Whole-cycle nursing simulation training system for breast reconstruction patient

Abstract

The invention discloses a complete-cycle nursing simulation training system for a breast reconstruction patient, and relates to the technical field of nursing simulation training for the breast reconstruction patient, and the system comprises a collection and preparation module which is used for collecting breast reconstruction data and constructing a support vector machine (SVM) model to generate a rehabilitation scheme; the guidance acquisition module is used for guiding the patient to act by using AR, and the patient acquires a rehabilitation scheme; the rehabilitation module is used for collecting patient data to generate a rehabilitation scheme; the adjustment encryption module is used for collecting feedback of the patient for adjustment and performing security encryption on the transmitted data; and the visual storage module is used for displaying the rehabilitation scheme of the patient in real time and storing breast reconstruction data. By integrating automatic literature capture, natural language processing, the support vector machine, the AR technology and the intelligent wearable device, the whole-process intelligence from rehabilitation scheme generation to real-time action guidance and rehabilitation effect evaluation is realized, and the use convenience and data security of a patient are improved.

Description

Technical Field

[0001] The invention relates to the technical field of nursing simulation training for breast reconstruction patients, in particular to a full-cycle nursing simulation training system for breast reconstruction patients. Background Art

[0002] Breast reconstruction surgery is an important part of breast cancer treatment, which aims to help patients restore their body shape and mental health. With the development of medical technology, breast reconstruction technology has developed from early basic implant surgery to today's highly personalized and refined reconstruction strategy. Breast reconstruction technology not only focuses on the restoration of appearance, but also pays more attention to the improvement of patients' overall rehabilitation quality and quality of life. In this context, intelligent simulation training system, as an emerging technology for auxiliary rehabilitation, provides patients with personalized rehabilitation guidance through highly integrated data processing and simulation training, and has gradually become a research hotspot.

[0003] The existing rehabilitation training system for breast reconstruction patients has several limitations. The rehabilitation training and management of breast reconstruction mostly rely on traditional physical therapy and doctors' experience guidance, lacking personalized and precise rehabilitation plans. Patients often lack effective real-time action guidance and feedback during rehabilitation, which limits the maximization of rehabilitation effects. Traditional rehabilitation plans are usually static and difficult to adjust according to the patient's real-time status and rehabilitation progress. Summary of the invention

[0004] In view of the problems existing in the existing full-cycle nursing simulation training system for breast reconstruction patients, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the rehabilitation training and management of breast reconstruction mostly rely on traditional physical therapy and doctor's experience guidance, lacking personalized and precise rehabilitation programs. Patients often lack effective real-time action guidance and feedback during rehabilitation, which limits the maximization of rehabilitation effects. Traditional rehabilitation programs are usually static and difficult to adjust according to the patient's real-time status and rehabilitation progress.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a full-cycle nursing simulation training system for breast reconstruction patients, which includes: an acquisition and planning module, which is used to collect breast reconstruction data and construct a support vector machine (SVM) model to generate a rehabilitation plan; a guidance acquisition module, which is used to use AR to guide the actions of breast reconstruction patients, and the patients input personal information to obtain a rehabilitation plan for breast reconstruction; a rehabilitation module, which is used to collect the real-time breast reconstruction data of the patients to generate a comprehensive rehabilitation plan; an adjustment and encryption module, which is used to collect patient feedback for adjustment and implement secure encryption on the transmitted data; a visualization storage module, which is used to display the patient's rehabilitation plan and action guidance in real time, and store, collect and analyze the generated breast reconstruction data.

[0007] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients of the present invention, wherein: the collection of breast reconstruction data refers to the use of the automated literature crawling tool Python to obtain text data from medical databases, clinical trial databases, and guidelines published by rehabilitation professional organizations;

[0008] Text preprocessing of the collected text data includes data cleaning, standardization and outlier processing;

[0009] Apply natural language processing technology NLP and use TF-IDF algorithm to extract text from preprocessed text data, including the patient's age, surgery details, rehabilitation progress, and medical indicator information. The formula is:

[0010] TF-IDF(c,d)=TF(c,d)×IDF(c),

[0011] Where c is a term, d is a document, TF(c,d) is the frequency of term c in document d, and IDF(c) is the inverse document frequency;

[0012] Data integration was performed on the preprocessed literature data and the extracted information to obtain comprehensive breast reconstruction data;

[0013] The combined breast reconstruction data were normalized.

[0014] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients of the present invention, wherein: the construction of the support vector machine (SVM) model to generate a rehabilitation plan refers to collecting historical text data for preprocessing, extraction, data integration and normalization to generate a data training set;

[0015] Construct a support vector machine (SVM) model, including an input layer and a kernel function output layer;

[0016] Define the input layer as normalized breast reconstruction data;

[0017] Use RBF radial basis function as kernel function K(x i ,x), handle nonlinear relationships, the formula is:

[0018] K(x i ,x)=exp(-γ‖x i -x‖ 2 ),

[0019] Where γ is the parameter of the RBF kernel, x i and x are the input data;

[0020] The decision output layer formula is:

[0021]

[0022] Where f(x) is the result predicted by the model, y i For data point x i The category label, b is the bias term, α i is the Lagrange multiplier, n is the total number of support vectors;

[0023] Use the data training set to train the support vector machine (SVM) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters;

[0024] The normalized breast reconstruction data were input into the trained support vector machine (SVM) model to obtain the classification results of the rehabilitation program.

[0025] A rehabilitation plan is generated based on the classification results, including recommended rehabilitation activities, frequency, and duration.

[0026] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients of the present invention, wherein: the use of AR to guide the movements of breast reconstruction patients refers to displaying 3D rehabilitation movements through AR smart glasses, and using the camera on the AR smart glasses to capture the actual movements of the patient;

[0027] Computer vision technology is used to capture the patient's movements and compare them with the preset 3D rehabilitation movements in real time. The deviation between the patient's movements and the standard movements is calculated in real time. The formula is:

[0028]

[0029] Where S is the action score, P m is the position parameter of the preset 3D rehabilitation action, O m is the position parameter of the patient’s actual action, and M is the number of actions;

[0030] According to the action score S, the action parts that need to be improved are provided through the AR smart glasses.

[0031] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients of the present invention, wherein: the patient inputting personal information to obtain the rehabilitation plan for breast reconstruction refers to generating a QR code for the patient, including the patient information;

[0032] The system automatically analyzes the patient's information and generates a rehabilitation plan through a trained machine learning model;

[0033] The rehabilitation plan is automatically generated and sent to the patient via email.

[0034] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients of the present invention, wherein: the collecting of the patient's real-time breast reconstruction data to generate a comprehensive rehabilitation plan refers to having the patient wear a smart bracelet, collecting the patient's real-time breast reconstruction data and performing preprocessing and normalization;

[0035] The principal component analysis (PCA) method is used to extract the features of the pre-processed real-time breast reconstruction data and generate real-time features.

[0036] Collect historical patient breast reconstruction data and perform preprocessing and normalization, use principal component analysis (PCA) to extract the processed historical patient breast reconstruction data and generate a historical training set;

[0037] Construct a convolutional neural network (CNN) model, including input layer, convolution layer, pooling layer, and fully connected output layer;

[0038] Define the input layer as real-time features;

[0039] Use the historical training set to train the convolutional neural network (CNN) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters;

[0040] Input the real-time features into the trained convolutional neural network (CNN) model to obtain the prediction results;

[0041] A rehabilitation plan is automatically generated based on the prediction results, and the newly generated rehabilitation plan is compared and integrated with the patient's existing rehabilitation plan to generate a comprehensive rehabilitation plan.

[0042] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients of the present invention, wherein: the collecting of patient feedback for adjustment refers to collecting patient feedback data through hospital surveys, using data analysis tools to regularly analyze the feedback data, identifying problems and trends in the rehabilitation process, and generating analysis reports;

[0043] The medical team holds regular meetings to discuss and decide on adjustments to the rehabilitation program based on feedback reports;

[0044] Update the adjusted rehabilitation plan into the system and notify relevant patients and medical staff;

[0045] Track the effectiveness of new initiatives after implementation.

[0046] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients of the present invention, wherein: the implementation of secure encryption of the transmitted data refers to using a key management system to generate and manage keys;

[0047] The breast reconstruction data generated by the analysis was encrypted with AES;

[0048] Set access permissions and use authentication for access;

[0049] For the encrypted breast reconstruction data, the decryption key is obtained from the key management system, and the encrypted data is decrypted using the AES decryption algorithm and the key to restore the original data.

[0050] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients of the present invention, wherein: the real-time display of the patient's rehabilitation plan and action guidance refers to using the modern front-end technology stack React.js to build an interactive user interface;

[0051] Develop customized charts using the data visualization library D3.js to display rehabilitation plans, rehabilitation progress, and breast reconstruction data;

[0052] Patients can access after real-name authentication.

[0053] As a preferred solution of the full-cycle nursing simulation training system for breast reconstruction patients described in the present invention, wherein: the storing of the breast reconstruction data generated by the collection and analysis refers to storing the breast reconstruction data generated by the collection and analysis in a database, implementing data security protection measures, backing up the breast reconstruction data in the cloud, and regularly performing integrity checks on active data and backup data.

[0054] The beneficial effects of the present invention are as follows: the present invention realizes the intelligence of the entire process from the generation of rehabilitation plans to real-time action guidance and rehabilitation effect evaluation by integrating automated literature capture, natural language processing, support vector machines, AR technology and smart wearable devices, thereby improving the accuracy and effectiveness of training, and enhancing the ease of use and data security of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0056] Figure 1 This is a schematic diagram of the structure of the full-cycle nursing simulation training system for breast reconstruction patients.

[0057] Figure 2 Schematic diagram of the process of the full-cycle nursing simulation training system for breast reconstruction patients. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0061] Example 1

[0062] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a full-cycle nursing simulation training system for breast reconstruction patients, the full-cycle nursing simulation training system for breast reconstruction patients includes:

[0063] S1, acquisition and planning module, used to collect breast reconstruction data and build a support vector machine (SVM) model to generate a rehabilitation plan;

[0064] Specifically, the collection of breast reconstruction data refers to the use of the automated literature crawling tool Python to obtain text data from medical databases, clinical trial databases, and guidelines published by rehabilitation professional organizations;

[0065] Text preprocessing of the collected text data includes data cleaning, standardization and outlier processing;

[0066] Apply natural language processing technology NLP and use TF-IDF algorithm to extract text from preprocessed text data, including the patient's age, surgery details, rehabilitation progress, and medical indicator information. The formula is:

[0067] TF-IDF(c,d)=TF(c,d)×IDF(c),

[0068] Where c is a term, d is a document, TF(c,d) is the frequency of term c in document d, and IDF(c) is the inverse document frequency;

[0069] Data integration was performed on the preprocessed literature data and the extracted information to obtain comprehensive breast reconstruction data;

[0070] The combined breast reconstruction data were normalized.

[0071] The use of automated literature crawling makes the data collection process efficient and extensive, ensuring the comprehensiveness and update of the collected information, which is particularly important for the timeliness and scientificity of data in the medical field. Data cleaning eliminates redundant and irrelevant data and improves the accuracy of data analysis. Standardization ensures consistency between different source data, facilitating subsequent analysis; outlier processing eliminates possible data entry errors or extreme values ​​and enhances data reliability. The TF-IDF algorithm can be used to identify the most informative data from a large amount of text, providing a scientific basis for subsequent data analysis and decision-making. Normalization is a key step to ensure that different data features contribute weights fairly in the model, especially when performing algorithms such as support vector machines (SVM) that rely on distance calculations.

[0072] Furthermore, constructing a support vector machine (SVM) model to generate a rehabilitation plan refers to collecting historical text data for preprocessing, extraction, data integration and normalization to generate a data training set;

[0073] Construct a support vector machine (SVM) model, including an input layer and a kernel function output layer;

[0074] Define the input layer as normalized breast reconstruction data;

[0075] Use RBF radial basis function as kernel function K(x i ,x), handle nonlinear relationships, the formula is:

[0076] K(x i ,x)=exp(-γ‖x i -x‖ 2 ),

[0077] Where γ is the parameter of the RBF kernel, x i and x are the input data;

[0078] The decision output layer formula is:

[0079]

[0080] Where f(x) is the result predicted by the model, y i For data point x i The category label, b is the bias term, α i is the Lagrange multiplier, n is the total number of support vectors;

[0081] Use the data training set to train the support vector machine (SVM) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters;

[0082] The normalized breast reconstruction data were input into the trained support vector machine (SVM) model to obtain the classification results of the rehabilitation program.

[0083] A rehabilitation plan is generated based on the classification results, including recommended rehabilitation activities, frequency, and duration.

[0084] The collected historical text data were cleaned, standardized, processed for outliers, and normalized to ensure that the data had a consistent format and range before entering the model. This step is crucial to improving the training efficiency and prediction accuracy of the model, because normalization can prevent the model from being overly sensitive to certain features during training, thereby avoiding overfitting. The SVM model using the RBF kernel function can effectively handle nonlinear problems in breast reconstruction data, enabling the model to find the optimal classification boundary in complex rehabilitation data. By defining the input layer as normalized data, the model's ability to process data can be further improved to ensure that data of different dimensions have a balanced impact on the model. The processed breast reconstruction data is input into the trained SVM model, and personalized rehabilitation plans are generated based on the classification results of the model. These rehabilitation plans include recommended rehabilitation activities, frequency, and duration, directly targeting the specific needs of patients and providing recommendations that are most suitable for their rehabilitation stage and physical condition.

[0085] S2, a guidance acquisition module, which is used to use AR to guide the breast reconstruction patient's movements, and the patient enters personal information to obtain a breast reconstruction rehabilitation plan;

[0086] Specifically, using AR to guide the movements of breast reconstruction patients refers to displaying 3D rehabilitation movements through AR smart glasses and using the camera on the AR smart glasses to capture the patient's actual movements;

[0087] Computer vision technology is used to capture the patient's movements and compare them with the preset 3D rehabilitation movements in real time. The deviation between the patient's movements and the standard movements is calculated in real time. The formula is:

[0088]

[0089] Where S is the action score, P m is the position parameter of the preset 3D rehabilitation action, O m is the position parameter of the patient’s actual action, and M is the number of actions;

[0090] According to the action score S, the action parts that need to be improved are provided through the AR smart glasses.

[0091] By displaying the rehabilitation movements of the 3D model through AR smart glasses, patients can intuitively see the correct way to perform each rehabilitation movement. This intuitive demonstration helps patients understand and accurately imitate complex rehabilitation movements, especially those that require precise control after breast reconstruction. The camera on the AR smart glasses captures the patient's actual movements and uses computer vision technology to compare them with the preset 3D rehabilitation movements in real time. Through comparison and analysis, the system can accurately evaluate the accuracy of the patient's movements and promptly discover deviations in the execution of the movements. The movement score is achieved by calculating the deviation between the position parameters of the preset movement and the position parameters of the patient's actual movement. This scoring system provides patients with instant feedback, points out the movement parts that need to be improved, and helps patients gradually adjust and improve each rehabilitation movement. Based on the movement score, AR smart glasses can provide patients with specific improvement suggestions, such as adjusting the angle of the arm and improving the standing posture. This real-time feedback mechanism significantly improves the efficiency and effectiveness of rehabilitation training, enabling patients to conduct rehabilitation safely and effectively under the guidance of professionals.

[0092] Further, the patient inputting personal information to obtain a rehabilitation plan for breast reconstruction refers to generating a QR code for the patient, including the patient's information;

[0093] The system automatically analyzes the patient's information and generates a rehabilitation plan through a trained machine learning model;

[0094] The rehabilitation plan is automatically generated and sent to the patient via email.

[0095] S3, rehabilitation module, used to collect patients' real-time breast reconstruction data to generate a comprehensive rehabilitation plan;

[0096] Specifically, collecting the patient's real-time breast reconstruction data to generate a comprehensive rehabilitation plan means having the patient wear a smart bracelet, collecting the patient's real-time breast reconstruction data, and performing preprocessing and normalization;

[0097] The principal component analysis (PCA) method is used to extract the features of the pre-processed real-time breast reconstruction data and generate real-time features.

[0098] Collect historical patient breast reconstruction data and perform preprocessing and normalization, use principal component analysis (PCA) to extract the processed historical patient breast reconstruction data and generate a historical training set;

[0099] Construct a convolutional neural network (CNN) model, including input layer, convolution layer, pooling layer, and fully connected output layer;

[0100] Define the input layer as real-time features;

[0101] Use the historical training set to train the convolutional neural network (CNN) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters;

[0102] Input the real-time features into the trained convolutional neural network (CNN) model to obtain the prediction results;

[0103] A rehabilitation plan is automatically generated based on the prediction results, and the newly generated rehabilitation plan is compared and integrated with the patient's existing rehabilitation plan to generate a comprehensive rehabilitation plan.

[0104] The data are preprocessed and normalized to ensure the quality and consistency of data input into the model and reduce the impact of noise and outliers. The key features of real-time data are extracted through principal component analysis, which helps to highlight the main variables that affect the patient's rehabilitation process while reducing model complexity and the risk of overfitting. The data processed by PCA can more clearly reflect the patient's rehabilitation status and provide effective input for subsequent data analysis. These historical data provide a training basis for the CNN model, enabling the model to learn lessons from the rehabilitation experience of past patients. CNN is trained using historical training sets, and the model parameters are optimized using loss functions and Adam optimizer to ensure the accuracy and reliability of predictions. The real-time features are input into the trained CNN model, and rehabilitation plans are automatically generated based on the model's prediction results. These newly generated rehabilitation plans are compared and integrated with the patient's existing rehabilitation plans to develop a comprehensive and updated rehabilitation plan.

[0105] S4, adjustment encryption module, used to collect patient feedback for adjustment and implement secure encryption for transmitted data;

[0106] Specifically, collecting patient feedback for adjustment means collecting patient feedback data through hospital surveys, using data analysis tools to regularly analyze the feedback data, identifying problems and trends in the rehabilitation process, and generating analysis reports;

[0107] The medical team holds regular meetings to discuss and decide on adjustments to the rehabilitation program based on feedback reports;

[0108] Update the adjusted rehabilitation plan into the system and notify relevant patients and medical staff;

[0109] Track the effectiveness of new initiatives after implementation.

[0110] Effective feedback collection can ensure that the rehabilitation program is more in line with the actual needs and expectations of patients, thereby improving treatment outcomes and patient satisfaction. Data analysis tools are used to regularly analyze the collected feedback and identify common problems and development trends in the rehabilitation process. Through these analyses, the medical team can accurately understand the effectiveness of the rehabilitation program, including which measures are effective and which need to be improved. Data-driven analysis helps the medical team make evidence-based decisions to optimize the rehabilitation path. Regular meetings are held, and the medical team discusses potential adjustments to the rehabilitation program based on the analysis report. This link is a manifestation of multidisciplinary cooperation. Medical personnel from different professions can jointly evaluate the comprehensive effects of the program to ensure that each adjustment is the result of comprehensive consideration. According to the meeting decision, the rehabilitation program is adjusted and updated in the system. The updated program is then notified to the relevant patients and medical personnel to ensure that every patient can rehabilitate according to the latest scientific guidance. After the implementation of the new rehabilitation program, continue to monitor its effects and collect patient feedback. This continuous monitoring and evaluation process ensures that the rehabilitation program always maintains the highest implementation standards and adaptability.

[0111] Furthermore, implementing secure encryption for transmitted data means using a key management system to generate and manage keys;

[0112] The breast reconstruction data generated by the analysis was encrypted with AES;

[0113] Set access permissions and use authentication for access;

[0114] For the encrypted breast reconstruction data, the decryption key is obtained from the key management system, and the encrypted data is decrypted using the AES decryption algorithm and the key to restore the original data.

[0115] The encryption keys are generated and managed through the key management system to ensure the security and effectiveness of the keys. Systematic key management avoids the risk of key leakage and provides a centralized and automated way to handle keys, greatly reducing the possibility of human error and key abuse. The breast reconstruction data is encrypted with AES to ensure the security of the data during storage and transmission. AES provides strong encryption protection, so that the data cannot be interpreted even if it is intercepted, thereby protecting the privacy of patients and the confidentiality of the data. Access to encrypted data is controlled by setting access rights and using authentication mechanisms, which ensures that only authorized users can access sensitive data, thereby preventing unauthorized access and data leakage. When access to the original data is required, the appropriate decryption key is obtained from the key management system and the data is decrypted using the AES decryption algorithm. This step makes the use of data safe and flexible, and authorized users can easily access the required information while ensuring data security.

[0116] S5, a visual storage module, used to display the patient's rehabilitation plan and action guidance in real time, and store, collect and analyze the breast reconstruction data generated;

[0117] Specifically, real-time display of patients’ rehabilitation plans and action guidance means building an interactive user interface using the modern front-end technology stack React.js;

[0118] Develop customized charts using the data visualization library D3.js to display rehabilitation plans, rehabilitation progress, and breast reconstruction data;

[0119] Patients can access after real-name authentication.

[0120] The user interface developed with React.js is not only responsive but also user-friendly, ensuring a smooth experience for patients when querying and interacting. React's componentized architecture allows developers to efficiently build and maintain complex user interfaces and adapt to rapidly changing needs, such as real-time updating of rehabilitation program information. Charts developed with D3.js can accurately display all aspects of the rehabilitation program, including rehabilitation progress and breast reconstruction data. These charts use dynamic visualization methods to enable patients to intuitively understand their rehabilitation progress and related health data, so that they can better follow rehabilitation plans and adjust their lifestyles. Patients undergo real-name authentication before using the system. This measure ensures the security of data access and the protection of personal privacy. Through real-name authentication, the system can ensure that only authorized users can access their personal sensitive data to prevent data abuse or leakage.

[0121] Furthermore, storing the breast reconstruction data generated by the collection and analysis means storing the breast reconstruction data generated by the collection and analysis in a database, implementing data security protection measures, backing up the breast reconstruction data in the cloud, and regularly performing integrity checks on active data and backup data.

[0122] Storing all data related to breast reconstruction in a specially designed database not only facilitates data management and query, but also ensures data security and integrity through various functions provided by the database management system. The application of the database allows data to be stored in a structured manner, facilitates complex query and analysis, and improves the efficiency and accuracy of data use. Encryption measures ensure that only authorized users can access sensitive data to prevent data leakage or illegal access. Through encryption technology, even if the data is illegally obtained, it cannot be interpreted, thereby protecting the confidentiality of the data. Backing up the data to the cloud provides redundancy for data storage and enhances the data's disaster resistance and recovery capabilities. The advantage of cloud backup is that it provides flexible scalability and low maintenance costs, while ensuring that data can be restored at any location. By regularly performing integrity checks on active data and backup data, any abnormal changes or damage to the data can be discovered in a timely manner. This step is the key to ensuring long-term secure storage of data and helps maintain data accuracy and reliability.

Claims

1. A full-cycle nursing simulation training system for breast reconstruction patients, characterized by: include, The acquisition and planning module is used to collect breast reconstruction data and build a support vector machine (SVM) model to generate a rehabilitation plan; The guidance acquisition module is used to use AR to guide the breast reconstruction patient's movements, and the patient enters personal information to obtain the breast reconstruction rehabilitation plan; The rehabilitation module collects patients’ real-time breast reconstruction data to generate a comprehensive rehabilitation plan; Adjust the encryption module to collect patient feedback for adjustment and implement secure encryption for transmitted data; The visual storage module is used to display the patient's rehabilitation plan and action guidance in real time, and to store, collect and analyze the breast reconstruction data generated.

2. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 1, characterized in that: The breast reconstruction data collection refers to the use of the automated literature crawling tool Python to obtain text data from medical databases, clinical trial databases, and guidelines published by rehabilitation professional organizations; Text preprocessing of the collected text data includes data cleaning, standardization and outlier processing; Apply natural language processing technology NLP and use TF-IDF algorithm to extract text from preprocessed text data, including the patient's age, surgery details, rehabilitation progress, and medical indicator information. The formula is: TF-IDF(c,d)=TF(c,d)×IDF(c), Where c is a term, d is a document, TF(c,d) is the frequency of term c in document d, and IDF(c) is the inverse document frequency; Data integration was performed on the preprocessed literature data and the extracted information to obtain comprehensive breast reconstruction data; The combined breast reconstruction data were normalized.

3. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 2, characterized in that: The construction of the support vector machine (SVM) model to generate a rehabilitation plan refers to collecting historical text data for preprocessing, extraction, data integration and normalization to generate a data training set; Construct a support vector machine (SVM) model, including an input layer and a kernel function output layer; Define the input layer as normalized breast reconstruction data; Use RBF radial basis function as kernel function K(x i ,x), handle nonlinear relationships, the formula is: K(x i ,x)=exp(-γ‖x i -x‖ 2 ), Where γ is the parameter of the RBF kernel, x i and x are the input data; The decision output layer formula is: Where f(x) is the result predicted by the model, y i For data point x i The category label, b is the bias term, α i is the Lagrange multiplier, n is the total number of support vectors; Use the data training set to train the support vector machine (SVM) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters; The normalized breast reconstruction data were input into the trained support vector machine (SVM) model to obtain the classification results of the rehabilitation program. A rehabilitation plan is generated based on the classification results, including recommended rehabilitation activities, frequency, and duration.

4. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 3, characterized in that: The use of AR to guide the patient's movements during breast reconstruction refers to displaying 3D rehabilitation movements through AR smart glasses and using the camera on the AR smart glasses to capture the patient's actual movements; Computer vision technology is used to capture the patient's movements and compare them with the preset 3D rehabilitation movements in real time. The deviation between the patient's movements and the standard movements is calculated in real time. The formula is: Where S is the action score, P m is the position parameter of the preset 3D rehabilitation action, O m is the position parameter of the patient’s actual action, and M is the number of actions; According to the action score S, the action parts that need to be improved are provided through the AR smart glasses.

5. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 4, characterized in that: The patient inputting personal information to obtain a rehabilitation plan for breast reconstruction refers to generating a QR code for the patient, including the patient's information; The system automatically analyzes the patient's information and generates a rehabilitation plan through a trained machine learning model; The rehabilitation plan is automatically generated and sent to the patient via email.

6. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 5, characterized in that: The collecting of the patient's real-time breast reconstruction data to generate a comprehensive rehabilitation program refers to having the patient wear a smart bracelet to collect the patient's real-time breast reconstruction data and perform preprocessing and normalization; The principal component analysis (PCA) method is used to extract the features of the pre-processed real-time breast reconstruction data and generate real-time features. Collect historical patient breast reconstruction data and perform preprocessing and normalization, use principal component analysis (PCA) to extract the processed historical patient breast reconstruction data and generate a historical training set; Construct a convolutional neural network (CNN) model, including input layer, convolution layer, pooling layer, and fully connected output layer; Define the input layer as real-time features; Use the historical training set to train the convolutional neural network (CNN) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters; Input the real-time features into the trained convolutional neural network (CNN) model to obtain the prediction results; A rehabilitation plan is automatically generated based on the prediction results, and the newly generated rehabilitation plan is compared and integrated with the patient's existing rehabilitation plan to generate a comprehensive rehabilitation plan.

7. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 6, characterized in that: Collecting patient feedback for adjustment refers to collecting patient feedback data through hospital surveys, using data analysis tools to regularly analyze the feedback data, identifying problems and trends in the rehabilitation process, and generating analysis reports; The medical team holds regular meetings to discuss and decide on adjustments to the rehabilitation program based on feedback reports; Update the adjusted rehabilitation plan into the system and notify relevant patients and medical staff; Track the effectiveness of new initiatives after implementation.

8. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 7, characterized in that: The implementation of secure encryption for transmitted data refers to using a key management system to generate and manage keys; The breast reconstruction data generated by the analysis was encrypted with AES; Set access permissions and use authentication for access; For the encrypted breast reconstruction data, the decryption key is obtained from the key management system, and the encrypted data is decrypted using the AES decryption algorithm and the key to restore the original data.

9. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 8, characterized in that: The real-time display of the patient's rehabilitation plan and action guidance refers to building an interactive user interface using the modern front-end technology stack React.js; Develop customized charts using the data visualization library D3.js to display rehabilitation plans, rehabilitation progress, and breast reconstruction data; Patients can access after real-name authentication.

10. The full-cycle nursing simulation training system for breast reconstruction patients according to claim 9, characterized in that: Storing the breast reconstruction data generated by the collection and analysis refers to storing the breast reconstruction data generated by the collection and analysis in a database, implementing data security protection measures, backing up the breast reconstruction data in the cloud, and regularly performing integrity checks on active data and backup data.

Images