Patient non-drug care scheme determination method and device, electronic equipment and storage medium

Abstract

The invention discloses a non-drug nursing scheme determination method and device for a patient, electronic equipment and a storage medium. The method comprises the steps that the disease type, the drug use condition, the treatment progress, the culture background and the exercise habit of the current patient are acquired; inputting the disease type, the medication condition, the treatment progress and the cultural background of the current patient into a diet plan network model, so that the diet plan network model generates a diet plan of the current patient; inputting the disease type, the medication condition, the treatment progress and the exercise habit of the current patient into an exercise plan network model, so that the exercise plan network model generates an exercise plan of the current patient; and determining a non-drug care scheme of the current patient according to the diet plan of the current patient and the motion plan of the current patient. By implementing the method, the auxiliary effect of non-drug treatment in patient nursing can be considered, so that acceleration of the rehabilitation process is promoted, and a better nursing effect is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical management, and in particular to a patient non-drug nursing scheme determination method and device, electronic equipment and storage medium. BACKGROUND

[0002] Patient care plays a crucial role in the medical process. Nursing not only involves basic vital sign monitoring and drug treatment implementation for patients, but also covers comprehensive interventions such as diet and exercise. Good nursing can significantly improve the recovery speed of patients and improve the quality of life, especially for patients with chronic diseases and long-term treatment, the role of nursing is particularly important.

[0003] However, the existing nursing system often focuses too much on drug treatment and clinical operation, ignoring the auxiliary role of non-drug treatment in patient care. Currently, most nursing schemes mainly focus on the implementation of drug treatment, ensuring that patients take medicine on time and in the right amount, and monitoring the side effects and efficacy of the medicine. This drug-centered nursing model can indeed help patients control their condition and relieve symptoms in the short term, but in the long term, it tends to overlook comprehensive intervention on the overall health of patients. Non-drug treatments, such as diet management and exercise therapy, have been proven by research to have an important auxiliary role in the recovery process of many diseases. These interventions can assist drug treatment by enhancing patients' physical function and improving their quality of life, thereby achieving more comprehensive rehabilitation effects. SUMMARY

[0004] The present application provides a patient non-drug nursing scheme determination method, device, electronic equipment and storage medium. By implementing the present application, the auxiliary role of non-drug treatment in patient care can be considered, thereby promoting the acceleration of the rehabilitation process and achieving better nursing effects.

[0005] One embodiment of the present application provides a patient non-drug nursing scheme determination method, comprising:

[0006] Obtaining the disease type, medication, treatment progress, cultural background and exercise habit of the current patient;

[0007] Inputting the disease type, medication, treatment progress and cultural background of the current patient into a diet plan network model to enable the diet plan network model to generate a diet plan for the current patient based on the disease type, medication, treatment progress and cultural background of the current patient; wherein the diet plan network model is trained from a plurality of first training samples corresponding to patients with set diet plans; each first training sample includes the disease type, medication, treatment progress and cultural background of the patient; and each training sample corresponds to a label representing the diet plan of the patient;

[0008] inputting the disease type, medication, treatment progress and exercise habit of the current patient into the exercise plan network model, so that the exercise plan network model generates an exercise plan for the current patient according to the disease type, medication, treatment progress and exercise habit of the current patient; wherein the exercise plan network model is trained by a plurality of second training samples corresponding to patients with set exercise plans; each second training sample includes the disease type, medication, treatment progress and exercise habit of the patient; and each second training sample corresponds to a label for representing the exercise plan of the patient;

[0009] determining a non-drug care plan for the current patient according to the current patient's diet plan and the current patient's exercise plan.

[0010] Further, the diet plan network model is trained in the following manner:

[0011] obtaining a plurality of first training samples corresponding to patients with set diet plans;

[0012] inputting each first training sample into the diet plan network model in turn, training the diet plan network model until a preset first training number is reached; wherein the diet plan network model outputs a predicted diet plan of the patient corresponding to each received first training sample; calculates a first loss function value according to the predicted diet plan and the corresponding diet plan label; and updates the diet plan network model according to the first loss function value.

[0013] Further, the exercise plan network model is trained in the following manner:

[0014] obtaining a plurality of second training samples corresponding to patients with set exercise plans;

[0015] inputting each second training sample into the exercise plan network model in turn, training the exercise plan network model until a preset second training number is reached; wherein the exercise plan network model outputs a predicted exercise plan of the patient corresponding to each received second training sample; calculates a second loss function value according to the predicted exercise plan and the corresponding exercise plan label; and updates the exercise plan network model according to the second loss function value.

[0016] Further, before inputting the disease type, medication, treatment progress and cultural background of the current patient into the diet plan network model, it further includes:

[0017] cleaning and multi-label classification encoding the disease type, medication and cultural background of the current patient; and cleaning and label encoding the treatment progress of the current patient.

[0018] Further, before inputting the disease type, medication, treatment progress and exercise habit of the current patient into the exercise plan network model, the method further includes:

[0019] The disease type and medication of the current patient are cleaned and multi-label classified and encoded, and the treatment progress and exercise habit of the current patient are cleaned and labeled.

[0020] On the basis of the above method embodiment, the application provides a device embodiment.

[0021] An embodiment of the application provides a patient non-drug nursing scheme determination device, which comprises a patient data acquisition module, a diet plan generation module, an exercise plan generation module and a non-drug treatment scheme generation module.

[0022] The patient data acquisition module is configured to acquire the disease type, medication, treatment progress, cultural background and exercise habit of the current patient.

[0023] The diet plan generation module is configured to input the disease type, medication, treatment progress and cultural background of the current patient into a diet plan network model, so that the diet plan network model generates a diet plan of the current patient according to the disease type, medication, treatment progress and cultural background of the current patient; wherein the diet plan network model is trained by a plurality of first training samples corresponding to patients with set diet plans; each first training sample comprises the disease type, medication, treatment progress and cultural background of a patient; and each training sample corresponds to a label for representing the diet plan of the patient.

[0024] The exercise plan generation module is configured to input the disease type, medication, treatment progress and exercise habit of the current patient into an exercise plan network model, so that the exercise plan network model generates an exercise plan of the current patient according to the disease type, medication, treatment progress and exercise habit of the current patient; wherein the exercise plan network model is trained by a plurality of second training samples corresponding to patients with set exercise plans; each second training sample comprises the disease type, medication, treatment progress and exercise habit of a patient; and each second training sample corresponds to a label for representing the exercise plan of the patient.

[0025] The non-drug treatment scheme generation module is configured to determine a non-drug nursing scheme of the current patient according to the diet plan of the current patient and the exercise plan of the current patient.

[0026] Further, the patient non-drug nursing scheme determination device further comprises a diet plan network model training module.

[0027] The dietary plan network model training module is configured to acquire first training samples corresponding to patients with set dietary plans, input each first training sample into the dietary plan network model in sequence, train the dietary plan network model until a preset first training number is reached, wherein the dietary plan network model outputs a predicted dietary plan of a patient corresponding to each received first training sample, calculates a first loss function value according to the predicted dietary plan and a corresponding dietary plan label, and updates the dietary plan network model according to the first loss function value.

[0028] Further, the patient non-drug care plan determination apparatus further comprises a movement plan network model training module.

[0029] The movement plan network model training module is configured to acquire second training samples corresponding to patients with set movement plans.

[0030] The movement plan network model training module is configured to acquire second training samples corresponding to patients with set movement plans.

[0031] On the basis of the above-mentioned method embodiment, the present application correspondingly provides an electronic device embodiment.

[0032] An embodiment of the present application provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor can implement the patient non-drug care plan determination method in any of the above-mentioned method embodiments when executing the computer program.

[0033] On the basis of the above-mentioned method embodiment, the present application correspondingly provides a storage medium embodiment.

[0034] An embodiment of the present application provides a storage medium, which stores a computer program, and the computer program can implement the patient non-drug care plan determination method in any of the above-mentioned method embodiments when executed by a processor.

[0035] Compared with the prior art, the present application has the following beneficial effects:

[0036] The embodiment of the present application provides a patient non-drug nursing scheme determination method, device, electronic equipment and storage medium. The method generates personalized diet plan and exercise plan by comprehensively using multi-dimensional data such as disease type, medication, treatment progress, cultural background and exercise habit of the patient, so as to provide a complete non-drug treatment scheme for the patient. The scheme strengthens the auxiliary role of non-drug treatment in patient care, significantly promotes the rehabilitation process of the patient, and improves the life quality of the patient. By inputting the multiple data of the patient into the diet plan and exercise plan network model, the personalized diet and exercise scheme is generated, the patient can effectively promote the rehabilitation of the disease, improve the nutritional status, enhance the physical strength and immunity, and thus accelerate the rehabilitation process under the reasonable diet and exercise adjustment. At the same time, by comprehensively using the diet and exercise plan, the non-drug nursing scheme can help the patient to better cooperate with the drug treatment, improve the overall health level, reduce the occurrence of complications, and reduce the risk of long-term hospitalization. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 FIG. 1 is a flow diagram of a patient non-drug nursing scheme determination method provided by an embodiment of the present application.

[0038] Figure 2 FIG. 2 is a structural diagram of a patient non-drug nursing scheme determination device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0040] As shown in FIG. 1, an embodiment of the present application provides a patient non-drug nursing scheme determination method, which at least includes the following steps: Figure 1

[0041] Step S1, obtaining the disease type, medication, treatment progress, cultural background and exercise habit of the current patient;

[0042] It should be noted that the disease type of the current patient is a specific disease category, such as diabetes, heart disease, hypertension, etc.; the medication of the current patient is the type of drug used by the patient; the treatment progress of the current patient is the initial stage, stable period, recovery period and complete recovery, etc.; the cultural background of the current patient is the religious belief of the patient; and the exercise habit of the current patient is the exercise frequency of the patient;

[0043] ​Step S2, input the disease type, medication, treatment progress and cultural background of the current patient into the diet plan network model, so that the diet plan network model generates a diet plan for the current patient according to the disease type, medication, treatment progress and cultural background of the current patient; wherein the diet plan network model is trained by a plurality of first training samples corresponding to patients with set diet plans; each first training sample includes the disease type, medication, treatment progress and cultural background of the patient; and each training sample corresponds to a label for representing the diet plan of the patient;

[0044] Specifically, in an optional embodiment, the diet plan network model is trained in the following way:

[0045] Obtain a plurality of first training samples corresponding to patients with set diet plans;

[0046] Input each first training sample into the diet plan network model in turn, train the diet plan network model, until a preset first training number is reached; wherein the diet plan network model outputs the predicted diet plan of the patient corresponding to each received first training sample; calculate the first loss function value according to the predicted diet plan and the corresponding diet plan label; update the diet plan network model according to the first loss function value.

[0047] Specifically, inputting the disease type, medication, treatment progress and cultural background of the current patient into the diet plan network model can help generate a personalized diet plan. First, by collecting the disease type, medication, treatment progress and cultural background of the patient, etc. Data is input into the diet plan network model, the model will generate a diet plan suitable for the current patient according to these information. This process can ensure that the diet plan meets the medical requirements while also taking into account the cultural differences of patients, increasing patient compliance and satisfaction with the diet plan.

[0048] The diet plan network model is trained by a large amount of historical patient data. Each training sample is composed of the disease type, medication, treatment progress and cultural background of the patient, and corresponds to a diet plan label. Each label represents a diet plan that has been set, including specific diet content, taboo food and other diet adjustment suggestions. Through the learning of a large amount of historical data, the diet plan network model can capture the rules and characteristics of different patient groups, thereby providing accurate diet plans for current patients.

[0049] The training process of the model can use a supervised learning method to optimize based on historical data to improve the accuracy and personalization level of the generated diet plan. Ultimately, in this way, the diet plan network model can automatically generate a diet plan that meets the needs of patients according to their health status, treatment stage, and cultural background, providing scientific, reasonable, and personalized nutritional support for patients.

[0050] In an optional embodiment, before inputting the disease type, medication, treatment progress, and cultural background of the current patient into the diet plan network model, the following steps are further included:

[0051] Cleaning and multi-label classification encoding of the disease type, medication, and cultural background of the current patient; cleaning and label encoding of the treatment progress of the current patient.

[0052] It can be understood that multi-label classification encoding is suitable for cases where each sample can belong to multiple categories at the same time, such as disease type, medication, and cultural background; label encoding is suitable for features with clear categories and limited number of categories, such as treatment progress.

[0053] Step S3, inputting the disease type, medication, treatment progress, and exercise habit of the current patient into the exercise plan network model, so that the exercise plan network model generates an exercise plan for the current patient according to the disease type, medication, treatment progress, and exercise habit of the current patient; wherein the exercise plan network model is trained by a plurality of second training samples corresponding to patients with set exercise plans; each second training sample includes the disease type, medication, treatment progress, and exercise habit of the patient; and each second training sample corresponds to a label for representing the exercise plan of the patient;

[0054] Specifically, in an optional embodiment, the exercise plan network model is trained in the following way:

[0055] Obtaining a plurality of second training samples corresponding to patients with set exercise plans;

[0056] Inputting each second training sample into the exercise plan network model in turn to train the exercise plan network model until a preset second training number is reached; wherein the exercise plan network model outputs the predicted exercise plan of the patient corresponding to each received second training sample; calculates a second loss function value according to the predicted exercise plan and the corresponding exercise plan label; and updates the exercise plan network model according to the second loss function value.

[0057] Specifically, the disease type, medication, treatment progress, and exercise habits of the current patient are input into the exercise plan network model, which helps tailor personalized exercise programs for the patient. This process combines the patient's health status, treatment stage, and exercise needs to ensure that the exercise plan meets the patient's treatment goals while taking into account the patient's physical condition and exercise capacity. In this way, patients not only receive effective rehabilitation support during treatment, but also promote recovery and improve quality of life through reasonable exercise within their physical condition.

[0058] The exercise plan network model is trained using historical patient exercise data, with each training sample containing multi-dimensional information such as the patient's disease type, medication, treatment progress, and exercise habits, and associated with corresponding exercise plan labels. Each label represents a specific exercise plan, covering exercise intensity, frequency, duration, and exercise form suitable for the patient. During training, the model learns the relationship between different disease states, treatment stages, and individual exercise habits, enabling it to provide personalized exercise programs for current patients.

[0059] The diversity of these training samples ensures that the exercise plan network model can meet the needs of different patient groups, and patients with different disease types and treatment plans can receive targeted exercise guidance. By using supervised learning, the model is optimized through a large amount of historical data, enhancing its adaptability to individual differences and improving the scientificity and practicality of exercise plans. Ultimately, based on this information, the exercise plan network model will generate an exercise program that closely matches the patient's health status and lifestyle, helping patients achieve the best results during rehabilitation.

[0060] Before inputting the disease type, medication, treatment progress, and exercise habits of the current patient into the exercise plan network model, the following steps are included:

[0061] Cleaning and multi-label classification encoding of the current patient's disease type and medication; cleaning and label encoding of the current patient's treatment progress and exercise habits.

[0062] It can be understood that multi-label classification encoding is suitable for cases where each sample can belong to multiple categories, such as disease type and medication; label encoding is suitable for features with clear categories and limited number of categories, such as treatment progress and exercise habits.

[0063] Step S4, determining the non-drug care plan for the current patient based on the current patient's diet plan and the current patient's exercise plan.

[0064] It should be noted that the non-drug care scheme of the current patient is determined according to the diet plan and the exercise plan of the current patient to achieve the overall rehabilitation of the patient, and provides personalized health management in addition to traditional drug treatment. Diet and exercise are crucial non-drug intervention means in patient care, and they have important auxiliary effects on the physical recovery, immune enhancement and disease prevention of patients. By combining the diet plan and the exercise plan of the patient, the non-drug care scheme can better meet the comprehensive needs of the patient on the basis of personalized treatment, thereby promoting the overall rehabilitation of the patient.

[0065] In determining the non-drug care scheme, first, according to the specific diet plan of the patient, ensure that the diet structure and nutrient intake are highly matched with the disease type, treatment stage and individual needs of the patient. For example, for diabetic patients, the diet plan may focus on low-sugar, low-salt, high-fiber foods; while for patients with high blood pressure, it may be necessary to limit the intake of salt and fat. At the same time, the exercise plan also needs to consider the exercise ability, disease type and treatment progress of the patient, to avoid excessive exercise or improper exercise methods that may cause physical discomfort or exacerbate the disease. Therefore, by organically combining the diet plan and the exercise plan, a comprehensive and scientific non-drug care scheme can be formed to maximize support for the physical rehabilitation of the patient.

[0066] As shown in Figure 2 An embodiment of the present application provides a patient non-drug care scheme determination device, comprising: a patient data acquisition module, a diet plan generation module, an exercise plan generation module and a non-drug treatment scheme generation module;

[0067] The patient data acquisition module is configured to acquire the disease type, medication, treatment progress, cultural background and exercise habit of the current patient.

[0068] The diet plan generation module is configured to input the disease type, medication, treatment progress and cultural background of the current patient into a diet plan network model, so that the diet plan network model generates a diet plan for the current patient according to the disease type, medication, treatment progress and cultural background of the current patient. The diet plan network model is trained by a plurality of first training samples corresponding to patients with set diet plans; each first training sample includes the disease type, medication, treatment progress and cultural background of the patient; and each training sample corresponds to a label for representing the diet plan of the patient.

[0069] The motion plan generation module is configured to input the disease type, medication, treatment progress, and exercise habit of the current patient into a motion plan network model, so that the motion plan network model generates a motion plan for the current patient according to the disease type, medication, treatment progress, and exercise habit of the current patient; wherein the motion plan network model is trained by a plurality of second training samples corresponding to patients with set motion plans; each second training sample includes the disease type, medication, treatment progress, and exercise habit of a patient; and each second training sample corresponds to a label for representing the motion plan of the patient.

[0070] The non-drug treatment plan generation module is configured to determine a non-drug care plan for the current patient according to the diet plan of the current patient and the motion plan of the current patient.

[0071] In a preferred embodiment, the patient non-drug care plan determination device further comprises a diet plan network model training module.

[0072] The diet plan network model training module is configured to obtain a plurality of first training samples corresponding to patients with set diet plans; sequentially input each first training sample into a diet plan network model to train the diet plan network model until a preset first training number is reached; wherein the diet plan network model outputs a predicted diet plan of a patient corresponding to each received first training sample; calculates a first loss function value according to the predicted diet plan and a corresponding diet plan label; and updates the diet plan network model according to the first loss function value.

[0073] In an optional embodiment, the patient non-drug care plan determination device further comprises a motion plan network model training module.

[0074] The motion plan network model training module is configured to obtain a plurality of second training samples corresponding to patients with set motion plans.

[0075] Sequentially input each second training sample into a motion plan network model to train the motion plan network model until a preset second training number is reached; wherein the motion plan network model outputs a predicted motion plan of a patient corresponding to each received second training sample; calculates a second loss function value according to the predicted motion plan and a corresponding motion plan label; and updates the motion plan network model according to the second loss function value.

[0076] It should be noted that the above-described embodiments of the device correspond to the above-described embodiments of the application, and can implement the patient non-drug nursing scheme determination method according to any one of the above-described embodiments of the application. In addition, the above-described embodiments of the device are merely illustrative, and the modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the embodiments. In addition, the connection between the modules in the device embodiments provided by the application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0077] On the basis of the above-described method embodiments of the application, an electronic device embodiment is provided.

[0078] An embodiment of the application provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, when the processor executes the computer program, the patient non-drug nursing scheme determination method according to any one of the above-described embodiments of the application is implemented, or when the processor executes the computer program, the functions of the modules in the above-described device embodiments are implemented.

[0079] For example, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the application. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the terminal device.

[0080] The terminal device can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The terminal device can include, but is not limited to, a processor and a memory.

[0081] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The processor is a control center of the terminal device, and connects all parts of the terminal device through various interfaces and lines.

[0082] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the terminal device by running or executing the computer program and / or modules stored in the memory, and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application program required by a function, etc.; and the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a nonvolatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0083] On the basis of the above-mentioned method embodiment, the application further provides a storage medium embodiment;

[0084] Another embodiment of the application provides a storage medium, which comprises a stored computer program. When the computer program runs, the device where the storage medium is located executes the above-mentioned any one non-drug nursing scheme determination method of the application.

[0085] The storage medium is a computer readable storage medium, and the computer program includes computer program code in the form of source code, object code, an executable file, or some intermediate form, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in a jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include an electrical carrier signal and a telecommunication signal.

[0086] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0087] The above is the preferred embodiment of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which are also considered within the scope of protection of the present application.

Claims

1. A method for determining a non-pharmacological care plan for a patient, characterized in that, include: Obtain information on the current patient's disease type, medication use, treatment progress, cultural background, and exercise habits; The current patient's disease type, medication status, treatment progress, and cultural background are input into the diet planning network model. The diet planning network model generates a diet plan for the current patient based on these factors. The diet planning network model is trained using a set of first training samples corresponding to several patients with pre-defined diet plans. Each first training sample includes the patient's disease type, medication status, treatment progress, and cultural background. Each training sample also corresponds to a label representing the patient's diet plan. The current patient's disease type, medication status, treatment progress, and exercise habits are input into the exercise planning network model, so that the exercise planning network model can generate an exercise plan for the current patient based on the current patient's disease type, medication status, treatment progress, and exercise habits. The exercise planning network model is trained from several second training samples corresponding to patients with pre-set exercise plans. Each second training sample includes: the patient's disease type, medication status, treatment progress, and exercise habits; and each second training sample corresponds to a label used to represent the patient's exercise plan. Based on the patient's current diet and exercise plan, determine the patient's non-pharmacological care plan.

2. The method for determining a non-pharmacological care plan for a patient as described in claim 1, characterized in that, The diet plan network model was trained using the following method: Obtain a first training sample corresponding to several patients with pre-set diet plans; Each first training sample is sequentially input into the diet planning network model to train the diet planning network model until a preset first training iteration is reached. Each time a first training sample is received, the diet planning network model outputs a predicted diet plan for the patient corresponding to that first training sample. A first loss function value is calculated based on the predicted diet plan and its corresponding label. The diet planning network model is then updated based on the first loss function value.

3. The method for determining a non-pharmacological care plan for a patient as described in claim 2, characterized in that, The motion planning network model was trained using the following method: Obtain a second training sample corresponding to several patients who have already set exercise plans; Each second training sample is sequentially input into the exercise planning network model to train the exercise planning network model until a preset second training iteration is reached. Each time a second training sample is received, the exercise planning network model outputs a predicted exercise plan for the patient corresponding to that second training sample. A second loss function value is calculated based on the predicted exercise plan and its corresponding exercise plan label. The exercise planning network model is then updated based on the second loss function value.

4. The method for determining a non-pharmacological care plan for a patient as described in claim 3, characterized in that, Before inputting the patient's current disease type, medication status, treatment progress, and cultural background into the diet plan network model, the following is also included: Clean and classify the current patient's disease type, medication status, and cultural background using multiple labels; clean and label the current patient's treatment progress.

5. The method for determining a non-pharmacological care plan for a patient as described in claim 4, characterized in that, Before inputting the patient's current disease type, medication status, treatment progress, and exercise habits into the exercise planning network model, the following steps are also included: Clean and classify the current patient's disease type and medication status using multiple tags; clean and tag the current patient's treatment progress and exercise habits using multiple tags.

6. A device for determining a non-pharmacological care plan for a patient, characterized in that, include: Patient data acquisition module, diet plan generation module, exercise plan generation module, and non-drug treatment plan generation module; The patient data acquisition module is used to acquire the current patient's disease type, medication status, treatment progress, cultural background, and exercise habits; The diet plan generation module is used to input the current patient's disease type, medication status, treatment progress, and cultural background into the diet plan network model, so that the diet plan network model can generate a diet plan for the current patient based on the current patient's disease type, medication status, treatment progress, and cultural background. The diet plan network model is trained using first training samples corresponding to several patients with pre-set diet plans. Each first training sample includes: the patient's disease type, medication status, treatment progress, and cultural background; and each training sample corresponds to a label used to represent the patient's diet plan. The exercise plan generation module is used to input the current patient's disease type, medication status, treatment progress, and exercise habits into the exercise plan network model, so that the exercise plan network model can generate an exercise plan for the current patient based on the current patient's disease type, medication status, treatment progress, and exercise habits. The exercise plan network model is trained using a number of second training samples corresponding to patients with pre-set exercise plans. Each second training sample includes: the patient's disease type, medication status, treatment progress, and exercise habits; and each second training sample corresponds to a label representing the patient's exercise plan. The non-drug treatment plan generation module is used to determine the non-drug care plan for the current patient based on the current patient's diet plan and exercise plan.

7. The device for determining a non-pharmacological care plan for a patient as described in claim 6, characterized in that, Also includes: Diet planning network model training module; The diet plan network model training module is used to obtain the first training samples corresponding to several patients with pre-set diet plans; Each first training sample is sequentially input into the diet planning network model to train the diet planning network model until a preset first training iteration is reached. Each time a first training sample is received, the diet planning network model outputs a predicted diet plan for the patient corresponding to that first training sample. A first loss function value is calculated based on the predicted diet plan and its corresponding label. The diet planning network model is then updated based on the first loss function value.

8. The device for determining a non-pharmacological care plan for a patient as described in claim 7, characterized in that, Also includes: Exercise planning network model training module; The exercise plan network model training module is used to obtain second training samples corresponding to several patients with pre-set exercise plans; Each second training sample is sequentially input into the exercise planning network model to train the exercise planning network model until a preset second training iteration is reached; wherein, when the exercise planning network model receives a second training sample, it outputs the predicted exercise plan of the patient corresponding to the second training sample; and the second loss function value is calculated based on the predicted exercise plan and the corresponding exercise plan label; The motion planning network model is updated based on the second loss function value.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it can implement the method for determining a non-pharmacological care plan for a patient as described in any one of claims 1 to 5.

10. A storage medium having a computer program stored thereon, characterized in that: When executed by a processor, the computer program can implement the method for determining a non-pharmacological care plan for a patient as described in any one of claims 1 to 5.

Images