A data analysis-based pelvic floor muscle rehabilitation training management system and method

Abstract

This disclosure relates to a data analysis-based pelvic floor muscle rehabilitation training management system and method. It involves acquiring pelvic floor muscle rehabilitation training data from patients undergoing initial training tasks, conducting comparative analysis based on this data, and further optimizing the initial training tasks for these patients based on the analysis results. This optimized training task, combined with the optimized training task and the comparative analysis results, allows for the development of new training tasks for these patients. This technical solution manages patients through a control group approach and optimizes their training tasks through comparative data analysis, enabling effective and flexible management of pelvic floor muscle rehabilitation training tasks and improving the patients' pelvic floor muscle rehabilitation training experience.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more specifically, to a data analysis-based pelvic floor muscle rehabilitation training management system and method. Background Technology

[0002] Pelvic floor muscle rehabilitation training is an important rehabilitation method, mainly used to prevent and treat pelvic floor dysfunction disorders such as urinary incontinence and pelvic organ prolapse. Pelvic floor muscle rehabilitation training management techniques are a management approach for pelvic floor muscle rehabilitation training. By effectively managing pelvic floor muscle rehabilitation training, the effectiveness of the training can be improved, thereby enhancing the patient's rehabilitation experience.

[0003] Currently, the management of pelvic floor muscle rehabilitation training can be achieved by configuring corresponding management applications. For example, patent CN115602285A describes a pelvic floor muscle rehabilitation training information management system, which can effectively manage various related data involved in pelvic floor muscle rehabilitation training. However, this management system mainly focuses on designing various flexible management functions but lacks effective data analysis methods, thus failing to achieve effective and flexible management of patients' training tasks. Summary of the Invention

[0004] The purpose of this disclosure is to provide a data analysis-based pelvic floor muscle rehabilitation training management system and method, which can effectively and flexibly manage patients' pelvic floor muscle rehabilitation training tasks, thereby improving patients' pelvic floor muscle rehabilitation training experience.

[0005] To achieve the above objectives, in a first aspect, this disclosure provides a data analysis-based method for managing pelvic floor muscle rehabilitation training, comprising: acquiring pelvic floor muscle rehabilitation training data obtained by patients under control management using an original training task, wherein the patients under control management include at least two patients who meet preset control management conditions; performing a comparative analysis on the pelvic floor muscle rehabilitation training data corresponding to the patients under control management to obtain comparative analysis results; optimizing the original training task of the patients under control management based on the comparative analysis results to obtain an optimized training task; determining a new training task based on the comparative analysis results and the optimized training task, and feeding back the new training task to the patients under control management so that the patients under control management can use the new training task for pelvic floor muscle rehabilitation training.

[0006] Optionally, the pelvic floor muscle rehabilitation training management method further includes: acquiring patient information and original training tasks corresponding to multiple patients, wherein the original training tasks are training tasks formulated by doctors for patients; determining at least two patients from the multiple patients who meet preset control management conditions based on the patient information and original training tasks corresponding to the multiple patients, wherein the preset control management conditions include conditions related to the training tasks and conditions related to the patient information; identifying the at least two patients as the patients to be managed under control; acquiring pelvic floor muscle rehabilitation training data obtained by the patients to be managed under control using the original training tasks includes: feeding back the original training tasks corresponding to the patients to be managed under control to the patients to be managed under control, so that the patients to be managed under control can use the original training tasks to perform pelvic floor rehabilitation training; and receiving pelvic floor muscle rehabilitation training data uploaded by the patients to be managed under control or pelvic floor muscle rehabilitation training personnel.

[0007] Optionally, the pelvic floor muscle rehabilitation training data includes first pelvic floor muscle contraction data collected during the pelvic floor muscle rehabilitation training of the patients under control using the original training task, and second pelvic floor muscle contraction data collected after the patients under control complete the pelvic floor muscle rehabilitation training using the original training task. The step of performing a comparative analysis on the pelvic floor muscle rehabilitation training data corresponding to the patients under control to obtain the comparative analysis results includes: determining first control pelvic floor muscle contraction data from the first pelvic floor muscle contraction data corresponding to each of the at least two patients; determining second control pelvic floor muscle contraction data from the second pelvic floor muscle contraction data corresponding to each of the at least two patients; determining third control pelvic floor muscle contraction data corresponding to each of the at least two patients from the first and second pelvic floor muscle contraction data corresponding to each of the at least two patients; for any one of the at least two patients, determining the predicted training effect corresponding to that patient using a pre-trained prediction model based on the first control pelvic floor muscle contraction data, the second control pelvic floor muscle contraction data, and the third control pelvic floor muscle contraction data corresponding to that patient; and determining the comparative analysis results based on the predicted training effects corresponding to each of the at least two patients.

[0008] Optionally, the pelvic floor muscle rehabilitation training management method further includes: acquiring training data, the training data including multiple training samples, each training sample including: a first control sample, a second control sample, a third control sample, and a sample label, wherein the first control sample is determined based on a first pelvic floor muscle contraction data sample, the second control sample is determined based on a second pelvic floor muscle contraction data sample, and the third control sample is determined based on the first pelvic floor muscle contraction data sample and the second pelvic floor muscle contraction data sample, the first pelvic floor muscle contraction data sample being pelvic floor muscle contraction data collected during the patient's pelvic floor muscle rehabilitation training using the training task, the second pelvic floor muscle contraction data sample being pelvic floor muscle contraction data collected after the patient completes the pelvic floor muscle rehabilitation training using the training task, and the sample label being the patient's actual training effect; and training a prediction model to be trained based on the training data to obtain a pre-trained prediction model.

[0009] Optionally, the control analysis results are used to characterize the predictive training effects corresponding to the at least two patients, and the predictive training effects include: recovery probability. The step of optimizing the original training task for the patients under control management based on the control analysis results to obtain an optimized training task includes: if there is a recovery probability higher than a preset recovery probability among the recovery probabilities corresponding to the at least two patients, determining the difference between the recovery probabilities corresponding to the at least two patients; if the difference between the recovery probabilities corresponding to the at least two patients is higher than a preset difference, updating the original training task corresponding to the patient with a lower recovery probability based on the original training task corresponding to the patient with the higher recovery probability, to obtain an optimized training task corresponding to the patient with a lower recovery probability; if the difference between the recovery probabilities corresponding to the at least two patients is lower than a preset difference, determining a difference training task between the original training tasks corresponding to the at least two patients, and updating the original training tasks corresponding to the at least two patients based on the difference training task, to obtain an optimized training task corresponding to the at least two patients.

[0010] Optionally, the control analysis results are used to characterize the predicted training effects corresponding to the at least two patients respectively. The predicted training effects include: recovery probability. The step of optimizing the original training task of the patients to be managed according to the control analysis results to obtain the optimized training task includes: in the case that there is no recovery probability higher than the preset recovery probability among the recovery probabilities corresponding to the at least two patients respectively, determining the same training task between the original training tasks corresponding to the at least two patients respectively, and updating the original training tasks corresponding to the at least two patients respectively according to the same training task to obtain the optimized training task corresponding to the at least two patients respectively.

[0011] Optionally, the original training task shown is a training task formulated by the doctor for the patients to be managed under control. The step of determining a new training task based on the control analysis results and the optimized training task includes: feeding back the optimized training task and the control analysis results to the doctor; receiving the training task fed back by the doctor; and determining the new training task based on the training task fed back by the doctor and the optimized training task, wherein the new training task includes at least the optimized training task.

[0012] Optionally, the pelvic floor muscle rehabilitation training management method further includes: in response to detecting a rehabilitated patient among the patients to be managed under control, updating the preset control management conditions according to the patient information and original training task corresponding to the rehabilitated patient to obtain updated control management conditions; obtaining patient information and original training task corresponding to at least one new patient, wherein the original training task is a training task formulated by a doctor for the new patient; determining a target patient from the at least one new patient according to the patient information and original training task corresponding to the at least one new patient, the patient information and original training task corresponding to the non-rehabilitated patient among the patients to be managed under control, and the updated control management conditions; and updating the patients to be managed under control according to the target patient.

[0013] Optionally, the preset control management conditions include conditions related to the type of training task and conditions related to the expected recovery time included in the patient information. Updating the preset control management conditions based on the patient information corresponding to the recovered patient and the original training task includes: updating the conditions related to the expected recovery time included in the patient information of the recovered patient; and updating the conditions related to the task type of the original training task corresponding to the recovered patient.

[0014] In a second aspect, this disclosure provides a data analysis-based pelvic floor muscle rehabilitation training management system, characterized in that it includes: a data acquisition device for acquiring pelvic floor muscle rehabilitation training data; and a data processing device for executing the data analysis-based pelvic floor muscle rehabilitation training management method as described in the first aspect of this disclosure.

[0015] This disclosed technical solution obtains pelvic floor muscle rehabilitation training data from patients undergoing pelvic floor muscle rehabilitation training using original training tasks. Based on this data, a comparative analysis is performed. Furthermore, based on the results of the comparative analysis, the original training tasks for the patients undergoing pelvic floor muscle rehabilitation training are optimized to obtain optimized training tasks. Therefore, based on the optimized training tasks and the comparative analysis results, new training tasks can be developed for the patients undergoing pelvic floor muscle rehabilitation training. This technical solution manages patients through a control group approach and optimizes their training tasks through comparative data analysis, enabling effective and flexible management of patients' pelvic floor muscle rehabilitation training tasks, thereby improving patients' pelvic floor muscle rehabilitation training experience.

[0016] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0018] Figure 1 This is an example diagram illustrating an application scenario according to an exemplary embodiment.

[0019] Figure 2 This is a flowchart illustrating a data analysis-based pelvic floor muscle rehabilitation training management method according to an exemplary embodiment.

[0020] Figure 3 This is a schematic diagram illustrating a process for determining a control group of patients according to an exemplary embodiment.

[0021] Figure 4 This is a block diagram illustrating a data analysis-based pelvic floor muscle rehabilitation training management device according to an exemplary embodiment.

[0022] Figure 5 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0023] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0024] Pelvic floor muscle rehabilitation training is an important rehabilitation method, mainly used to prevent and treat pelvic floor dysfunction disorders such as urinary incontinence and pelvic organ prolapse. Pelvic floor muscle rehabilitation training management techniques are a management approach for pelvic floor muscle rehabilitation training. By effectively managing pelvic floor muscle rehabilitation training, the effectiveness of the training can be improved, thereby enhancing the patient's rehabilitation experience.

[0025] Currently, the management of pelvic floor muscle rehabilitation training can be achieved by configuring corresponding management applications. For example, patent CN115602285A describes a pelvic floor muscle rehabilitation training information management system, which can effectively manage various related data involved in pelvic floor muscle rehabilitation training. However, this management system mainly focuses on designing various flexible management functions but lacks effective data analysis methods, thus failing to achieve effective and flexible management of patients' training tasks.

[0026] Based on this, the present disclosure provides a technical solution that obtains pelvic floor muscle rehabilitation training data obtained by patients under control using the original training task for pelvic floor muscle rehabilitation training, performs a comparative analysis based on the pelvic floor muscle rehabilitation training data, and further optimizes the original training task of the patients under control based on the comparative analysis results to obtain an optimized training task. Thus, based on the optimized training task and the comparative analysis results, a new training task can be formulated for the patients under control.

[0027] This technical solution manages patients through a control group approach and optimizes their training tasks through comparative data analysis. This enables effective and flexible management of patients' pelvic floor muscle rehabilitation training tasks, thereby improving their pelvic floor muscle rehabilitation training experience.

[0028] The technical solutions of this disclosure can be applied to various management scenarios involving pelvic floor muscle rehabilitation training. In these application scenarios, the technical solutions of this disclosure can assist in the formulation of training tasks.

[0029] Regarding training tasks, these can be based on pelvic floor muscle rehabilitation training equipment.

[0030] Figure 1 This is an example diagram illustrating an application scenario according to an exemplary embodiment, such as... Figure 1 As shown, this application scenario involves data acquisition equipment and data processing equipment.

[0031] The data acquisition device can be a pelvic floor muscle rehabilitation training device or a terminal device that interacts with the pelvic floor muscle rehabilitation training device, which can acquire pelvic floor muscle rehabilitation training data.

[0032] Data processing equipment can be a host computer, server, etc., which is connected to the data acquisition equipment to perform data analysis based on the data collected by the data acquisition equipment, thereby realizing rehabilitation training management.

[0033] Regarding pelvic floor muscle rehabilitation training equipment, examples include electrical stimulation devices, which use electrical signals to stimulate the pelvic floor muscles, enhancing muscle strength and coordination. Biofeedback training equipment works by using sensors to convert the contraction and relaxation of the pelvic floor muscles into visual signals, helping patients more accurately perceive and control pelvic floor muscle movement. The method involves detecting the electrical activity of the pelvic floor muscles through electrode patches or probes and displaying it on a screen; the patient then adjusts muscle contraction and relaxation based on the feedback signals.

[0034] Figure 2 This is a flowchart illustrating a data analysis-based pelvic floor muscle rehabilitation training management method according to an exemplary embodiment. This method can be applied to... Figure 1 The data processing apparatus shown includes the following steps:

[0035] Step S21: Obtain pelvic floor muscle rehabilitation training data obtained by patients under control using the original training task to perform pelvic floor muscle rehabilitation training. The patients under control include at least two patients who meet the preset control management conditions.

[0036] Step S22: Perform a comparative analysis on the pelvic floor muscle rehabilitation training data of the patients under control management to obtain the comparative analysis results.

[0037] Step S23: Based on the results of the control analysis, optimize the original training task for the patients under control management to obtain the optimized training task.

[0038] Step S24: Based on the results of the control analysis and the optimized training task, determine the new training task and provide feedback on the new training task to the patients to be managed in control, so that the patients to be managed in control can use the new training task for pelvic floor muscle rehabilitation training.

[0039] In this embodiment of the disclosure, patients requiring pelvic floor muscle rehabilitation training are managed using a control group approach. Each control group patient can be considered as a patient to be managed under control, and patients from different control groups are managed separately.

[0040] Therefore, in step S21, the patients to be managed as controls can be understood as all patients in a control group. Different control groups can be managed in the same way. In this embodiment of the disclosure, a control group is used as an example for introduction.

[0041] In some embodiments, the control group may consist of at least two patients who meet preset control management criteria. For example, a management approach of two patients per group or four patients per group may be used. For ease of management, the number of patients in a control group may be relatively small.

[0042] Therefore, before management, patients can be divided into multiple control groups.

[0043] As an optional implementation method, the determination of the patients to be managed (i.e., the patient control group) includes: obtaining patient information and original training tasks corresponding to multiple patients, wherein the original training tasks are training tasks formulated by doctors for the patients; determining at least two patients from the multiple patients who meet preset control management conditions based on the patient information and original training tasks corresponding to multiple patients, wherein the preset control management conditions include conditions related to the training tasks and conditions related to the patient information; and determining at least two patients as patients to be managed as controls.

[0044] In this implementation, the original training tasks for multiple patients are formulated by the doctor, and the patient information is patient-related information that can be directly obtained from the corresponding database.

[0045] In some embodiments, the preset control management conditions include conditions related to the training task and conditions related to patient information.

[0046] Regarding the training tasks, for example, Training Task 1: Training through exercise, three sets each morning, noon and evening; Training Task 2: Training through electrical stimulation, once every other day; Training Task 3: Training through biofeedback, once every other day.

[0047] Patient information may include basic information such as the patient's age and the severity of the illness, as well as the estimated recovery time determined at the time of diagnosis.

[0048] For example, the conditions associated with the training task can limit the type, intensity, and number of training tasks. Only when these conditions are met can a patient be considered for control management.

[0049] Conditions related to patient information can limit the severity of the patient's illness, the patient's age, and the patient's expected recovery time (determined at the time of diagnosis by the physician). Only patients who meet these conditions can be considered for control management.

[0050] In some embodiments, the preset comparison management conditions can be configured according to the needs of different application scenarios.

[0051] For example, conditions related to training tasks could be: the types of training tasks are the same or similar; the total number of training tasks is the same or similar; the intensity of training tasks is the same or similar.

[0052] For example, conditions related to patient information could be: patients with the same or similar severity of illness, patients of similar age, and patients with similar expected recovery times.

[0053] The patient information corresponding to multiple patients is compared with the original training task. By using preset control management conditions, it is determined whether each patient meets the conditions to be a control patient. If the conditions are met, the patient can be identified as a patient to be managed under control.

[0054] Figure 3 This is a schematic diagram illustrating a process for determining a control group of patients according to an exemplary embodiment, such as... Figure 3 As shown, there are currently 9 patients who need pelvic floor muscle rehabilitation training management, namely patients 1 to 9. Patient information and original training tasks for these 9 patients were retrieved. Then, by comparing the preset control management conditions, four control management patient groups were obtained, namely: [patient 1, patient 3], [patient 2, patient 7], [patient 4, patient 6], [patient 8, patient 9].

[0055] Each control group consists of two patients, while the remaining patient, number 5, does not meet the criteria and requires separate management.

[0056] Furthermore, in step S11, the original training task corresponding to the patient to be managed is fed back to the patient to be managed so that the patient to be managed can use the original training task to perform pelvic floor rehabilitation training; and the pelvic floor muscle rehabilitation training data uploaded by the patient to be managed is received.

[0057] In this implementation, after identifying the patients to be managed as a control group, the original training task can be fed back to them; and subsequently, the patients can upload their pelvic floor muscle rehabilitation training data. For example, patients voluntarily record and upload their pelvic floor muscle rehabilitation training data.

[0058] In some embodiments, pelvic floor muscle rehabilitation training is usually conducted by pelvic floor muscle rehabilitation trainers, or the data can be uploaded by the pelvic floor muscle rehabilitation trainers; no limitation is made here.

[0059] In some embodiments, pelvic floor muscle rehabilitation training data includes first pelvic floor muscle contraction data collected during pelvic floor muscle rehabilitation training using the original training task in patients under control management, and second pelvic floor muscle contraction data collected after patients under control management have completed pelvic floor muscle rehabilitation training using the original training task.

[0060] In this embodiment of the disclosure, a comparative analysis is performed based on pelvic floor muscle contraction data, wherein the pelvic floor muscle contraction data may include: muscle contraction intensity and contraction frequency determined based on the electrical signals converted from pelvic floor muscle contractions.

[0061] In some embodiments, during pelvic floor muscle rehabilitation training, the contraction of the pelvic floor muscles can be detected to obtain first pelvic floor muscle contraction data. Furthermore, after completing the pelvic floor muscle rehabilitation training, the voluntary contraction of the pelvic floor muscles can be detected after a period of time to obtain second pelvic floor muscle contraction data.

[0062] Furthermore, in step S22, the control analysis process may include: determining first control pelvic floor muscle contraction data from the first pelvic floor muscle contraction data corresponding to at least two patients; determining second control pelvic floor muscle contraction data from the second pelvic floor muscle contraction data corresponding to at least two patients; determining third control pelvic floor muscle contraction data corresponding to at least two patients from the first and second pelvic floor muscle contraction data corresponding to at least two patients; for any one of the at least two patients, determining the prediction training effect corresponding to that patient using a pre-trained prediction model based on the first control pelvic floor muscle contraction data, the second control pelvic floor muscle contraction data, and the third control pelvic floor muscle contraction data corresponding to that patient; and determining the control analysis result based on the prediction training effects corresponding to at least two patients.

[0063] In some embodiments, taking the number of patients as 2 as an example, patient A corresponds to the first pelvic floor muscle contraction data F1 and the second pelvic floor muscle contraction data S1; patient B corresponds to the first pelvic floor muscle contraction data F2 and the second pelvic floor muscle contraction data S2.

[0064] Therefore, the first control pelvic floor muscle contraction data can be determined from F1 and F2; the second control pelvic floor muscle contraction data can be determined from S1 and S2; and the third control pelvic floor muscle contraction data corresponding to patient A can be determined from F1 and S1, and the third control pelvic floor muscle contraction data corresponding to patient B can be determined from F2 and S2.

[0065] It can be seen that the first and second control pelvic floor muscle contraction data are not specific to any particular patient and can be understood as control data between patients; the third control pelvic floor muscle contraction data are specific to any particular patient and can be understood as control data within the patient themselves.

[0066] In some embodiments, the first control pelvic floor muscle contraction data can be data showing differences among the first pelvic floor muscle contraction data corresponding to at least two patients. The second control pelvic floor muscle contraction data can be data showing differences among the second pelvic floor muscle contraction data corresponding to at least two patients. The third control pelvic floor muscle contraction data can be data showing differences among the first and second pelvic floor muscle contraction data corresponding to any patient.

[0067] Furthermore, for any patient, the training effect can be predicted based on the first control pelvic floor muscle contraction data, the second control pelvic floor muscle contraction data, and the corresponding third control pelvic floor muscle contraction data, thus obtaining the predicted training effect.

[0068] The training process for the pre-trained predictive model may include: acquiring training data, which includes multiple training samples. Each training sample includes a first control sample, a second control sample, a third control sample, and sample labels. The first control sample is determined based on the first pelvic floor muscle contraction data sample, the second control sample is determined based on the second pelvic floor muscle contraction data sample, and the third control sample is determined based on the first and second pelvic floor muscle contraction data samples. The first pelvic floor muscle contraction data sample is pelvic floor muscle contraction data collected during the patient's pelvic floor muscle rehabilitation training using the training task. The second pelvic floor muscle contraction data sample is pelvic floor muscle contraction data collected after the patient completes the pelvic floor muscle rehabilitation training using the training task. The sample labels represent the patient's actual training effect. Based on the training data, the predictive model to be trained is trained to obtain the pre-trained predictive model.

[0069] In some embodiments, the implementation of the first control sample, the second control sample, and the third control sample can refer to the implementation of the three types of data described above. The difference is that the aforementioned three types of data are determined based on the patients to be managed, while the three types of sample data here can be determined from a large amount of patient data. Furthermore, the sample label can be the patient's actual training effect; the sample label here can be 0 or 1, where 1 represents eventual recovery after training, and 0 represents eventual failure to recover after training.

[0070] In some embodiments, the pre-trained prediction model can be a multi-layer neural network model, with different layers of neural networks used to predict training effects based on different control samples; finally, the classification layer obtains the final prediction training effect based on the prediction training effect output by the multi-layer neural network.

[0071] As an example, the loss function for a multi-layer neural network or classification layer could be: Where N is the number of samples, and K is the number of classes. ij It is the label (0 or 1) of the i-th sample belonging to the j-th class. It is the predicted probability that the i-th sample belongs to the j-th class.

[0072] In some embodiments, by extracting differential data between patients and differential data of patients before and after training, the training effect of patients can be effectively and accurately predicted.

[0073] In some embodiments, the predictive training effects corresponding to at least two patients can be used as the results of a control analysis. Thus, the control analysis results are used to characterize the predictive training effects corresponding to at least two patients, whereby the predictive training effects include: the recovery probability, i.e., the recovery probability ultimately output by the pre-trained predictive model.

[0074] In step S23, based on the results of the control analysis, the original training task of the patients under control management is optimized to obtain the optimized training task.

[0075] As an optional implementation, step S23 includes: if there is a recovery probability higher than a preset recovery probability among the recovery probabilities corresponding to at least two patients, determining the difference between the recovery probabilities corresponding to at least two patients; if the difference between the recovery probabilities corresponding to at least two patients is higher than the preset difference, updating the original training task corresponding to the patient with a lower recovery probability based on the original training task corresponding to the patient with a higher recovery probability, to obtain an optimized training task corresponding to the patient with a lower recovery probability; if the difference between the recovery probabilities corresponding to at least two patients is lower than the preset difference, determining the differential training task between the original training tasks corresponding to at least two patients, updating the original training tasks corresponding to at least two patients based on the differential training task, to obtain an optimized training task corresponding to at least two patients.

[0076] It is understandable that if there is a recovery probability higher than the preset recovery probability among the recovery probabilities of at least two patients, it indicates that there are patients with better recovery. In this case, the training task can be optimized through differential analysis of the training task.

[0077] In some embodiments, the preset recovery probability can be a pre-configured probability representing a higher likelihood of recovery. For example, the preset recovery probability can be a value between 70% and 80%.

[0078] In some embodiments, the preset difference can be a pre-configured difference that characterizes a large difference in the probability of recovery. For example, the preset difference can be a value between 5% and 10%.

[0079] In some embodiments, updating the original training task corresponding to a patient with a lower recovery probability based on the original training task corresponding to a patient with a higher recovery probability may include: adding the original training task corresponding to a patient with a higher recovery probability to the original training task corresponding to a patient with a lower recovery probability. When updating, the update may be based on the principle of non-duplication.

[0080] In some embodiments, updating the original training tasks corresponding to at least two patients based on the differential training task may include: analyzing the importance of the differential training task in the corresponding original training task, retaining the differential training task with higher importance, and replacing the differential training task with lower importance with the differential training task with higher importance.

[0081] For example, if training task 1 for patient A and training task 2 for patient B are training tasks with differences, while all other training tasks are the same, then we analyze the importance of training task 1 in patient A's training tasks and the importance of training task 2 in patient B's training tasks. Through analysis, we determine that training task 1 is more important in patient A's training tasks. Therefore, patient A's training task does not need to be updated, while patient B's training task 2 needs to be replaced with training task 1.

[0082] In some embodiments, the importance of training tasks can be determined based on their order, frequency, and intensity. Generally, the earlier or later a task is ranked, the higher its frequency and intensity, and the greater its importance.

[0083] As an optional implementation, step S23 includes: if there is no recovery probability higher than the preset recovery probability among the recovery probabilities corresponding to at least two patients, determining the same training task between the original training tasks corresponding to at least two patients, updating the original training tasks corresponding to at least two patients according to the same training task, and obtaining the optimized training tasks corresponding to at least two patients.

[0084] In this implementation, if there is no recovery probability higher than the preset recovery probability among the recovery probabilities of at least two patients, it indicates that the recovery of at least two patients is poor. In this case, the training task can be optimized based on the same training task.

[0085] In some embodiments, the same training tasks for at least two patients can be directly adjusted to achieve task updates. For example, the task intensity and frequency of the same training tasks can be optimized to increase the probability of recovery.

[0086] In some embodiments, the original training task is a training task developed by a physician for patients to be managed as a control group.

[0087] As an optional implementation, step S24 includes: feeding back the optimized training task and control analysis results to the doctor; receiving the training task fed back by the doctor; and determining a new training task based on the training task fed back by the doctor and the optimized training task, wherein the new training task includes at least the optimized training task.

[0088] In this implementation, doctors can determine the doctor-specific training task based on the results of the comparative analysis of the optimized training task. The training task provided by the doctor can be the optimized training task, indicating no new optimization suggestions. Alternatively, the training task provided by the doctor can be a modified training task, which may include new or reduced training tasks, and may encompass the training task suggestions given by the doctor.

[0089] In some embodiments, deduplication is performed based on the training task provided by the doctor and the optimized training task to obtain a final new training task. It is necessary to ensure that the new training task includes at least the optimized training task to achieve the desired training task optimization effect.

[0090] In some embodiments, the control patient group needs to be updated in a timely manner based on the patients' recovery progress.

[0091] Therefore, as an optional implementation, the method further includes: in response to detecting the presence of a recovered patient among the patients to be managed as a control, updating the preset control management conditions according to the patient information corresponding to the recovered patient and the original training task to obtain the updated control management conditions; obtaining the patient information and original training task corresponding to at least one new patient, wherein the original training task is a training task formulated by the doctor for the new patient; identifying a target patient from at least one new patient according to the patient information and original training task corresponding to at least one new patient, the patient information and original training task corresponding to the non-recovered patient among the patients to be managed as a control, and the updated control management conditions; and updating the patients to be managed as a control according to the target patient.

[0092] In this implementation, if a recovered patient appears among the patients to be managed as a control group, it indicates that the control patient group needs to be updated.

[0093] In some embodiments, updating the preset control management conditions based on the patient information corresponding to the rehabilitation patient and the original training task may include: updating the conditions related to the expected rehabilitation time included in the patient information of the rehabilitation patient; and updating the conditions related to the task type of the preset control management conditions based on the task type of the original training task corresponding to the rehabilitation patient.

[0094] In some embodiments, the accuracy of the estimated recovery time can be determined based on the actual recovery time of the patient. For example, the greater the difference between the actual recovery time and the estimated recovery time, the lower the accuracy of the estimated recovery time.

[0095] Furthermore, if the accuracy of the predicted recovery time is low, the difference condition for predicted recovery time in the preset control management conditions can be adjusted to be more lenient. For example, if the original conditions required the difference in predicted recovery time to be within 1 day, the updated conditions can allow the difference to be within 2 days. If the accuracy of the predicted recovery time is high, the difference condition for predicted recovery time in the preset control management conditions can be adjusted to be more stringent. For example, if the original conditions required the difference in predicted recovery time to be within 1 day, the updated conditions can allow the difference to be within 0.5 days.

[0096] In some embodiments, if the task type in the preset control management conditions includes the task type of the original training task corresponding to the rehabilitation patient, then the conditions related to the task type in the preset control management conditions need not be updated.

[0097] If the task types in the preset control management conditions do not include the task types of the original training tasks corresponding to the rehabilitation patients, then the task types of the original training tasks corresponding to the rehabilitation patients can be added to the preset control management conditions.

[0098] For example, the original preset control management conditions only allowed control management for the same task type. Now it can be changed to allow control management in the case of task types that include the original training tasks corresponding to rehabilitation patients.

[0099] Alternatively, other update methods can be used, which are not limited here.

[0100] Figure 4 This is a block diagram illustrating a data analysis-based pelvic floor muscle rehabilitation training management device 400 according to an exemplary embodiment, such as... Figure 4 As shown, the device includes:

[0101] The acquisition module 401 is used to acquire pelvic floor muscle rehabilitation training data obtained by patients under control management using the original training task to perform pelvic floor muscle rehabilitation training. The patients under control management include at least two patients who meet the preset control management conditions.

[0102] Analysis module 402 is used to perform comparative analysis on the pelvic floor muscle rehabilitation training data of the patients to be managed, and obtain comparative analysis results.

[0103] The optimization module 403 is used to optimize the original training task of the patient under control based on the control analysis results, resulting in an optimized training task. Based on the control analysis results and the optimized training task, a new training task is determined and fed back to the patient under control, enabling the patient to use the new training task for pelvic floor muscle rehabilitation training.

[0104] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0105] Figure 5 This is a block diagram illustrating an electronic device 500 according to an exemplary embodiment. For example... Figure 5 As shown, the electronic device 500 may include a processor 501 and a memory 502. The electronic device 500 may also include one or more of a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0106] The processor 501 controls the overall operation of the electronic device 500 to complete all or part of the steps in the data analysis-based pelvic floor muscle rehabilitation training management method described above. The memory 502 stores various types of data to support the operation of the electronic device 500. This data may include, for example, instructions for any application or method operating on the electronic device 500, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 502 or transmitted via communication component 505. The audio component also includes at least one speaker for outputting audio signals. I / O interface 504 provides an interface between processor 501 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of these. Therefore, the corresponding communication component 505 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0107] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described data analysis-based pelvic floor muscle rehabilitation training management method.

[0108] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the data analysis-based pelvic floor muscle rehabilitation training management method described above. For example, the computer-readable storage medium may be the memory 502 including the program instructions described above, which may be executed by the processor 501 of the electronic device 500 to complete the data analysis-based pelvic floor muscle rehabilitation training management method described above.

[0109] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, which, when executed by the processor, implements the above-described data analysis-based pelvic floor muscle rehabilitation training management method.

[0110] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, which, when executed by the processor, implements the steps of the above-described data analysis-based pelvic floor muscle rehabilitation training management method.

[0111] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0112] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0113] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for managing pelvic floor muscle rehabilitation training based on data analysis, characterized by, The method comprises the following steps: obtaining pelvic floor muscle rehabilitation training data of patients to be managed by comparison, the patients to be managed by comparison comprising at least two patients satisfying preset comparison management conditions; performing comparison analysis on the pelvic floor muscle rehabilitation training data corresponding to the patients to be managed by comparison to obtain comparison analysis results; optimizing the original training task of the patients to be managed by comparison according to the comparison analysis results to obtain an optimized training task; specifically, in the case that the rehabilitation probabilities corresponding to the at least two patients respectively are higher than a preset rehabilitation probability, determining the difference between the rehabilitation probabilities corresponding to the at least two patients respectively; in the case that the difference between the rehabilitation probabilities corresponding to the at least two patients respectively is higher than a preset difference value, updating the original training task corresponding to the patient with a lower rehabilitation probability according to the original training task corresponding to the patient with a higher rehabilitation probability to obtain an optimized training task corresponding to the patient with a lower rehabilitation probability; in the case that the difference between the rehabilitation probabilities corresponding to the at least two patients respectively is lower than the preset difference value, determining a difference training task between the original training tasks corresponding to the at least two patients respectively, and updating the original training tasks corresponding to the at least two patients respectively according to the difference training task to obtain optimized training tasks corresponding to the at least two patients respectively; determining a new training task according to the comparison analysis results and the optimized training task, and feeding back the new training task to the patients to be managed by comparison so that the patients to be managed by comparison perform pelvic floor muscle rehabilitation training using the new training task.

2. The pelvic floor rehabilitation training management method according to claim 1, characterized by, The pelvic floor muscle rehabilitation training management method further comprises: obtaining patient information and original training tasks corresponding to a plurality of patients, the original training tasks being training tasks formulated by doctors for the patients; determining at least two patients satisfying preset comparison management conditions from the plurality of patients according to the patient information and the original training tasks corresponding to the plurality of patients, wherein the preset comparison management conditions comprise conditions related to training tasks and conditions related to patient information; determining the at least two patients as the patients to be managed by comparison; feeding back the original training tasks corresponding to the patients to be managed by comparison to the patients to be managed by comparison so that the patients to be managed by comparison perform pelvic floor muscle rehabilitation training using the original training tasks; receiving pelvic floor muscle rehabilitation training data uploaded by the patients to be managed by comparison or pelvic floor muscle rehabilitation training personnel.

3. The pelvic floor rehabilitation training management method according to claim 1, characterized by, The pelvic floor muscle rehabilitation training data includes first pelvic floor muscle contraction data collected during the process of pelvic floor muscle rehabilitation training of the to-be-managed patient using an original training task and second pelvic floor muscle contraction data collected after the to-be-managed patient completes the pelvic floor muscle rehabilitation training using the original training task, the pelvic floor muscle rehabilitation training data corresponding to the to-be-managed patient is analyzed by comparison to obtain a comparison analysis result, including: determining first comparison pelvic floor muscle contraction data from the first pelvic floor muscle contraction data corresponding to the at least two patients respectively; determining second comparison pelvic floor muscle contraction data from the second pelvic floor muscle contraction data corresponding to the at least two patients respectively; determining third comparison pelvic floor muscle contraction data corresponding to the at least two patients respectively from the first pelvic floor muscle contraction data and the second pelvic floor muscle contraction data corresponding to the at least two patients respectively; for any one of the at least two patients, determining a predicted training effect corresponding to the patient by a pre-trained prediction model according to the first comparison pelvic floor muscle contraction data, the second comparison pelvic floor muscle contraction data, and the third comparison pelvic floor muscle contraction data corresponding to the patient; determining the comparison analysis result according to the predicted training effect corresponding to the at least two patients respectively.

4. The pelvic floor rehabilitation training management method according to claim 3, characterized by, The pelvic floor muscle rehabilitation training management method further includes: obtaining training data, the training data including a plurality of training samples, each training sample including: a first comparison sample, a second comparison sample, a third comparison sample, and a sample label, wherein the first comparison sample is determined according to a first pelvic floor muscle contraction data sample, the second comparison sample is determined according to a second pelvic floor muscle contraction data sample, the third comparison sample is determined according to the first pelvic floor muscle contraction data sample and the second pelvic floor muscle contraction data sample, the first pelvic floor muscle contraction data sample is pelvic floor muscle contraction data collected during the process of pelvic floor muscle rehabilitation training of a patient using a training task, the second pelvic floor muscle contraction data sample is pelvic floor muscle contraction data collected after the patient completes the pelvic floor muscle rehabilitation training using the training task, and the sample label is a true training effect of the patient; training a prediction model to be trained according to the training data to obtain a pre-trained prediction model.

5. The pelvic floor rehabilitation training management method according to claim 1, characterized by, The comparison analysis result is used to represent the predicted training effect corresponding to the at least two patients respectively, and the predicted training effect includes: rehabilitation probability, the original training task of the to-be-managed patient is optimized according to the comparison analysis result to obtain an optimized training task, including: in the case that there is no rehabilitation probability higher than a preset rehabilitation probability in the rehabilitation probability corresponding to the at least two patients respectively, determining a same training task between the original training tasks corresponding to the at least two patients respectively, updating the original training tasks corresponding to the at least two patients respectively according to the same training task to obtain the optimized training tasks corresponding to the at least two patients respectively.

6. The pelvic floor rehabilitation training management method according to claim 1, characterized by, The original training task is a training task formulated by a doctor for the patient to be managed, and the new training task is determined according to the comparison analysis result and the optimized training task, including: feeding back the optimized training task and the comparison analysis result to the doctor; receiving the training task fed back by the doctor; determining the new training task according to the training task fed back by the doctor and the optimized training task, wherein the new training task at least includes the optimized training task.

7. The pelvic floor rehabilitation training management method according to claim 1, characterized by, The pelvic floor muscle rehabilitation training management method further includes: In response to detecting that a rehabilitation patient appears in the patients to be managed, updating the preset comparison management condition according to the patient information and the original training task corresponding to the rehabilitation patient, to obtain an updated comparison management condition; obtaining patient information and an original training task corresponding to at least one new patient, wherein the original training task is a training task formulated by a doctor for the new patient; determining a target patient from the at least one new patient according to the patient information and the original training task corresponding to the at least one new patient, the patient information and the original training task corresponding to the non-rehabilitation patients in the patients to be managed, and the updated comparison management condition; updating the patients to be managed according to the target patient.

8. The pelvic floor rehabilitation training management method according to claim 7, characterized by, The preset comparison management condition includes a condition related to the type of training task and a condition related to the expected rehabilitation time included in the patient information, and updating the preset comparison management condition according to the patient information and the original training task corresponding to the rehabilitation patient includes: updating the condition related to the expected rehabilitation time included in the patient information in the preset comparison management condition according to the expected rehabilitation time included in the patient information corresponding to the rehabilitation patient; updating the condition related to the type of training task in the preset comparison management condition according to the type of the original training task corresponding to the rehabilitation patient. 9.A data analysis-based pelvic floor muscle rehabilitation training management system, characterized by, It includes: a data acquisition device for collecting pelvic floor muscle rehabilitation training data; a data processing device for executing the pelvic floor muscle rehabilitation training management method based on data analysis according to any one of claims 1-8.

Images