Pelvic floor muscle pressure detection method and system for pelvic floor muscle function screening

Abstract

The invention relates to the technical field of data denoising, in particular to a pelvic floor muscle pressure detection method and system for pelvic floor muscle function screening, and the method comprises the steps: obtaining pelvic floor muscle pressure time sequence data, segmenting the pelvic floor muscle pressure time sequence data, and obtaining a plurality of pressure sequence segments; based on the length of each pressure sequence segment, screening out suspected noise sequence segments from each pressure sequence segment; according to the pressure change trend in the process of recovering the suspected noise sequence segment to the normal, combining the speed of recovering the suspected noise sequence segment to the normal to obtain the recovery trend stability of the suspected noise sequence segment, and combining the normal state maintenance duration after the suspected noise sequence segment to obtain the abnormal factor of the suspected noise sequence segment; and according to the abnormal factors, screening the suspected noise sequence segments to obtain the noise sequence segments, so that the accuracy of noise identification can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data denoising, and particularly relates to a pelvic floor muscle pressure detection method and system for pelvic floor muscle function screening. Background Art

[0002] Pelvic floor muscle function screening is an examination for evaluating the function of pelvic floor muscles. Among them, pelvic floor muscle pressure data can most directly and quantitatively reflect the physiological state and function of pelvic floor muscles, and has the advantages of non-invasiveness, convenience, and rapidity, etc. It can obtain a large amount of effective data in a short time, so it is widely used in pelvic floor muscle function screening.

[0003] Pelvic floor muscle pressure detection requires high-precision sensors to accurately capture weak pressure changes. During long-term use, the sensors may have stability problems such as noise interference. There are many types of noises that appear, and individual types of noises often confuse with normal physiological phenomena of the body. For example, short-term noises such as electromagnetic interference and normal physiological phenomena of the body such as abdominal pressure. The impacts of both on pelvic floor muscle pressure data are sudden and the impact time is short. When detecting noises in pelvic floor muscle pressure data, it is easy to cause the problem of low accuracy in noise recognition. For example, short-term noises may be recognized as normal data. Summary of the Invention

[0004] In order to solve the technical problem of low accuracy in noise recognition when detecting noises in pelvic floor muscle pressure data, the purpose of the present invention is to provide a pelvic floor muscle pressure detection method and system for pelvic floor muscle function screening. The specific technical solutions adopted are as follows: In the first aspect of the present invention, a pelvic floor muscle pressure detection method for pelvic floor muscle function screening is provided, including: Obtain pelvic floor muscle pressure time series data, segment the pelvic floor muscle pressure time series data to obtain a plurality of pressure sequence segments; Based on the lengths of the respective pressure sequence segments, screen out suspected noise sequence segments from the respective pressure sequence segments; According to the pressure change trend during the process of the suspected noise sequence segment returning to normal, and combining with the speed of the suspected noise sequence segment returning to normal, obtain the recovery trend stability of the suspected noise sequence segment; According to the recovery trend stability and the duration of maintaining the normal state after the suspected noise sequence segment, obtain the abnormal factor of the suspected noise sequence segment; According to the abnormal factor, screen out noise sequence segments from the respective suspected noise sequence segments.

[0005] In an exemplary embodiment, the segmenting the pelvic floor muscle pressure time series data to obtain a plurality of pressure sequence segments includes: The pelvic floor muscle pressure time series data is segmented by using an adaptive piecewise constant approximation method to obtain multiple pressure sequence segments.

[0006] In an exemplary embodiment, screening out suspected noise sequence segments from each pressure sequence segment based on the length of each pressure sequence segment includes: Obtaining the mode of the lengths from the lengths of each pressure sequence segment; Obtaining the length difference between the length of each pressure sequence segment and the length of the mode; According to the length difference and the number of occurrences of the mode, obtaining the period abnormality degree of each pressure sequence segment, where the period abnormality degree is proportional to the length difference and proportional to the number of occurrences; Screening out suspected noise sequence segments from each pressure sequence segment according to the period abnormality degree of each pressure sequence segment.

[0007] In an exemplary embodiment, the process of obtaining the speed at which the suspected noise sequence segment returns to normal includes: Obtaining the target sequence segment of the first suspected noise sequence segment, where the first suspected noise sequence segment is any one of the suspected noise sequence segments, and the target sequence segment is the pressure sequence segment corresponding to the mode that first appears after the first suspected noise sequence segment; Obtaining the duration of the recovery stage sequence segment of the first suspected noise sequence segment, where the recovery stage sequence segment is the time period between the first suspected noise sequence segment and its corresponding target sequence segment; Obtaining the eigenvalue difference between the eigenvalue of the first suspected noise sequence segment and the eigenvalue of its corresponding target sequence segment; According to the duration of the recovery stage sequence segment and the eigenvalue difference, obtaining the speed at which the first suspected noise sequence segment returns to normal; the speed is inversely proportional to the duration of the recovery stage sequence segment and inversely proportional to the eigenvalue difference.

[0008] In an exemplary embodiment, the process of obtaining the pressure change trend during the process of the suspected noise sequence segment returning to normal includes: Obtaining each wave peak in the recovery stage sequence segment; Obtaining the quantity proportion of the first wave peak, where the first wave peak is a wave peak that satisfies the following condition: the peak value is greater than the peak value of the next adjacent wave peak.

[0009] In an exemplary embodiment, obtaining the recovery trend stability of the suspected noise sequence segment according to the pressure change trend during the process of the suspected noise sequence segment returning to normal and combining with the speed at which the suspected noise sequence segment returns to normal includes: The recovery trend stability of the first suspected noise sequence segment is obtained based on the speed of the first suspected noise sequence segment returning to normal, the proportion of the number of first peaks corresponding to the first suspected noise sequence segment, and the peak change fluctuation degree of the first peak of the recovery stage sequence segment of the first suspected noise sequence segment; the recovery trend stability is directly proportional to the speed, directly proportional to the proportion of the number, and inversely proportional to the peak change fluctuation degree.

[0010] In an exemplary embodiment, the process of obtaining the duration of maintaining the normal state after the suspected noise sequence segment includes: Obtain the duration of the time period between the target sequence segment of the first suspected noise sequence segment and the second suspected noise sequence segment as the duration of maintaining the normal state; the second suspected noise sequence segment is the first suspected noise sequence segment that appears after the target sequence segment.

[0011] In an exemplary embodiment, obtaining the abnormal factor of the suspected noise sequence segment according to the recovery trend stability and the duration of maintaining the normal state after the suspected noise sequence segment includes: Obtain the abnormal factor of the first suspected noise sequence segment according to the recovery trend stability of the first suspected noise sequence segment and the duration of maintaining the normal state of the first suspected noise sequence segment; the abnormal factor is inversely proportional to the recovery trend stability and inversely proportional to the duration of maintaining the normal state.

[0012] In an exemplary embodiment, screening the noise sequence segment from each suspected noise sequence segment according to the abnormal factor includes: Use the suspected noise sequence segment corresponding to the abnormal factor greater than or equal to the preset abnormal threshold as the noise sequence segment.

[0013] In a second aspect of the present invention, a pelvic floor muscle pressure detection system for pelvic floor muscle function screening is provided, including: a memory and a processor; the memory is connected to the processor; the memory is used to store program instructions; the processor is used to implement the above-mentioned pelvic floor muscle pressure detection method for pelvic floor muscle function screening when the program instructions are executed.

[0014] The present invention has the following beneficial effects: By segmenting the pelvic floor muscle pressure time-series data to obtain multiple pressure sequence segments, and then analyzing each pressure sequence segment, the reliability of the pelvic floor muscle pressure time-series data can be improved, thereby enhancing the accuracy of subsequent data denoising. First, based on the lengths of the pressure sequence segments, suspected noise sequence segments are screened out from each pressure sequence segment. Then, taking the suspected noise sequence segments as the analysis objects, according to the data change characteristics and noise interference characteristics when abnormalities occur, the recovery trend stability of each suspected noise sequence segment is analyzed, so as to obtain the abnormal factor of each suspected noise sequence segment. By screening the noise sequence segments according to the abnormal factors, the accuracy of noise recognition can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flowchart of a pelvic floor muscle pressure detection method for pelvic floor muscle function screening provided by an embodiment of the present invention; Figure 2 is a waveform schematic diagram of the pelvic floor muscle pressure time-series data provided by an embodiment of the present invention; Figure 3 is a flowchart for screening suspected noise sequence segments provided by an embodiment of the present invention; Figure 4 is a flowchart for obtaining the speed at which a suspected noise sequence segment returns to normal provided by an embodiment of the present invention; Figure 5 is a flowchart for obtaining the pressure change trend provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following describes in detail the specific embodiments, structures, features, and effects of the present invention in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The data information collected in this application has been obtained with full consent and authorization, and the collection, use, and processing of relevant information need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0018] The application scenario of a pelvic floor muscle pressure detection method for pelvic floor muscle function screening provided in this embodiment is as follows: The pelvic floor muscle pressure of a user is detected by a pelvic floor muscle pressure measuring instrument. Specifically, the pressure sensor in the pelvic floor muscle pressure measuring instrument senses the pelvic floor muscle pressure of the user. The pressure data of the pelvic floor muscles directly reflects the contraction and relaxation functions of the user's pelvic floor muscles. However, when collecting the pelvic floor muscle pressure data, it is inevitably affected by the user himself and environmental factors, and there may be certain measurement errors in the pressure sensor itself, resulting in abnormal noise data fluctuations in the collected pressure data. The purpose of a pelvic floor muscle pressure detection method for pelvic floor muscle function screening provided in this embodiment is to improve the accuracy of noise recognition of pelvic floor muscle pressure data.

[0019] As Figure 1 shown, a pelvic floor muscle pressure detection method for pelvic floor muscle function screening provided in this embodiment includes the following steps: Step 1: Obtain the pelvic floor muscle pressure time series data, and segment the pelvic floor muscle pressure time series data to obtain multiple pressure sequence segments.

[0020] Step 2: Based on the length of each pressure sequence segment, screen out the suspected noise sequence segments from each pressure sequence segment.

[0021] Step 3: According to the pressure change trend and pressure fluctuation situation during the recovery of the suspected noise sequence segment to the normal state, and combined with the recovery speed of the suspected noise sequence segment to the normal state, obtain the recovery trend stability of the suspected noise sequence segment.

[0022] Step 4: According to the recovery trend stability and the normal state maintenance duration after the suspected noise sequence segment, obtain the abnormal factor of the suspected noise sequence segment.

[0023] Step 5: According to the abnormal factor, screen out the noise sequence segments from each suspected noise sequence segment.

[0024] The following combines the accompanying drawings to illustrate the specific implementation process of each step of a pelvic floor muscle pressure detection method for pelvic floor muscle function screening provided in this embodiment.

[0025] Step 1: Obtain the pelvic floor muscle pressure time series data, and segment the pelvic floor muscle pressure time series data to obtain multiple pressure sequence segments.

[0026] Collect the pelvic floor muscle pressure of the user at a preset acquisition frequency, and the acquisition frequency is set according to the actual situation. For example, the acquisition frequency is once per second.

[0027] Preset a monitoring time period, which includes multiple acquisition moments, and obtain multiple pelvic floor muscle pressure data within this monitoring time period, so as to form pelvic floor muscle pressure time series data in sequence. Among them, the duration of the monitoring time period is set according to actual needs. For example, the entire detection process of pelvic floor muscle pressure is used as this monitoring time period.

[0028] The contraction strength of the pelvic floor muscles is reflected by the change in pelvic floor muscle pressure. The higher the pelvic floor muscle pressure, the greater the corresponding muscle contraction force. Normal pelvic floor muscle pressure data usually shows periodic changes because the pelvic floor muscles are affected by voluntary control and periodic contractions. As Figure 2 shown, the abscissa is time and the ordinate is the amplitude of pelvic floor muscle pressure data.

[0029] If the recovery of pelvic floor muscle pressure is too slow, it indicates that the pelvic floor muscles do not contract normally, or may be greatly affected by noise. Sustained high pressure may be related to abdominal pressure. The voluntary contraction and relaxation of the pelvic floor muscles themselves have a certain rhythm, and the time intervals of their contraction and relaxation are relatively stable.

[0030] For the convenience of subsequent processing, the pelvic floor muscle pressure time series data is segmented to obtain multiple pressure sequence segments. The specific segmentation method is set according to actual needs. In an exemplary embodiment, in order to improve the reliability of data segmentation, and the pelvic floor muscle pressure data within the same pressure sequence segment is relatively relevant, and the differences in pelvic floor muscle pressure data between different pressure sequence segments are relatively large. In this embodiment, the Adaptive Piecewise Constant Approximation (APCA) method is used to segment the pelvic floor muscle pressure time series data to obtain multiple pressure sequence segments. The adaptive piecewise constant approximation method is a commonly used time series data segmentation method and will not be elaborated here. After using the adaptive piecewise constant approximation method for segmentation, each obtained pressure sequence segment has an APCA constant value (i.e., APCA approximation value), such as the pressure mean value of each pressure sequence segment.

[0031] Step 2: Based on the lengths of each pressure sequence segment, screen out suspected noise sequence segments from each pressure sequence segment.

[0032] After obtaining each pressure sequence segment, since under normal circumstances, each pressure sequence segment has regularity and periodicity, then, according to the lengths of each pressure sequence segment, suspected noise sequence segments can be screened out from each pressure sequence segment. In an exemplary embodiment, as Figure 3 shown, a specific screening process of suspected noise sequence segments is given: Step 2-1: Obtain the mode of the lengths from the lengths of each pressure sequence segment.

[0033] Obtain the lengths of each pressure sequence segment, that is, the number of acquisition moments included in each pressure sequence segment. And construct a length sequence based on the lengths of each pressure sequence segment. Obtain the mode of the lengths in this length sequence. The mode is the data value that appears most frequently in a set of data, that is, obtain the length that appears most frequently. If there are several modes, arbitrarily select one mode for analysis. Since the mode is the length that appears most frequently, it can also be understood that the pressure sequence segment corresponding to the mode is the pressure sequence segment under normal conditions.

[0034] Step 2-2: Obtain the length differences between each pressure sequence segment and the length of the mode.

[0035] Obtain the length differences between each pressure sequence segment and the length of the mode. Specifically: Calculate the absolute value of the difference between the length of each pressure sequence segment and the mode, as the length difference between each pressure sequence segment and the length of the mode.

[0036] Step 2-3: Obtain the period abnormality degree of each pressure sequence segment according to the length difference and the number of times the mode appears.

[0037] The greater the length difference between the pressure sequence segment and the length of the mode, it indicates that the difference between the length of the pressure sequence segment and the length of the most common pressure sequence segment is greater, and the period of the pressure sequence segment is more abnormal, that is, the period abnormality degree is greater. The number of times the mode appears is used as the credibility of the mode. The more times the mode appears, the higher the credibility of the corresponding mode. Therefore, according to the length difference and the number of times the mode appears, obtain the period abnormality degree of each pressure sequence segment. The period abnormality degree is proportional to the length difference and proportional to the number of times the mode appears.

[0038] In an exemplary embodiment, a specific calculation formula for the period abnormality degree of the pressure sequence segment is given as follows: ; Wherein, represents the period abnormality degree of the xth pressure sequence segment, represents the length of the xth pressure sequence segment, represents the mode, represents the absolute value of the difference between the length of the xth pressure sequence segment and the mode, represents the number of times the mode appears, norm represents the normalization function. The normalization method here can be: Obtain the maximum and minimum values of the product of the absolute value of the difference between the lengths of all pressure sequence segments and the mode and the number of times the mode appears, and then use the maximum-minimum value normalization method to perform normalization, and classify it into the numerical range of 0-1 for subsequent comparison.

[0039] Step 2-4: Screen out suspected noise sequence segments from each pressure sequence segment according to the degree of periodic abnormality of each pressure sequence segment.

[0040] The periodicity of the pressure sequence segment reflects the contraction and relaxation patterns of the pelvic floor muscles, usually showing regular fluctuations. However, affected by abdominal pressure and external environmental factors, the periodicity of the pelvic floor muscle pressure data may be disrupted. Among them, abdominal pressure is closely related to breathing or the activities of abdominal muscles. During breathing, the pressure generated by abdominal muscles will disrupt the periodicity of the pelvic floor muscle pressure.

[0041] Therefore, the degree of periodic abnormality of each pressure sequence segment reflects the degree of periodic abnormality of each pressure sequence segment. The greater the degree of periodic abnormality, the more abnormal the periodic state. Therefore, screen out suspected noise sequence segments from each pressure sequence segment according to the degree of periodic abnormality of each pressure sequence segment. In an exemplary embodiment, a threshold value of the degree of periodic abnormality is preset. The numerical range of the preset threshold value of the degree of periodic abnormality is 0-1, and its specific value is set according to actual judgment needs. If more accurate noise denoising judgment is required, the preset threshold value of the degree of periodic abnormality can be set smaller, so that more pressure sequence segments are determined as suspected noise sequence segments. Correspondingly, more suspected noise sequence segments need to be processed subsequently; if a looser noise denoising judgment is required, the preset threshold value of the degree of periodic abnormality can be set larger, so that fewer pressure sequence segments are determined as suspected noise sequence segments. Correspondingly, fewer suspected noise sequence segments need to be processed subsequently. In an exemplary embodiment, the preset threshold value of the degree of periodic abnormality is taken as 0.7.

[0042] Compare the degree of periodic abnormality of each pressure sequence segment with the preset threshold value of the degree of periodic abnormality, and determine the pressure sequence segment corresponding to the degree of periodic abnormality that is greater than or equal to the preset threshold value of the degree of periodic abnormality as a suspected noise sequence segment.

[0043] Step 3: Obtain the recovery trend stability of the suspected noise sequence segment according to the pressure change trend during the process of the suspected noise sequence segment returning to normal, combined with the speed of the suspected noise sequence segment returning to normal.

[0044] Under normal circumstances, during the contraction and relaxation process, the pressure of the pelvic floor muscles usually recovers relatively quickly, and the pressure curve shows a rapid decline to the resting state, indicating the elasticity and good function of the muscles.

[0045] Taking the suspected noise sequence segment as the key analysis object, the suspected noise sequence segment will gradually return to the normal state later. During the process of returning to the normal state, the pressure change trend of the pelvic floor muscle will affect the stability of the recovery trend of the suspected noise sequence segment. Moreover, the speed at which the suspected noise sequence segment returns to normal will also determine the stability of the recovery trend of the suspected noise sequence segment. Therefore, according to the pressure change trend during the process of the suspected noise sequence segment returning to normal, combined with the speed at which the suspected noise sequence segment returns to normal, the stability of the recovery trend of the suspected noise sequence segment is obtained.

[0046] In an exemplary embodiment, as Figure 4 shown, a specific obtaining process of the speed at which the suspected noise sequence segment returns to normal is given: Step 3-1: Obtain the target sequence segment of the first suspected noise sequence segment.

[0047] The pressure sequence segment corresponding to the mode is the pressure sequence segment with the most occurrences of length, that is, the most frequently occurring pressure sequence segment. Then, the pressure sequence segment corresponding to the mode is the pressure sequence segment under normal circumstances, that is, the pressure sequence segment corresponding to the mode cannot be a suspected noise sequence segment.

[0048] For the sake of convenience of explanation, assume that the first suspected noise sequence segment is any suspected noise sequence segment. Search backward from the first suspected noise sequence segment and end the search when the pressure sequence segment corresponding to the mode appears for the first time. Obtain the pressure sequence segment corresponding to the mode that appears for the first time after the first suspected noise sequence segment, and define this pressure sequence segment as the target sequence segment of the first suspected noise sequence segment.

[0049] Step 3-2: Obtain the duration of the recovery stage sequence segment of the first suspected noise sequence segment.

[0050] The first suspected noise sequence segment is a suspected abnormal pressure sequence segment, and the target sequence segment of the first suspected noise sequence segment is the target sequence segment under normal circumstances. Therefore, the time period between the first suspected noise sequence segment and the target sequence segment of the first suspected noise sequence segment can be understood as the recovery stage of the first suspected noise sequence segment returning to the normal state. Then, assume that the recovery stage sequence segment is the time period between the first suspected noise sequence segment and the target sequence segment of the first suspected noise sequence segment. And obtain the duration of the recovery stage sequence segment of the first suspected noise sequence segment. The duration of the recovery stage sequence segment of the first suspected noise sequence segment is the time interval between the first suspected noise sequence segment and its corresponding target sequence segment, and this time interval is the time interval between the end moment of the first suspected noise sequence segment and the start moment of its corresponding target sequence segment.

[0051] Step 3-3: Obtain the eigenvalue difference between the eigenvalue of the first suspected noise sequence segment and the eigenvalue of its corresponding target sequence segment.

[0052] Obtain the eigenvalue of the first suspected noise sequence segment and the eigenvalue of the target sequence segment of the first suspected noise sequence segment. Among them, the eigenvalue reflects the characteristics of the pressure data in the corresponding pressure sequence segment. In an exemplary embodiment, the eigenvalue is the average value of the pelvic floor muscle pressure in the corresponding pressure sequence segment, and can also be understood as the APCA approximation value of the corresponding pressure sequence segment. Then, the eigenvalue of the first suspected noise sequence segment is the average value of the pelvic floor muscle pressure of the first suspected noise sequence segment, that is, the APCA approximation value of the first suspected noise sequence segment; the eigenvalue of the target sequence segment of the first suspected noise sequence segment is the average value of the pelvic floor muscle pressure of the target sequence segment of the first suspected noise sequence segment, that is, the APCA approximation value of the target sequence segment of the first suspected noise sequence segment.

[0053] Obtain the eigenvalue difference between the eigenvalue of the first suspected noise sequence segment and the eigenvalue of its corresponding target sequence segment, specifically the absolute value of the difference between the eigenvalues. The eigenvalue difference characterizes the difference in pelvic floor muscle pressure between the abnormality and the normal corresponding to the first suspected noise sequence segment.

[0054] Step 3-4: Obtain the speed at which the first suspected noise sequence segment returns to normal according to the duration of the recovery stage sequence segment and the eigenvalue difference.

[0055] The longer the duration of the recovery stage sequence segment, it indicates that the longer the duration for the first suspected noise sequence segment to recover from abnormality to the normal state, and the slower the speed at which the first suspected noise sequence segment returns to normal; the greater the eigenvalue difference, the greater the difference in pelvic floor muscle pressure between the abnormality and the normal corresponding to the first suspected noise sequence segment, and the slower the speed at which the first suspected noise sequence segment returns to normal.

[0056] Therefore, according to the duration of the recovery stage sequence segment and the eigenvalue difference, obtain the speed at which the first suspected noise sequence segment returns to normal. The speed is inversely proportional to the duration of the recovery stage sequence segment and inversely proportional to the eigenvalue difference.

[0057] In an exemplary embodiment, a specific calculation method of the speed is given as follows: ; Among them, represents the speed at which the y-th suspected noise sequence segment returns to normal, represents the duration of the recovery stage sequence segment of the y-th suspected noise sequence segment, represents the eigenvalue difference between the eigenvalue of the y-th suspected noise sequence segment and the eigenvalue of the target sequence segment of the y-th suspected noise sequence segment.

[0058] represents the pair of Negative correlation normalization. The method of negative correlation normalization here can be: obtain the maximum and minimum values of the product of the duration and eigenvalue difference of the recovery stage sequence segments corresponding to each suspected noise sequence segment, and then use the maximum and minimum value normalization method to perform normalization, and finally calculate the difference between the value 1 and the normalized to achieve the negative correlation normalization of .

[0059] The slower the speed of the y-th suspected noise sequence segment to recover to normal, it may indicate stronger noise interference or longer noise influence. The faster the speed of the y-th suspected noise sequence segment to recover to normal, the y-th suspected noise sequence segment can quickly return to the resting state, that is, the normal state, in a short time, indicating that the y-th suspected noise sequence segment is just a temporary fluctuation or interference, such as a short-term electromagnetic interference from the outside world, which has the characteristics of suddenness and shortness, or is affected by abdominal pressure.

[0060] According to the above content, in addition to the normal physiological phenomenon of abdominal pressure that can cause the pelvic floor muscle pressure data to be periodically low, there are also two types of noises that can cause the periodicity to be low. The abnormality caused by one type requires a longer recovery time, that is, the slower the speed of the corresponding suspected noise sequence segment to recover to the normal state. The abnormality caused by the other noise requires a shorter recovery time, and the abdominal pressure will also return to the normal state by itself in a short time. The interference caused by this short-term noise and abdominal pressure to the pelvic floor muscle pressure data is relatively similar in terms of recovery speed. Therefore, further analysis is needed to better distinguish the short-term noise and abdominal pressure in the pelvic floor muscle pressure data.

[0061] To further distinguish the influence of short-term noise and abdominal pressure data in the pressure sequence segments with a faster recovery speed, by comparing the recovery trends and durations of multiple suspected noise sequence segments, analyze the variation rules during the recovery process. If there is a pressure sequence segment with a very unstable recovery or a long duration, it is more likely to be noise. Among them, the recovery process usually refers to the process in which the pelvic floor muscle pressure signal gradually returns to the normal state after being interfered by noise.

[0062] Then, obtain the pressure change trend during the process of the suspected noise sequence segment recovering to normal. In an exemplary embodiment, as Figure 5 shown, the following gives a specific acquisition process of the pressure change trend during the process of the suspected noise sequence segment recovering to normal: Step 3-5: Obtain each peak in the recovery stage sequence segment.

[0063] Obtain each peak in the recovery stage sequence segment of the y-th suspected noise sequence segment, that is, each pressure maximum value.

[0064] Step 3-6: Obtain the proportion of the number of first peaks, where the first peak is a peak that satisfies the following condition: the peak value is greater than the peak value of the next adjacent peak.

[0065] Observe the peaks in the recovery phase sequence segment of the y-th suspected noise sequence segment, that is, the magnitude of the fluctuation of the pelvic floor muscle pressure data during the recovery process. If the magnitude of each fluctuation of the pressure data gradually decreases and tends to the normal state during the recovery process, it indicates that the recovery trend is relatively stable; if the magnitude of the pressure value fluctuates greatly and irregularly, such as rising sharply for a while and then falling sharply for a while, then the recovery trend is unstable. A large fluctuation means that there is relatively high noise.

[0066] For each peak in the recovery phase sequence segment of the y-th suspected noise sequence segment, calculate the difference between the peak value of the -th peak and the peak value of the -th peak. If is greater than 0 (that is, the peak value of the -th peak is greater than the peak value of the next adjacent peak), then record the -th peak as the first peak, and the first peak is a normal peak. Then, the first peak is a peak that satisfies the following condition: the peak value is greater than the peak value of the next adjacent peak.

[0067] Then, obtain the proportion of the number of first peaks in the recovery phase sequence segment of the y-th suspected noise sequence segment, that is, the ratio of the number of first peaks in the recovery phase sequence segment of the y-th suspected noise sequence segment to the total number of peaks in the recovery phase sequence segment of the y-th suspected noise sequence segment. The larger the proportion of the number of first peaks, the more normal peaks there are, and the more stable the recovery trend of the y-th suspected noise sequence segment.

[0068] Obtain the degree of peak value change fluctuation of the first peaks in the recovery phase sequence segment of the first suspected noise sequence segment. Taking the y-th suspected noise sequence segment as an example, obtain the peak values of the first peaks in the recovery phase sequence segment of the y-th suspected noise sequence segment, arrange them in chronological order to obtain the first peak peak value sequence, then calculate the difference sequence of the first peak peak values, and finally calculate the variance of this difference sequence as the degree of peak value change fluctuation of the first peaks in the recovery phase sequence segment of the y-th suspected noise sequence segment. The larger the variance, the more uneven the difference between adjacent normal peak values during the recovery process, and the more unstable the recovery trend.

[0069] Finally, according to the pressure change trend during the restoration of the suspected noise sequence segment to the normal process, combined with the restoration speed of the suspected noise sequence segment to the normal, the restoration trend stability of the suspected noise sequence segment is obtained. In an exemplary embodiment, the restoration trend stability of the first suspected noise sequence segment is obtained according to the restoration speed of the first suspected noise sequence segment to the normal, the proportion of the number of the first wave peaks corresponding to the first suspected noise sequence segment, and the peak value change fluctuation degree of the first wave peaks in the restoration stage sequence segment of the first suspected noise sequence segment. The faster the restoration speed of the first suspected noise sequence segment to the normal, that is, the greater the speed, the more stable the restoration trend of the first suspected noise sequence segment, that is, the greater the restoration trend stability of the first suspected noise sequence segment, and the restoration trend stability is directly proportional to the speed. Through the above analysis, the restoration trend stability is directly proportional to the proportion of the number and inversely proportional to the peak value change fluctuation degree.

[0070] In an exemplary embodiment, a specific calculation formula for the restoration trend stability is given as follows: ; Wherein, represents the restoration trend stability of the y-th suspected noise sequence segment, represents the number of the first wave peaks in the restoration stage sequence segment of the y-th suspected noise sequence segment, represents the total number of wave peaks in the restoration stage sequence segment of the y-th suspected noise sequence segment, represents the proportion of the number of the first wave peaks in the restoration stage sequence segment of the y-th suspected noise sequence segment. The more the proportion of the number of the first wave peaks, that is, the more the proportion of the number of normal wave peaks, the more stable the restoration trend of the y-th suspected noise sequence segment.

[0071] represents the variance of the difference sequence of the first wave peak peak sequence in the restoration stage sequence segment of the y-th suspected noise sequence segment. The greater the variance, the more uneven the difference between adjacent normal peak values during the restoration of the y-th suspected noise sequence segment, and the more unstable the restoration trend. represents the negative correlation normalization of. The negative correlation normalization method here can be: obtain the maximum and minimum values of the variances corresponding to each suspected noise sequence segment, then normalize using the maximum and minimum value normalization method, and finally calculate the difference between the value 1 and the normalized to achieve the negative correlation normalization of .

[0072] The speed of the y-th suspected noise sequence segment restoring to the normal state The faster, the more stable the restoration trend. represents the Normalization. The normalization method here can be: obtain the maximum and minimum values of the speeds corresponding to each suspected noise sequence segment, and then use the maximum and minimum value normalization method to perform normalization.

[0073] Step 4: Obtain the abnormal factor of the suspected noise sequence segment according to the recovery trend stability and the duration of maintaining the normal state after the suspected noise sequence segment.

[0074] In this step, it is necessary to further analyze the duration after the suspected noise sequence segment returns to the normal state, that is, the duration of maintaining the normal state. After the normal pelvic floor muscle pressure data returns to normal, it should maintain a relatively constant value within a certain period of time. However, if the normal state is quickly broken again, new fluctuations or abnormalities occur, that is, the duration of maintaining the normal state is short, it indicates that the suspected noise sequence segment is more likely to be noise.

[0075] Therefore, it is necessary to obtain the duration of maintaining the normal state after the suspected noise sequence segment. In an exemplary embodiment, for the first suspected noise sequence segment, after obtaining the target sequence segment of the first suspected noise sequence segment, the first suspected noise sequence that appears for the first time is defined as the second suspected noise sequence segment. Then, the second suspected noise sequence segment indicates that an abnormal situation has occurred again after the first suspected noise sequence segment has returned to the normal state. Then, the starting moment of the second suspected noise sequence segment is the abnormal state start moment when changing from the normal state to the abnormal state. Obtain the duration of the period between the target sequence segment of the first suspected noise sequence segment and the second suspected noise sequence segment as the duration of maintaining the normal state of the first suspected noise sequence segment. The duration of maintaining the normal state is the time interval between the end moment of the target sequence segment of the first suspected noise sequence segment and the starting moment of the second suspected noise sequence segment.

[0076] Then, according to the recovery trend stability of the first suspected noise sequence segment and the duration of maintaining the normal state of the first suspected noise sequence segment, obtain the abnormal factor of the first suspected noise sequence segment. The higher the recovery trend stability of the first suspected noise sequence segment, the less abnormal the first suspected noise sequence segment is, that is, the smaller the abnormal factor. Therefore, the abnormal factor is inversely proportional to the recovery trend stability. The shorter the duration of maintaining the normal state of the first suspected noise sequence segment, it indicates that a new abnormality has occurred soon after returning to the normal state, that is, it has quickly entered the abnormal state again, that is, the abnormal factor is larger. Therefore, the abnormal factor is inversely proportional to the duration of maintaining the normal state.

[0077] In an exemplary embodiment, a specific calculation formula for the abnormal factor is given as follows: ; where, Denote the anomaly factor of the y-th suspected noise sequence segment. The anomaly factor is specifically the anomaly factor for restoring the trend. Denote the duration for maintaining the normal state corresponding to the y-th suspected noise sequence segment. The shorter the duration for maintaining the normal state, the more quickly a new anomaly appears after the y-th suspected noise sequence segment returns to the normal state, indicating a greater degree of anomaly.

[0078] Denote the normalization of. The normalization method here can be: obtain the maximum and minimum values of the product of the restoring trend stability and the duration for maintaining the normal state corresponding to each suspected noise sequence segment, and then use the maximum and minimum value normalization method to perform normalization.

[0079] Step 5: Screen out the noise sequence segments from each suspected noise sequence segment according to the anomaly factor.

[0080] Use Step 4 to obtain the anomaly factors of each suspected noise sequence segment. The larger the anomaly factor, the more abnormal the corresponding suspected noise sequence segment, that is, the more likely there is noise. Therefore, screen out the noise sequence segments from each suspected noise sequence segment according to the anomaly factor.

[0081] In an exemplary embodiment, preset an anomaly threshold. The numerical range of the preset anomaly threshold is 0 - 1, and the specific value of the preset anomaly threshold needs to be further set according to actual needs. If the requirements for noise detection are more stringent, the preset anomaly threshold can be set smaller, so as to be able to identify more suspected noise sequence segments as noise sequence segments. Correspondingly, if the requirements for noise detection are more relaxed, the preset anomaly threshold can be set larger, so as to be able to identify fewer suspected noise sequence segments as noise sequence segments. In an exemplary embodiment, the preset anomaly threshold is taken as 0.7.

[0082] Compare the anomaly factors of each suspected noise sequence segment with the preset anomaly threshold, and obtain the suspected noise sequence segments corresponding to the anomaly factors greater than or equal to the preset anomaly threshold. Take the suspected noise sequence segments corresponding to the anomaly factors greater than or equal to the preset anomaly threshold as the noise sequence segments. Thus, accurate noise identification of the pelvic floor muscle pressure time series data is achieved.

[0083] In subsequent actual applications, the anomaly factor of the z-th noise sequence segment can also be used as the weight of all pelvic floor muscle pressure data in the z-th noise sequence segment. Take the value 1 as the weight of all pelvic floor muscle pressure data in each other pressure sequence segment except the noise sequence segment. Thus, the weight of each pelvic floor muscle pressure data in the pelvic floor muscle pressure time series data is obtained, and the weighted filtering algorithm is used to filter and denoise the pelvic floor muscle pressure time series data.

[0084] This embodiment also provides a pelvic floor muscle pressure detection system for pelvic floor muscle function screening, including: a memory and a processor; the memory is connected to the processor, and the memory is used to store program instructions; the processor is used to implement the steps in the above-mentioned embodiment of the pelvic floor muscle pressure detection method for pelvic floor muscle function screening when the program instructions are executed.

[0085] In an exemplary embodiment, the present invention provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the steps in the above-mentioned embodiment of the pelvic floor muscle pressure detection method for pelvic floor muscle function screening.

[0086] It should be noted that: the above-mentioned sequence of embodiments of the present invention is only for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0087] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A pelvic floor muscle pressure detection method for pelvic floor muscle function screening, characterized in that, Including: Obtain the time series data of pelvic floor muscle pressure, segment the time series data of pelvic floor muscle pressure to obtain multiple pressure sequence segments; Based on the lengths of the respective pressure sequence segments, screen out suspected noise sequence segments from the respective pressure sequence segments; According to the pressure change trend during the process of the suspected noise sequence segment returning to normal, combined with the speed at which the suspected noise sequence segment returns to normal, obtain the recovery trend stability of the suspected noise sequence segment; According to the recovery trend stability and the duration of maintaining the normal state after the suspected noise sequence segment, obtain the abnormal factor of the suspected noise sequence segment; According to the abnormal factor, screen out the noise sequence segments from the respective suspected noise sequence segments.

2. The pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to claim 1, characterized in that, The process of segmenting the time series data of pelvic floor muscle pressure to obtain multiple pressure sequence segments includes: Use the adaptive piecewise constant approximation method to segment the time series data of pelvic floor muscle pressure to obtain multiple pressure sequence segments.

3. The pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to claim 1, characterized in that, The process of screening out suspected noise sequence segments from the respective pressure sequence segments based on the lengths of the respective pressure sequence segments includes: Obtain the mode of the lengths from the lengths of the respective pressure sequence segments; Obtain the length difference between the length of each pressure sequence segment and the length of the mode; According to the length difference and the number of occurrences of the mode, obtain the period abnormality degree of each pressure sequence segment, and the period abnormality degree is proportional to the length difference and proportional to the number of occurrences; According to the period abnormality degree of each pressure sequence segment, screen out suspected noise sequence segments from the respective pressure sequence segments.

4. A pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to claim 1, characterized in that, The process of obtaining the speed at which the suspected noise sequence segment returns to normal includes: Obtain the target sequence segment of the first suspected noise sequence segment, where the first suspected noise sequence segment is any one of the suspected noise sequence segments, and the target sequence segment is the pressure sequence segment corresponding to the mode that first appears after the first suspected noise sequence segment; Obtain the duration of the recovery stage sequence segment of the first suspected noise sequence segment, where the recovery stage sequence segment is the time period between the first suspected noise sequence segment and its corresponding target sequence segment; Obtain the eigenvalue difference between the eigenvalue of the first suspected noise sequence segment and the eigenvalue of its corresponding target sequence segment; According to the duration of the recovery stage sequence segment and the eigenvalue difference, obtain the speed at which the first suspected noise sequence segment returns to normal; the speed is inversely proportional to the duration of the recovery stage sequence segment and inversely proportional to the eigenvalue difference.

5. A pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to claim 4, characterized in that The process of obtaining the pressure change trend during the process of the suspected noise sequence segment returning to normal includes: Obtain each wave peak in the recovery stage sequence segment; Obtain the proportion of the number of the first wave peaks, where the first wave peak is a wave peak that satisfies the following condition: the peak value is greater than the peak value of the next adjacent wave peak.

6. The pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to claim 5, characterized in that, The process of obtaining the recovery trend stability of the suspected noise sequence segment according to the pressure change trend during the process of the suspected noise sequence segment returning to normal, combined with the speed at which the suspected noise sequence segment returns to normal, includes: The recovery trend stability of the first suspected noise sequence segment is obtained based on the speed of the first suspected noise sequence segment returning to normal, the proportion of the number of the first peaks corresponding to the first suspected noise sequence segment, and the peak change fluctuation degree of the first peaks of the recovery stage sequence segments of the first suspected noise sequence segment; the recovery trend stability is directly proportional to the speed, directly proportional to the proportion of the number, and inversely proportional to the peak change fluctuation degree.

7. A pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to claim 4, characterized in that, The process of obtaining the duration of maintaining the normal state after the suspected noise sequence segment includes: Obtaining the duration of the time period between the target sequence segment of the first suspected noise sequence segment and the second suspected noise sequence segment as the duration of maintaining the normal state; the second suspected noise sequence segment is the first suspected noise sequence segment that appears after the target sequence segment.

8. A pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to claim 7, characterized in that, The obtaining of the abnormal factor of the suspected noise sequence segment according to the recovery trend stability and the duration of maintaining the normal state after the suspected noise sequence segment includes: Obtaining the abnormal factor of the first suspected noise sequence segment according to the recovery trend stability of the first suspected noise sequence segment and the duration of maintaining the normal state of the first suspected noise sequence segment; the abnormal factor is inversely proportional to the recovery trend stability and inversely proportional to the duration of maintaining the normal state.

9. A pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to claim 1, characterized in that, The screening of the noise sequence segment from each suspected noise sequence segment according to the abnormal factor includes: Taking the suspected noise sequence segment corresponding to the abnormal factor greater than or equal to the preset abnormal threshold as the noise sequence segment.

10. A pelvic floor muscle pressure detection system for pelvic floor muscle function screening, characterized in that, Includes: A memory and a processor; The memory is connected to the processor; The memory is used for storing program instructions; The processor is used for implementing the pelvic floor muscle pressure detection method for pelvic floor muscle function screening according to any one of claims 1-9 when the program instructions are executed.

Images