Intelligent peritoneal dialysis exit simulation training method and system

Abstract

The invention discloses an intelligent peritoneal dialysis exit simulation training method and system, and relates to the technical field related to medical teaching models.The method comprises the steps that historical training data of a user to be subjected to simulation training is obtained, and the simulation training category of the user is obtained through screening; according to the simulation training category, the outlet unit is replaced, and the secretion liquid control module is controlled to perform liquid secretion flow control; collecting a training image sequence when a user performs nursing training, performing training standard degree identification to obtain a training standard degree, and performing classification to obtain a training score; and updating the training score of the simulation training category into the database, and displaying the training score. The technical problem that in the prior art, a peritoneal dialysis training model can only simulate a normal exit and cannot effectively simulate a difficult exit, and consequently the training effect of nursing personnel is poor is solved, and the technical effects that the training effect is enhanced, and the ability of the nursing personnel to deal with complex situations is improved are achieved.

Description

Technical Field

[0001] This application relates to the technical field of medical teaching models, and particularly to an intelligent peritoneal dialysis exit simulation training method and system. Background Art

[0002] As an important renal replacement therapy method, peritoneal dialysis is widely used in the treatment of uremic patients. During the peritoneal dialysis process, the patient introduces dialysate into the abdominal cavity and performs dialysis through the peritoneum to remove metabolic wastes and excess water from the body. During peritoneal dialysis, the care of the dialysis catheter exit is crucial, directly related to the patient's health and quality of life. In reality, due to individual differences among patients and external environmental factors, various problems may occur at the peritoneal dialysis exit, such as difficult situations like redness and swelling, scabbing, polyp formation, and purulent secretion infection. Traditional training mainly relies on written descriptions and picture displays, lacking intuitiveness and practicality, and it is difficult to effectively train nurses and patients to identify and care for various abnormal conditions at the dialysis catheter exit. Moreover, most peritoneal dialysis training models use normal exits as simulation models and usually focus on basic nursing operations, lacking simulation of various difficult peritoneal dialysis exit situations, resulting in ineffective training for nursing staff and patients and their inability to effectively respond to various complex situations that may occur clinically.

[0003] In the current related technologies, there is a technical problem that peritoneal dialysis training models can only simulate normal exits and cannot effectively simulate difficult exits, resulting in poor training effects for nursing staff. Summary of the Invention

[0004] This application provides an intelligent peritoneal dialysis exit simulation training method and system, which solves the technical problem in the prior art that peritoneal dialysis training models can only simulate normal exits and cannot effectively simulate difficult exits, resulting in poor training effects for nursing staff, and achieves the technical effect of enhancing the training effect and improving the ability of nursing staff to handle complex situations.

[0005] This application provides an intelligent peritoneal dialysis exit simulation training method, including: obtaining the historical training data of a user to be subjected to simulation training, and screening to obtain the simulation training category of the user, where the simulation training category includes an exit unit and the secretion liquid flow rate; according to the simulation training category, replacing the exit unit and controlling the secretion liquid control module to perform liquid secretion flow rate control; collecting the training image sequence when the user conducts nursing training, performing training standard recognition to obtain the training standard, and classifying to obtain the training score; updating the training score of the simulation training category to the database and displaying it.

[0006] In a possible implementation manner, the intelligent peritoneal dialysis exit simulation training method further performs the following processing: obtaining historical training data of a user to be subjected to simulation training, where the historical training data includes multiple historical training scores of multiple sample simulation training categories, and each sample simulation training category includes a combination of an exit unit and a secreted liquid flow rate; screening, according to the multiple historical training scores, to obtain a simulation training category for the current user to perform simulation training.

[0007] In a possible implementation manner, the intelligent peritoneal dialysis exit simulation training method further performs the following processing: determining whether there is a missing historical training score for the user, and if so, randomly selecting a sample simulation training category within the sample simulation training category corresponding to the missing historical training score as the simulation training category for the current user to perform simulation training; if not, selecting the sample simulation training category corresponding to the lowest historical training score as the simulation training category for the current user to perform simulation training.

[0008] In a possible implementation manner, the intelligent peritoneal dialysis exit simulation training method further performs the following processing: collecting images during the nursing training of the user under the simulation training category and arranging them according to the collection timestamps to obtain a training image sequence; preprocessing the training image sequence and performing training standardization recognition to obtain a training standardization degree.

[0009] In a possible implementation manner, the intelligent peritoneal dialysis exit simulation training method further performs the following processing: using a convolutional neural network to construct a training standardization recognition channel, where the training standardization recognition channel includes multiple training standardization recognition paths corresponding to multiple sample simulation training categories; inputting the training image sequence into the training standardization recognition path corresponding to the simulation training category to identify and obtain the training standardization degree.

[0010] In a possible implementation manner, the intelligent peritoneal dialysis exit simulation training method further performs the following processing: collecting multiple sample training image sequence sets according to the historical training data records of the multiple sample simulation training categories, and performing training standardization annotation on each sample training image sequence to obtain multiple sample training standardization degree sets; using a convolutional neural network to construct a network architecture of the multiple training standardization recognition paths; respectively using the multiple sample training image sequence sets and the multiple sample training standardization degree sets as input features and output features to perform supervised training on the multiple training standardization recognition paths until the training verification converges; integrating the multiple training standardization recognition paths to obtain a training standardization recognition channel.

[0011] In a possible implementation manner, the intelligent peritoneal dialysis exit simulation training method further performs the following processing: obtaining a set of sample training standard degrees, and constructing a mapped set of sample training scores, where the magnitudes of the training standard degree and the training score are positively correlated; constructing a score classifier according to the set of sample training standard degrees and the set of sample training scores; inputting the training standard degree into the score classifier, and obtaining a training score through mapped assignment.

[0012] This application also provides an intelligent peritoneal dialysis exit simulation training system, including: a simulation training category obtaining module, configured to obtain historical training data of a user to be subjected to simulation training, and filter to obtain the simulation training category of the user, where the simulation training category includes an exit unit and a secreted liquid flow rate; a liquid secretion flow rate control module, configured to replace the exit unit according to the simulation training category, and control the secreted liquid control module to perform liquid secretion flow rate control; a training standard degree identification module, configured to collect a sequence of training images when the user conducts nursing training, perform training standard degree identification, obtain a training standard degree, and classify to obtain a training score; a training score update module, configured to update the training score of the simulation training category to a database and display it.

[0013] It is intended to obtain historical training data of a user to be subjected to simulation training through an intelligent peritoneal dialysis exit simulation training method and system provided by this application, and filter to obtain the simulation training category of the user; replace the exit unit according to the simulation training category, and control the secreted liquid control module to perform liquid secretion flow rate control; collect a sequence of training images when the user conducts nursing training, perform training standard degree identification, obtain a training standard degree, and classify to obtain a training score; update the training score of the simulation training category to a database and display it. This solves the technical problem in the prior art that the peritoneal dialysis training model can only simulate normal exits and cannot effectively simulate difficult exits, resulting in poor training effects for nursing staff, and achieves the technical effect of enhancing the training effect and improving the ability of nursing staff to handle complex situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be precisely executed in sequence. On the contrary, according to needs, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps of operations can be removed from these processes.

[0015] Figure 1 It is a schematic flowchart of an intelligent peritoneal dialysis exit simulation training method provided by an embodiment of this application.

[0016] Figure 2 This is a schematic structural diagram of an intelligent peritoneal dialysis exit simulation training system provided by an embodiment of the present application.

[0017] Explanation of the reference numerals in the drawings: Simulation training category acquisition module 10, liquid secretion flow control module 20, training standard recognition module 30, training score update module 40. Specific implementation manners

[0018] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific implementation manners of the present application are specifically exemplified below.

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0020] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first" and "second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, systems, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0021] An embodiment of the present application provides an intelligent peritoneal dialysis exit simulation training method, as Figure 1 shown. The method is applied to an intelligent peritoneal dialysis exit simulation model, and the model includes a model body and a variety of exit units. A secretion liquid control module is arranged in the model body. The method includes:

[0022] Specifically, the intelligent peritoneal dialysis exit simulation model refers to a simulation model that mimics the exit site during peritoneal dialysis and serves as a realistic and interactive training tool for peritoneal dialysis caregivers. Without involving real patients, the intelligent peritoneal dialysis exit simulation model can reproduce various operations, failures, and abnormal conditions of the peritoneal dialysis exit through simulation technology, helping caregivers to train and operate in a virtual environment, enhancing their skills and emergency response capabilities. It includes a model body and multiple exit units. Among them, the model body refers to the main body of the entire simulation model, with an interactive and operable physical structure that can simulate the shape and material of the peritoneal dialysis exit and can simulate different types of peritoneal dialysis exits (i.e., multiple exit units, each exit unit simulating the state of the peritoneal dialysis exit under different conditions), such as the conventional peritoneal dialysis exit site and difficult exit sites (such as red and swollen exits, scabbed exits, purulent secretion-infected exits, polyp exits, etc.); a secreted liquid control module is set inside the model body, which can simulate the inflow and outflow of liquid during peritoneal dialysis. The secreted liquid control module can precisely control the secretion flow rate and velocity of the dialysate and simulate the flow state of the liquid at the exit (such as clear or purulent liquid), so as to provide a realistic operation experience and help users conduct nursing training under different conditions in the simulation environment. Through the intelligent peritoneal dialysis exit simulation model, caregivers can practice operations in a risk-free environment, improve their ability to handle different peritoneal dialysis exit problems, and thus improve the nursing level and clinical operation safety.

[0023] Step S100, obtain the historical training data of the user to be subjected to simulation training, and screen to obtain the simulation training category of the user, where the simulation training category includes an exit unit and a secreted liquid flow rate.

[0024] Preferably, collect and analyze the past training records of users to be trained through simulation (such as nursing staff or patients undergoing peritoneal dialysis). The historical training data may include information such as the training courses the user has participated in, the training duration, and the skills mastered; the operations and performances of the user in previous simulation trainings, such as whether there were incorrect operations and how to handle difficult problems; data such as the scores, evaluations, and feedback of the user in the training; whether the user has had special needs or situations (such as dealing with special peritoneal dialysis exit problems), etc. Then, automatically screen the simulation training categories for the user based on the historical training data, that is, screen out the training content suitable for the user. The simulation training categories include the exit unit and the secreted liquid flow rate. Among them, the exit unit refers to different types of peritoneal dialysis exit simulation models. According to the training needs or experience level of the user, select a suitable exit unit for simulation. For example, if the user has ever dealt with a purulent infection exit situation, recommend a relevant exit unit for deeper training based on the historical training data; if the user's training is relatively basic, recommend simulating a normal ordinary exit. The secreted liquid flow rate refers to parameters such as the rate and flow of liquid inflow and outflow during the simulation process. Adjust the secreted liquid flow rate according to the user's experience or training needs to simulate the peritoneal dialysis process under different flow rates. For example, if the user is already familiar with the operation of normal flow rates, more complex situations can be set, such as a decrease in liquid flow rate (which may be related to exit problems) or unstable liquid flow rate, etc., to enhance the user's coping ability. Based on the screening of the user's historical training data, the training content for each user can be more customized. Different users can obtain different combinations of exit units and liquid flow rates according to their training progress, experience, skills, etc., to maximize the training effect and improve the operation ability, so as to ensure that users can obtain simulation training that matches their skill level and training needs during the training process, thereby effectively improving the learning efficiency and training effect of users.

[0025] Further, step S100 further includes step S110 of obtaining the historical training data of the user to be trained through simulation, where the historical training data includes multiple historical training scores of multiple sample simulation training categories, and each sample simulation training category includes a combination of an exit unit and a secreted liquid flow rate; step S120 of screening the simulation training category for the current user to be trained through simulation based on the multiple historical training scores.

[0026] Preferably, by analyzing historical training data, especially simulation training scores of different categories, to determine the simulation training content suitable for the current user. Specifically, the historical training data contains the simulation training records of multiple users in the past. The sample simulation training categories refer to the classification based on different simulation training contents. Each sample simulation training category includes the combination of the outlet unit and the secreted liquid flow rate. Each record includes simulation training scores of different categories, reflecting the training effect or performance of the user in that category. By analyzing the historical training score data, based on the user's historical performance, training objectives, and the correlation of historical scores, select the category relevant to the current user's training needs, that is, the most suitable simulation training category for the current user to conduct, to help the user conduct more personalized and accurate simulation training according to their own historical training performance and needs, thereby improving the training effect and efficiency.

[0027] Further, step S120 further includes step S121, determining whether there are missing historical training scores for the user. If so, randomly select a sample simulation training category within the sample simulation training category corresponding to the missing historical training scores as the simulation training category for the current user to conduct simulation training; step S122, if not, select the sample simulation training category corresponding to the lowest historical training score as the simulation training category for the current user to conduct simulation training.

[0028] Preferably, determining whether there are missing historical training scores for the user, that is, in the user's historical training data, the scores of some simulation training categories are not recorded, indicating that the user has not conducted corresponding simulation training in some training categories, or for some reason, the score data of this category fails to be collected. Specifically, check the user's historical training score records to determine whether there is a lack of scores for one or more simulation training categories. If there are missing historical training scores, randomly select one from the simulation training categories corresponding to the missing scores as the next simulation training category for the current user to ensure that the user receives comprehensive training; if there are no missing historical training scores, that is, the historical training scores are complete and there are no gaps, select the category corresponding to the lowest score among all the user's historical training categories as the category for the current user to conduct simulation training. The lowest score reflects that the user's performance in this category is weak or the skills are not proficient enough. Through further training in this category, help the user improve the skills in this aspect, and then ensure that the user can obtain balanced learning throughout the training process, not only filling the past training gaps but also conducting additional intensive training in the area with the worst performance.

[0029] Step S200, according to the simulation training category, replace the outlet unit, and control the secreted liquid control module to conduct liquid secretion flow rate control.

[0030] Preferably, the components of the simulation model are adjusted according to the simulation training category (i.e., according to the user's training needs), including replacing the outlet unit and controlling the secretion liquid control module to control the liquid secretion flow rate, that is, simulating different peritoneal dialysis outlet conditions and precisely controlling the liquid flow according to these conditions. Specifically, the outlet unit in the model is replaced according to the selected training category to simulate different peritoneal dialysis outlets. For example, a certain type of training needs to simulate a normal outlet (i.e., a conventional outlet without any complications), while another type of training needs to simulate a complex outlet (such as abnormal conditions like purulent secretions, redness, swelling, scabbing, etc.), so as to help the trainer cope with different peritoneal dialysis care challenges and improve their adaptability to complex clinical situations; according to the requirements of the simulation training category, the secretion volume and flow rate of the liquid can also be adjusted through the secretion liquid control module, that is, the liquid flow volume can be adjusted according to different training scenarios (such as normal flow or abnormal conditions with different flow rates), including normal flow. For example, when there is no abnormality at the outlet, the normal inflow and outflow of the liquid are simulated, and abnormal flow, such as when there is redness, swelling, purulent secretions, etc. at the outlet, the flow rate may decrease or change irregularly. By simulating this change, the training personnel can adapt to the situation of unstable liquid flow rate, helping the training personnel to conduct efficient simulation and training in various peritoneal dialysis scenarios that may occur in the real world, and further improving the user's operation skills and the ability to cope with various peritoneal dialysis problems.

[0031] Step S300, collect the training image sequence when the user conducts the nursing training, perform training standard degree recognition, obtain the training standard degree, and classify to obtain the training score.

[0032] Preferably, during the intelligent peritoneal dialysis exit simulation training, by collecting the training image sequence of the user during the nursing training, analyzing the actual performance of the user's operation, and generating a quantitative evaluation result. Specifically, using a camera, sensor or other device, during the process of the user's nursing training operation, collect relevant operation images or video data in real time from different angles to comprehensively capture the user's operation process. The training image sequence can include the user's hand movements, operation procedures, tool usage, nursing steps, etc. Then, use image recognition, artificial intelligence or pattern matching to analyze the user's action characteristics (such as speed, angle, strength, etc.), compare the collected image sequence with the pre-stored standard operation process and standard image data, identify whether the user's operation meets the specifications, and judge whether the expected training requirements are met. For example, whether the user's actions are correct when dealing with liquid secretion control, whether the steps are standardized when replacing the exit unit, and whether the safety requirements are followed during the nursing process, etc. Then, quantify the deviation degree between the user's actual operation and the standard requirements according to the comparison and judgment results to obtain the training standard degree. For example, if the user's operation completely meets the standard, the training standard degree is 100%, if there are some step deviations or errors, the standard degree may decrease, and a specific training standard degree is given according to the deviation degree. Finally, classify the user's performance according to the training standard degree to obtain a training score. For example, excellent (standard degree 90% - 100%) indicates that the user's operation meets the standard, qualified (standard degree 75% - 89%) indicates that the user's operation basically meets the standard with minor deviations, and unqualified (standard degree below 75%) indicates that the user's operation has obvious deviations or errors, such as a certain operation action being too fast, liquid flow control being inadequate, etc. By classifying and scoring, clarify the advantages and disadvantages of the user's operation, provide feedback and improvement suggestions, so as to improve the training efficiency and effect.

[0033] Further, step S300 further includes step S310, collecting the images of the user during the nursing training under the simulation training category and arranging them according to the collection timestamp to obtain a training image sequence; step S320, preprocessing the training image sequence to perform training standard degree recognition to obtain the training standard degree.

[0034] Preferably, when the user performs an operation of a certain simulation training category (such as normal exit care, infection exit care, etc.), the operation images of the user are recorded in real time from multiple angles through cameras or high-resolution sensors installed around the simulation model (such as the user's hand movements, care processes, and interaction details with the simulation model), including the user's specific operation steps (such as replacing the exit unit, adjusting the liquid flow rate) and related detailed actions (such as gestures, strength, movement trajectories, etc.), which are used to analyze whether the user's actions are standardized and whether the operations meet the standards. Each captured image will carry an accurate timestamp to record the time when the image is generated. The images are arranged according to the timestamps to form a training image sequence, that is, a continuous image stream organized in chronological order, completely recording the entire process of the user's operation; through image preprocessing, irrelevant information or interference factors in the training images are removed, mainly including image denoising, using filtering techniques to eliminate noise in the images and improve image clarity; image cropping, cropping the key information areas in the images (such as the user's hand movement and exit model areas) to remove the redundant background; image enhancement, adjusting the brightness, contrast, etc. of the images to make the operation details more prominent; image feature extraction, extracting key points or features in the operation process (such as finger positions, tool usage, etc.); finally, according to the captured training image sequence, it is analyzed whether the user's operation meets the standardized process of the training, that is, by comparing with the standard action model, the accuracy, standardization, and proficiency of the user in the operation process are evaluated. Specifically, using action recognition algorithms, the key actions in the image sequence are analyzed, and the characteristic data of the user's operation (such as action trajectories, gesture angles, strength) are extracted. The extracted operation features are compared with the preset standard operation model to identify the deviation between the user's operation and the standard operation. According to the number and severity of the deviations, the standard degree of the user's operation is quantified, and then the training standard degree is obtained, providing feedback on the user's operation performance and improvement suggestions, which helps the user improve their nursing skills.

[0035] Further, step S320 further includes step S321, using a convolutional neural network to construct a training standard degree recognition channel, where multiple training standard degree recognition paths corresponding to various sample simulation training categories are included in the training standard degree recognition channel; step S322, inputting the training image sequence into the training standard degree recognition path corresponding to the simulation training category to identify and obtain the training standard degree.

[0036] Preferably, a convolutional neural network (CNN) and a multi-path recognition model are used to analyze the operation standardization of users, so as to evaluate their training standard degree under specific simulation training categories. Specifically, the convolutional neural network (CNN) is a deep learning algorithm that is good at processing image data, especially suitable for extracting image features and identifying patterns. It is used to analyze the operation image sequence of users, identify the action features therein and compare them with the standard model to evaluate the operation standardization of users. A training standard degree recognition channel is constructed using the convolutional neural network to evaluate the operation performance of users during the training process. The purpose is to process the input image sequence layer by layer, extract key features (such as action trajectories, gesture angles, etc.), and classify or score them, and finally output the training standard degree of users. Among them, the training standard degree recognition channel includes multiple training standard degree recognition paths corresponding to various sample simulation training categories. Specifically, in order to adapt to different simulation training categories (such as normal exit care, infection exit care, scab exit care, and liquid flow adjustment), each category requires a different recognition path to obtain multiple training standard degree recognition paths. In each path, the convolutional neural network (CNN) extracts the image sequence features of users according to the operation standards and action models of the corresponding category, processes them layer by layer, and finally identifies the training standard degree of this category. The collected user operation image sequence (after preprocessing) is used as the input and fed into the corresponding recognition path frame by frame. According to the current simulation training category, the corresponding standard degree recognition path is automatically selected. The features in the image are extracted through multiple convolutional layers and pooling layers, such as the direction of gestures, the speed of actions, the position of operations, etc. These features are compared with the standard model to obtain the deviation situation and training standard degree of users, reflecting the operation standardization of users, so as to improve the comprehensiveness of user skills and training effects.

[0037] Furthermore, step S321 further includes step A: according to the historical training data records of the various sample simulation training categories, collect multiple sample training image sequence sets, and label the training standard degree for each sample training image sequence to obtain multiple sample training standard degree sets; step B: use a convolutional neural network to construct the network architecture of the multiple training standard degree recognition paths; step C: respectively use the multiple sample training image sequence sets and multiple sample training standard degree sets as input features and output features to perform supervised training on the multiple training standard degree recognition paths until the training verification converges; step D: integrate the multiple training standard degree recognition paths to obtain a training standard degree recognition channel.

[0038] Preferably, from the historical training data records of various sample simulation training categories, the operation image sequences of the user under various simulation training categories are collected, that is, a set of multiple sample training image sequences, which record the actual operation process of the user, including different types of nursing scenarios, covering various common operation situations, such as standard operations, non-standard operations, and operations with minor or serious deviations. Then, the training standard degree corresponding to each sample image sequence is labeled to obtain a corresponding set of multiple sample training standard degrees. Then, a network architecture with multiple training standard degree recognition paths is constructed based on a convolutional neural network. Specifically, according to different simulation training categories (such as "normal exit care" or "infection exit care"), multiple independent convolutional neural network recognition paths are designed. Each recognition path includes modules such as a convolutional layer, a pooling layer, and a fully connected layer, which are used to extract the action features in the image sequence. Then, with the set of sample training image sequences as the input features and the set of sample training standard degrees as the output features, the multiple training standard degree recognition paths are supervised and trained, including inputting the image sequence to extract features layer by layer, comparing with the standard degree annotation and calculating the error until the training verification converges (such as the error drops to the lowest and tends to be stable), indicating that the recognition path already has good recognition ability. Finally, the multiple trained training standard degree recognition paths are integrated to form a training standard degree recognition channel, which can select the corresponding recognition path according to the simulation training category of the input data and output the standard degree evaluation result, comprehensively realizing the intelligent and accurate training evaluation function and improving the user's skill level.

[0039] Further, step S300 further includes step S330 of obtaining a set of sample training standard degrees and constructing a mapped set of sample training scores, where the size of the training standard degree is positively correlated with the training score; step S340 of constructing a score classifier according to the set of sample training standard degrees and the set of sample training scores; and step S350 of inputting the training standard degree into the score classifier to obtain a training score through mapping and assignment.

[0040] Preferably, a mapped sample training score set is constructed according to the sample training standardization set, that is, the standardization data is mapped to the corresponding training score through a linear function to obtain the sample training score set. Among them, the training score is an index for quantitatively evaluating the user's performance, which is associated with the standardization and is used to more intuitively reflect the user's comprehensive performance. The size of the training standardization and the training score is positively correlated, indicating that the higher the standardization, the higher the training score. Then, a classification model is constructed based on a machine learning model (such as linear regression, decision tree, random forest, or support vector machine, etc.). Using the sample training standardization set as the input feature and the sample training score set as the target label, the classification model is trained to obtain a score classifier that can map the input training standardization to the training score. Finally, the training standardization is input into the score classifier, and through the mapping rule of the classifier, the corresponding training score is calculated. The mapped score is used as the user's training result, stored in the database and provided for the user to view, realizing the accurate calculation from the user's operation standardization to the final training score, thereby providing a clear and reliable score result for the user, helping to take corresponding measures to improve the training effect.

[0041] Step S400: Update the training score of the simulation training category to the database and display it.

[0042] Preferably, the training performance and score result of the user's simulation training category are updated and stored in the database and presented in a visual form. Specifically, the training score is the result obtained by quantitatively evaluating the user's operation performance (such as nursing techniques, liquid secretion control, etc.) in the simulation training category, such as excellent, qualified, unqualified. Then, the user's score result together with relevant information (such as user identity, training time, simulation category, specific scoring items, etc.) is uploaded to the database and stored in a structured form to ensure efficient retrieval and analysis of the data. It is visually displayed to allow users or administrators to intuitively understand the training result, identify deficiencies and formulate improvement plans, and at the same time conduct an overall evaluation of the training effect. Users and managers can access and view the score data through the computer terminal or mobile terminal to ensure the transparency and usability of the score information, which helps to improve the user's training and learning effect.

[0043] In the above text, with reference to Figure 1 A method for intelligent peritoneal dialysis exit simulation training according to an embodiment of the present invention is described in detail. Next, with reference to Figure 2 A system for intelligent peritoneal dialysis exit simulation training according to an embodiment of the present invention will be described.

[0044] An intelligent peritoneal dialysis exit simulation training system according to an embodiment of the present invention is used to solve the technical problem in the prior art that the peritoneal dialysis training model can only simulate normal exits and cannot effectively simulate difficult exits, resulting in poor training effects for nursing staff, and achieves the technical effect of enhancing the training effect and improving the ability of nursing staff to cope with complex situations. As Figure 2 shown, an intelligent peritoneal dialysis exit simulation training system includes: a simulation training category acquisition module 10, a liquid secretion flow control module 20, a training standard recognition module 30, and a training score update module 40.

[0045] The simulation training category acquisition module 10 is used to obtain the historical training data of a user to be subjected to simulation training, and screen to obtain the simulation training category of the user. Among them, the simulation training category includes an exit unit and a secreted liquid flow rate; the liquid secretion flow control module 20 is used to replace the exit unit according to the simulation training category, and control the secreted liquid control module to perform liquid secretion flow control; the training standard recognition module 30 is used to collect the training image sequence when the user conducts nursing training, perform training standard recognition, obtain the training standard, and classify to obtain the training score; the training score update module 40 is used to update the training score of the simulation training category to the database and display it.

[0046] Next, the specific configuration of the simulation training category acquisition module 10 will be described in detail. The simulation training category acquisition module 10 may further include: a historical training data acquisition unit, which is used to obtain the historical training data of a user to be subjected to simulation training. Among them, the historical training data includes multiple historical training scores of multiple sample simulation training categories, and each sample simulation training category includes a combination of an exit unit and a secreted liquid flow rate; a simulation training category screening and acquisition unit, which is used to screen and obtain the simulation training category for the current user to conduct simulation training according to the multiple historical training scores.

[0047] Next, the specific configuration of the simulation training category acquisition module 10 will be described in further detail. The simulation training category acquisition module 10 may further include: a historical training score judgment unit, which is used to judge whether there is a missing historical training score for the user. If so, randomly select a sample simulation training category within the sample simulation training category corresponding to the missing historical training score as the simulation training category for the current user to conduct simulation training; the sample simulation training category selection unit is used to, if not, select the sample simulation training category corresponding to the lowest historical training score as the simulation training category for the current user to conduct simulation training.

[0048] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the protection scope of this application. In some cases, the actions or steps recorded in this application can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An intelligent peritoneal dialysis outlet simulation training method, characterized in that: The method is applied to an intelligent peritoneal dialysis outlet simulation model, the model comprising a model body and a plurality of outlet units, the model body being provided with a secretion liquid control module, the method comprising: Acquire historical training data of a user to be subjected to simulation training, and filter to obtain a simulation training category of the user, wherein the simulation training category includes an outlet unit and a secretion liquid flow rate; According to the simulation training category, replacing the outlet unit, and controlling the secretion liquid control module to control the liquid secretion flow rate; Collecting a training image sequence of the user during nursing training, performing training standard degree recognition, obtaining the training standard degree, and classifying to obtain a training score; The training score of the simulation training category is updated in the database and displayed.

2. The intelligent peritoneal dialysis outlet simulation training method according to claim 1, characterized in that: Obtain historical training data of the user to be trained in simulation, and filter to obtain the simulation training category of the user, including: Acquiring historical training data of a user to be subjected to simulation training, wherein the historical training data includes a plurality of historical training scores of a plurality of sample simulation training categories, each of which includes a combination of an outlet unit and a secretion liquid flow rate; According to the multiple historical training scores, the simulation training category for the current user to perform simulation training is obtained by screening.

3. The intelligent peritoneal dialysis outlet simulation training method according to claim 2, characterized in that: According to the multiple historical training scores, the simulation training category for the current user to perform simulation training is obtained by screening, including: Determine whether the user has any missing historical training scores, and if so, randomly select a sample simulation training category from the sample simulation training categories corresponding to the missing historical training scores as the simulation training category for the current user to perform simulation training; If not, the sample simulation training category corresponding to the lowest historical training score is selected as the simulation training category for the current user to perform simulation training.

4. The intelligent peritoneal dialysis outlet simulation training method according to claim 1, characterized in that: Collecting a training image sequence when the user is undergoing nursing training, performing training standard degree recognition, and obtaining the training standard degree, including: Collecting images of the user during nursing training under the simulation training category, and arranging them according to acquisition timestamps to obtain a training image sequence; The training image sequence is preprocessed, and the training standard degree is identified to obtain the training standard degree.

5. The intelligent peritoneal dialysis outlet simulation training method according to claim 4, characterized in that: Conduct training standard identification and obtain training standard, including: A convolutional neural network is used to construct a training standard degree recognition channel, wherein the training standard degree recognition channel includes a plurality of training standard degree recognition paths corresponding to a plurality of sample simulation training categories; The training image sequence is input into a training standard degree recognition path corresponding to the simulation training category to identify and obtain the training standard degree.

6. The intelligent peritoneal dialysis outlet simulation training method according to claim 5, characterized in that: Using convolutional neural networks, we build a training standard recognition channel, including: According to the historical training data records of the multiple sample simulation training categories, multiple sample training image sequence sets are collected, and each sample training image sequence is labeled with a training standard degree to obtain multiple sample training standard degree sets; Using a convolutional neural network, constructing a network architecture of the plurality of training standard recognition paths; Using the plurality of sample training image sequence sets and the plurality of sample training standard degree sets as input features and output features respectively, and performing supervised training on the plurality of training standard degree recognition paths until the training verification converges; The multiple training standard degree recognition paths are integrated to obtain a training standard degree recognition channel.

7. The intelligent peritoneal dialysis outlet simulation training method according to claim 1, characterized in that: The classifications receive training scores, including: Obtain a sample training standard degree set and construct a mapped sample training score set, wherein the training standard degree and the training score are positively correlated; Constructing a scoring classifier according to the sample training standard set and the sample training scoring set; The training criteria are input into the scoring classifier and the mapping assignments are obtained to obtain training scores.

8. An intelligent peritoneal dialysis outlet simulation training system, characterized in that: The system is used to implement an intelligent peritoneal dialysis outlet simulation training method according to any one of claims 1 to 7, and the system comprises: A simulation training category acquisition module, used to acquire historical training data of a user to be subjected to simulation training, and screen and obtain the simulation training category of the user, wherein the simulation training category includes an outlet unit and a secretion liquid flow rate; A liquid secretion flow control module, used to replace the outlet unit according to the simulation training category, and control the secretion liquid control module to perform liquid secretion flow control; A training standard degree recognition module is used to collect a training image sequence when the user is undergoing nursing training, perform training standard degree recognition, obtain training standard degrees, and classify and obtain training scores; The training score updating module is used to update the training score of the simulation training category into the database and display it.

9. The intelligent peritoneal dialysis outlet simulation training system according to claim 8, characterized in that: The simulation training category acquisition module includes: A historical training data acquisition unit, used to acquire historical training data of a user to be subjected to simulation training, wherein the historical training data includes a plurality of historical training scores of a plurality of sample simulation training categories, each of which includes a combination of an outlet unit and a secretion liquid flow rate; The simulation training category screening and obtaining unit is used to screen and obtain the simulation training category for the current user to perform simulation training according to the multiple historical training scores.

10. The intelligent peritoneal dialysis outlet simulation training system according to claim 9, characterized in that: The simulation training category acquisition module also includes: A historical training score judgment unit is used to judge whether the user has a vacant historical training score, and if so, randomly select a sample simulation training category from the sample simulation training categories corresponding to the vacant historical training score as the simulation training category for the current user to perform simulation training; The sample simulation training category selection unit is used to, if not, select the sample simulation training category corresponding to the lowest historical training score as the simulation training category for the current user to perform simulation training.

Images