Pelvic floor patient condition dynamic tracking system based on Internet technology

Abstract

The invention relates to the technical field of medical diagnosis, in particular to a pelvic floor patient condition dynamic tracking system based on the Internet technology, and the system comprises a data acquisition module, a clustering module, a historical patient screening module, a model construction module and a data screening module. Analyzing pelvic floor monitoring data of different historical patients, and clustering all the historical patients to obtain a plurality of clusters; screening the historical patients in each cluster according to the reference of different historical patients; based on the pelvic floor monitoring data of the screened target historical patient, constructing an illness state reference model corresponding to each cluster; and determining a matched illness state reference model in all illness state reference models so as to screen effective illness state data in the real-time pelvic floor monitoring data of the patient. According to the invention, the screening accuracy of effective data in pelvic floor function real-time monitoring data is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical diagnosis, and particularly to a dynamic tracking system for the condition of pelvic floor patients based on Internet technology. Background Art

[0002] Dynamic tracking of the condition is an important part of medical health management, which involves continuous monitoring and analysis of the disease development process, facilitating timely adjustment of treatment plans and improving treatment effects. In the dynamic tracking of patients' conditions, Internet technology mainly realizes real-time update and efficient management of information through cloud platforms, intelligent follow-up systems, etc. It solves the problems of untimely update and difficult search of paper documents or local electronic systems, and also makes the condition data safer and less vulnerable to damage. Pelvic floor dysfunction is a common gynecological disease, especially more common in women who have given birth multiple times or are older. Since the pelvic floor repair usually takes a long time, in order to timely detect changes in the condition, provide effective treatment for patients, and avoid deterioration of the condition, it is particularly important to track the condition of pelvic floor patients based on Internet technology.

[0003] For long-term pelvic floor repair, the real-time monitoring data of patients' pelvic floor functions are often large. Due to interference from monitoring environments, human factors, etc., there are often interference data in the large amount of data, which may lead to deviations in the analysis of patients' conditions during the process of tracking the conditions of pelvic floor patients, and is not conducive to doctors formulating reasonable treatment plans. In order to improve the repair effect of the pelvic floor muscles, a condition reference model can be constructed based on the pelvic floor function monitoring data of a large number of patients, and the condition reference model is used to screen the effective condition data in the real-time monitoring data of patients' pelvic floor functions. However, since the diseases of pelvic floor patients include various conditions such as pelvic floor muscle hypotonia, urinary incontinence, organ prolapse, etc., and the compliance and the degree of attention to condition tracking of different patients are different, resulting in different pelvic floor repair effects for different patients. At this time, directly constructing a condition reference model based on the pelvic floor function monitoring data of a large number of patients will lead to an inaccurate constructed condition reference model, thereby affecting the screening accuracy of the effective data in the real-time monitoring data of patients' pelvic floor functions and being not conducive to accurate analysis of patients' conditions. Summary of the Invention

[0004] In order to solve the above technical problem that in the process of dynamically tracking the condition of pelvic floor patients, the effective data in the real-time monitoring data of pelvic floor functions cannot be accurately screened, the purpose of the present invention is to provide a dynamic tracking system for the condition of pelvic floor patients based on Internet technology, and the specific technical solutions adopted are as follows: In the first aspect, the present invention provides a dynamic tracking system for the condition of pelvic floor patients based on Internet technology, and the system includes: A data acquisition module for acquiring pelvic floor monitoring data of different historical patients and pelvic floor monitoring data of real-time patients, where the pelvic floor monitoring data includes different types of pelvic floor electromyogram signals corresponding to different times; A clustering module for determining the class differences between any two historical patients based on the differences between the same type of pelvic floor electromyogram signals of different historical patients at different times and the differences between the changes of the same type of pelvic floor electromyogram signals of different historical patients over time, and clustering all historical patients based on the class differences to obtain several clusters; A historical patient screening module for determining the referability of different historical patients based on the changes of different types of pelvic floor electromyogram signals of different historical patients over time, and screening the historical patients in each cluster according to the referability; A model construction module for constructing a disease reference model corresponding to each cluster based on the pelvic floor monitoring data of the target historical patients selected from each cluster; A data screening module for analyzing the pelvic floor monitoring data of real-time patients, determining the matching disease reference model among all the disease reference models, and screening the effective disease data in the pelvic floor monitoring data of real-time patients based on the matching disease reference model.

[0005] Combined with the first aspect above, in some possible implementation manners, the clustering module includes: A similarity acquisition module for determining the similarity of the pelvic floor monitoring data between any two historical patients at different times based on the differences between the same type of pelvic floor electromyogram signals of any one historical patient at any one time and any other historical patient at any one time; A first disease degree acquisition module for determining the disease degree of any one historical patient at different times based on the differences between different types of pelvic floor electromyogram signals of any one historical patient at different times and the corresponding normal reference values; A first disease recovery speed acquisition module for determining the disease recovery speed of any one historical patient at different times based on the difference magnitude between the disease degrees of any one historical patient at adjacent times; A possibility acquisition module for comprehensively determining the possibility that the pelvic floor monitoring data between any two historical patients at different times is the corresponding data based on the similarity of the pelvic floor monitoring data between any two historical patients at different times and the differences in the disease recovery speed at different times; A class difference acquisition module for determining the class differences between any two historical patients based on the possibility that the pelvic floor monitoring data between any two historical patients at different times is the corresponding data.

[0006] In combination with the above first aspect, in some possible implementation manners, the similarity acquisition module includes: A first accumulated difference value acquisition unit, configured to determine an accumulated value of absolute values of differences between pelvic floor electromyogram signals of the same type between any one historical patient at any one time and any other historical patient at any one time, so as to obtain a first accumulated difference value; A similarity acquisition unit, configured to perform negative correlation normalization processing on the first accumulated difference value, so as to obtain the similarity of pelvic floor monitoring data between any two historical patients at different times.

[0007] In combination with the above first aspect, in some possible implementation manners, the first disease degree acquisition module includes: A second accumulated difference value acquisition unit, configured to determine an accumulated value of absolute values of differences between different types of pelvic floor electromyogram signals of any one historical patient at the same time and corresponding normal reference values, so as to obtain a second accumulated difference value; A disease degree acquisition unit, configured to perform positive correlation normalization processing on the second accumulated difference value, so as to obtain the disease degree of any one historical patient at different times.

[0008] In combination with the above first aspect, in some possible implementation manners, the historical patient screening module includes: A symptom degree change index acquisition module, configured to determine a symptom degree change index of any one historical patient according to the difference magnitude between the disease degrees of any one historical patient at adjacent times; A time consistency acquisition module, configured to determine the time interval consistency of any one historical patient according to the distribution of time intervals between adjacent times of any one historical patient; A referenceability acquisition module, configured to determine the product of the symptom degree change index and the time interval consistency of any one historical patient, so as to obtain the referenceability of any one historical patient.

[0009] In combination with the above first aspect, in some possible implementation manners, the consistency acquisition module includes: An average time interval acquisition unit, configured to determine the average time interval between adjacent times of any one historical patient according to the overall distribution level of time intervals between adjacent times of any one historical patient; A maximum time interval acquisition unit, configured to determine the maximum time interval among the time intervals between adjacent times of any one historical patient; A time interval consistency acquisition unit, configured to determine the ratio of the average time interval to the maximum time interval, so as to obtain the time interval consistency of any one historical patient.

[0010] In combination with the above first aspect, in some possible implementation manners, the model construction module includes: A first data point acquisition module, configured to use the disease severity of the target historical patients in each cluster class at different times as the abscissa, and use the disease recovery speed at different times as the ordinate to construct data points corresponding to each cluster class; A disease condition reference model acquisition module, configured to perform linear fitting on the data points corresponding to each cluster class, and use the obtained fitting line as the disease condition reference model corresponding to each cluster class.

[0011] In combination with the above first aspect, in some possible implementation manners, the data screening module includes: A second disease severity acquisition module, configured to determine the disease severity of the real-time patient at different times according to the differences between different types of pelvic floor electromyogram signals of the real-time patient at different times and the corresponding normal reference values; A second disease recovery speed acquisition module, configured to determine the disease recovery speed of the real-time patient at different times according to the magnitude of the differences between the disease severities of the real-time patient at adjacent times; A second data point acquisition module, configured to use the disease severity of the real-time patient at different times as the abscissa, and use the disease recovery speed at different times as the ordinate to construct data points corresponding to the real-time patient at different times; A linear fitting module, configured to perform linear fitting on the data points corresponding to the real-time patient to obtain a fitting line corresponding to the real-time patient; A matching disease condition reference model acquisition module, configured to compare the slopes of the fitting line corresponding to the real-time patient with the fitting lines corresponding to each disease condition reference model, and use the disease condition reference model with the closest slope as the matching disease condition reference model.

[0012] In combination with the above first aspect, in some possible implementation manners, the data screening module further includes: A time window determination module, configured to construct each time window of the pelvic floor monitoring data of the real-time patient under different time window sizes; A rationality determination module, configured to determine the rationality of different time window sizes according to the distances from the data points corresponding to each time in each time window of the real-time patient to the fitting line corresponding to the matching disease condition reference model, and the magnitude of the differences between the disease severities of each time between adjacent time windows; An effective condition data determination module, configured to use the time window size corresponding to the maximum rationality as the target time window size, determine the target time in each time window of the real-time patient under the target time window size, and use different types of pelvic floor electromyogram signals of the real-time patient corresponding to the target time as effective condition data, where the target time refers to at least one time when the data points in the time window best conform to the fitting line corresponding to the matching condition reference model.

[0013] Combined with the first aspect above, in some possible implementation manners, the rationality determination module includes: A window distance determination unit, configured to determine the central data point of the data points corresponding to each time in each time window of the real-time patient, and determine the distance from the central data point to the fitting line corresponding to the matching condition reference model, so as to obtain a window distance; A first sum determination unit, configured to determine the first sum of the window distances corresponding to each time window of the real-time patient; An average disease degree determination unit, configured to determine the average disease degree of the real-time patient in each time window according to the overall distribution level of the disease degrees of each time in each time window of the real-time patient; A second sum determination unit, configured to determine the second sum of the absolute values of the differences between the average disease degrees in two adjacent time windows of the real-time patient; A rationality determination unit, configured to perform negative correlation normalization processing on the product of the first sum and the second sum, so as to obtain the rationality of different time window sizes.

[0014] In a second aspect, the present invention further provides a method for dynamically tracking the conditions of pelvic floor patients based on Internet technology, and the method includes: Obtain the pelvic floor monitoring data of different historical patients and the pelvic floor monitoring data of a real-time patient, where the pelvic floor monitoring data includes different types of pelvic floor electromyogram signals corresponding to different times; According to the differences between the same type of pelvic floor electromyogram signals of different historical patients at different times, and the differences between the changes of the same type of pelvic floor electromyogram signals of different historical patients over time, determine the category differences between any two historical patients, and based on the category differences, cluster all historical patients to obtain several clusters; Based on the changes of different types of pelvic floor electromyogram signals of different historical patients over time, determine the referability of different historical patients, and screen the historical patients in each cluster according to the referability; Based on the pelvic floor monitoring data of the target historical patients screened out in each cluster, construct a condition reference model corresponding to each cluster; Analyze the pelvic floor monitoring data of a real-time patient, determine the matching disease reference models among all the disease reference models, and screen the effective disease data in the pelvic floor monitoring data of the real-time patient based on the matching disease reference models.

[0015] In a third aspect, the present invention further provides a dynamic tracking device for the conditions of pelvic floor patients based on Internet technology, including a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the device executes the module implementation steps in the above first aspect or any possible implementation manner of the first aspect.

[0016] In a fourth aspect, the present invention further provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, the computer is caused to execute the module implementation steps in the above first aspect or any possible implementation manner of the first aspect.

[0017] In a fifth aspect, the present invention further provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer is caused to execute the module implementation steps in the above first aspect or any possible implementation manner of the first aspect.

[0018] The present invention has the following beneficial effects: By obtaining the pelvic floor monitoring data of different historical patients and real-time patients, where the pelvic floor monitoring data includes different types of pelvic floor electromyogram signals corresponding to different times, and analyzing the pelvic floor monitoring data of historical patients, all historical patients are divided into different disease types to obtain several clusters. At the same time, in order to avoid the influence of interfering data on the accuracy of constructing the disease reference model, representative target historical patients are selected as references among all historical patients in the same cluster, and the pelvic floor monitoring data of the target historical patients is used to construct the disease reference model corresponding to each cluster. Analyze the pelvic floor monitoring data of the real-time patient, determine the matching disease reference models among all the disease reference models, and screen the effective disease data in the pelvic floor monitoring data of the real-time patient based on the matching disease reference model. By classifying historical patients with different disease types and using the pelvic floor monitoring data of representative target historical patients with strong reference in each disease type of patients to construct the corresponding disease reference model, the accuracy of the constructed disease reference model is effectively guaranteed. Furthermore, the effective disease data in the pelvic floor monitoring data of the real-time patient is screened using the disease reference model of the same disease type as the real-time patient, effectively ensuring the screening accuracy of the effective disease data. Description of the Drawings

[0019] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 It is a schematic structural diagram of a dynamic condition tracking system for pelvic floor patients based on Internet technology according to an embodiment of the present invention; Figure 2 It is a step flowchart of a dynamic condition tracking method for pelvic floor patients based on Internet technology according to an embodiment of the present invention; Figure 3 It is a schematic structural diagram of a dynamic condition tracking device for pelvic floor patients based on Internet technology according to an embodiment of the present invention. Detailed implementation manners

[0021] To clearly illustrate the technical features of this solution, the present invention will be described in detail below through specific implementation manners in combination with the drawings.

[0022] The embodiments of the present invention will be described in more detail below with reference to the drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0023] It should be understood that the steps recorded in the method embodiments of the present invention can be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this regard.

[0024] The term "including" and its variants used herein are open-ended, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0025] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions executed by these devices, modules or units or their interdependent relationships.

[0026] In the embodiments of the present invention, although operations or steps are described in a specific order in the drawings, it should not be construed as requiring these operations or steps to be performed in the specific order shown or in a serial order, nor requiring all the operations or steps shown to obtain the desired result. In the embodiments of the present invention, these operations or steps can be performed serially; they can also be performed in parallel; or a part of these operations or steps can be performed.

[0027] Meanwhile, it can be understood that the data involved in the technical solution of the present invention (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws, regulations and related provisions. Unless otherwise defined, all the technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs, and all the parameters or indicators in the formulas involved in the present invention are numerical values after normalization to eliminate the influence of dimensions.

[0028] To solve the technical problem that in the process of dynamically tracking the condition of pelvic floor patients, it is impossible to accurately screen the valid data in the real-time monitoring data of pelvic floor function, the embodiments of the present invention provide a dynamic condition tracking system for pelvic floor patients based on Internet technology. This system is essentially a software system, which is composed of modules that implement corresponding functions, and the corresponding structural schematic diagram is as Figure 1 shown. The core of this system is to implement a method for dynamically tracking the condition of pelvic floor patients based on Internet technology. Each module in this system corresponds to each step in the method, and the flowchart corresponding to this method is as Figure 2 shown. The following will introduce each module of this system in detail in combination with the specific steps in this method.

[0029] A data acquisition module, which is used to acquire the pelvic floor monitoring data of different historical patients and the pelvic floor monitoring data of real-time patients, and the pelvic floor monitoring data includes different types of pelvic floor electromyogram signals corresponding to different times.

[0030] Specifically, during the dynamic tracking of the condition of pelvic floor patients, due to interference from the monitoring environment, human factors, etc. The monitoring environment interference refers to the interference of other devices during the monitoring process, and the human factor interference refers to the interference of the patient's monitoring actions and positions. There are often interference data in the pelvic floor monitoring data of the patient obtained, and the data on the patient's condition is small. Therefore, when directly using the real-time pelvic floor monitoring data to analyze the patient's condition, there may be deviations, which is not conducive to doctors formulating reasonable treatment plans. For this reason, a large amount of pelvic floor monitoring data of historical patients can be obtained to construct a condition reference model for pelvic floor patients, so that the condition-related data, that is, the effective condition data, in the existing pelvic floor monitoring data of real-time patients can be extracted by using the condition reference model, so as to facilitate the accurate analysis of the condition of real-time patients, formulate reasonable treatment plans, and ultimately improve the repair effect of the pelvic floor muscles. It should be understood that a real-time patient refers to a patient who needs to be dynamically tracked for their condition.

[0031] To construct a condition reference model for pelvic floor patients, a pelvic floor muscle treatment instrument is used to monitor the pelvic floor muscles of patients, and the monitored pelvic floor muscle electrical signals are uploaded to the doctor-patient interaction platform and the pelvic floor patient information sharing platform in a timely manner. Through the platform database, several condition monitoring data of several pelvic floor patients can be obtained. Here, the pelvic floor patients are also called historical patients, and several condition monitoring data constitute the pelvic floor monitoring data of each historical patient. Among them, each condition monitoring data of each historical patient includes different types of pelvic floor muscle electrical signals, and each condition monitoring data corresponds to a time, which refers to the time of the above different types of pelvic floor muscle electrical signals of the patient. The pelvic floor muscle electrical signal refers to the pelvic floor physiological parameters of the patient monitored by the pelvic floor muscle treatment instrument, and specifically may include: the average value of the anterior baseline plateau period, the high-tension condition of the anterior baseline plateau period, the average value of the contraction potential of type II muscle fibers, the contraction time of type II muscle fibers, the contraction grade of type II muscle fibers, the average value of the posterior baseline plateau period, the high-tension condition of the posterior baseline plateau period, the average value of the contraction potential of type I muscle fibers, the contraction time of type I muscle fibers, and the contraction grade of type I muscle fibers.

[0032] Similarly, when using a pelvic floor muscle treatment instrument to monitor the pelvic floor muscles of real-time patients, the condition monitoring data of each day within a period of time (such as one month) before the treatment of real-time patients can be obtained, that is, different types of pelvic floor muscle electrical signals every day. These condition monitoring data together constitute the pelvic floor monitoring data of real-time patients.

[0033] The clustering module is used to determine the category differences between any two historical patients based on the differences between the same type of pelvic floor muscle electrical signals of different historical patients at different times and the differences between the changes of the same type of pelvic floor muscle electrical signals of different historical patients over time, and cluster all historical patients based on the category differences to obtain several clusters. [[ID=!0]] [[ID=!1]]

[0034] Specifically, when using a large amount of pelvic floor monitoring data of historical patients to construct a disease reference model for pelvic floor patients, since the diseases of pelvic floor patients include various types such as pelvic floor muscle hypotonia, urinary incontinence, and organ prolapse, and the compliance of different patients is different, and the degree of attention to disease tracking is different, resulting in different pelvic floor repair effects for different patients. At this time, directly constructing a disease reference model based on the pelvic floor function monitoring data of a large number of patients will lead to an inaccurate constructed disease reference model, ultimately affecting the accuracy of screening the disease-related data, that is, the effective disease data, in the existing pelvic floor monitoring data of real-time patients.

[0035] To ensure the accurate screening of the disease-related data, that is, the effective disease data, in the existing pelvic floor monitoring data of real-time patients, considering that the disease types and degrees of pelvic floor patients are all reflected in the pelvic floor electromyogram signals, a large amount of pelvic floor monitoring data of historical patients is analyzed to classify the patients. Thus, a disease reference model can be constructed based on the pelvic floor monitoring data of each category of patients. Furthermore, based on the pelvic floor monitoring data of real-time patients, the matching disease reference model among all disease reference models is determined, so as to enable real-time patients to refer to the disease in a more refined category, ultimately realizing the accurate screening of disease-related data and ensuring the personalized treatment of real-time patients.

[0036] Furthermore, the above clustering module includes: A similarity acquisition module, which is used to determine the similarity of pelvic floor monitoring data between any two historical patients at different times according to the difference between the same type of pelvic floor electromyogram signals between any one historical patient at any time and any other historical patient at any time; A first disease degree acquisition module, which is used to determine the disease degree of any one historical patient at different times according to the difference between different types of pelvic floor electromyogram signals of any one historical patient at different times and the corresponding normal reference values; A first disease recovery speed acquisition module, which is used to determine the disease recovery speed of any one historical patient at different times according to the difference magnitude between the disease degrees of any one historical patient at adjacent times; A possibility acquisition module, which is used to comprehensively determine the possibility that the pelvic floor monitoring data between any two historical patients at different times is the corresponding data according to the similarity of the pelvic floor monitoring data between any two historical patients at different times and the difference in the disease recovery speed at different times; A category difference acquisition module, which is used to determine the category difference between any two historical patients according to the possibility that the pelvic floor monitoring data between any two historical patients at different times is the corresponding data.

[0037] Specifically, let the pelvic floor electromyogram signals included in the pelvic floor monitoring data be n types. The similarity between any two condition monitoring data of different historical patients, that is, the similarity of the pelvic floor monitoring data at different times, refers to the similarity of different types of pelvic floor electromyogram signals. The higher the similarity of all types of pelvic floor electromyogram signals, that is, the smaller the difference, the higher the similarity of the pelvic floor monitoring data of different historical patients at different times.

[0038] Further, the above similarity acquisition module includes: The first cumulative difference value acquisition unit is used to determine the cumulative value of the absolute values of the differences of the same type of pelvic floor electromyogram signals between any one historical patient at any one time and any other historical patient at any one time, so as to obtain the first cumulative difference value; The similarity acquisition unit is used to perform negative correlation normalization processing on the first cumulative difference value, so as to obtain the similarity of the pelvic floor monitoring data between any two historical patients at different times.

[0039] In this embodiment, the similarity of the pelvic floor monitoring data between any two historical patients at different times is determined according to the following formula: ; In the formula: represents the similarity of the pelvic floor monitoring data of the i-th historical patient at any one time and the pelvic floor monitoring data of the j-th historical patient at any one time; represents the number of types of pelvic floor electromyogram signals included in the pelvic floor monitoring data; represents the -th type of pelvic floor electromyogram signal in the pelvic floor monitoring data of the i-th historical patient at any one time; represents the -th type of pelvic floor electromyogram signal in the pelvic floor monitoring data of the j-th historical patient at any one time; exp represents the exponential function with the natural constant e as the base.

[0040] In the above formula, the first cumulative difference value is obtained by calculating the cumulative value of the absolute values of the differences of the same type of pelvic floor electromyogram signals in the pelvic floor monitoring data of the i-th historical patient at any one time and the pelvic floor monitoring data of the j-th historical patient at any one time , because the smaller the value of this first cumulative difference value , it indicates that the similarity of all types of pelvic floor electromyogram signals in the pelvic floor monitoring data of the i-th historical patient at any one time and the pelvic floor monitoring data of the j-th historical patient at any one time is higher. Therefore, negative correlation normalization processing is performed on this first cumulative difference value , so as to obtain the similarity of the pelvic floor monitoring data of the i-th historical patient at any one time and the pelvic floor monitoring data of the j-th patient at any one time .

[0041] Since the severity of the diseases of different historical patients varies, the required recovery time naturally differs as well. Therefore, when classifying historical patients, it is also necessary to consider the disease severity and the disease recovery speed of different historical patients. The disease recovery speed is the degree of improvement of the disease severity per unit time.

[0042] Furthermore, the above first disease severity acquisition module includes: A second cumulative difference value acquisition unit, configured to determine the cumulative value of the absolute values of the differences between different types of pelvic floor electromyogram signals of any historical patient at the same time and the corresponding normal reference values, so as to obtain a second cumulative difference value; A disease severity acquisition unit, configured to perform positive correlation normalization processing on the second cumulative difference value, so as to obtain the disease severity of any historical patient at different times.

[0043] In this embodiment, the normal reference values of different types of pelvic floor electromyogram signals in the pelvic floor monitoring data are obtained. The normal reference value refers to the standard value of the pelvic floor electromyogram signal. Taking the average value of the previous baseline plateau period as an example, its normal reference value is . Denote the normal reference values of n types of pelvic floor electromyogram signals in the pelvic floor monitoring data as .

[0044] For any historical patient, compare the different types of pelvic floor electromyogram signals of the patient at each time with the corresponding normal reference values, so as to obtain the disease severity of the historical patient at each time: ; In the formula: represents the disease severity of any historical patient at each time; represents the number of types of pelvic floor electromyogram signals included in the pelvic floor monitoring data; represents the th type of pelvic floor electromyogram signal in the pelvic floor monitoring data of any historical patient at each time; represents the th type of pelvic floor electromyogram signal in the pelvic floor monitoring data; represents the normalization function.

[0045] In the above formula, the second cumulative difference value is obtained by calculating the cumulative value of the absolute values of the differences between different types of pelvic floor electromyogram signals in the pelvic floor monitoring data of any historical patient at each time and the corresponding normal reference values , when the second cumulative difference value has a larger value, it indicates that the difference between different types of pelvic floor electromyogram signals and the corresponding normal reference values is greater, and the disease severity of the historical patient at this time is higher. Therefore, using The function performs positive correlation normalization on the second cumulative difference value to obtain the disease severity of historical patients at each time .

[0046] For any historical patient, according to the difference in disease severity between adjacent times, the disease recovery speed at different times is determined by the following formula: ; In the formula: represents the disease recovery speed of any historical patient at the t-th time; , , respectively represent the disease severity of any historical patient at the (t - 1)-th, t-th, and (t + 1)-th times; respectively represent the time intervals from the (t - 1)-th time to the t-th time and from the t-th time to the (t + 1)-th time for any historical patient.

[0047] Since the disease severity of the same type of historical patients usually shows consistency over time, and different historical patients may be in different disease stages, the obtained pelvic floor monitoring data will be different, and the disease recovery speeds shown will also be different. For any i-th historical patient and j-th historical patient, by comprehensively considering the similarity of their pelvic floor monitoring data at different times and the difference in disease recovery speeds at different times, the possibility that their pelvic floor monitoring data at different times are corresponding data can be determined. Among them, the possibility that the pelvic floor monitoring data of any i-th historical patient and j-th historical patient are corresponding data refers to the likelihood that the pelvic floor monitoring data of any i-th historical patient and j-th historical patient are pelvic floor monitoring data belonging to the same disease stage.

[0048] In this embodiment, for any i-th historical patient and j-th historical patient, the possibility that their pelvic floor monitoring data at different times are corresponding data is determined by the following formula: ; In the formula: represents the possibility that the pelvic floor monitoring data of any i-th historical patient at any time and the pelvic floor monitoring data of any j-th patient at any time are corresponding data; represents the similarity between the pelvic floor monitoring data of any i-th historical patient at any time and the pelvic floor monitoring data of any j-th historical patient at any time ; represents the pelvic floor monitoring data of any i-th historical patient at any time The recovery rate of the disease; represents the disease recovery rate of any j-th historical patient at any one time ; exp represents the exponential function with the natural constant e as the base.

[0049] In the above formula, when the pelvic floor monitoring data of any i-th historical patient at any one time and the pelvic floor monitoring data of any j-th patient at any one time are more likely to be the corresponding data, and the difference between the disease recovery rate of the i-th historical patient at any one time and the disease recovery rate of the j-th historical patient at any one time is smaller, it indicates that the pelvic floor monitoring data of the i-th historical patient at any one time and the pelvic floor monitoring data of the j-th patient at any one time are more likely to be the pelvic floor monitoring data belonging to the same disease stage, and the possibility that the pelvic floor monitoring data at the two times are the corresponding data is greater.

[0050] For any i-th historical patient and j-th historical patient, the greater the difference in their corresponding data, the greater the category difference between them. Thus, the category difference between any i-th historical patient and j-th historical patient can be calculated.

[0051] Specifically, for any i-th historical patient and j-th historical patient, among all the pelvic floor monitoring data of the j-th historical patient at all times, the pelvic floor monitoring data with the greatest possibility of being the corresponding data to the pelvic floor monitoring data of the i-th historical patient at the s-th time is recorded as the corresponding data of the pelvic floor monitoring data of the i-th historical patient at the s-th time. Thus, the corresponding data of the pelvic floor monitoring data of the i-th historical patient at each time in all the pelvic floor monitoring data of the j-th historical patient can be determined. Similarly, the corresponding data of the pelvic floor monitoring data of the j-th historical patient at each time in all the pelvic floor monitoring data of the i-th historical patient can be determined.

[0052] Furthermore, according to the possibility that the pelvic floor monitoring data of the i-th historical patient at each time corresponds to the corresponding data in all the pelvic floor monitoring data of the j-th historical patient, and the possibility that the pelvic floor monitoring data of the j-th historical patient at each time corresponds to the corresponding data in all the pelvic floor monitoring data of the i-th historical patient, the category difference between any i-th historical patient and j-th historical patient is determined by the following formula: ; In the formula: Represents the class difference between any i-th historical patient and j-th historical patient; Represents the quantity of pelvic floor monitoring data of any i-th historical patient, that is, the quantity at all times of any i-th historical patient; Represents the possibility that the pelvic floor monitoring data of the s-th time of any i-th historical patient corresponds to the corresponding data among the pelvic floor monitoring data of all times of the j-th historical patient; Represents the quantity of pelvic floor monitoring data of any j-th historical patient, that is, the quantity at all times of any j-th historical patient; Represents the possibility that the pelvic floor monitoring data of the v-th time of any j-th historical patient corresponds to the corresponding data among the pelvic floor monitoring data of all times of the i-th historical patient; exp represents the exponential function with the natural constant e as the base.

[0053] In the above formula, when the cumulative sum of the possibilities that the pelvic floor monitoring data of each time of the i-th historical patient corresponds to the corresponding data among the pelvic floor monitoring data of all times of the j-th historical patient, and the cumulative sum of the possibilities that the pelvic floor monitoring data of each time of the j-th historical patient corresponds to the corresponding data among the pelvic floor monitoring data of all times of the i-th historical patient are smaller, it indicates that the i-th historical patient and the j-th historical patient are less likely to be of the same class, and the corresponding class difference should be larger.

[0054] In the same way as above, the class difference between any two historical patients can be determined. Taking the class difference between historical patients as the distance, the elbow method is used to determine the value of k, and the k-means algorithm is used to cluster all historical patients to obtain several cluster classes, and each cluster class contains several historical patients. Each cluster class corresponds to historical patients of a certain disease type.

[0055] The historical patient screening module is used to determine the referability of different historical patients based on the change of different types of pelvic floor electromyogram signals of different historical patients over time, and screen the historical patients in each of the cluster classes according to the referability.

[0056] Specifically, after all historical patients are divided into multiple clusters, a disease reference model can be constructed based on the pelvic floor monitoring data of all historical patients in each cluster. However, since pelvic floor monitoring data requires the cooperation of patients, which involves patient compliance and the standardization of operations, including historical patients with poor compliance and insufficient operational standards in the establishment of the disease reference model will result in insufficient accuracy of the final constructed disease reference model. At the same time, since the recovery conditions of different patients are different, there may be recurring situations. Therefore, it is necessary to screen representative patients from all historical patients in the same cluster as a reference, so as to ensure the accuracy of the pelvic floor monitoring data and the regularity of the recovery of the symptoms reflected, and ultimately improve the accuracy of the constructed disease reference model.

[0057] Furthermore, the above-mentioned historical patient screening module includes: A symptom degree change index acquisition module is used to determine the symptom degree change index of any historical patient based on the difference between the symptom degrees of any historical patient at adjacent times; A time consistency acquisition module is used to determine the time interval consistency of any historical patient based on the distribution of time intervals between adjacent times of any historical patient; The referenceability acquisition module is used to determine the product of the symptom degree change index and the time interval consistency of any historical patient, so as to obtain the referenceability of any historical patient.

[0058] Specifically, the time interval between every two adjacent times of any historical patient is determined, and the distribution of the time interval is analyzed. The more drastic the change in the time interval, the weaker the regularity of the time interval, that is, the poorer the consistency of the time interval, which means that the reference value of the pelvic floor monitoring data of the corresponding historical patient is lower; at the same time, the smaller the difference between the severity of the symptoms of the historical patient at each adjacent time, which reflects that the recurrence of the symptoms of the historical patient is more significant, and also means that the reference value of the pelvic floor monitoring data of the corresponding historical patient is lower.

[0059] Furthermore, the consistency acquisition module includes: an average time interval obtaining unit, for determining an average time interval between adjacent times of any historical patient according to an overall distribution level of time intervals between adjacent times of any historical patient; a maximum time interval obtaining unit, configured to determine a maximum time interval among time intervals between adjacent times of any historical patient; The time interval consistency obtaining unit is used to determine the ratio of the average time interval to the maximum time interval, thereby obtaining the time interval consistency of any historical patient.

[0060] In this embodiment, for any i-th historical patient, according to the difference in the disease severity between adjacent times and the distribution of the time intervals between adjacent times, the referenceability of the i-th historical patient is determined by the following formula: ; In the formula: represents the referenceability of any i-th historical patient; represents the number of pelvic floor monitoring data of any i-th historical patient, that is, the number of all times of any i-th historical patient; respectively represent the disease severity at the s + 1-th and s-th times of any i-th historical patient; represents the sum of the time intervals between all adjacent times of any i-th historical patient; represents the maximum interval time of the time intervals between all adjacent times of any i-th historical patient; exp represents the exponential function with the natural constant e as the base.

[0061] In the above formula, represents the symptom severity change index of any i-th historical patient, which reflects the difference in the disease severity of the pelvic floor monitoring data at all consecutive times. The smaller the difference, the more significant the recurrence of the disease of the i-th historical patient, and thus the stronger the referenceability of the i-th historical patient. At the same time, calculate the ratio of the average time interval to the maximum time interval between adjacent times of the i-th historical patient , the ratio represents the time interval consistency of any i-th historical patient, which reflects the regularity of the time intervals of the pelvic floor monitoring data at all consecutive times. The larger this value, the stronger the time interval consistency, and the stronger the referenceability of the i-th historical patient.

[0062] In any one cluster, in the above manner, the referenceability of each historical patient can be determined. Sort the referenceabilities of all historical patients in the cluster from largest to smallest, and use the historical patients corresponding to the referenceabilities before the first 50% as the target historical patients in this cluster. In this way, the screening of historical patients in each cluster can be achieved. Subsequently, by constructing a disease condition reference model corresponding to each cluster based on the pelvic floor monitoring data of the screened target historical patients, the accuracy of the constructed disease condition reference model can be effectively guaranteed.

[0063] The model construction module is used to construct a disease condition reference model corresponding to each cluster based on the pelvic floor monitoring data of the target historical patients screened in each cluster.

[0064] Specifically, for each cluster class, based on the pelvic floor monitoring data of all target historical patients screened out in this cluster class, a disease condition reference model corresponding to this cluster class can be constructed.

[0065] Furthermore, the above model construction module includes: A first data point acquisition module, which is used to take the disease condition degrees of target historical patients in each of the cluster classes at different times as the abscissa, and the disease condition recovery speeds at different times as the ordinate, to construct data points corresponding to each of the cluster classes; A disease condition reference model acquisition module, which is used to perform linear fitting on the data points corresponding to each of the cluster classes, and take the obtained fitting line as the disease condition reference model corresponding to each of the cluster classes.

[0066] Specifically, for the pelvic floor monitoring data of all target historical patients in each cluster class, taking the disease condition degree corresponding to the time of the pelvic floor monitoring data as the abscissa, and the disease condition recovery speed corresponding to the time of the pelvic floor monitoring data as the ordinate, plot the data points corresponding to the pelvic floor monitoring data of all target historical patients in each cluster class in a two-dimensional coordinate system. Then use the least squares method to perform linear fitting on all the data points, and the obtained fitting line is the disease condition reference model corresponding to the historical patients in this cluster class.

[0067] In the above manner, the disease condition reference model corresponding to each cluster class can be determined.

[0068] A data screening module, which is used to analyze the pelvic floor monitoring data of a real-time patient, determine the matching disease condition reference model among all the disease condition reference models, and screen the valid disease condition data in the pelvic floor monitoring data of the real-time patient based on the matching disease condition reference model.

[0069] Specifically, for a real-time patient, compare the obtained pelvic floor monitoring data with the disease condition reference models corresponding to different cluster classes, so as to obtain the matching disease condition reference model to which it belongs, and then the valid disease condition data in the pelvic floor monitoring data of this real-time patient can be screened based on the matching disease condition reference model.

[0070] Furthermore, the data screening module includes: A second disease condition degree acquisition module, which is used to determine the disease condition degrees of the real-time patient at different times according to the differences between different types of pelvic floor electromyogram signals of the real-time patient at different times and the corresponding normal reference values; A second disease condition recovery speed acquisition module, which is used to determine the disease condition recovery speeds of the real-time patient at different times according to the magnitudes of the differences between the disease condition degrees of the real-time patient at adjacent times; A second data point acquisition module, which is used to take the disease condition degrees of the real-time patient at different times as the abscissa, and the disease condition recovery speeds at different times as the ordinate, to construct data points corresponding to the real-time patient at different times; A linear fitting module, which is used to perform linear fitting on the data points corresponding to the real-time patient to obtain the fitting line corresponding to the real-time patient; A matching disease condition reference model acquisition module, which is used to compare the slopes of the fitting lines corresponding to the real-time patient with the fitting lines corresponding to each disease condition reference model, and use the disease condition reference model with the closest slope as the matching disease condition reference model.

[0071] Specifically, based on the pelvic floor monitoring data of the real-time patient, that is, the different types of pelvic floor electromyogram signals of the real-time patient at different times, in the same way as obtaining the disease condition degree and disease condition recovery speed of any historical patient at different times above, the disease condition degree and disease condition recovery speed of the real-time patient at different times can be obtained. Furthermore, in the same way as constructing the data points corresponding to each cluster class above, the data points corresponding to the real-time patient at different times can be constructed. Then, the least squares method is used to perform linear fitting on these data points to obtain the fitting line corresponding to the real-time patient. The fitting line corresponding to the real-time patient is compared with the fitting lines corresponding to each disease condition reference model, and the disease condition reference model with the closest slope to the fitting line corresponding to the real-time patient among all the fitting lines corresponding to the disease condition reference models is recorded as the matching disease condition reference model of the real-time patient.

[0072] Considering that the recovery time of pelvic floor patients is usually long, and the real-time patient performs pelvic floor muscle monitoring every day, and obvious disease condition changes may occur only after one week or half a month. Then, the pelvic floor monitoring data during this period can all be represented by a small amount of monitoring data and used as effective disease condition data, so as to reduce the influence of interference data. For this reason, a suitable time period, that is, a time window, is determined to segment the pelvic floor monitoring data of the real-time patient, so as to screen out the effective disease condition data in the pelvic floor monitoring data corresponding to each time period.

[0073] Furthermore, the above data screening module further includes: A time window determination module, which is used to construct each time window of the pelvic floor monitoring data of the real-time patient under different time window sizes; A rationality determination module, which is used to determine the rationality of different time window sizes according to the distances from the data points corresponding to each time in each time window of the real-time patient to the fitting line corresponding to the matching disease condition reference model, and the difference in disease condition degrees at each time between adjacent time windows. An effective condition data determination module is used to take the time window size corresponding to the maximum rationality as the target time window size, determine the target time in each time window of the real-time patient under the target time window size, and use the pelvic floor electromyogram signals of different types corresponding to the target time of the real-time patient as the effective condition data. The target time refers to at least one time in the time window where the corresponding data points best conform to the fitting line of the matching condition reference model.

[0074] Specifically, the time window size is determined. When the time window size is too large, it will result in less effective condition data and unable to fully represent the disease condition changes of the real-time patient. When the time window size is too small, it will be greatly affected by data fluctuations and the referenceability of the selected data is insufficient. Therefore, with 5 days as the initial time window size, 1 day as the step size, and 15 days as the termination time window size, multiple different time window sizes are determined.

[0075] Under different time window sizes, each time window of the pelvic floor monitoring data of the real-time patient is constructed, that is, taking each time window size as the time period length, the time series of the real-time patient is segmented, and each segmented time subsequence is a time window.

[0076] Under the same time window size, the data points corresponding to each time in each time window of the real-time patient are analyzed. The smaller the distance from the data point to the fitting line of the matching condition reference model, the more the data points corresponding to each time in the time window conform to the condition reference model, and at this time the rationality of this time window size is higher; at the same time, the smaller the difference in the disease condition degree of each time between adjacent time windows, the less affected by data fluctuations. At this time, on the basis of conforming to the condition reference model, a larger time window size indicates a higher rationality of this time window size.

[0077] Furthermore, the above-mentioned rationality determination module includes: A window distance determination unit is used to determine the central data point of the data points corresponding to each time in each time window of the real-time patient, and determine the distance from the central data point to the fitting line of the matching condition reference model to obtain the window distance; A first sum determination unit is used to determine the first sum of the window distances corresponding to each time window of the real-time patient; An average disease condition degree determination unit is used to determine the average disease condition degree of the real-time patient in each time window according to the overall distribution level of the disease condition degree of each time in each time window of the real-time patient; A second sum determination unit is used to determine the second sum of the absolute values of the differences in the average disease condition degree between each adjacent two time windows of the real-time patient; A rationality determination unit is configured to perform negative correlation normalization processing on the product of the first cumulative sum and the second cumulative sum, so as to obtain the rationality of different time window sizes.

[0078] Specifically, under the same time window size, the average value of the disease severity corresponding to each time in each time window of the real-time patient and the average value of the disease recovery speed are determined, and the corresponding average disease severity and average disease recovery speed corresponding to each time window are obtained. Taking the average disease severity as the abscissa and the average disease recovery speed as the ordinate, data points are determined in the two-dimensional coordinate system where the fitting line corresponding to the matching disease condition reference model is located, and this data point is called the central data point corresponding to the real-time patient in each time window. Based on the distance from the central data point corresponding to the real-time patient in each time window to the fitting line corresponding to the matching disease condition reference model, this distance is called the window distance, and the absolute value of the difference between the average disease severities of the real-time patient in two adjacent time windows, the rationality of this time window size is determined by the following formula: ; In the formula: represents the rationality of any time window size; represents the total number of time windows corresponding to the real-time patient under any time window size; represents the average disease severity corresponding to the w-th time window corresponding to the real-time patient under any time window size, represents the average disease recovery speed corresponding to the w-th time window corresponding to the real-time patient under any time window size; represents the average disease severity corresponding to the w-th time window corresponding to the real-time patient under any time window size and the average disease recovery speed of the corresponding central data point to the distance of the fitting line corresponding to the matching disease condition reference model; represents the average disease severity corresponding to the (w - 1)-th time window corresponding to the real-time patient under any time window size; exp represents the exponential function with the natural constant e as the base.

[0079] In the above formula, by calculating the cumulative sum of the distances from the central data points corresponding to each time window corresponding to the real-time patient under any time window size to the fitting line corresponding to the matching disease condition reference model, the first cumulative sum is obtained, and the second cumulative sum of the absolute values of the differences between the average disease severities of the real-time patient in two adjacent time windows is calculated Since the first cumulative sum The smaller the value of and the second cumulative sum is, the higher the rationality of the corresponding time window size. Therefore, the product of the first cumulative sum and the second cumulative sum is negatively correlated and normalized using an exponential function to obtain the rationality of the time window size.

[0080] In the above manner, the rationality of different time window sizes can be determined. The time window size corresponding to the maximum rationality is used as the target time window size, and each time window of the real-time patient under the target time window size is used as the target time window. The distance from each data point corresponding to each time in each target time window to the fitting line corresponding to the matching disease reference model is determined, and different types of pelvic floor electromyogram signals at the time corresponding to the minimum distance are used as a set of effective disease data, thereby obtaining several sets of effective disease data. The number of sets of effective disease data is the number of target time windows.

[0081] The effective disease data in the pelvic floor monitoring data of the real-time patient is uploaded and synchronized. At the same time, in order to facilitate doctors and nurses to refer to the comprehensive monitoring information of the real-time patient and analyze the monitoring data of the real-time patient, the disease-related data of the real-time patient is also uploaded and synchronized. Specifically, in the doctor-patient interaction platform and the pelvic floor patient information sharing platform, the effective disease data in the pelvic floor monitoring data of the real-time patient is prominently marked at the patient end, and all the pelvic floor monitoring data, effective disease data, and reference disease data of the real-time patient are synchronized to the doctor end and the nurse end for doctors and nurses to refer to and analyze, and timely adjust the pelvic floor treatment plan. Among them, the reference disease data is the disease degree and disease recovery speed corresponding to the fitting line of the matching disease reference model of the real-time patient. All the pelvic floor monitoring data and reference disease data of the real-time patient together constitute the disease-related data of the real-time patient.

[0082] In addition, after one target time window, if the real-time patient still has not uploaded monitoring data such as effective disease data and disease-related data, the patient can be reminded to monitor in time to ensure the timely update of the monitoring data and ensure the normal progress of the dynamic tracking of the pelvic floor patient's condition.

[0083] Based on the same inventive concept, an embodiment of the present invention also provides a method for dynamically tracking the condition of pelvic floor patients based on Internet technology, as Figure 2 shown. The method includes: Obtain the pelvic floor monitoring data of different historical patients and the pelvic floor monitoring data of a real-time patient, where the pelvic floor monitoring data includes different types of pelvic floor electromyogram signals corresponding to different times; Based on the differences between the same type of pelvic floor electromyogram signals of different historical patients at different times, and the differences between the changes of the same type of pelvic floor electromyogram signals of different historical patients over time, determine the category differences between any two historical patients, and cluster all historical patients based on the category differences to obtain several clusters; Based on the changes over time of different types of pelvic floor electromyogram signals of different historical patients, determine the referenceability of different historical patients, and screen the historical patients in each cluster according to the referenceability; Based on the pelvic floor monitoring data of the target historical patients selected from each cluster, construct a disease reference model corresponding to each cluster; Analyze the pelvic floor monitoring data of the real-time patient, determine the matching disease reference model among all the disease reference models, and screen the effective disease data in the pelvic floor monitoring data of the real-time patient based on the matching disease reference model.

[0084] Based on the same inventive concept, an embodiment of the present invention further provides a pelvic floor patient disease dynamic tracking device based on Internet technology, as Figure 3 shown. The device includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302. When the processor 302 executes the computer program 303, the device can execute the module implementation steps in any one of the aforementioned pelvic floor patient disease dynamic tracking systems based on Internet technology.

[0085] An embodiment of the present invention can divide the functions of the device according to the module implementation step examples in the above system. For example, it can correspond to each functional module, or integrate two or more functions into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0086] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, the computer executes the module implementation steps in any one of the aforementioned pelvic floor patient disease dynamic tracking systems based on Internet technology.

[0087] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium storing computer program code, which, when running on a computer, causes the computer to execute the module implementation steps in any of the aforementioned pelvic floor patient condition dynamic tracking systems based on Internet technology.

[0088] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A dynamic tracking system for the condition of pelvic floor patients based on Internet technology, characterized in that, The system includes: A data acquisition module, configured to acquire pelvic floor monitoring data of different historical patients and pelvic floor monitoring data of a real-time patient, where the pelvic floor monitoring data includes different types of pelvic floor electromyogram signals corresponding to different times; A clustering module, configured to determine the class differences between any two historical patients based on the differences between the same type of pelvic floor electromyogram signals of different historical patients at different times and the differences between the changes of the same type of pelvic floor electromyogram signals of different historical patients over time, and cluster all historical patients based on the class differences to obtain several clusters; A historical patient screening module, configured to determine the referability of different historical patients based on the changes of different types of pelvic floor electromyogram signals of different historical patients over time, and screen the historical patients in each cluster according to the referability; A model construction module, configured to construct a disease reference model corresponding to each cluster based on the pelvic floor monitoring data of the target historical patients screened out in each cluster; A data screening module, configured to analyze the pelvic floor monitoring data of the real-time patient, determine the matching disease reference model among all the disease reference models, and screen the effective disease data in the pelvic floor monitoring data of the real-time patient based on the matching disease reference model.

2. The dynamic condition tracking system for pelvic floor patients based on Internet technology according to claim 1, characterized in that, The clustering module includes: A similarity acquisition module, configured to determine the similarity of the pelvic floor monitoring data between any two historical patients at different times based on the differences between the same type of pelvic floor electromyogram signals of any one historical patient at any one time and any other historical patient at any one time; A first disease degree acquisition module, configured to determine the disease degree of any one historical patient at different times based on the differences between different types of pelvic floor electromyogram signals of any one historical patient at different times and the corresponding normal reference values; A first disease recovery speed acquisition module, configured to determine the disease recovery speed of any one historical patient at different times based on the difference magnitude between the disease degrees of any one historical patient at adjacent times; A possibility acquisition module, configured to comprehensively determine the possibility that the pelvic floor monitoring data between any two historical patients at different times is the corresponding data based on the similarity of the pelvic floor monitoring data between any two historical patients at different times and the difference in the disease recovery speed at different times; A class difference acquisition module, configured to determine the class differences between any two historical patients based on the possibility that the pelvic floor monitoring data between any two historical patients at different times is the corresponding data.

3. The dynamic condition tracking system for pelvic floor patients based on Internet technology according to claim 2, characterized in that, The similarity acquisition module includes: A first cumulative difference value acquisition unit, configured to determine the cumulative value of the absolute values of the differences of the same type of pelvic floor electromyogram signals between any one historical patient at any one time and any other historical patient at any one time, to obtain a first cumulative difference value; A similarity acquisition unit, configured to perform a negative correlation normalization process on the first cumulative difference value, so as to obtain the similarity of the pelvic floor monitoring data between any two historical patients at different times.

4. The pelvic floor patient condition dynamic tracking system based on Internet technology according to claim 2, wherein The first disease degree acquisition module includes: A second cumulative difference value acquisition unit, configured to determine a cumulative value of absolute values of differences between different types of pelvic floor electromyogram signals of any historical patient at the same time and corresponding normal reference values, so as to obtain a second cumulative difference value; A disease severity acquisition unit, configured to perform a positive correlation normalization process on the second cumulative difference value, so as to obtain the disease severity of any historical patient at different times.

5. The pelvic floor patient condition dynamic tracking system based on Internet technology according to claim 2, characterized in that, The historical patient screening module includes: A symptom severity change index acquisition module, configured to determine a symptom severity change index of any historical patient according to the difference magnitude between the disease severities of any historical patient at adjacent times; A time consistency acquisition module, configured to determine the time interval consistency of any historical patient according to the distribution of time intervals between adjacent times of any historical patient; A referenceability acquisition module, configured to determine a product of the symptom severity change index and the time interval consistency of any historical patient, so as to obtain the referenceability of any historical patient.

6. The dynamic condition tracking system for pelvic floor patients based on Internet technology according to claim 5, wherein The consistency acquisition module includes: An average time interval acquisition unit, configured to determine an average time interval between adjacent times of any historical patient according to the overall distribution level of time intervals between adjacent times of any historical patient; A maximum time interval acquisition unit, configured to determine a maximum time interval among time intervals between adjacent times of any historical patient; A time interval consistency acquisition unit, configured to determine a ratio of the average time interval to the maximum time interval, so as to obtain the time interval consistency of any historical patient.

7. The pelvic floor patient condition dynamic tracking system based on Internet technology according to claim 2, wherein The model construction module includes: A first data point acquisition module, configured to construct data points corresponding to each cluster class, with the disease severity of the target historical patient in each cluster class at different times as the abscissa and the disease recovery speed at different times as the ordinate; A disease condition reference model acquisition module, configured to perform linear fitting on the data points corresponding to each cluster class, and use the obtained fitting line as the disease condition reference model corresponding to each cluster class.

8. The dynamic condition tracking system for pelvic floor patients based on Internet technology according to claim 7, characterized in that, The data screening module includes: A second disease severity acquisition module, configured to determine the disease severity of a real-time patient at different times according to the difference between different types of pelvic floor electromyogram signals of the real-time patient at different times and corresponding normal reference values; A second disease recovery speed acquisition module, configured to determine the disease recovery speed of the real-time patient at different times according to the difference magnitude between the disease severities of the real-time patient at adjacent times; A second data point acquisition module, configured to construct data points corresponding to the real-time patient at different times, with the disease severity of the real-time patient at different times as the abscissa and the disease recovery speed at different times as the ordinate; A linear fitting module, configured to perform linear fitting on the data points corresponding to the real-time patient, to obtain a fitting line corresponding to the real-time patient; A matching disease condition reference model acquisition module, configured to compare the slopes of the fitting line corresponding to the real-time patient and the fitting lines corresponding to each disease condition reference model, and use the disease condition reference model with the closest slope as the matching disease condition reference model.

9. The dynamic condition tracking system for pelvic floor patients based on Internet technology according to claim 8, wherein The data screening module further includes: A time window determination module, configured to construct each time window of the pelvic floor monitoring data of a real-time patient under different time window sizes; A rationality determination module, configured to determine the rationality of different time window sizes according to the distances from the data points corresponding to each time in each of the time windows of the real-time patient to the fitting line corresponding to the matching disease reference model, and the difference in the disease severity levels at each time between adjacent time windows; An effective disease data determination module, configured to use the time window size corresponding to the maximum rationality as the target time window size, determine the target time in each time window of the real-time patient under the target time window size, and use different types of pelvic floor electromyogram signals corresponding to the target time of the real-time patient as effective disease data, where the target time refers to at least one time when the data point corresponding to the time in the time window most conforms to the fitting line corresponding to the matching disease reference model.

10. The dynamic condition tracking system for pelvic floor patients based on Internet technology according to claim 9, wherein The rationality determination module includes: A window distance determination unit, configured to determine the central data point of the data points corresponding to each time in each of the time windows of the real-time patient, and determine the distance from the central data point to the fitting line corresponding to the matching disease reference model, to obtain a window distance; A first sum determination unit, configured to determine the first sum of the window distances corresponding to each of the time windows of the real-time patient; An average disease severity determination unit, configured to determine the average disease severity of the real-time patient in each of the time windows according to the overall distribution level of the disease severity levels at each time in each of the time windows of the real-time patient; A second sum determination unit, configured to determine the second sum of the absolute values of the differences in the average disease severity between each two adjacent time windows of the real-time patient; A rationality determination unit, configured to perform a negative correlation normalization process on the product of the first sum and the second sum, so as to obtain the rationality of different time window sizes.

Images