Medical record report generation method and device, equipment, storage medium and program product

Abstract

The invention relates to a medical record report generation method and device, equipment, a storage medium and a program product, which are applied to diagnostic equipment. The method comprises the steps of firstly obtaining question and answer data of a user in a current inquiry process, then inputting the question and answer data into a preset diagnosis model for diagnosis and recognition to obtain a diagnosis result, and then generating a medical record report according to the question and answer data and the diagnosis result; the diagnosis result comprises diagnosis information and suggestion information, and the preset diagnosis model is obtained based on sample question and answer data and initial diagnosis model training. According to the method, the preset diagnosis model is trained in advance to diagnose the diagnosis result of the user according to the question and answer data, and then the corresponding medical record report is generated based on the diagnosis result and the question and answer data, so that the process reduces the burden of manually inputting the medical record by a doctor and improves the working efficiency.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment, storage medium and program product for generating a medical record report. Background Art

[0002] With the progress of society and the improvement of people's living standards, people are paying more and more attention to health, and the number of medical treatments is rising. In this context, how to efficiently use limited medical resources to meet the growing health needs has become an important challenge facing the medical field.

[0003] Medical records are important documents that record the occurrence, development, outcome and medical process of patients' diseases. They play a vital role in medical treatment, prevention, teaching, scientific research, hospital management and other aspects. With the development of electronic information technology, electronic medical record systems have gradually replaced traditional paper medical records and become an indispensable part of medical institutions. At present, the process of generating electronic medical records is generally that users manually input a large amount of medical data on a preset medical record template, and generate electronic medical records based on the medical data and the preset medical record template.

[0004] However, the above-mentioned electronic medical record generation method has the problem of low generation efficiency. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, equipment, storage medium and program product for generating medical record reports that can improve the efficiency of generating electronic medical record reports in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for generating a medical record report, which is applied to a diagnostic device, comprising:

[0007] Obtain the user's question and answer data during the consultation process;

[0008] The question and answer data is input into the preset diagnostic model for diagnostic identification to obtain a diagnostic result; the diagnostic result includes diagnostic information and recommendation information; the preset diagnostic model is trained based on the sample question and answer data and the initial diagnostic model;

[0009] Generate a medical record report based on the question and answer data and diagnosis results.

[0010] In one embodiment, the step of obtaining the question and answer data of the user during the consultation process includes:

[0011] Obtain the question data asked by the user during the consultation process;

[0012] Input the question data into the response model for identification, and obtain the response data during the consultation process;

[0013] Question and answer data are generated based on the question data and the answer data.

[0014] In one embodiment, the preset diagnosis model includes a recognition model and a query model. The question and answer data is input into the preset diagnosis model for diagnosis recognition to obtain a diagnosis result, including:

[0015] Input the question-and-answer data into the recognition model to identify the disease type and obtain diagnostic information;

[0016] The diagnosis information and question-answer data are input into the query model to search the medical knowledge base and obtain recommended information.

[0017] In one embodiment, the method further comprises:

[0018] Obtain standard question and answer data corresponding to standard medical record reports;

[0019] The standard question-and-answer data is input into the candidate diagnosis model for training to obtain the preset diagnosis model.

[0020] In one embodiment, the above-mentioned obtaining of standard question and answer data corresponding to the standard medical record report includes:

[0021] Acquire first sample question and answer data of a plurality of first sample users in a consultation process within a historical time period;

[0022] Input each first sample question and answer data into a candidate diagnosis model for diagnosis identification, and obtain multiple candidate medical record reports;

[0023] Screening out medical record reports that meet preset conditions from multiple candidate medical record reports as standard medical record reports;

[0024] The first sample question and answer data corresponding to the standard medical record report is screened out from the first sample question and answer data as the standard question and answer data.

[0025] In one embodiment, the method further comprises:

[0026] Acquire second sample question and answer data of multiple second sample users in the consultation process within a historical time period; the second sample question and answer data includes medical question and answer data and medical knowledge data;

[0027] The second sample question and answer data is input into the initial diagnosis model for training to obtain a candidate diagnosis model.

[0028] In a second aspect, the present application also provides a device for generating a medical record report, comprising:

[0029] The acquisition module is used to obtain the question and answer data of the user during the consultation process;

[0030] The recognition module is used to input the question and answer data into the preset diagnosis model for diagnosis recognition to obtain the diagnosis result; the diagnosis result includes diagnosis information and suggestion information; the preset diagnosis model is obtained based on the sample question and answer data and the initial diagnosis model training;

[0031] The generation module is used to generate a medical record report based on the question and answer data and diagnosis results.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Obtain the user's question and answer data during the consultation process;

[0034] The question and answer data is input into the preset diagnostic model for diagnostic identification to obtain a diagnostic result; the diagnostic result includes diagnostic information and recommendation information; the preset diagnostic model is trained based on the sample question and answer data and the initial diagnostic model;

[0035] Generate a medical record report based on the question and answer data and diagnosis results.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0037] Obtain the user's question and answer data during the consultation process;

[0038] The question and answer data is input into the preset diagnostic model for diagnostic identification to obtain a diagnostic result; the diagnostic result includes diagnostic information and recommendation information; the preset diagnostic model is trained based on the sample question and answer data and the initial diagnostic model;

[0039] Generate a medical record report based on the question and answer data and diagnosis results.

[0040] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0041] Obtain the user's question and answer data during the consultation process;

[0042] The question and answer data is input into the preset diagnostic model for diagnostic identification to obtain a diagnostic result; the diagnostic result includes diagnostic information and recommendation information; the preset diagnostic model is trained based on the sample question and answer data and the initial diagnostic model;

[0043] Generate a medical record report based on the question and answer data and diagnosis results.

[0044] The above-mentioned method, device, equipment, storage medium and program product for generating medical record reports are applied to diagnostic equipment, first obtaining the user's question and answer data during the current consultation process, then inputting the question and answer data into a preset diagnostic model for diagnostic identification to obtain a diagnosis result, and then generating a medical record report based on the question and answer data and the diagnosis result; the diagnosis result includes diagnostic information and recommendation information, and the preset diagnostic model is trained based on sample question and answer data and an initial diagnostic model. The above-mentioned method pre-trains a preset diagnostic model to diagnose the user's diagnosis result based on the question and answer data, and then generates a corresponding medical record report based on the diagnosis result and the question and answer data. This process not only reduces the burden of doctors manually entering medical records and improves work efficiency, but also pre-trains a preset diagnostic model to generate accurate diagnosis results, and generates accurate and professional electronic medical records based on the diagnosis results, providing medical staff with comprehensive and detailed medical information and decision support, thereby optimizing the overall quality of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 is an application environment diagram of a method for generating a medical record report in one embodiment;

[0047] Figure 2 is a flow chart of a method for generating a medical record report in one embodiment;

[0048] Figure 3 is a flow chart of a method for generating a medical record report in another embodiment;

[0049] Figure 4 is a flow chart of a method for generating a medical record report in another embodiment;

[0050] Figure 5 is a flow chart of a method for generating a medical record report in another embodiment;

[0051] Figure 6 is a flow chart of a method for generating a medical record report in another embodiment;

[0052] Figure 7 is a flow chart of a method for generating a medical record report in another embodiment;

[0053] Figure 8 is a flowchart of a method for generating a medical record report in another embodiment;

[0054] Fig. 9 is a flowchart of a method for generating a medical record report in another embodiment;

[0055] Fig.10 is a structural block diagram of a device for generating a medical record report in one embodiment;

[0056] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] With the progress of society and the improvement of people's living standards, people are paying more and more attention to health, and the number of medical treatments is rising. In this context, how to efficiently use limited medical resources to meet the growing health needs has become an important challenge facing the medical field.

[0059] Medical records are important documents that record the occurrence, development, outcome, and medical process of patients' diseases. They play a vital role in medical treatment, prevention, teaching, scientific research, and hospital management. With the development of electronic information technology, electronic medical record systems have gradually replaced traditional paper medical records and become an indispensable part of medical institutions. Electronic medical record systems record, store, and manage patients' medical information through electronic devices, greatly improving the accessibility and manageability of medical information.

[0060] At present, the process of generating electronic medical records generally requires users to manually input a large amount of medical data on a preset medical record template, and then generate an electronic medical record based on the medical data and the preset medical record template. This cumbersome filling method is not only inefficient, but also involves repetitive labor, which affects the work efficiency of medical staff. In addition, the existing system often cannot automatically match the patient's basic information and medical record characteristics, making it difficult to provide medical staff with relevant historical medical record references, which limits the potential of electronic medical record systems in clinical decision support.

[0061] In addition, the existing electronic medical record system still relies on the doctor's semi-automatic operation during the input and sorting process, which not only distracts the doctor's attention, but also may affect the careful observation and diagnosis of the patient. Doctors need to fill in medical records while seeing patients, which may reduce work efficiency, and completing a large number of records in a short period of time may affect the comprehensive assessment of the patient's condition, thereby affecting the accuracy of the diagnosis.

[0062] After introducing the background technology of the method for generating a medical record report provided in the embodiment of the present application, the following briefly describes the implementation environment involved in the method for generating a medical record report provided in the embodiment of the present application. The method for generating a medical record report provided in the embodiment of the present application can be applied to Figure 1 In the implementation environment shown. The implementation environment includes a diagnostic device 104 and a data storage system 102, and the data storage system 102 can store data that the diagnostic device 104 needs to process. The data storage system 102 can be integrated on the diagnostic device 104, or it can be placed on the cloud or other network servers. Among them, the data storage system 102 can collect and pre-store the user's question and answer data during the historical consultation process, and the diagnostic device 104 can obtain the user's question and answer data during the current consultation process from the data storage system 102, and predict the user's physical condition based on the user's question and answer data during the current consultation process, obtain the user's diagnosis result, and generate a medical record report based on the user's question and answer data during the current consultation process and the user's diagnosis result.

[0063] In other possible implementations, the method for generating a medical record report provided in the embodiment of the present application can also be applied to a terminal, which can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart car devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.

[0064] After introducing the application scenarios of the method for generating a medical record report provided in the embodiment of the present application, the following focuses on introducing the method for generating a medical record report described in the present application.

[0065] In one embodiment, Figure 2 As shown, a method for generating a medical record report is provided, and the method is applied to Figure 1 Taking the diagnostic device 104 in the example as an example, the method includes the following steps:

[0066] S201. Obtain the question and answer data of the user during the current consultation process.

[0067] Among them, the question and answer data refers to the question data asked by user A during the medical consultation process and the answer data determined by user B based on the question data, wherein user A can be a patient, user B can be a doctor, or can be trained based on a neural network, which can recognize the question data and determine the answer data corresponding to the question data based on the recognition results.

[0068] In an embodiment of the present application, when it is necessary to efficiently and accurately generate a medical record report based on the question and answer data of the user during the consultation process, the question and answer data of the user during the current consultation process can be obtained first.

[0069] Optionally, a response model can be pre-trained so that when a user inputs question data in the response model, the response model outputs response data, and when the user inputs different question and answer data in the response model multiple times, the response model outputs corresponding response data based on the different question and answer data. Then, based on multiple different question and answer data and their corresponding response data, the question and answer data in the consultation process are merged.

[0070] Optionally, during the consultation process between the user and the doctor, the user's question data and the doctor's reply data may be recorded at any time to obtain multiple sets of the user's question data and the doctor's reply data, and question and answer data may be generated based on the multiple sets of question data and reply data, and the question and answer data may be uploaded to the server, so that the server may obtain the user's question and answer data during the current consultation process.

[0071] S202: Input the question and answer data into a preset diagnosis model for diagnosis and identification to obtain a diagnosis result.

[0072] The diagnosis result includes diagnosis information and recommendation information. The diagnosis information includes information such as the user's symptom location, symptom severity and symptom type. The recommendation information refers to the treatment recommendations provided to the user by the preset diagnosis model based on the user's diagnosis information. For example, if the diagnosis information is "leg joint sports injury", the corresponding recommendation information includes "rest in bed, apply hot compress, and maintain mild joint movement".

[0073] Among them, the preset diagnosis model is trained based on sample question and answer data and the initial diagnosis model.

[0074] In the embodiment of the present application, after obtaining the question and answer data of the user during the current medical consultation process, the question and answer data can be input into a pre-trained preset diagnostic model for diagnostic identification to obtain a diagnostic result.

[0075] The preset diagnosis model includes a recognition network, a prediction network, and a query network, etc. Optionally, after obtaining the question and answer data of the user during the current consultation process, the question and answer data can be first input into the recognition network to identify the disease type, and the disease type corresponding to the user can be obtained. The disease type and the question and answer data are then input into the prediction network for prediction to obtain the predicted diagnosis information of the user, and then the user's diagnosis information is input into the query network to query and obtain the suggestion information corresponding to the diagnosis information, thereby outputting the user's diagnosis information and suggestion information.

[0076] S203. Generate a medical record report based on the question and answer data and the diagnosis results.

[0077] In the embodiment of the present application, after obtaining the user's question and answer data during the consultation process and the diagnosis result predicted based on the question and answer data, a medical record report can be generated based on the user's question and answer data, the diagnosis result and the medical record report template. Optionally, the medical record report template can be obtained first, and the question and answer data and the diagnosis result can be input into the corresponding positions of the medical record report template to obtain the medical record report.

[0078] The method for generating a medical record report provided in the embodiment of the present application is applied to a diagnostic device, first obtaining the user's question and answer data during the current consultation process, then inputting the question and answer data into a preset diagnostic model for diagnostic identification to obtain a diagnosis result, and then generating a medical record report based on the question and answer data and the diagnosis result; the diagnosis result includes diagnostic information and recommendation information, and the preset diagnostic model is trained based on sample question and answer data and an initial diagnostic model. The above method pre-trains a preset diagnostic model to diagnose the user's diagnosis result based on the question and answer data, and then generates a corresponding medical record report based on the diagnosis result and the question and answer data. This process not only reduces the burden of doctors manually entering medical records and improves work efficiency, but also pre-trains a preset diagnostic model to generate accurate diagnosis results, and generates accurate and professional electronic medical records based on the diagnosis results, providing medical staff with comprehensive and detailed medical information and decision support, thereby optimizing the overall quality of medical services.

[0079] In one embodiment, Figure 2 Based on the embodiment shown, the method for obtaining the question and answer data of the user during the consultation process can be described in detail, such as Figure 3 As shown, the above S201 "obtaining the question and answer data of the user during the current consultation process" includes:

[0080] S301, obtaining the question data of the user during the current consultation process.

[0081] In an embodiment of the present application, before obtaining the question and answer data of the user during the current consultation, the question data of the user during the current consultation can also be obtained first; optionally, the user can input the corresponding question data on the diagnostic device so that the diagnostic device can obtain the question data of the user during the current consultation.

[0082] S302: Input the question data into the response model for recognition, and obtain the response data during the consultation process.

[0083] The reply model is used to generate corresponding reply data according to the user's question data. The reply model can be pre-trained based on the sample question data with the labeled type and the initial reply model.

[0084] In the embodiment of the present application, after obtaining the question data asked by the user during the current medical consultation, the question data may be input into a response model for identification to obtain the response data during the medical consultation.

[0085] Optionally, the response model includes a recognition network and a query network. After obtaining the question data asked by the user during the current consultation, the question data can be first input into the recognition network for recognition to obtain the consultation type, and then the consultation type and question data can be input into the query network for recognition to obtain the reply data corresponding to the question data.

[0086] It should be noted that the response model can not only determine the reply data corresponding to the question data based on the user's question data, but also has the function of guiding the user to ask questions to ensure the integrity and accuracy of the question and answer data finally obtained during the consultation process.

[0087] S303: Generate question and answer data based on the question data and the answer data.

[0088] In the embodiment of the present application, after the question data and the answer data are obtained, the question data and the answer data are combined to generate corresponding question and answer data. Optionally, the user can input multiple question data in sequence on the diagnostic device, and the diagnostic device obtains multiple answer data according to the corresponding identification of the multiple question data of the user, and after the user stops asking questions, each question data and the corresponding answer data are combined to obtain multiple sets of question and answer data.

[0089] The method for generating question and answer data provided in the embodiment of the present application realizes replying to question data through a pre-trained reply model, and obtains question and answer data based on the combination of question data and reply data, thereby providing a certain data basis for the subsequent generation of medical record reports based on the question and answer data.

[0090] In one embodiment, Figure 2 Based on the embodiment shown, the above-mentioned preset diagnosis model includes a recognition model and a query model, and the process of obtaining the diagnosis result can be described in detail, such as Figure 4 As shown, the above S202 "inputting the question and answer data into a preset diagnosis model for diagnosis and identification to obtain a diagnosis result" includes:

[0091] S401. Input the question and answer data into the recognition model to identify the disease type and obtain diagnosis information.

[0092] In an embodiment of the present application, after the question and answer data is obtained as described above, the question and answer data may be first input into a recognition model for recognition to obtain the user's diagnostic information.

[0093] S402: Input the diagnosis information and question and answer data into the query model to search the medical knowledge base and obtain recommended information.

[0094] In an embodiment of the present application, after obtaining the user's diagnosis information and the user's question and answer data during the diagnosis process, the diagnosis information and question and answer data are input into a query model to perform a medical database search to obtain recommendation information corresponding to the diagnosis information.

[0095] The method for obtaining diagnostic results provided in the embodiments of the present application, through the recognition model and the query model, obtains the diagnostic results through diagnostic identification based on the question and answer data, thereby providing a certain data basis for the subsequent generation of the corresponding medical record report based on the diagnostic results and the question and answer data.

[0096] In one embodiment, Figure 2-Figure 4 Based on any of the embodiments shown, Figure 5 As shown, the above method also includes:

[0097] S204. Obtain standard question and answer data corresponding to the standard medical record report.

[0098] The standard medical record report refers to a medical record that meets preset conditions, and the preset conditions may be conditions that have been identified by medical personnel and meet industry standards. The standard question and answer data corresponding to the standard medical record report refers to the question and answer data used when generating the standard medical record report.

[0099] It should be noted that the medical record reports corresponding to each question and answer data may be pre-stored in a storage database of the diagnostic device.

[0100] In an embodiment of the present application, multiple medical record reports can be first obtained from a storage database, and a standard medical record report can be determined from the multiple medical record reports based on preset conditions. After the standard medical record report is determined, question and answer data corresponding to the standard medical record report can continue to be queried and obtained from the storage database, and the question and answer data corresponding to the standard medical record report can be determined as standard question and answer data.

[0101] Optionally, the following provides a method for obtaining standard question and answer data corresponding to a standard medical record report, see Figure 6 The above S204 "obtaining standard question and answer data corresponding to the standard medical record report" includes:

[0102] S501: Obtain first sample question and answer data of a plurality of first sample users in a medical consultation process within a historical time period.

[0103] The first sample user is a user defined to distinguish from the second sample user mentioned below, and is essentially a plurality of users. The first sample question and answer data is the question and answer data corresponding to the first sample user, and the first sample question and answer data is also question and answer data defined to distinguish from the second sample question and answer data mentioned below, and is essentially question and answer data.

[0104] Among them, the first sample question and answer data aims to guide the first sample users to provide more detailed information about their medical conditions. The question data in the first sample question and answer data covers symptom descriptions, past medical history, living habits, family medical history and other information to ensure that the medical information of the first sample users can be comprehensively collected.

[0105] In the embodiment of the present application, before obtaining the medical record report, it is also necessary to obtain first sample question and answer data of multiple first sample users in the consultation process within a historical time period.

[0106] S502: Input each first sample question and answer data into a candidate diagnosis model for diagnosis identification, and obtain a plurality of candidate medical record reports.

[0107] Among them, the candidate medical record reports include standard medical record reports that meet the preset conditions, as well as ordinary medical record reports that do not meet the preset conditions.

[0108] In an embodiment of the present application, after obtaining the multiple first sample question and answer data as mentioned above, each first sample question and answer data can be respectively input into a candidate diagnosis model for diagnostic identification to obtain a first diagnosis result corresponding to each first sample question and answer data, and then multiple candidate medical record reports are generated based on each first sample question and answer data and the first diagnosis result corresponding to each first sample question and answer data.

[0109] Optionally, a set of medical record report generation rules can be formulated in advance, and after obtaining the first sample question and answer data and the first diagnosis result, a corresponding candidate medical record report can be generated based on the medical record report generation rules. It should be noted that the medical record report generation rules should include the sorting and formatting of information and the use of necessary medical terms.

[0110] S503. Filter out a medical record report that meets preset conditions from a plurality of candidate medical record reports as a standard medical record report.

[0111] In an embodiment of the present application, after obtaining multiple candidate medical record reports as mentioned above, it is determined whether each candidate medical record report meets the preset conditions. If the candidate medical record report meets the preset conditions, the candidate medical record report is determined as a standard medical record report. If the candidate medical record report does not meet the preset conditions, the candidate medical record report is determined as an ordinary medical record report.

[0112] Optionally, the generated candidate medical record reports can be manually scored to obtain the score of each candidate medical record report, and the candidate medical record reports that meet the preset score threshold can be used as standard medical record reports. For example, medical professionals can be organized to conduct quality assessments on multiple candidate medical record reports. The assessment criteria should include the completeness, accuracy, logic, and compliance with medical document specifications of the medical records. At the same time, a detailed scoring system is established to quantitatively evaluate the quality of each candidate medical record report. The scoring system should cover all key parts of the medical record, such as the patient's chief complaint, current medical history, past medical history, physical examination, auxiliary examinations, diagnosis, treatment plan, etc.

[0113] S504. Filter out first sample question and answer data corresponding to the standard medical record report from the first sample question and answer data as standard question and answer data.

[0114] In an embodiment of the present application, after the standard medical record report is determined from the multiple candidate medical record reports, the first sample question and answer data corresponding to the standard medical record report can be screened out from the first sample question and answer data as the standard question and answer data.

[0115] Thus, a method for obtaining standard question and answer data corresponding to a standard medical record report is provided. By screening the standard medical record report from multiple candidate medical record reports and training the candidate diagnosis model based on the standard question and answer data corresponding to the standard medical record report, a preset diagnosis model is obtained. The advantages and disadvantages of the candidate diagnosis model when generating medical record reports can be understood in a timely manner, thereby paying special attention to omitted information in the medical record, inaccurate diagnosis, and inappropriate treatment recommendations; in addition, by determining the standard question and answer data corresponding to the standard medical record report, the candidate diagnosis model can be more effectively guided to generate more accurate and comprehensive medical record content.

[0116] S205: Input the standard question and answer data into the candidate diagnosis model for training to obtain a preset diagnosis model.

[0117] Among them, the candidate diagnostic model refers to a diagnostic model after pre-training the initial diagnostic model, and the diagnostic accuracy of the initial diagnostic model is lower than the diagnostic accuracy of the preset diagnostic model.

[0118] In the embodiment of the present application, after the standard question and answer data is obtained, the standard question and answer data can be input into the candidate diagnosis model, and the candidate diagnosis model is trained to obtain a preset diagnosis model. Optionally, after the standard question and answer data is obtained, these standard question and answer data can promote a deeper and more comprehensive doctor-patient dialogue, thereby generating a better medical record report.

[0119] Optionally, the above-screened standard medical record reports and standard question-answering data are integrated together to form a training dataset for the second round of fine-tuning, and the candidate diagnosis model is fine-tuned for the second round using the training dataset for the second round of fine-tuning. This process may include further optimizing the parameters of the model to better adapt to the task of high-quality medical record generation.

[0120] It should be noted that before the second round of fine-tuning of the candidate diagnostic model, necessary checks and adjustments need to be made to the candidate diagnostic model, including confirming the model structure, cleaning up model parameters, setting an appropriate learning rate, etc.

[0121] Optionally, during the fine-tuning process of the candidate diagnostic model, if it is found that the candidate diagnostic model still has problems in some aspects, such as improper processing of certain types of medical record information, the training strategy or model structure should be adjusted in time. In addition, based on the results of performance monitoring and evaluation, multiple iterations of fine-tuning may be required, each time optimizing based on the previous results. After completing the second round of fine-tuning, use the test set to conduct a comprehensive evaluation of the preset diagnostic model to ensure that the preset diagnostic model can stably generate high-quality electronic medical records in practical applications. Once the model shows satisfactory performance on the test set, prepare to deploy the model in an actual medical environment for use by doctors and patients. After the model is deployed, establish a continuous feedback mechanism to collect usage feedback from doctors and patients so that the preset diagnostic model can be further optimized and upgraded in the future.

[0122] The present application provides a training method for a preset diagnostic model, namely, training the diagnostic model based on standard question and answer data corresponding to a standard medical record report. Since the standard question and answer data corresponding to the standard medical record report is screened question and answer data, the diagnostic model trained based on the screened question and answer data is more accurate, thereby providing a certain data basis for subsequent prediction of accurate diagnostic results based on an accurate diagnostic model, and then generating an accurate medical record report.

[0123] In one embodiment, Figure 5 Based on the embodiment shown, Figure 7 As shown, the above method also includes:

[0124] S206: Obtain second sample question and answer data of multiple second sample users in the consultation process within a historical time period.

[0125] Among them, the second sample question and answer data includes medical question and answer data and medical knowledge data, of which the medical knowledge data knowledge graph, medical knowledge guide library and medical knowledge question bank are composed of three parts. Among them, the medical question and answer data integrates online medical consultation dialogues, real doctor consultation exchanges, and question and answer dialogues generated by the general large model based on the orthopedic medical knowledge graph. The knowledge graph is built and visualized based on public data sets, providing a professional and detailed medical knowledge foundation for the model. The medical knowledge guide library brings together professional literature, encyclopedias and medical articles written by real doctors. The medical knowledge question bank includes medical professional examination question banks such as practicing physician examinations and rehabilitation medicine treatment technology qualification examinations.

[0126] The second sample user is a user defined to distinguish from the first sample user mentioned above, and is essentially a plurality of users. The second sample question and answer data is the question and answer data corresponding to the second sample user, and the second sample question and answer data is also question and answer data defined to distinguish from the first sample question and answer data mentioned above, and is essentially question and answer data.

[0127] In an embodiment of the present application, before training the candidate diagnostic model, it is also necessary to first obtain the second sample question and answer data of multiple second sample users during the consultation process in the historical time period. Optionally, after obtaining the second sample question and answer data, the second sample question and answer data can be cleaned and screened, and combined with manual sampling review and intelligent evaluation to ensure the accuracy and professionalism of the data. The second sample question and answer data provides a new research direction and practical basis for the application of large language models in medical sub-fields, which is expected to significantly improve the efficiency and accuracy of medical consultation, and provide patients with more professional and personalized medical advice.

[0128] S207. Input the second sample question and answer data into the initial diagnosis model for training to obtain a candidate diagnosis model.

[0129] Among them, the initial diagnostic model can be a bidirectional encoder representation from transformers (BERT), a generative pre-trained transformer (GPT) or its variants, which have demonstrated strong performance in the field of natural language processing.

[0130] In an embodiment of the present application, after the second sample question and answer data is obtained as described above, the second sample question and answer data can be input into the initial diagnosis model for training to obtain a candidate diagnosis model. Optionally, after the second sample question and answer data is obtained as described above, the second sample question and answer data can be preprocessed, including text cleaning, word segmentation, stop word removal and standardization, etc., to ensure data quality. In addition, the second sample question and answer data needs to be annotated so that the model can recognize and learn the intent, entities and relationships in the second sample question and answer data.

[0131] It should be noted that during the training process of the candidate diagnostic model, structured knowledge such as knowledge graphs, medical guide libraries and medical question banks can be integrated into the candidate diagnostic model training process to enhance the candidate diagnostic model's understanding and reasoning ability of medical knowledge.

[0132] Optionally, after inputting the second sample question and answer data into the initial diagnosis model for training and obtaining the candidate diagnosis model, the second sample question and answer data can be manually labeled. For example, a team of professional medical personnel and data scientists can be organized to manually label the medical entities (such as diseases, symptoms, and drugs), intentions (such as inquiries and suggestions), and emotional states (such as anxiety and satisfaction) in the collected second sample question and answer data.

[0133] Optionally, a set of detailed manual annotation specifications and guidelines can be prepared in advance to ensure that all annotators can perform manual annotation according to uniform standards. The manual annotation specifications and guidelines should include clear definitions of various medical entities and intents, as well as matters that need to be paid attention to during the annotation process.

[0134] In addition, after the second sample Q&A data is manually annotated, a strict quality control process can be carried out, including regular annotation quality inspection and evaluation, for example, through random sampling and cross-validation methods to ensure the accuracy and consistency of manual annotation. For another example, professional doctors with clinical experience review the manually annotated results to ensure that the annotated medical information is accurate and meets the requirements of clinical practice.

[0135] Optionally, the annotated second sample question and answer data can be sorted, that is, the annotated data can be sorted to form a correspondence between the second sample question and answer data and the annotated text corresponding to the second sample question and answer data, and the question and answer data can be classified according to the type to obtain the correspondence between the second sample question and answer data under each type and the annotated text corresponding to the second sample question and answer data, so as to facilitate subsequent model training and analysis.

[0136] Furthermore, after the second sample question and answer data is manually labeled, the model parameters of the candidate diagnostic model can be fine-tuned based on the labeled second sample question and answer data to ensure the prediction accuracy of the candidate diagnostic model. Optionally, the second sample question and answer data is manually labeled to obtain the labeled second sample question and answer data, and then the second sample question and answer data is input into the pre-trained candidate diagnostic model for prediction to obtain the prediction result, and then the labeled second sample question and answer data and the prediction result are compared to obtain the comparison result, and the model parameters of the candidate diagnostic model are fine-tuned according to the comparison result. The model parameters include the learning rate, the depth of fine-tuning (whether only the top layer is fine-tuned or the whole model is fine-tuned), and the regularization method.

[0137] The candidate diagnostic model training method provided in this application provides a certain data basis for subsequent training of the preset diagnostic model based on the candidate diagnostic model.

[0138] In one embodiment, Figure 8 As shown, a method for generating a medical record report is also provided, comprising:

[0139] S10, obtaining the question data of the user during the current consultation process;

[0140] S11, inputting the question data into the response model for recognition, and obtaining the response data in the consultation process;

[0141] S12, generating question and answer data according to the question data and the answer data;

[0142] S13, inputting the question and answer data into the recognition model to identify the disease type and obtain diagnosis information;

[0143] S14, inputting the diagnosis information and question-answer data into the query model to search the medical knowledge base and obtain recommended information;

[0144] S15. Generate a medical record report based on the question and answer data and the diagnosis results.

[0145] In one embodiment, Fig. 9 As shown, a training method for a preset diagnostic model is also provided, including:

[0146] S20, obtaining first sample question and answer data of a plurality of first sample users in a consultation process within a historical time period;

[0147] S21, inputting each first sample question and answer data into a candidate diagnosis model for diagnosis identification, and obtaining a plurality of candidate medical record reports;

[0148] S22, selecting a medical record report that meets preset conditions from multiple candidate medical record reports as a standard medical record report;

[0149] S23, selecting first sample question and answer data corresponding to the standard medical record report from the first sample question and answer data as standard question and answer data;

[0150] S24, obtaining second sample question and answer data of multiple second sample users in the consultation process within a historical time period;

[0151] S25, inputting the second sample question and answer data into the initial diagnosis model for training to obtain a candidate diagnosis model;

[0152] S26. Input the standard question and answer data into the candidate diagnosis model for training to obtain a preset diagnosis model.

[0153] The above method pre-trains a preset diagnostic model to diagnose the user's diagnostic results based on the question and answer data, and then generates a corresponding medical record report based on the diagnostic results and the question and answer data. This process not only reduces the burden of doctors manually entering medical records and improves work efficiency, but also pre-trains a preset diagnostic model to generate accurate diagnostic results, and generates accurate and professional electronic medical records based on the diagnostic results, providing medical staff with comprehensive and detailed medical information and decision-making support, thereby optimizing the overall quality of medical services.

[0154] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0155] Based on the same inventive concept, the embodiment of the present application also provides a device for generating a medical record report for implementing the method for generating a medical record report involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more medical record report generation devices provided below can refer to the limitations of the method for generating a medical record report above, and will not be repeated here.

[0156] In an exemplary embodiment, Fig.10 As shown, a device for generating a medical record report is provided, comprising: an acquisition module 10, an identification module 11 and a generation module 12, wherein:

[0157] The acquisition module 10 is used to acquire the question and answer data of the user during the current consultation process.

[0158] The recognition module 11 is used to input the question and answer data into the preset diagnosis model for diagnosis recognition to obtain the diagnosis result; the diagnosis result includes diagnosis information and suggestion information; the preset diagnosis model is obtained based on the sample question and answer data and the initial diagnosis model training.

[0159] The generating module 12 is used to generate a medical record report according to the question and answer data and the diagnosis result.

[0160] In an exemplary embodiment, the acquisition module 10 includes: an acquisition unit, an identification unit and a generation unit, wherein:

[0161] An acquisition unit, specifically used to acquire the question data of the user during the current consultation process;

[0162] The recognition unit is specifically used to input the question data into the response model for recognition, and obtain the response data in the consultation process;

[0163] The generating unit is specifically used to generate question and answer data according to the question data and the answer data.

[0164] In an exemplary embodiment, the preset diagnosis model includes a recognition model and a query model, and the recognition module 11 includes: a recognition unit and a retrieval unit, wherein:

[0165] The recognition unit is specifically used to input the question and answer data into the recognition model to identify the disease type and obtain the diagnosis information;

[0166] The retrieval unit is specifically used to input the diagnosis information and question and answer data into the query model to search the medical knowledge base and obtain the recommended information.

[0167] In an exemplary embodiment, the above device further includes: an acquisition module and a training module, wherein:

[0168] An acquisition module is used to obtain standard question and answer data corresponding to a standard medical record report;

[0169] The training module is used to input standard question and answer data into the candidate diagnosis model for training to obtain a preset diagnosis model.

[0170] In an exemplary embodiment, the acquisition module includes: an acquisition unit, an identification unit, a first determination unit and a second determination unit, wherein:

[0171] An acquisition unit, specifically used to acquire first sample question and answer data of a plurality of first sample users in a consultation process within a historical time period;

[0172] The identification unit is specifically used to input each first sample question and answer data into a candidate diagnosis model for diagnosis identification, and obtain multiple candidate medical record reports;

[0173] A first determining unit is specifically used to select a medical record report that meets a preset condition from a plurality of candidate medical record reports as a standard medical record report;

[0174] The second determining unit is specifically used to filter out the first sample question and answer data corresponding to the standard medical record report from the first sample question and answer data as the standard question and answer data.

[0175] In an exemplary embodiment, the above device further includes: an acquisition module and a training model, wherein:

[0176] An acquisition module, used to acquire second sample question and answer data of a plurality of second sample users in a consultation process within a historical time period; the second sample question and answer data includes medical question and answer data and medical knowledge data;

[0177] The training module is used to input the second sample question and answer data into the initial diagnosis model for training to obtain a candidate diagnosis model.

[0178] Each module in the above-mentioned medical record report generation device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0179] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store question and answer data during the consultation process. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a question and answer data method is implemented.

[0180] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0181] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0182] Obtain the user's question and answer data during the consultation process;

[0183] The question and answer data is input into the preset diagnostic model for diagnostic identification to obtain a diagnostic result; the diagnostic result includes diagnostic information and recommendation information; the preset diagnostic model is trained based on the sample question and answer data and the initial diagnostic model;

[0184] Generate a medical record report based on the question and answer data and diagnosis results.

[0185] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0186] Obtain the question data asked by the user during the consultation process;

[0187] Input the question data into the response model for identification, and obtain the response data during the consultation process;

[0188] Question and answer data are generated based on the question data and the answer data.

[0189] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0190] Input the question-and-answer data into the recognition model to identify the disease type and obtain diagnostic information;

[0191] The diagnosis information and question-answer data are input into the query model to search the medical knowledge base and obtain recommended information.

[0192] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0193] Obtain standard question and answer data corresponding to standard medical record reports;

[0194] The standard question-and-answer data is input into the candidate diagnosis model for training to obtain the preset diagnosis model.

[0195] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0196] Acquire first sample question and answer data of a plurality of first sample users in a consultation process within a historical time period;

[0197] Input each first sample question and answer data into a candidate diagnosis model for diagnosis identification, and obtain multiple candidate medical record reports;

[0198] Screening out medical record reports that meet preset conditions from multiple candidate medical record reports as standard medical record reports;

[0199] The first sample question and answer data corresponding to the standard medical record report is screened out from the first sample question and answer data as the standard question and answer data.

[0200] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0201] Acquire second sample question and answer data of multiple second sample users in the consultation process within a historical time period; the second sample question and answer data includes medical question and answer data and medical knowledge data;

[0202] The second sample question and answer data is input into the initial diagnosis model for training to obtain a candidate diagnosis model.

[0203] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0204] Obtain the user's question and answer data during the consultation process;

[0205] The question and answer data is input into the preset diagnostic model for diagnostic identification to obtain a diagnostic result; the diagnostic result includes diagnostic information and recommendation information; the preset diagnostic model is trained based on the sample question and answer data and the initial diagnostic model;

[0206] Generate a medical record report based on the question and answer data and diagnosis results.

[0207] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0208] Obtain the question data asked by the user during the consultation process;

[0209] Input the question data into the response model for identification, and obtain the response data during the consultation process;

[0210] Question and answer data are generated based on the question data and the answer data.

[0211] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0212] Input the question-and-answer data into the recognition model to identify the disease type and obtain diagnostic information;

[0213] The diagnosis information and question-answer data are input into the query model to search the medical knowledge base and obtain recommended information.

[0214] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0215] Obtain standard question and answer data corresponding to standard medical record reports;

[0216] The standard question-and-answer data is input into the candidate diagnosis model for training to obtain the preset diagnosis model.

[0217] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0218] Acquire first sample question and answer data of a plurality of first sample users in a consultation process within a historical time period;

[0219] Input each first sample question and answer data into a candidate diagnosis model for diagnosis identification, and obtain multiple candidate medical record reports;

[0220] Screening out medical record reports that meet preset conditions from multiple candidate medical record reports as standard medical record reports;

[0221] The first sample question and answer data corresponding to the standard medical record report is screened out from the first sample question and answer data as the standard question and answer data.

[0222] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0223] Acquire second sample question and answer data of multiple second sample users in the consultation process within a historical time period; the second sample question and answer data includes medical question and answer data and medical knowledge data;

[0224] The second sample question and answer data is input into the initial diagnosis model for training to obtain a candidate diagnosis model.

[0225] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0226] Obtain the user's question and answer data during the consultation process;

[0227] The question and answer data is input into the preset diagnostic model for diagnostic identification to obtain a diagnostic result; the diagnostic result includes diagnostic information and recommendation information; the preset diagnostic model is trained based on the sample question and answer data and the initial diagnostic model;

[0228] Generate a medical record report based on the question and answer data and diagnosis results.

[0229] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0230] Obtain the question data asked by the user during the consultation process;

[0231] Input the question data into the response model for identification, and obtain the response data during the consultation process;

[0232] Question and answer data are generated based on the question data and the answer data.

[0233] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0234] Input the question-and-answer data into the recognition model to identify the disease type and obtain diagnostic information;

[0235] The diagnosis information and question-answer data are input into the query model to search the medical knowledge base and obtain recommended information.

[0236] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0237] Obtain standard question and answer data corresponding to standard medical record reports;

[0238] The standard question-and-answer data is input into the candidate diagnosis model for training to obtain the preset diagnosis model.

[0239] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0240] Acquire first sample question and answer data of a plurality of first sample users in a consultation process within a historical time period;

[0241] Input each first sample question and answer data into a candidate diagnosis model for diagnosis identification, and obtain multiple candidate medical record reports;

[0242] Screening out medical record reports that meet preset conditions from multiple candidate medical record reports as standard medical record reports;

[0243] The first sample question and answer data corresponding to the standard medical record report is screened out from the first sample question and answer data as the standard question and answer data.

[0244] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0245] Acquire second sample question and answer data of multiple second sample users in the consultation process within a historical time period; the second sample question and answer data includes medical question and answer data and medical knowledge data;

[0246] The second sample question and answer data is input into the initial diagnosis model for training to obtain a candidate diagnosis model.

[0247] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0248] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0249] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0250] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a medical record report, characterized in that: The method is applied to a diagnostic device, and the method comprises: Obtain the user's question and answer data during the consultation process; The question and answer data is input into a preset diagnostic model for diagnostic identification to obtain a diagnostic result; the diagnostic result includes diagnostic information and recommendation information; the preset diagnostic model is obtained based on the sample question and answer data and the initial diagnostic model training; Generate a medical record report based on the question and answer data and the diagnosis result.

2. The method according to claim 1, characterized in that The obtaining of the user's question and answer data during the consultation process includes: Obtaining the question data of the user during the current consultation process; Inputting the question data into the response model for identification to obtain the response data in the consultation process; The question and answer data is generated based on the question data and the answer data.

3. The method according to claim 1, characterized in that The preset diagnosis model includes a recognition model and a query model. The question-answer data is input into the preset diagnosis model for diagnosis recognition to obtain a diagnosis result, including: Inputting the question and answer data into the recognition model to identify the disease type and obtain the diagnosis information; The diagnosis information and the question and answer data are input into the query model to perform a medical knowledge base search to obtain the recommendation information.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtain standard question and answer data corresponding to standard medical record reports; The standard question and answer data is input into the candidate diagnosis model for training to obtain the preset diagnosis model.

5. The method according to claim 4, characterized in that The obtaining of standard question and answer data corresponding to the standard medical record report includes: Acquire first sample question and answer data of a plurality of first sample users in a consultation process within a historical time period; Inputting each of the first sample question and answer data into the candidate diagnosis model for diagnosis identification, thereby obtaining the plurality of candidate medical record reports; Selecting a medical record report that meets a preset condition from the plurality of candidate medical record reports as the standard medical record report; The first sample question and answer data corresponding to the standard medical record report is screened out from the first sample question and answer data as the standard question and answer data.

6. The method according to claim 4, characterized in that The method further comprises: Acquire second sample question and answer data of a plurality of second sample users in a consultation process within a historical time period; the second sample question and answer data includes medical question and answer data and medical knowledge data; The second sample question and answer data is input into the initial diagnosis model for training to obtain the candidate diagnosis model.

7. A device for generating a medical record report, characterized in that: Applied to diagnostic equipment, the device comprises: The acquisition module is used to obtain the question and answer data of the user during the consultation process; An identification module is used to input the question and answer data into a preset diagnosis model for diagnosis and identification to obtain a diagnosis result; the diagnosis result includes diagnosis information and suggestion information; the preset diagnosis model is obtained based on sample question and answer data and initial diagnosis model training; A generation module is used to generate a medical record report based on the question and answer data and the diagnosis result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images