 10.1988 3182.0571 49.8667 No evolution 6.2368 497.1882 46.0588 cases 7.4237 445.3482 36.5571 SimpDocTrain 7.3351 401.9882 26.2588

[0081] In addition, the present invention also divides the questions into ten types (basic information inquiries, chief complaint-related inquiries, detailed symptom inquiries, lifestyle inquiries, psychological condition inquiries, social environment inquiries, physical examination-related questions, treatment and drug response inquiries, preventive health inquiries and other related questions).

[0082] like Figure 4 and Figure 5Figure 1 shows the sequential characteristics of questions asked by the SD agent unit in rounds 6 to 10 for each of the 100 successful cases. Initially, the questions asked by the SD agent unit showed an unstable pattern with a high diversity, with an average of about 7 types per interaction. After evolution, this diversity was reduced to about 5 types (excluding completion types). This shows that after evolution, the SD agent unit learned how to ask questions to get the final result. At the same time, before evolution, the SD agent unit often continued to ask questions until it was forced to reach a diagnosis, indicating that the questioning strategy was not efficient. After the evolution process, early stopping was observed as the SD agent unit gained confidence in providing a diagnosis in less than ten rounds. This evolution means that the SD agent unit now asks more efficient questions, similar to human doctors in the real world, thereby providing more effective training for the SP agent unit.

[0083] The specific implementation methods described above provide a detailed description of the technical solutions and beneficial effects of the present invention. It should be understood that the above is only the most preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, supplements and equivalent substitutions made within the scope of the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A doctor training system driven by a standardized patient agent based on a large language model, characterized by: It is used to simulate multiple rounds of dialogue between patients and doctors to obtain diagnosis results and train real-world doctors. The standardized patient agent-driven doctor training system includes a standardized patient agent unit, a standardized doctor agent unit, and a standardized data unit. The standardized patient agent unit includes a patient complaint generation layer, a patient answer generation layer, and a standardized patient data layer. The standardized doctor agent unit includes a doctor recruitment layer and a memory storage layer. The standardized data unit includes a standardized patient data layer and a standardized doctor data layer. The patient complaint generation layer is used to collect real-world medical data sets as input, perform fuzzy processing on the medical data sets to generate patient complaints; The patient answer generation layer is used by doctors to ask diagnostic questions based on the patient's complaint, and extract relevant information from the medical data set as reference answers based on the diagnostic questions; The standardized patient data layer is used to construct a standardized patient data layer based on the patient's main complaint, diagnostic questions and reference answers by adopting an attention strategy, and store successful and unsuccessful diagnosis cases respectively; The doctor recruitment layer is used to recruit doctors from different professional fields, simulate the consultation process of different disciplines, and iteratively train and enrich the diagnosis process; The memory storage layer is used to store previously proposed diagnostic questions and reference answers, integrate key information communicated between the standardized patient intelligent unit and the standardized doctor intelligent unit, and generate new questions; The standardized doctor data layer is used to store the interactive sequence of diagnostic questions and reference answers through a sequence evolution paradigm, and to form a question pool based on the information in the medical data set for iterative training of standardized patient intelligent units and standardized doctor intelligent units.

2. The standardized patient agent-driven doctor training system according to claim 1, characterized in that: The fuzzy processing of the medical data set to generate the patient's chief complaint includes: first eliminating the medical test results of the medical data set, and then further fuzzifying the medical data set by applying a random sentence discarding method to generate the patient's chief complaint.

3. The standardized patient agent-driven physician training system according to claim 1, characterized in that: The extracting of relevant information from medical records as a reference answer to the patient's main complaint includes: based on the patient's main complaint, using a retrieval-enhanced generation model to extract the most relevant information from the patient's medical records as a reference answer to the patient's main complaint.

4. The standardized patient agent-driven physician training system according to claim 1, characterized in that: The standardized patient data layer is constructed based on the patient's chief complaint, diagnostic questions and reference answers to the diagnostic questions. The construction format is question-information-answer-requirement pairs, wherein the question shows the diagnostic question raised by the doctor, the information is detailed information obtained by the retrieval enhancement generation model, the answer contains verified responses and thought chains, and the requirement is determined by the attention strategy.

5. The standardized patient agent-driven doctor training system according to claim 4, characterized in that: The requirements are determined through an attention strategy, including: determining basic rows related to the diagnostic problem through the attention strategy, and submitting the basic rows related to the diagnostic problem to the standardized patient intelligent body unit to obtain corresponding requirements.

6. The standardized patient agent-driven physician training system according to claim 1, characterized in that: The patient triage based on diagnostic cases includes: the standardized patient intelligent unit searches for relevant diagnostic records from the standardized patient data layer, calculates the similarity between new questions and questions in the standardized patient data layer, and uses an external text embedder to obtain several data pairs related to question-information-answer-requirement pairs.

7. The standardized patient agent-driven physician training system according to claim 1, characterized in that: The storage memory of previously proposed diagnostic questions and reference answers includes: managing the visibility between the diagnostic questions and reference answer contexts by adopting immediate and summary memory, maintaining smooth communication, achieving smooth transitions between long rounds of questions, and alleviating the length limit between the diagnostic questions and reference answer contexts.

8. The standardized patient agent-driven physician training system according to claim 1, characterized in that: The formation of a question pool based on the information in the medical data set includes: the standardized doctor intelligent body unit obtains the patient's medical data set, formulates corresponding diagnostic questions based on the symptoms, medical examinations and living habits information in the medical data set, and forms these corresponding diagnostic questions into a common question pool.

9. A doctor training method driven by a standardized patient agent based on a large language model, characterized in that: The doctor training method uses the doctor training system driven by the standardized patient agent based on the large language model according to any one of claims 1 to 8, comprising the following steps: Collect real-world medical data sets as input, perform fuzzy processing on the medical data sets to generate patient complaints, and standard doctor agent units perform department triage based on the complaints; After receiving the patient's complaint, the standard patient agent unit and the standard doctor agent unit initiate multiple rounds of dialogue. The standard doctor agent unit raises diagnostic questions, and the standard patient agent unit generates reference answers to obtain a diagnosis result. The standard patient agent unit and the standard doctor agent unit are combined with real-world medical cases and evolve through multiple iterative cycles of diagnostic questions and reference answers, simulating the training of real-world doctors in various departments for real-world doctor training.

Images