Medical suggestion generation method and device, electronic equipment and computer program product

Abstract

The invention provides a medical suggestion generation method and device, electronic equipment and a computer program product, and the method can carry out the disease analysis of a user based on the medical data of the user, and determines the disease analysis result of the user, and the disease analysis result comprises the current disease of the user and the concurrent diseases of the disease. And generating a medical suggestion for the disease analysis result. Therefore, the medical suggestions for the diseases of the user and concurrent diseases caused by the diseases can be generated according to the medical data of the user, and the purpose of automatically recommending personalized disease prevention strategies for people is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of medical advice generation, and in particular to a method, device, electronic device and computer program product for generating medical advice. Background Art

[0002] As living standards continue to improve, people's awareness of health examinations and disease prevention has significantly increased. However, despite the increasing abundance of physical examination data, most people still find it difficult to accurately interpret this data, and are unable to independently assess their health status and develop prevention strategies. Therefore, how to automatically recommend personalized disease prevention strategies for people has become a technical problem that technicians in this field need to solve urgently. Summary of the invention

[0003] In view of this, the present application proposes a method, device, electronic device and computer program product for generating medical advice, which can automatically recommend personalized disease prevention strategies to people.

[0004] The technical solutions proposed in this application are as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for generating medical advice, comprising:

[0006] Performing disease analysis on the user based on the user's medical data to determine the disease analysis result of the user; the disease analysis result includes the user's current disease and concurrent diseases of the disease;

[0007] Generate medical advice based on the disease analysis results.

[0008] Furthermore, in the above method, the step of performing disease analysis on the user based on the user's medical data to determine the disease analysis result of the user includes:

[0009] The user's medical data is input into a pre-trained disease analysis model so that the disease analysis model performs disease analysis on the user based on the medical data to determine the disease analysis result of the user.

[0010] Further, in the method described above, the disease analysis model includes a first disease analysis network and a second disease analysis network;

[0011] The first disease analysis network is used to determine the current disease of the user based on the medical data of the user;

[0012] The second disease analysis network is used to determine a concurrent disease of the disease according to the current disease of the user.

[0013] Furthermore, in the above method, the training process of the second disease analysis network includes:

[0014] Disease knowledge is input into the second disease analysis network so that the second disease analysis network learns the disease knowledge; wherein the disease knowledge of any disease includes the disease cause of the disease, and / or other diseases that can be caused by the disease.

[0015] Furthermore, the above method further includes:

[0016] Obtain feedback results from the user regarding the medical advice, and perform intensive training on the disease analysis model according to the feedback results.

[0017] Furthermore, in the above method, the disease analysis result also includes the disease level of the disease; the disease level includes disease tendency, early stage of disease and late stage of disease;

[0018] The generating of medical advice for the disease analysis result comprises:

[0019] A medical recommendation is generated that meets the disease level requirements of the disease and is specific to the disease.

[0020] Furthermore, the above method further includes:

[0021] Acquire initial medical content uploaded by a user; the initial medical content includes at least one of text medical content, image medical content and audio medical content;

[0022] The medical data of the user is extracted from the initial medical content; the medical data includes at least one of the group to which the user belongs, the user's gender, age, occupation, chief complaint, current medical history, past medical history, family history, personal history, examination and diagnosis.

[0023] In a second aspect, an embodiment of the present application provides a device for generating medical advice, including:

[0024] A determination module, configured to perform disease analysis on the user based on the user's medical data and determine a disease analysis result of the user; the disease analysis result includes the user's current disease and concurrent diseases of the disease;

[0025] A generating module is used to generate medical advice based on the disease analysis results.

[0026] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0027] A memory and a processor; wherein the memory is used to store programs; and the processor is used to implement any of the methods described above by running the programs in the memory.

[0028] In a fourth aspect, an embodiment of the present application provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the computer program implements any one of the above methods. Optionally, the computer program can be stored in a readable storage medium of a computer device or in the cloud; the processor of the computer device reads the computer program from the readable storage medium or the cloud.

[0029] The method for generating medical advice proposed in this application can perform disease analysis on the user based on the user's medical data, determine the user's disease analysis results, where the disease analysis results include the user's current disease and the concurrent diseases of the disease, and generate medical advice for the disease analysis results. In this way, medical advice for the user's disease and the concurrent diseases caused by the disease can be generated based on the user's medical data, achieving the purpose of automatically recommending personalized disease prevention strategies for people. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0031] Figure 1 It is a schematic diagram of a feasible application scenario of the method for generating medical advice provided in an embodiment of the present application.

[0032] Figure 2 It is a flowchart of a method for generating medical advice provided in an embodiment of the present application.

[0033] Figure 3 This is a schematic diagram of a disease knowledge construction idea provided in an embodiment of the present application.

[0034] Figure 4 It is a flowchart of another method for generating medical advice provided in an embodiment of the present application.

[0035] Figure 5 It is a structural schematic diagram of a medical advice generating device provided in an embodiment of the present application.

[0036] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0038] With the continuous improvement of living standards, people's awareness of health examinations and disease prevention has significantly increased. People are no longer satisfied with basic medical needs, but are more proactive in paying attention to their own health and actively seeking various physical examination services to fully understand their physical condition.

[0039] Although today's physical examination items are numerous and advanced technology has made physical examination data increasingly rich and detailed, most people still feel overwhelmed when faced with these complex data and find it difficult to accurately interpret the deeper meaning. Whether it is a blood test, urine test or more professional imaging test results, the professional terms and numerical ranges often confuse non-medical professionals, making it impossible for them to independently assess their own health status. At the same time, due to the lack of sufficient medical knowledge and guidance, many people do not know how to develop effective prevention strategies to adjust their lifestyles or make necessary medical interventions in a timely manner even if they find abnormal indicators in the physical examination data.

[0040] Based on this, the present application proposes a method, device, electronic device and computer program product for generating medical advice. This technical solution achieves the purpose of automatically recommending personalized disease prevention strategies to people by generating medical advice for the user's disease and complications caused by the disease based on the user's medical data.

[0041] Figure 1 The feasible application scenarios of the method for generating medical advice are shown, such as Figure 1 In the scenario shown, a client and a server are set up.

[0042] The client can be an electronic device with network access capability. Specifically, for example, the client can be a desktop computer, a tablet computer, a laptop computer, a smart phone, a digital assistant, a smart wearable device, a shopping guide terminal, a television, etc. Among them, the smart wearable device includes but is not limited to a smart bracelet, a smart watch, a smart glasses, a smart helmet, a smart necklace, etc. Alternatively, the client can also be software that can run in an electronic device.

[0043] The server can be an electronic device with certain computing and processing capabilities. It can have a network communication module, a processor, and a memory, etc. Of course, the server can also refer to software running in an electronic device. The server can also be a distributed server, which can be a system with multiple processors, memories, network communication modules, etc. operating in collaboration. Alternatively, the server can also be a server cluster formed by several servers. Alternatively, with the development of science and technology, the server can also be a new technical means that can realize the corresponding functions of the implementation method of the specification. For example, it can be a new form of "server" based on quantum computing.

[0044] The client and the server can communicate through the target network. The target network can be any type of network. For example, the target network can be a network that can be subdivided into multiple subnetworks. The target network or the multiple subnetworks contained in the target network can be at least one of a cellular mobile network (such as 2G, 3G, 4G or 5G), ZIGBEE, WIFI, Bluetooth, or any combination of at least one of these networks and other networks.

[0045] In the above feasible application scenario, the client obtains the user's medical data and sends the user's medical data to the server. The server performs disease analysis on the user based on the user's medical data, determines the user's disease analysis result, and the disease analysis result includes the user's current disease and the concurrent diseases of the disease. Medical advice for the disease analysis result is generated and sent to the client. The client displays the medical advice to the user. In this way, medical advice for the user's disease and the concurrent diseases caused by the disease can be generated based on the user's medical data, so as to achieve the purpose of automatically recommending personalized disease prevention strategies for people.

[0046] Furthermore, an embodiment of the present application proposes a method for generating medical advice, which can be executed by an electronic device, and the electronic device can be any device with data and instruction processing functions, for example, it can be various types of user terminals such as a laptop computer, a tablet computer, a desktop computer, a mobile device (for example, a mobile phone, a personal digital assistant, a dedicated messaging device), or a combination of any two or more of these electronic devices, or it can be the server in the above embodiment.

[0047] See also Figure 2 As shown, the method includes:

[0048] S101. Perform disease analysis on the user based on the user's medical data to determine the disease analysis result of the user.

[0049] The user's medical data refers to information that can reflect the user's health status, which is generally generated when the user goes to a hospital for medical treatment or goes to a physical examination center for a physical examination, and this embodiment does not limit this. The user's medical data may specifically include information such as population, gender, age, occupation, chief complaint, current medical history, past history, family history, personal history, examination, diagnosis, etc., and this embodiment does not limit this. The user's medical records, physical examination forms and other data can be obtained, and the user's medical data can be extracted from the user's medical records, physical examination forms and other data.

[0050] Based on the user's medical data, the user's disease analysis is performed to obtain the user's disease analysis results, wherein the disease analysis results include the user's current disease and concurrent diseases of the disease.

[0051] The user's current disease refers to the user's existing disease or disease tendency determined based on medical data. It should be noted that disease tendency means that the user has not yet suffered from the disease, and if the disease is allowed to develop, the user will have a greater chance of suffering from the disease; and, based on the user's population, occupation or family history and other information, it is determined that the user is susceptible to the disease. For example, if the user belongs to a child, then the user is susceptible to myopia, and the disease tendency includes myopia tendency. For example, if the user belongs to a pregnant woman, then the user is susceptible to gestational hypertension, and the disease tendency includes gestational hypertension tendency. If the user's family history includes hypertension, the user is susceptible to hypertension, and the disease tendency includes hypertension. If the user's occupation includes coal miners and decoration workers, the user is susceptible to pneumoconiosis, and the disease tendency includes pneumoconiosis, etc. Existing disease refers to the disease that the user has already suffered from.

[0052] Concurrent diseases of a disease refer to other diseases that occur during the development of the current disease, including all possible concurrent diseases of the disease from the disease tendency period to the late stage of the disease. For example, if a user has a disease A, and the user has disease B and disease E when he has a tendency to develop disease A, and disease C is likely to occur in the early stage of disease A, and disease D is likely to occur in the late stage of disease A, then it can be determined that disease B, disease E, disease C and disease D are all concurrent diseases of disease A.

[0053] In some embodiments, when analyzing a disease of a user, the user's current disease is first determined based on the user's medical data, and then concurrent diseases of the disease are analyzed based on the user's current disease.

[0054] Specifically, the user's current disease can be determined based on the user's medical data by training the first disease analysis model. A large number of sample users' medical data can be obtained as training samples, and the diseases corresponding to each training sample can be marked, including the sample user's disease tendency and existing diseases, as training labels. During training, the training samples are input into the first disease analysis model to obtain the prediction results output by the first disease analysis model. By comparing the prediction results output by the first disease analysis model and the training labels, the loss value of the first disease analysis model is determined. With the goal of reducing the loss value of the first disease analysis model, the parameters of the first disease analysis model are adjusted, and then the above training process is repeated until the performance of the first disease analysis model is satisfactory. The above-mentioned first disease analysis model can be obtained by training based on any neural network model, or based on training based on a pre-trained model, such as a pre-trained large model similar to ChatGPT.

[0055] The user's medical data is input into the first disease analysis model, and the first disease analysis model outputs the user's current disease.

[0056] Then, through the second disease analysis model, the concurrent diseases of the disease are determined based on the user's current disease.

[0057] Specifically, the concurrent disease knowledge of various diseases can be constructed, and the concurrent disease knowledge of various diseases can be input into the large language model so that the large language model can learn the concurrent disease knowledge of various diseases. In this way, the large language model has the ability to output the concurrent diseases of the disease according to the input disease, and the large language model with this ability is defined as the second disease analysis model. The large language model can adopt ChatGPT, etc., which is not limited in this embodiment.

[0058] Then the user's current disease is input into the second disease analysis model, and the second disease analysis model outputs the concurrent diseases of the disease. It should be noted that if the user's current disease has no concurrent diseases, the content output by the second disease analysis model is empty, or it indicates that the disease has no concurrent diseases. For example, if the user is a healthy child and the child's current disease is myopia tendency, there is no concurrent disease.

[0059] S102. Generate medical advice based on the disease analysis results.

[0060] After obtaining the disease analysis results, medical advice based on the disease analysis results is generated.

[0061] Specifically, medical advice data packets for various diseases may be stored in advance. For example, for hypertension, the following medical advice data packets may be stored in advance:

[0062] First, adjust your lifestyle.

[0063] Diet adjustment: Strictly control the intake of sodium salt, and the daily salt intake should be controlled within 6 grams. Eat more foods and fruits rich in potassium ions and calcium ions, such as bananas, fresh vegetables, etc. Avoid greasy food, reduce the intake of high-fat and high-sugar foods, and keep a light diet.

[0064] Weight control: For overweight or obese people, they should keep their weight within the normal range (BMI 18-24) through aerobic exercise (such as jogging, cycling, swimming, etc., each time lasting more than 30 minutes, at least 3 times a week) and reasonable diet control.

[0065] Improve your lifestyle: Avoid staying up late, anxiety, stress and fatigue, maintain a regular schedule and get enough sleep. Learn to deal with stress, avoid excessive tension and anxiety, and stay in a good mood.

[0066] Quit smoking and limit alcohol consumption: Harmful substances such as nicotine in tobacco can accelerate atherosclerosis, and excessive alcohol intake is harmful to myocardial cells. You should try to avoid smoking and excessive drinking.

[0067] Second, drug treatment.

[0068] Commonly used antihypertensive drugs:

[0069] Calcium channel blockers: such as nifedipine, amlodipine, etc. ACEI (angiotensin converting enzyme inhibitor): such as topril, enalapril, etc. ARB (angiotensin receptor blocker): similar to ACEI, but with different mechanisms of action. β-blockers: such as metoprolol, etc. Diuretics: such as hydrochlorothiazide, etc.

[0070] Third, regular monitoring and follow-up.

[0071] Measure blood pressure regularly: It is recommended that patients with hypertension measure their blood pressure regularly to understand their blood pressure control status.

[0072] Follow-up management: For patients diagnosed with hypertension, long-term follow-up management should be carried out, including regular follow-up visits, adjustment of treatment plans, etc.

[0073] Fourth, other matters needing attention.

[0074] Avoid drug abuse: Certain over-the-counter and illicit drugs can increase blood pressure and should be avoided.

[0075] Comprehensive treatment: Hypertensive patients may have other high-risk cardiovascular and cerebrovascular diseases and therefore require comprehensive treatment, such as lipid-lowering therapy.

[0076] After determining the user's current disease and concurrent diseases according to the steps of the above embodiment, the corresponding medical advice data package is extracted and outputted.

[0077] For example, if it is determined that the disease analysis result includes that the user's current disease is disease A, and the concurrent diseases are disease B and disease C, then the medical advice data package for disease A, the medical advice data package for disease B, and the medical advice data package for disease C can be extracted respectively as medical advice for the disease analysis result.

[0078] In the above embodiment, the user's disease analysis can be performed based on the user's medical data to determine the user's disease analysis results, where the disease analysis results include the user's current disease and the concurrent diseases of the disease, and generate medical advice for the disease analysis results. In this way, medical advice for the user's disease and the concurrent diseases caused by the disease can be generated based on the user's medical data, achieving the purpose of automatically recommending personalized disease prevention strategies for people.

[0079] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment perform disease analysis on the user based on the user's medical data to determine the disease analysis result of the user, which may specifically include the following steps:

[0080] The user's medical data is input into a pre-trained disease analysis model so that the disease analysis model performs disease analysis on the user based on the medical data and determines the user's disease analysis result.

[0081] Specifically, in the embodiments of the present application, a disease analysis model is pre-trained, and the disease analysis model can determine the disease analysis result of the user based on medical data.

[0082] Specifically, the disease analysis model may include a first disease analysis network and a second disease analysis network.

[0083] The first disease analysis network is used to infer the user's current disease based on the user's medical data, including disease tendencies and existing diseases. A regression model or a classification and clustering analysis model can be used as the basic model of the first disease analysis network to infer from the user's medical data whether the user is a healthy person, a sub-healthy person, a high-risk person for certain diseases, a chronic disease person, etc., and determine the user's current disease.

[0084] Among them, regression models include linear regression models, polynomial regression models and hierarchical regression models. Linear regression models are applicable when there is a linear relationship between variables. They estimate the influence of independent variables on dependent variables through regression analysis and predict the value of dependent variables under different conditions. Polynomial regression models are applicable when the relationship between variables is not a simple linear relationship. They introduce polynomial terms of age and gender into the model to fit the data more flexibly. Hierarchical regression models analyze the influence of specific variables (such as gender) on height, weight and BMI on the basis of controlling other variables. They first establish a model containing all control variables and then gradually add specific variables for analysis.

[0085] The classification and cluster analysis model includes the classification model and the cluster analysis model. The classification model classifies people according to characteristics such as age and gender, and studies the differences in height, weight, and BMI between different categories. It uses classification algorithms such as logistic regression, decision tree, and random forest for modeling; the cluster analysis model clusters people according to characteristics such as height, weight, and BMI, identifies subgroups with similar characteristics, and uses clustering algorithms such as K-means clustering and hierarchical clustering for analysis.

[0086] The specific training process of the first disease analysis network is the same as the training process of the first disease analysis model in the above embodiment. The first disease analysis network can be trained with reference to the training method of the first disease analysis model recorded in the above embodiment, which is not limited in this embodiment.

[0087] Then, based on the second disease analysis network, the concurrent diseases of the disease are determined according to the current disease of the user. In some embodiments, the second disease analysis network is trained in the same manner as the second disease analysis model in the above embodiment. Those skilled in the art train the second disease analysis network with reference to the training manner of the second disease analysis model described in the above embodiment, which is not limited in this embodiment.

[0088] In the above embodiment, the user's current disease and concurrent diseases can be automatically inferred based on the user's medical data without the need for human intervention, and the degree of intelligence is high.

[0089] In addition to training the second disease analysis network according to the training method of the second disease analysis model recorded in the above embodiment, as an optional implementation method, another embodiment of the present application discloses that the training process of the second disease analysis network may also include:

[0090] The disease knowledge is input into the disease analysis model so that the disease analysis model learns the disease knowledge. The disease knowledge of any disease includes the disease cause of the disease and / or other diseases that the disease can cause.

[0091] Disease causes refer to other diseases that can cause a certain disease. For example, if disease A and disease B can cause disease C, then disease A and disease B are disease causes of disease C. Disease causes of a certain disease generally occur before contracting the disease, that is, they occur during the disease tendency period of the disease. It can be understood that the concurrent disease in the above embodiment includes the disease cause that occurs during the disease tendency period.

[0092] Other diseases that can be caused by the disease refer to complications of the disease, that is, other diseases that patients with the disease are also prone to suffer from. For example, patients with disease C are prone to suffer from disease A and disease D at the same time, so disease A and disease D are other diseases that can be caused by disease C. Complications of a disease generally occur after suffering from the disease. It can be understood that the concurrent diseases in the above embodiments include complications that occur after suffering from the disease.

[0093] In this embodiment, hypertension is taken as an example to further illustrate disease knowledge.

[0094] Disease-causing factors for high blood pressure include:

[0095] First, kidney disease. Chronic nephritis: Inflammation of the glomeruli caused by infection, disease and other reasons. Renal insufficiency may lead to high blood pressure. Acute glomerulonephritis: Abnormal kidney function and metabolic disorders may affect blood circulation, thereby inducing high blood pressure. Renal vascular stenosis: Common in elderly people with renal artery atherosclerosis, it may also be caused by heart diseases such as coronary heart disease, which may cause high blood pressure due to stenosis and blockage of renal blood vessels.

[0096] Second, vascular disease. Coronary heart disease: Stenosis and blockage of the heart's blood vessels may lead to high blood pressure. At the same time, high blood pressure will also increase the risk of coronary heart disease, because high blood pressure will damage the arterial endothelial cells, causing cholesterol and other lipids to deposit on the blood vessel walls, forming atherosclerotic plaques. Aortic stenosis: Aortic disease caused by congenital or acquired factors is also a common cause of high blood pressure.

[0097] Third, endocrine diseases. Hyperthyroidism: The body secretes thyroid hormone vigorously, and metabolism is accelerated, which may lead to high blood pressure. Primary aldosteronism: Endocrine abnormalities may lead to high blood pressure. Pheochromocytoma: Originated from chromaffin tissue in the adrenal medulla, sympathetic ganglia or other parts, this tumor can continuously release a large amount of catecholamines, causing persistent or paroxysmal hypertension and multiple organ function and metabolic disorders.

[0098] Fourth, sleep apnea syndrome. When the airway is blocked during sleep, such as snoring, it causes hypoxia, which may also cause high blood pressure over a long period of time.

[0099] Other diseases that can be caused by high blood pressure include:

[0100] First, cardiovascular disease. Coronary heart disease: Hypertension is one of the main risk factors for coronary heart disease. Long-term hypertension can lead to coronary artery sclerosis and increase the risk of serious heart events such as myocardial infarction. Heart failure: Hypertension can increase the burden on the heart, leading to changes in heart structure and function, and eventually developing into heart failure. Arrhythmia: Hypertension can cause changes in cardiac electrophysiology and increase the risk of arrhythmia.

[0101] Second, cerebrovascular disease. Stroke: Hypertension is the main risk factor for stroke, including cerebral hemorrhage and cerebral infarction. Long-term hypertension can lead to cerebral vascular sclerosis and increase the risk of stroke. Transient ischemic attack: Hypertension can cause cerebral vasospasm or microthrombosis, leading to transient ischemic attack.

[0102] Third, kidney disease. Hypertensive nephropathy: Long-term hypertension can lead to changes in kidney structure and function, manifested as proteinuria, decreased renal function, etc. Renal failure: If hypertensive nephropathy is not treated in time, it can develop into renal failure and require dialysis or kidney transplantation.

[0103] Fourth, retinopathy. Hypertensive retinopathy: Hypertension can cause changes in retinal blood vessels, including vascular sclerosis, hemorrhage, exudation, etc., which may lead to blindness in severe cases.

[0104] Fifth, peripheral vascular disease. Lower limb arteriosclerosis obliterans: Hypertension can accelerate the process of lower limb arteriosclerosis, leading to lower limb arteriosclerosis or occlusion, and symptoms such as intermittent claudication.

[0105] The disease knowledge is input into the second disease analysis network, so that the second disease analysis network can learn the disease knowledge and accurately determine the concurrent diseases of the disease according to the user's current disease.

[0106] In some embodiments, the disease knowledge of any disease includes the disease cause of the disease and other diseases that the disease can cause. This embodiment provides two ideas, one is to build knowledge from the disease cause of the disease, and the other is to build knowledge from the complications of the disease. In this way, the model can learn the relationship between diseases from the two knowledge construction ideas, and can identify all the complications of the current disease, including the disease causes that occur during the disease tendency period and the complications after the disease, so as to recommend medical advice more accurately.

[0107] For example, Figure 3 As shown, knowledge is constructed from the perspective that disease 1 can cause disease 4, disease 5, and disease 6, and from the perspective that disease 1, disease 2, and disease 3 are the causes of disease 4. The model can learn the relationship between disease 1 and disease 4 from these two knowledge construction ideas, and thus recommend medical advice more accurately.

[0108] As an optional implementation, another embodiment of the present application discloses that the method of the above embodiment may specifically include the following steps:

[0109] Obtain user feedback on medical advice and conduct enhanced training of the disease analysis model based on the feedback results.

[0110] In order to further optimize the disease analysis model and enable the model to continuously adapt to new data and scenarios, the disease analysis model can be trained intensively. Specifically, the user's feedback on medical advice can be obtained, and then the parameters of the disease analysis model can be adjusted according to the feedback results to achieve the purpose of intensive training of the disease analysis model.

[0111] More specifically, the user's feedback results on the medical advice can be collected, including positive feedback results and negative feedback results. Positive feedback results include user satisfaction with the medical advice, such as the user performing operations such as thumbs up and high-score evaluation; negative feedback results include user dissatisfaction with the medical advice, such as the user performing operations such as thumbs down and low-score evaluation.

[0112] Based on the collected feedback, the reinforcement learning algorithm is used to update the parameters of the disease analysis model. The reinforcement learning algorithm adjusts the behavior strategy of the disease analysis model based on the reward or penalty signal fed back by the user to maximize the long-term reward. Positive feedback results correspond to reward signals, and negative feedback results correspond to penalty signals. As user feedback continues to accumulate, the disease analysis model will gradually become more intelligent and accurate.

[0113] As an optional implementation, another embodiment of the present application discloses that the disease analysis result of the above embodiment also includes the disease level of the disease, and the disease level includes disease tendency, early stage of the disease, and late stage of the disease; the steps of the above embodiment generate medical advice for the disease analysis result, including:

[0114] Generate disease-specific medical recommendations that meet disease-level requirements.

[0115] The above-mentioned disease tendency means that the user has not yet contracted the disease, but if the disease is allowed to develop, the user will have a greater chance of contracting the disease, and that the user is susceptible to the disease based on information such as the user's demographic, occupation or family history; early stage of disease means that the user has the disease, but is in the early stages of development and the symptoms are not severe; late stage of disease means that the user has the disease and is in the advanced stage of the disease.

[0116] Generally, different treatment methods are used at different stages of the disease. In the embodiment of the present application, the disease analysis results include disease levels, and the disease levels correspond to different stages of the disease, so as to determine more accurate medical advice based on the type and level of the disease.

[0117] For example, during the disease-prone period, the main treatment method is prevention; in the early stages of the disease, preventive measures such as early detection, early diagnosis, and early treatment should be taken to prevent the disease from recurring or turning into a chronic disease. The main measures include screening, regular physical examinations, and key monitoring of high-risk groups; in the late stages of the disease, a comprehensive management strategy for the disease that has already occurred is aimed at reducing the impact of the disease, preventing and delaying chronic complications, reducing mortality, and improving the patient's quality of life. Based on this, medical advice during the disease-prone period can be defined as primary prevention, medical advice in the early stages of the disease can be defined as secondary prevention, and medical advice in the late stages of the disease can be defined as tertiary prevention.

[0118] Primary prevention is etiology prevention. For example, for children, a service package for preventing myopia can be output as medical advice; for pregnant women, a service package for preventing gestational diabetes and thyroid disease during pregnancy can be output as medical advice; for mothers, a service package for preventing postpartum depression can be output as medical advice; for coal miners, a service package for preventing pneumoconiosis can be output as medical advice.

[0119] Secondary prevention is the early detection and treatment of diseases, such as screening for breast cancer, cervical cancer, colorectal cancer, etc., personalized health guidance and management for high-risk groups, and standardized treatment and follow-up of existing diseases such as hypertension and diabetes.

[0120] The third level of prevention is to reduce the impact of the disease and prevent recurrence, such as providing rehabilitation guidance and management for patients with chronic diseases, intervening in the sequelae of the disease, and providing psychological support and psychotherapy services.

[0121] In the embodiment of the present application, medical advice corresponding to different diseases at different disease levels is pre-set, so that after the disease and the disease level are determined, the medical advice of the corresponding disease and the corresponding level can be provided to the user, thereby providing the user with more accurate medical services.

[0122] For example, medical advice for hypertension in the disease prone period, the early stage of the disease, and the late stage of the disease is preset. When it is determined that the user's disease is hypertension and is in the disease prone period, medical advice for hypertension in the disease prone period can be directly output.

[0123] It should be noted that the concurrent diseases determined in the above embodiment are diseases that have not yet occurred and are in the disease-prone period. Therefore, for the concurrent diseases, medical advice for the concurrent diseases in the disease-prone period can be output.

[0124] Specifically, in the embodiment of the present application, when determining the user's current disease and concurrent diseases, if there are concurrent diseases that are repeated with the current disease, the repeated diseases are deleted. Then, the corresponding medical advice is output according to the disease level of the current disease, and the medical advice for the disease tendency period of the concurrent disease is output.

[0125] In some embodiments, the first disease analysis network of the above embodiment is used not only to determine the current disease of the user based on the medical data of the user, but also to determine the disease level of the current disease of the user.

[0126] When training the first disease analysis network, a large amount of medical data is obtained as training samples, and the diseases and disease levels corresponding to each training sample are marked as training labels. During training, the training samples are input into the first disease analysis network to obtain the prediction results output by the first disease analysis network. By comparing the prediction results output by the first disease analysis network and the training labels, the loss value of the first disease analysis network is determined. The parameters of the first disease analysis network are adjusted with the goal of reducing the loss value of the first disease analysis network, and then the above training process is repeated until the performance of the first disease analysis network is satisfactory. A regression model, or a classification and clustering analysis model can be used as the basic model of the first disease analysis network, which is not limited in this embodiment.

[0127] The user's medical data can be input into the first disease analysis network, and the first disease analysis network can output the user's current disease and the disease level of the disease.

[0128] As an optional implementation, another embodiment of the present application discloses that the method of the above embodiment further includes:

[0129] Acquire initial medical content uploaded by the user; the initial medical content includes at least one of text medical content, image medical content and audio medical content; extract the user's medical data from the initial medical content; the medical data includes at least one of the user's population, the user's gender, age, occupation, chief complaint, current medical history, past medical history, family history, personal history, examination and diagnosis.

[0130] The user can upload the initial medical content so as to extract the user's medical data based on the initial medical content. The format of the initial medical content is not limited in the embodiments of the present application, and it can be text medical content in text format, image medical content in image format, audio medical content in audio format, etc.

[0131] Text medical content includes the user's electronic medical records, electronic physical examination reports, etc.; image medical content includes the user's face image, image test results, etc., and image test results include electrocardiograms, electroencephalograms, etc.; audio medical content includes the user's voice content during consultation, etc., which is not limited in this embodiment. In addition, a questionnaire can be used to guide users to fill in information, and portrait information such as age, gender, diagnosis, etc. can also be extracted from the user's records as initial medical content.

[0132] Deep learning natural language processing technologies such as convolutional neural networks and recurrent neural networks can be used to convert the initial medical content into text structure, image OCR recognition, and speech recognition, and the generated word vectors can be learned to complete the natural language classification and understanding process to obtain the user's medical data. In some embodiments, the user's medical data is structured data.

[0133] The medical data includes at least one of the user's population, gender, age, occupation, chief complaint, current medical history, past medical history, family history, personal history, examination and diagnosis.

[0134] With such a configuration, initial medical contents in different formats can be processed to obtain medical data, so as to determine corresponding medical recommendations based on the medical data.

[0135] In a specific embodiment, Figure 4 As shown, the user uploads text medical content, image medical content, and audio medical content as initial medical content.

[0136] The user's gender, age, occupation, chief complaint, current medical history, past medical history, family history, personal history, examination and diagnosis data are extracted from the initial medical content as medical data using deep learning natural language processing technology.

[0137] Then, the medical data is processed through the first disease analysis network to obtain that the user's current disease is disease A, and disease A corresponds to secondary prevention.

[0138] The second disease analysis network was used to conduct further analysis based on disease A, and it was determined that the complications of disease A included disease B and disease C.

[0139] Then, the medical advice corresponding to the secondary prevention of disease A, the medical advice corresponding to the primary prevention of disease B, and the medical advice corresponding to the primary prevention of disease C are extracted from the pre-stored data and output.

[0140] Corresponding to the above-mentioned method for generating medical advice, the present application embodiment also discloses a device for generating medical advice, see Figure 5 As shown, the device comprises:

[0141] The determination module 100 is used to perform disease analysis on the user based on the user's medical data and determine the disease analysis result of the user; the disease analysis result includes the user's current disease and concurrent diseases of the disease;

[0142] The generating module 110 is used to generate medical advice based on the disease analysis results.

[0143] As an optional implementation method, another embodiment of the present application discloses that the determination module 100 of the above embodiment is specifically used to input the user's medical data into a pre-trained disease analysis model so that the disease analysis model performs disease analysis on the user based on the medical data and determines the user's disease analysis result.

[0144] As an optional implementation method, another embodiment of the present application discloses that the disease analysis model includes a first disease analysis network and a second disease analysis network; the first disease analysis network is used to determine the user's current disease based on the user's medical data; the second disease analysis network is used to determine the complications of the disease based on the user's current disease.

[0145] As an optional implementation, another embodiment of the present application discloses that the method further includes:

[0146] The training module is used to input disease knowledge into the second disease analysis network so that the second disease analysis network learns disease knowledge; wherein the disease knowledge of any disease includes the disease cause of the disease, and / or other diseases that the disease can cause.

[0147] As an optional implementation, another embodiment of the present application discloses that the method further includes:

[0148] The reinforcement module is used to obtain user feedback on medical advice and to perform reinforcement training on the disease analysis model based on the feedback results.

[0149] As an optional implementation method, another embodiment of the present application discloses that the disease analysis result also includes the disease level of the disease; the disease level includes disease tendency, early disease stage and late disease stage; the generation module 110 of the above embodiment is specifically used to: generate medical advice that meets the disease level requirements of the disease and is targeted at the disease.

[0150] As an optional implementation, another embodiment of the present application discloses that the method further includes:

[0151] An extraction module is used to obtain initial medical content uploaded by a user; the initial medical content includes at least one of text medical content, image medical content and audio medical content; the user's medical data is extracted from the initial medical content; the medical data includes at least one of the user's population, the user's gender, age, occupation, chief complaint, current medical history, past medical history, family history, personal history, examination and diagnosis.

[0152] Specifically, the device provided in this embodiment belongs to the same application concept as the method provided in the above embodiment of this application, can execute the method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of the execution method. For the technical details not fully described in this embodiment, please refer to the specific processing content of the method provided in the above embodiment of this application, which will not be repeated here.

[0153] The functions implemented by the above modules can be implemented by the same or different processors respectively, and the embodiments of the present application are not limited thereto.

[0154] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by the configuration file, so as to realize the functions of some or all of the above units. All units of the above devices can be implemented in the form of a processor calling software, or in the form of hardware circuits, or in part by a processor calling software, and the remaining part is implemented in the form of hardware circuits.

[0155] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0156] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0157] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0158] An embodiment of the present application further provides a control device, which includes a processor and an interface circuit. The processor in the control device is connected to an input-output component through the interface circuit of the control device.

[0159] The input-output component specifically refers to a hardware component that enables a user to input information and output information to the user, such as a microphone, keyboard, handwriting tablet, touch screen, display, speaker, printer, etc.

[0160] The above-mentioned interface circuit can be any interface circuit that can realize the data communication function, for example, it can be a USB interface circuit, a Type-C interface circuit, a serial port circuit, a PCIE circuit, etc.

[0161] The processor in the control device is a circuit with signal processing capability, which automatically recommends personalized disease prevention strategies to people by executing any of the methods for generating medical advice described in the above embodiments. The specific implementation of the processor can refer to the above processor implementation, and the embodiments of this application are not strictly limited.

[0162] When the control device is applied to a device with a human-computer interaction function, the input and output components of the control device may be input components and output components on the device, such as a microphone, a keyboard, a handwriting tablet, a touch screen, a display, an audio player, etc. At the same time, the processor of the control device may be a CPU or GPU, etc. provided by the device, and the interface circuit of the control device may be an interface circuit between the information input component of the device and a processor such as a CPU or GPU.

[0163] Corresponding to the above-mentioned method for generating medical advice, the present application embodiment also discloses an electronic device, see Figure 6 As shown, the electronic device includes:

[0164] Memory 200 and processor 210;

[0165] The memory 200 is connected to the processor 210 and is used to store programs;

[0166] The processor 210 is configured to implement the method for generating medical advice disclosed in any of the above embodiments by running the program stored in the memory 200 .

[0167] Specifically, the electronic device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0168] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.

[0169] A bus may include a pathway that transfers information between components of a computer system.

[0170] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0171] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0172] The memory 200 stores a program for executing the technical solution of the present application, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes computer operation instructions. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0173] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0174] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0175] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0176] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement each step of the method for generating medical advice provided in the above embodiment of the present application.

[0177] In addition to the above methods and devices, the embodiments of the present application may also be a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for generating medical advice provided in any of the above embodiments of the present application may be executed. Optionally, the computer program may be stored in a readable storage medium or in the cloud of a computer device; the processor of the computer device reads the computer program from the readable storage medium or the cloud.

[0178] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0179] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK).

[0180] In addition, the embodiments of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes each step of the method for generating medical advice provided in the above embodiments.

[0181] The computer readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0182] Specifically, the specific working contents of each part of the above-mentioned electronic device, computer program product and storage medium, as well as the specific processing contents of the computer program product or the computer program on the above-mentioned storage medium when being executed by the processor, can all be referred to the contents of each embodiment of the above-mentioned method for generating medical advice, and will not be described in detail here.

[0183] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0184] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0185] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0186] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0187] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, such as multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0188] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0190] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0191] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0192] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0193] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating medical advice, characterized in that: include: Performing disease analysis on the user based on the user's medical data, and determining a disease analysis result of the user; The disease analysis result includes the user's current disease and the concurrent diseases of the disease; Generate medical advice based on the disease analysis results.

2. The method according to claim 1, characterized in that The performing disease analysis on the user based on the medical data of the user to determine the disease analysis result of the user includes: The user's medical data is input into a pre-trained disease analysis model so that the disease analysis model performs disease analysis on the user based on the medical data to determine the disease analysis result of the user.

3. The method according to claim 2, characterized in that The disease analysis model includes a first disease analysis network and a second disease analysis network; The first disease analysis network is used to determine the current disease of the user based on the medical data of the user; The second disease analysis network is used to determine a concurrent disease of the disease according to the current disease of the user.

4. The method according to claim 3, characterized in that The training process of the second disease analysis network includes: Disease knowledge is input into the second disease analysis network so that the second disease analysis network learns the disease knowledge; wherein the disease knowledge of any disease includes the disease cause of the disease, and / or other diseases that the disease can cause.

5. The method according to claim 2, characterized in that: Also includes: Obtain feedback results from the user regarding the medical advice, and perform intensive training on the disease analysis model according to the feedback results.

6. The method according to claim 1, characterized in that The disease analysis result also includes the disease level of the disease; the disease level includes disease tendency, early stage of disease and late stage of disease; The generating of medical advice for the disease analysis result comprises: A medical recommendation is generated that meets the disease level requirements of the disease and is specific to the disease.

7. The method according to claim 1, characterized in that Also includes: Obtaining initial medical content uploaded by users; The initial medical content includes at least one of text medical content, image medical content and audio medical content; The medical data of the user is extracted from the initial medical content; the medical data includes at least one of the group to which the user belongs, the user's gender, age, occupation, chief complaint, current medical history, past medical history, family history, personal history, examination and diagnosis.

8. A device for generating medical advice, characterized in that: include: A determination module, configured to perform disease analysis on the user based on the user's medical data and determine a disease analysis result of the user; The disease analysis result includes the user's current disease and the concurrent diseases of the disease; A generating module is used to generate medical advice based on the disease analysis results.

9. An electronic device, characterized in that: include: Memory and processor; Wherein, the memory is used to store programs; The processor is used to implement the method according to any one of claims 1 to 7 by running the program in the memory.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images