Control method for vaginal irrigation dilation based on multi-modal data

By analyzing pelvic floor electromyography signals and pH values ​​using multimodal data, the vaginal irrigation flow rate is dynamically adjusted, solving the problem of inaccurate flow rate control in existing technologies and achieving safe and efficient vaginal irrigation and dilation.

CN120789387BActive Publication Date: 2026-01-02ZHEJIANG DINO MEDICAL TECH CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202511303037.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-09-12
Publication Date
2026-01-02
Estimated Expiration
2045-09-12

AI Technical Summary

Technical Problem

Existing vaginal irrigation and dilation devices neglect the real-time interaction between pelvic floor electromyography signals and vaginal pH in flow rate control, resulting in rigid flow rate regulation, inaccurate control, and easy mucosal damage and increased pain.

Method used

A multimodal data control method is adopted. By acquiring pelvic floor electromyography (EMG) signals, pH value, and irrigation flow rate data, and combining them with the patient's basic information, the influence of EMG and pH is analyzed in real time, and the irrigation flow rate is dynamically adjusted. Principal component analysis and curve fitting techniques are used to obtain the flow rate adjustment weights to achieve precise control.

Benefits of technology

It improves the accuracy and safety of the irrigation flow rate, avoids mucosal damage, and enhances treatment efficiency and patient comfort.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120789387B_ABST
    Figure CN120789387B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of vaginal irrigation flow rate control, and particularly relates to a control method for vaginal irrigation dilation based on multi-modal data. The method acquires pelvic floor muscle electrical signals, pH values and irrigation flow rate data of a patient during a vaginal irrigation dilation process; acquires an electromyographic influence degree of the patient according to pelvic floor muscle electrical signals and irrigation flow rate data of a matching historical patient in an irrigation dilation stage; acquires a pH influence degree of the patient according to differences between the pH value of the patient at each time and a normal pH value range of the vagina, and changes in the pH value within a preset field time period at each time; and acquires a flow rate adjustment weight of the patient in real time according to the electromyographic influence degree and the pH influence degree, and controls an irrigation flow rate of the patient during the vaginal irrigation dilation process. The present application accurately acquires the flow rate adjustment weight in real time, accurately adjusts the irrigation flow rate, and effectively avoids damage to the vagina during the irrigation dilation process.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vaginal irrigation, in particular to a control method for vaginal irrigation dilation based on multi-modal data. BACKGROUND

[0002] Vaginal irrigation dilation is a routine operation in gynecology and is widely used in the treatment of bacterial vaginosis, trichomonas vaginitis and other infections, as well as in the preparation before hysteroscopy and biopsy assistance. The core goal is to remove pathogen secretions, reduce bacterial load or promote local drug absorption through irrigation fluid.

[0003] The current vaginal dilation and cleaning device adopts a preset flow rate control mode, which has realized basic automation, but the flow rate control ignores the real-time interactive influence of pelvic floor muscle electrical signals and vaginal pH value, and does not fully consider the individual differences of patients, thereby leading to rigid control strategy of the irrigation flow rate in the process of vaginal irrigation dilation, which cannot timely and accurately control the irrigation flow rate, and easily causes damage to the vaginal mucosa and increases the pain of patients. SUMMARY

[0004] In order to solve the technical problem of inaccurate control of the irrigation flow rate in the process of vaginal irrigation dilation, the purpose of the present application is to provide a control method for vaginal irrigation dilation based on multi-modal data, and the technical solution adopted is as follows:

[0005] The present application provides a control method for vaginal irrigation dilation based on multi-modal data, which comprises the following steps:

[0006] Obtain the pelvic floor muscle electrical signals, pH values and irrigation flow rate data of each patient at each time in the process of vaginal irrigation dilation, as well as the basic information of each patient; wherein the process of vaginal irrigation dilation includes an initial stage and an irrigation dilation stage;

[0007] According to the similarity of the basic information of the current patient and the historical patients, obtain the matching historical patients of the current patient; according to the peak amplitude of the pelvic floor muscle electrical signals and the irrigation flow rate data of each matching historical patient in each preset time period in the irrigation dilation stage, obtain the muscle electrical influence degree corresponding to each preset time period of the current patient;

[0008] According to the difference between the pH value of the current patient at each time and the normal pH value range of the vagina, and the change of the pH value in each preset time period at each time, obtain the pH influence degree of the current patient at each time;

[0009] According to the muscle electrical influence degree and the pH influence degree of the current patient in the corresponding time period from the starting time of the process of vaginal irrigation dilation to the current time, obtain the flow rate adjustment weight of the current patient in real time;

[0010] Real-time control the irrigation flow rate in the current patient's vaginal irrigation dilation process based on the flow rate adjustment weight.

[0011] Further, the method for obtaining the muscle tension degree comprises:

[0012] Each irrigation dilation stage of each matched historical patient is divided into each preset time period according to time sequence;

[0013] According to the peak amplitude of the pelvic floor muscle electrical signal in each preset time period of each matched historical patient, the muscle tension degree corresponding to each preset time period of each matched historical patient is obtained.

[0014] The mean value of all irrigation flow rate data in the preset time period of each matched historical patient in each muscle tension degree interval range is taken as the safe flow rate data of each interval range.

[0015] The ratio of the safe flow rate data to the preset reference flow rate data is taken as the electromyographic influence degree corresponding to the muscle tension degree in the corresponding interval range.

[0016] The electromyographic influence degree corresponding to the muscle tension degree of each preset time period of the current patient is taken as the electromyographic influence degree corresponding to each preset time period of the current patient. The preset time period of the current patient includes the preset time period of the current patient in the initial stage.

[0017] Further, the method for obtaining the muscle tension degree comprises:

[0018] For any patient, the peak amplitude in the pelvic floor muscle electrical signal corresponding to the maximum voluntary contraction of the pelvic floor muscle of the patient for a preset duration is taken as the maximum voluntary contraction amplitude of the patient.

[0019] For any preset time period of the patient, the ratio of the peak amplitude of the pelvic floor muscle electrical signal in the preset time period to the maximum voluntary contraction amplitude is taken as the muscle tension degree corresponding to the preset time period of the patient.

[0020] Further, the method for obtaining the pH influence degree comprises:

[0021] The mean value of the maximum pH value and the minimum pH value in the normal pH value range of the vagina is taken as the normal reference pH value.

[0022] The difference between the maximum pH value in the normal pH value range of the vagina and the normal reference pH value is taken as the pH value tolerance degree.

[0023] The difference between the pH value of the current patient at each time and the normal reference pH value is taken as the pH value deviation degree of the current patient at each time.

[0024] For any one moment of the current patient, the ratio of the degree of pH value deviation at this moment to the degree of pH value tolerance is taken as the degree of pH value abnormality of the current patient at this moment;

[0025] When the degree of pH value abnormality is greater than the preset abnormal threshold, the variance of the pH value difference of the current patient at all adjacent two moments in the preset neighborhood time period of this moment is taken as the degree of pH value change of the current patient at this moment;

[0026] The difference between the degree of pH value abnormality and the preset abnormal threshold is taken as the first difference;

[0027] The product of the first difference and the degree of pH value change is normalized to obtain the degree of pH influence of the current patient at this moment;

[0028] When the degree of pH value abnormality is less than or equal to the preset abnormal threshold, 0 is taken as the degree of pH influence of the current patient at this moment.

[0029] Further, the method for obtaining the flow rate adjustment weight is:

[0030] The end moment of each preset time period of the current patient is taken as the target moment of the current patient, and the degree of myoelectric influence corresponding to each preset time period of the current patient is taken as the degree of myoelectric influence of the current patient at each target moment;

[0031] The degree of pH influence is taken as the horizontal axis, and the degree of myoelectric influence is taken as the vertical axis to construct a two-dimensional coordinate system;

[0032] According to the coordinate points corresponding to the degree of myoelectric influence and the degree of pH influence of the current patient at each target moment in the initial stage in the two-dimensional coordinate system, an initial state muscle analysis value of the current patient is obtained;

[0033] According to the coordinate points corresponding to the degree of myoelectric influence and the degree of pH influence of the current patient at each target moment in the flushing and expansion stage up to the current moment in the two-dimensional coordinate system, a current muscle analysis value of the current patient is obtained; wherein the current moment is in the flushing and expansion stage of the current patient;

[0034] According to the difference between the current muscle analysis value and the initial state muscle analysis value, a dynamic reference weight of the last target moment of the current patient up to the current moment is obtained;

[0035] The product of the dynamic reference weight of the last target moment of the current patient up to the current moment and the degree of myoelectric influence is taken as the first control factor;

[0036] The product of the negative correlation result of the dynamic reference weight at the last target time of the current patient up to the current time and the pH influence degree is taken as a second regulation factor;

[0037] The addition result of the first regulation factor and the second regulation factor is taken as the flow rate adjustment weight at the last target time of the current patient up to the current time.

[0038] Further, the method for obtaining the initial state muscle analysis value is:

[0039] The coordinate point corresponding to the myoelectricity influence degree and the pH influence degree of the current patient at each target time in the initial stage in a two-dimensional coordinate system is taken as an initial coordinate point.

[0040] The straight line corresponding to the initial coordinate point is obtained by a principal component analysis algorithm, and is taken as an initial reference straight line.

[0041] The slope of the initial reference straight line is taken as the initial state muscle analysis value of the current patient.

[0042] Further, the method for obtaining the current muscle analysis value is:

[0043] The coordinate points corresponding to the myoelectricity influence degree and the pH influence degree of the current patient at each target time in the flushing and dilatation stage up to the current time in a two-dimensional coordinate system are curve-fitted to obtain a reference curve.

[0044] The first derivative of the coordinate point corresponding to the current patient at the last target time up to the current time in the reference curve is taken as the current muscle analysis value of the current patient.

[0045] Further, the method for obtaining the dynamic reference weight is:

[0046] The difference between the current muscle analysis value and the initial state muscle analysis value is normalized to obtain the dynamic reference weight at the last target time of the current patient up to the current time.

[0047] Further, the method for real-time controlling the flushing flow rate of the current patient in the vaginal flushing and dilatation process based on the flow rate adjustment weight is:

[0048] The product of the flow rate adjustment weight at the last target time of the current patient up to the current time and the flushing flow rate data is taken as the corrected flushing flow rate data at the last target time of the current patient up to the current time, and the flushing flow rate of the current patient in the vaginal flushing and dilatation process is real-time controlled.

[0049] Further, the method for obtaining the matching historical patient is:

[0050] The basic information of each patient is converted into a vector as a feature vector of each patient;

[0051] The cosine similarity of the feature vector of the current patient and each historical patient is obtained, which is the similarity degree; wherein, the historical patients are all historical patients without injury in the vaginal irrigation and dilation process;

[0052] When the similarity degree is greater than a preset similarity degree threshold, the corresponding historical patient is taken as the matching historical patient of the current patient.

[0053] The present application has the following advantages:

[0054] The present application first obtains the muscle influence degree of each preset time period of the current patient according to the peak amplitude of the pelvic floor muscle electrical signal and the irrigation flow rate data of the matching historical patient of the current patient in each preset time period in the irrigation and dilation stage, which is beneficial to accurately determine the safety flow rate demand of the current patient in real time, and is beneficial to improve the treatment level of the current patient; further, the pH influence degree of each time of the current patient is obtained according to the difference between the pH value of the current patient at each time and the normal pH value range of the vagina, and the change of the pH value in each preset field time period, which accurately reflects the abnormal situation of the pH value of the current patient at each time, ensures timely response to high-priority infection risk, and improves the accuracy of irrigation flow rate adjustment; in order to accurately analyze the real-time interactive influence of the pelvic floor muscle electrical signal and the vaginal pH value, the irrigation flow rate is controlled accurately based on the muscle influence degree and the pH influence degree, and then the flow rate adjustment weight of the current patient is obtained in real time according to the muscle influence degree and the pH influence degree of the current patient in the corresponding time period from the starting time of the vaginal irrigation and dilation process to the current time, which accurately reflects the adjustment situation of the irrigation flow rate of the current patient in real time; and then the irrigation flow rate of the current patient in the vaginal irrigation and dilation process is accurately controlled in real time based on the flow rate adjustment weight, so that the cleaning efficiency is guaranteed while the mucosal injury is avoided to the greatest extent, and the vaginal injury is effectively avoided. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0056] Figure 1 A schematic flow chart of a control method for vaginal irrigation and dilation based on multi-modal data provided by an embodiment of the present application;

[0057] Figure 2A flowchart of a flow rate adjustment weight acquisition method provided by an embodiment of the present application is shown in FIG. 1.

[0058] Figure 3 A block diagram of a control system for vaginal irrigation dilation based on multi-modal data provided by an embodiment of the present application is shown in FIG. 2.

[0059] Figure 4 A schematic diagram of a computer device provided by an embodiment of the present application is shown in FIG. 3. DETAILED DESCRIPTION

[0060] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purposes, the specific embodiments, structures, features and effects of the control method for vaginal irrigation dilation based on multi-modal data according to the present application are described in detail below in combination 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.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0062] The specific scheme of the control method for vaginal irrigation dilation based on multi-modal data provided by the present application is described in detail below in combination with the accompanying drawings.

[0063] Embodiment 1

[0064] The present application proposes a control method for vaginal irrigation dilation based on multi-modal data, please refer to Figure 1 , which shows a schematic flowchart of a control method for vaginal irrigation dilation based on multi-modal data provided by an embodiment of the present application. The method includes the following steps:

[0065] Step S1: Acquire the pelvic floor muscle electrical signal, pH value and irrigation flow rate data of each patient at each time during the vaginal irrigation dilation process, as well as the basic information of each patient; wherein the vaginal irrigation dilation process includes an initial stage and an irrigation dilation stage.

[0066] Specifically, it is known that the main working principle of vaginal irrigation dilation is that the vaginal dilation and cleaning device expands the vagina and then uses a specific cleaning liquid to irrigate the vagina. With the increase of the expansion time, the muscles in the patient's vagina are continuously stretched. When the muscle tension increases, the pelvic floor muscle contraction force increases, which in turn squeezes the blood vessels of the vaginal wall, causing the blood flow of the mucosal layer to decrease, and the mucosa's tolerance to mechanical stimulation decreases. At this time, if the irrigation flow rate is too high, the high-speed impact is easy to cause the rupture of the microvessels, causing damage to the vagina. The higher the muscle tension, the greater the probability of rupture when subjected to a higher flow rate of irrigation. In addition, the pH value in the vagina is an important indicator reflecting the balance of the internal environment of the vagina. Changes in the pH value directly affect the health status of the vaginal mucosa and the tolerance to cleaning operations. In order to avoid damage to the vagina of the patient during the vaginal irrigation dilation process, it is necessary to analyze the tension of the pelvic floor muscles and the changes in the pH value in the vagina in real time, and to accurately control the irrigation flow rate of the vagina.

[0067] In this embodiment, a high-sensitivity pelvic floor muscle electrical sensor and a fast-response pH sensor are used to obtain the pelvic floor muscle electrical signal and the pH value of each patient at each moment during the vaginal irrigation dilation process, and the irrigation flow rate data of each patient at each moment during the vaginal irrigation dilation process are also obtained. The frequency of collecting the pelvic floor muscle electrical signal, the pH value and the irrigation flow rate data is set to 50 hz in this embodiment, and the collector can set the collection frequency according to the actual situation, which is not limited herein. In this embodiment, the pelvic floor muscle electrical sensor uses a flexible electrode, the measurement range of the pH sensor is set to 3.0-6.0 with an accuracy of ±0.1, and the pH sensor is placed at the top of the irrigation head, which is beneficial to better detect the pH value in the vaginal environment. It should be noted that the above-mentioned patients include historical patients and current patients, wherein the historical patients are all historical patients without damage occurring during the vaginal irrigation dilation process; in addition, the complete vaginal irrigation dilation process includes an initial stage and an irrigation dilation stage, wherein the initial stage is used to analyze the information inside the vagina of the patient before irrigation, and there is no irrigation flow rate data in the initial stage; the irrigation dilation stage is used to analyze the information inside the vagina of the patient during the irrigation dilation process.

[0068] In order to find similar historical patients for the current patient in the future, so as to better control the irrigation flow rate of the irrigation liquid of the current patient during the vaginal irrigation dilation process, the basic information of each patient is obtained in this embodiment, wherein the basic information includes the age, body mass index, number of pregnancies and disease type code of the patient. It should be noted that the rules of the disease type code are that the bacterial vaginosis code is defined as 1, the trichomonas vaginitis code is defined as 2, and the preoperative cleaning code is defined as 3.

[0069] Step S2: According to the similarity of the basic information of the current patient and the historical patients, the matching historical patients of the current patient are obtained; according to the peak amplitude of the pelvic floor muscle electrical signal and the irrigation flow rate data of each matching historical patient in each preset time period in the irrigation and expansion stage, the muscle electrical influence degree corresponding to each preset time period of the current patient is obtained.

[0070] Specifically, in order to analyze the pelvic floor muscle tension of the current patient in real time, the embodiment first obtains the matching historical patients of the current patient according to the similarity of the basic information of the current patient and the historical patients, which can be matched by default. The historical patients are patients similar to the current patient in the process of vaginal irrigation and expansion, because the vaginal conditions of the current patient and the matching historical patients are similar; and then the influence of the pelvic floor muscle tension of the current patient on the irrigation flow rate can be indirectly determined in real time by analyzing the pelvic floor muscle electrical signal and the irrigation flow rate data of each matching historical patient in the process of vaginal irrigation and expansion. Therefore, the muscle electrical influence degree corresponding to each preset time period of the current patient is obtained according to the peak amplitude of the pelvic floor muscle electrical signal and the irrigation flow rate data of each matching historical patient in each preset time period in the irrigation and expansion stage. The smaller the muscle electrical influence degree, the more tense the pelvic floor muscle of the current patient in the corresponding preset time period, the stronger the muscle restriction should be, and the greater the degree of reducing the irrigation flow rate is required to avoid damage to the vagina. The peak amplitude is a known content and will not be described again.

[0071] Preferably, in one implementation manner of the embodiment, the method for obtaining the matching historical patients is that: the basic information of each patient is converted into a vector as a feature vector of each patient; wherein the elements at the same position in each feature vector correspond to the same kind of basic information. Then the cosine similarity of the feature vectors of the current patient and each historical patient is obtained, which is used as the similarity degree; the greater the similarity degree, the more similar the corresponding historical patient to the current patient, and then the embodiment sets the preset similarity degree threshold value to 0.5, and the implementer can set the size of the preset similarity degree threshold value according to the actual situation, which is not limited herein. When the similarity degree is greater than the preset similarity degree threshold value, the corresponding historical patient is taken as the matching historical patient of the current patient. The method for obtaining the cosine similarity is a known technology and will not be described again.

[0072] Preferably, in one implementation of the present embodiment, the method for obtaining the degree of muscle influence is as follows: each flushing and dilatation stage of each matched historical patient is sequentially divided into each preset time period according to time sequence; the present embodiment sets the length of the preset time period as 1 second, and the implementer can set the size of the preset time period according to the actual situation, which is not limited herein. The greater the peak amplitude of the pelvic floor electromyographic signal corresponding to a certain preset time period of a certain matched historical patient, the more tense the pelvic floor muscle of the matched historical patient in the preset time period, and then the present embodiment obtains the muscle tension degree corresponding to each preset time period of each matched historical patient according to the peak amplitude of the pelvic floor electromyographic signal corresponding to each preset time period of each matched historical patient. The specific method for obtaining the muscle tension degree is as follows: for any patient, first, the peak amplitude of the pelvic floor electromyographic signal corresponding to the maximum voluntary contraction of the pelvic floor muscle of the patient in the comfortable state for a preset length of time is taken as the maximum voluntary contraction amplitude of the patient; the present embodiment sets the preset length of time as 5 seconds, and the implementer can set the length of time according to the actual situation, which is not limited herein. For any preset time period of the patient, the ratio of the peak amplitude of the pelvic floor electromyographic signal in the preset time period to the maximum voluntary contraction amplitude is taken as the muscle tension degree corresponding to the preset time period of the patient. Because the contraction degree of the pelvic floor muscle of different patients is different, the present embodiment obtains the maximum voluntary contraction amplitude of each patient, so as to more accurately analyze the muscle tension degree corresponding to each preset time period of each patient; the value range of the muscle tension degree is 0 to 1, when the muscle tension degree is 0, it represents that the pelvic floor muscle is completely relaxed, and when the muscle tension degree is 1, it represents that the pelvic floor muscle is highly tense. By obtaining the muscle tension degree, the abstract pelvic floor electromyographic signal can be converted into an intuitive quantitative parameter, which can accurately reflect the change of the pelvic floor muscle tension degree in real time;

[0073] In order to accurately and efficiently determine the flushing flow rate corresponding to different muscle tension degrees, and then preset the interval range of the muscle tension degree division, the present embodiment sets the interval range of the muscle tension degree division as respectively, and the implementer can set the interval range of the muscle tension degree division according to the actual situation, which is not limited herein. The mean value of all flushing flow rate data in the preset time period of the matched historical patient corresponding to each muscle tension degree in each interval range is taken as the safe flow rate data of each interval range; for example, taking the interval range of as an example, the mean value of all flushing flow rate data in the preset time period of the matched historical patient corresponding to the muscle tension degree in the interval range of is taken as the safe flow rate data of The corresponding safe flow rate data. The ratio of the safe flow rate data for each interval range to the preset baseline flow rate data is used as the degree of electromyographic influence corresponding to the muscle tension level within the corresponding interval range. It should be noted that the preset baseline flow rate data is set by the doctor according to the type of disease. For example, the preset baseline flow rate data for preoperative cleaning is set to 100 ml / min, and it is not limited here.

[0074] Furthermore, the degree of electromyographic influence corresponding to the muscle tension level of the current patient in each preset time period is taken as the degree of electromyographic influence of the current patient in each preset time period; wherein, the preset time period of the current patient includes the preset time period of the current patient in the initial stage.

[0075] It should be noted that if no matching historical patients exist for the current patient, the negative correlation result of the muscle tension level for each preset time period of the current patient will be used as the electromyographic influence level for each preset time period of the current patient. In this embodiment, the result of subtracting the muscle tension level from 1 is used as the negative correlation result of the muscle tension level.

[0076] At this point, the degree of electromyographic influence corresponding to each preset time period of the current patient is obtained.

[0077] Step S3: Based on the difference between the current patient's pH value at each moment and the normal vaginal pH range, as well as the pH value changes within the preset time period at each moment, obtain the degree of pH influence at each moment for the current patient.

[0078] Specifically, numerous medical studies have shown that the vaginal pH of healthy women is typically maintained within a slightly acidic range of 3.8-4.5. Within this normal vaginal pH range, the growth of beneficial bacteria such as lactobacilli is promoted, while the growth of harmful bacteria is inhibited, thus maintaining the vaginal microecological balance. When the vaginal pH exceeds this normal range, mucosal tolerance decreases, requiring a reduced irrigation flow rate to prevent vaginal damage. Furthermore, rapid pH changes may indicate an acute infection requiring a priority response. Therefore, this embodiment uses the difference between the current patient's pH at each moment and the normal vaginal pH range, along with the pH changes within a preset time period, to determine the degree of pH influence at each moment. The greater the pH influence, the further the current patient's pH deviates from the normal vaginal pH range at that moment, and the lower the required irrigation flow rate.

[0079] Preferably, in one implementation mode of the present embodiment, the method for obtaining the degree of pH influence is as follows: taking the mean of the maximum pH value and the minimum pH value in the normal pH value range of the vagina as the normal reference pH value; taking the absolute value of the difference between the maximum pH value in the normal pH value range of the vagina and the normal reference pH value as the pH value tolerance degree; taking the absolute value of the difference between the pH value of the current patient at each time and the normal reference pH value as the pH value deviation degree of the current patient at each time; when the pH value deviation degree is less than or equal to the pH value tolerance degree, the pH value of the current patient at the corresponding time is within the normal pH value range of the vagina; and then for any time of the current patient, the ratio of the pH value deviation degree at the time to the pH value tolerance degree is taken as the pH value abnormality degree of the current patient at the time.

[0080] In the present embodiment, the preset abnormality threshold is set to 1, and when the pH value abnormality degree is greater than the preset abnormality threshold, it indicates that the pH value at the time is abnormal. In order to accurately analyze the abnormal situation of the pH value at the time, first, the variance of the absolute values of the differences between the pH values of the current patient at all adjacent two times in the preset neighborhood time period of the time is obtained as the pH value change degree of the current patient at the time; wherein the preset neighborhood time period of the time is a time period corresponding to a time length of 0.2 seconds with the time as the terminal time, and the implementer can set the time length of the preset neighborhood time period of the time according to the actual situation, which is not limited herein, but the terminal time of the preset neighborhood time period of the time must be the time. The greater the pH value change degree, the more likely the current patient has an acute change in the pH value at the time, the greater the risk of acute infection, and the more need for priority response; then the difference between the pH value abnormality degree of the current patient at the time and the preset abnormality threshold is obtained as the first difference; the greater the first difference, the more abnormal the pH value of the current patient at the time; and the product of the first difference and the pH value change degree is normalized as the pH influence degree of the current patient at the time. In the present embodiment, the product of the first difference and the pH value change degree is normalized by the norm normalization function.

[0081] When the pH value abnormality degree is less than or equal to the preset abnormality threshold, it indicates that the pH value at the time is not abnormal, i.e. within the normal pH value range of the vagina, and 0 is taken as the pH influence degree of the current patient at the time.

[0082] Thus, the pH influence degree of the current patient at each time is obtained.

[0083] Step S4: Real-time obtaining the flow rate adjustment weight of the current patient according to the muscle influence degree and the pH influence degree in the time period corresponding to the time when the vaginal irrigation and dilation process starts to the current time.

[0084] It is known that the smaller the myoelectricity influence degree and the greater the pH influence degree of the current patient are, the more necessary it is to reduce the irrigation flow rate to avoid damage to the vagina, and thus the embodiment acquires the flow rate adjustment weight of the current patient in real time according to the myoelectricity influence degree and the pH influence degree of the current patient in the time period corresponding to the time from the beginning of the vaginal irrigation and expansion process of the current patient to the current time, which is beneficial to accurately control the irrigation flow rate of the current patient in real time.

[0085] Preferably, in an implementable manner of the embodiment, the method for acquiring the flow rate adjustment weight is as follows Figure 2 which shows a flowchart of the method for acquiring the flow rate adjustment weight provided by the embodiment, and the method comprises the following steps:

[0086] Step S201: Acquire the initial state muscle analysis value of the current patient.

[0087] Considering that the time nodes corresponding to the myoelectricity influence degree and the pH influence degree are different, the embodiment takes the end time of each preset time period of the current patient as the target time of the current patient, and takes the myoelectricity influence degree corresponding to each preset time period of the current patient as the myoelectricity influence degree at each target time of the current patient. In order to accurately control the irrigation flow rate subsequently, the embodiment takes the pH influence degree as the horizontal axis and the myoelectricity influence degree as the vertical axis to construct a two-dimensional coordinate system, so as to accurately analyze the relationship between the myoelectricity influence degree and the pH influence degree, which is beneficial to accurately determine the adjustment weight of the myoelectricity influence degree and the pH influence degree subsequently, and to accurately acquire the flow rate adjustment weight. Considering that the original vaginal pH environment and the endurance of the pelvic floor muscles of different patients are different in actual situations, the embodiment acquires the initial state muscle analysis value of the current patient according to the coordinate points corresponding to the myoelectricity influence degree and the pH influence degree of the current patient at each target time in the initial stage in the two-dimensional coordinate system. The greater the initial state muscle analysis value is, the more sensitive the muscles of the vagina of the current patient are to the fluctuation of the pH value before irrigation.

[0088] In an implementable manner of the embodiment, the method for acquiring the initial state muscle analysis value is as follows: take the coordinate points corresponding to the myoelectricity influence degree and the pH influence degree of the current patient at each target time in the initial stage in the two-dimensional coordinate system as initial coordinate points; acquire the straight line corresponding to the initial coordinate points by principal component analysis algorithm as an initial reference straight line, which is beneficial to accurately analyze the relationship between the myoelectricity influence degree and the pH influence degree; and then take the slope of the initial reference straight line as the initial state muscle analysis value of the current patient. The method for acquiring the straight line by the principal component analysis algorithm is a known technology and will not be described herein.

[0089] Step S202: Acquire the current muscle analysis value of the current patient.

[0090] In order to accurately analyze the relationship between the myoelectricity influence degree and the pH influence degree of the current patient in the flushing process in real time, so as to accurately determine the adjustment weight of the myoelectricity influence degree and the pH influence degree in real time, and to accurately control the flushing flow rate of the current patient in the flushing process in real time, the embodiment obtains the current muscle analysis value of the current patient according to the coordinate points corresponding to the myoelectricity influence degree and the pH influence degree of the current patient at each target time point in the flushing expansion stage up to the current time point in a two-dimensional coordinate system; wherein the current time point is in the flushing expansion stage of the current patient. Through the current muscle analysis value, the relationship between the myoelectricity influence degree and the pH influence degree of the current patient is accurately analyzed in real time.

[0091] In an implementable manner of the embodiment, the method for obtaining the current muscle analysis value is: performing curve fitting on the coordinate points corresponding to the myoelectricity influence degree and the pH influence degree of the current patient at each target time point in the flushing expansion stage up to the current time point in a two-dimensional coordinate system, to obtain a reference curve; wherein the method for fitting the curve is a known technology and will not be described in detail. The first derivative of the coordinate point corresponding to the last target time point of the current patient in the reference curve up to the current time point is taken as the current muscle analysis value of the current patient.

[0092] Step S203: Real-time acquisition of the dynamic reference weight of the current patient.

[0093] In order to accurately determine the adjustment weight of the myoelectricity influence degree of the current patient in real time, the embodiment obtains the dynamic reference weight of the current patient at the last target time point up to the current time point according to the difference between the current muscle analysis value and the initial state muscle analysis value. The greater the dynamic reference weight is, the more sensitive the change of the current myoelectricity influence degree is, and the greater the influence of the myoelectricity influence degree on the flushing flow rate is.

[0094] In an implementable manner of the embodiment, the difference between the current muscle analysis value and the initial state muscle analysis value is normalized to obtain the dynamic reference weight of the current patient at the last target time point up to the current time point. The embodiment normalizes the difference between the current muscle analysis value and the initial state muscle analysis value by using the norm normalization function.

[0095] Step S204: Real-time acquisition of the flow rate adjustment weight of the current patient.

[0096] The greater the dynamic reference weight, the smaller the adjustment weight of the pH influence degree, and then the embodiment will multiply the dynamic reference weight at the last target time of the current patient up to the current time by the muscle influence degree to obtain a first regulation factor; multiply the negative correlation result of the dynamic reference weight at the last target time of the current patient up to the current time by the pH influence degree to obtain a second regulation factor; wherein the embodiment takes 1 minus the dynamic reference weight as the negative correlation result of the dynamic reference weight; and then adds the first regulation factor and the second regulation factor to obtain the flow rate adjustment weight at the last target time of the current patient up to the current time.

[0097] It should be noted that, because the length of the preset time period is 1 second, the embodiment obtains the flow rate adjustment weight for the current patient every second during the irrigation and expansion phase.

[0098] Step S5: Real-time control of the irrigation flow rate during the vaginal irrigation and expansion process of the current patient based on the flow rate adjustment weight.

[0099] Specifically, after obtaining the flow rate adjustment weight of the current patient in real time, the irrigation flow rate during the vaginal irrigation and expansion process of the current patient can be controlled in real time, that is, the irrigation flow rate data is adjusted to the modified irrigation flow rate data conforming to the current pH environment and the state of the pelvic floor muscle through linear regulation. The method for obtaining the modified irrigation flow rate data is: multiplying the flow rate adjustment weight at the last target time of the current patient up to the current time by the irrigation flow rate data to obtain the modified irrigation flow rate data at the last target time of the current patient up to the current time; and then real-time control of the irrigation flow rate during the vaginal irrigation and expansion process of the current patient is realized. It should be noted that the initial irrigation flow rate data is set by professionals according to the actual disease type, which is not limited herein, and in order to ensure the irrigation efficiency, the lower limit of the initial irrigation flow rate data is set to 0.5 ml / min in the embodiment, and the implementer can set the initial irrigation flow rate data according to the actual situation, which is not limited herein.

[0100] In addition, when the flow rate adjustment weight is greater than 1, it indicates that the flushing flow rate needs to be increased; when the flow rate adjustment weight is less than or equal to 1, it indicates that the flushing flow rate needs to be reduced; it is known that the inflation volume of the flushing head before the vagina is flushed and expanded has been set in advance, when the flushing flow rate is increased, the inflation volume of the flushing head will automatically increase, which is easy to cause damage to the vagina. In order to avoid the damage to the vagina caused by the vagina flushing and expanding device, and then when the flow rate adjustment weight is greater than 1, the product of the preset volume correction weight and the inflation volume of the current flushing head is taken as the corrected inflation volume of the current flushing head, so as to avoid that the inflation volume of the flushing head is too large, and at the same time, the flushing efficiency is not excessively affected; wherein, the preset volume correction weight is set to 0.95 in the embodiment, and the implementer can set the preset volume correction weight according to the actual situation, which is not limited herein, but the preset volume correction weight is greater than 0 and less than 1. When the flow rate adjustment weight is less than or equal to 1, the inflation volume of the flushing head does not need to be corrected. Considering that there is a certain delay in the change of the vagina environment after the flushing flow rate is changed in the actual situation, and in order to avoid that the adjustment frequency of the flushing flow rate data is too high to reduce the robustness of the system, and then the flushing flow rate data is corrected once every 2 minutes in the embodiment, and the implementer can set the time interval between the adjacent two corrections of the flushing flow rate data according to the actual situation, which is not limited herein.

[0101] It should be noted that when the flow rate adjustment weight is less than 0.2 for 3 seconds, or the pH value is greater than 5.5, or the muscle tension degree is greater than 0.9, it indicates that the vagina is in an extreme risk state at this time, and the vagina expansion and cleaning device automatically suspends flushing and sends an alarm to the medical staff for timely processing. The conditions corresponding to the above extreme risk state can be set according to the actual situation, which is not limited herein.

[0102] In summary, the embodiment obtains the pelvic floor muscle electrical signal, the pH value and the flushing flow rate data of the patient in the process of vaginal flushing and expansion; according to the pelvic floor muscle electrical signal and the flushing flow rate data of the matching historical patient of the current patient in the flushing and expansion stage, the muscle electrical influence degree of the current patient is obtained; according to the difference between the pH value of the current patient at each time and the normal pH value range of the vagina, and the change of the pH value in each time preset field time period, the pH influence degree of the current patient is obtained; according to the muscle electrical influence degree and the pH influence degree, the flow rate adjustment weight of the current patient is obtained in real time, and the flushing flow rate of the current patient in the process of vaginal flushing and expansion is controlled. The present application can accurately adjust the flushing flow rate by accurately obtaining the flow rate adjustment weight in real time, and effectively avoid the damage to the vagina in the process of flushing and expansion.

[0103] Embodiment 2:

[0104] The present application also provides a control system for vaginal flushing and expansion based on multi-modal data, please refer toFigure 3 Fig. 3 shows a structure diagram of a control system for vaginal irrigation dilation based on multi-modal data according to an embodiment of the present application, which includes a data acquisition module 10, an electromyography influence degree acquisition module 20, a pH influence degree acquisition module 30, a flow rate adjustment weight acquisition module 40, and an irrigation flow rate control module 50.

[0105] The data acquisition module 10 is configured to acquire the electromyography signal, the pH value, and the irrigation flow rate data of each patient at each time during the vaginal irrigation dilation process, as well as the basic information of each patient, wherein the vaginal irrigation dilation process includes an initial stage and an irrigation dilation stage.

[0106] The electromyography influence degree acquisition module 20 is configured to acquire the matching historical patient of the current patient according to the similarity of the basic information of the current patient and the historical patient, and acquire the electromyography influence degree corresponding to each preset time period of the current patient according to the peak amplitude of the electromyography signal and the irrigation flow rate data of each matching historical patient in each preset time period during the irrigation dilation stage.

[0107] The pH influence degree acquisition module 30 is configured to acquire the pH influence degree of the current patient at each time according to the difference between the pH value of the current patient at each time and the normal pH value range of the vagina, and the change of the pH value in each preset time period at each time.

[0108] The flow rate adjustment weight acquisition module 40 is configured to acquire the flow rate adjustment weight of the current patient in real time according to the electromyography influence degree and the pH influence degree of the current patient in the time period from the start time of the vaginal irrigation dilation process to the current time.

[0109] The irrigation flow rate control module 50 is configured to control the irrigation flow rate of the current patient in the vaginal irrigation dilation process in real time based on the flow rate adjustment weight.

[0110] It should be noted that the system provided in the above embodiment is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the control system for vaginal irrigation dilation based on multi-modal data and the control method for vaginal irrigation dilation based on multi-modal data provided in the above embodiment belong to the same concept, and the specific implementation process is described in detail in the method embodiment, which is not repeated here.

[0111] Embodiment 3:

[0112] The application further provides a device for controlling vaginal irrigation and dilation based on multi-modal data, which comprises a memory and a processor, wherein the memory stores executable program code, and the processor is configured to invoke and execute the executable program code to perform the method for controlling vaginal irrigation and dilation based on multi-modal data provided in the embodiments. The device can be a chip, an assembly or a module. The chip can comprise a processor and a memory connected to each other. When the processor invokes and executes the instructions, the chip can perform the method for controlling vaginal irrigation and dilation based on multi-modal data provided in the embodiments.

[0113] In addition, the embodiments of the present application also protect a computer device, please refer to Figure 4 The computer device comprises a memory 401, a processor 402 and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can perform any of the methods for controlling vaginal irrigation and dilation based on multi-modal data described above.

[0114] Embodiment 4

[0115] The embodiments also provide a computer readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the related method steps to perform the method for controlling vaginal irrigation and dilation based on multi-modal data provided in the embodiments.

[0116] Embodiment 5

[0117] The embodiments also provide a computer program product. When the computer program product runs on a computer, the computer executes the related steps to perform the method for controlling vaginal irrigation and dilation based on multi-modal data provided in the embodiments.

[0118] The device, the computer readable storage medium, the computer program product or the chip provided in the embodiments are used to perform the corresponding method provided above, so the beneficial effects achieved thereby can refer to the beneficial effects of the corresponding method provided above, which will not be described here.

[0119] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0120] The various embodiments described in this specification are presented by way of example, and each embodiment is not inherently more important than any other embodiment.

Claims

1. A control system for vaginal irrigation and dilation based on multimodal data, characterized in that, The system includes a data acquisition module, an electromyography influence acquisition module, a pH influence acquisition module, a flow rate adjustment weight acquisition module, and a flushing flow rate control module; The data acquisition module is used to acquire pelvic floor electromyography signals, pH value, and irrigation flow rate data for each patient at each moment during the vaginal irrigation and dilation process, as well as basic information for each patient; the vaginal irrigation and dilation process includes an initial stage and an irrigation and dilation stage; The electromyography (EMG) impact degree acquisition module is used to acquire matching historical patients for the current patient based on the similarity of basic information between the current patient and historical patients; and to acquire the EMG impact degree of the current patient for each preset time period based on the peak amplitude of pelvic floor EMG signals and the flushing flow rate data of each matching historical patient during each preset time period in the flushing and expansion phase. The pH impact degree acquisition module is used to acquire the pH impact degree of the current patient at each moment based on the difference between the current patient's pH value at each moment and the normal vaginal pH value range, as well as the pH value changes within a preset domain time period at each moment. The flow rate adjustment weight acquisition module is used to acquire the flow rate adjustment weight of the current patient in real time based on the degree of electromyographic influence and pH influence during the time period from the start of the vaginal irrigation and dilation process to the current time. The irrigation flow rate control module is used to control the irrigation flow rate in real time during the current patient's vaginal irrigation and dilation process based on the flow rate adjustment weight. The flow rate adjustment weight acquisition module is also used to determine the initial muscle analysis value based on the relationship between the degree of electromyography influence and the degree of pH influence in the current patient in the initial stage. The current muscle analysis value is determined based on the relationship between the two during the flushing and expansion phase up to the current moment; A dynamic reference weight is obtained by comparing the difference between the current muscle analysis value and the initial muscle analysis value. The first regulatory factor is obtained by multiplying the dynamic reference weight by the degree of electromyography influence, and the second regulatory factor is obtained by multiplying the negative correlation value of the dynamic reference weight by the degree of pH influence. The first and second regulatory factors are added together to obtain the real-time flow rate adjustment weight.

2. The control system for vaginal irrigation and dilation based on multimodal data as described in claim 1, characterized in that, The method for obtaining the degree of influence of electromyography is as follows: The flushing and dilation phase of each matched historical patient was divided into preset time periods according to the time sequence. Based on the peak amplitude of the corresponding pelvic floor electromyography signal in each preset time period for each matched historical patient, the muscle tension level corresponding to each preset time period for each matched historical patient is obtained. The system pre-defines the range of muscle tension levels and uses the average of all flushing flow rate data from historical patients within a pre-defined time period corresponding to each muscle tension level in each range as the safe flow rate data for each range. The ratio of the safe flow rate data to the preset benchmark flow rate data is used as the degree of electromyographic influence corresponding to the degree of muscle tension within the corresponding interval. The degree of electromyographic influence corresponding to the muscle tension level of the current patient in each preset time period is taken as the degree of electromyographic influence of the current patient in each preset time period; wherein, the preset time period of the current patient includes the preset time period of the current patient in the initial stage.

3. The control system for vaginal irrigation and dilation based on multimodal data as described in claim 2, characterized in that, The method for obtaining the muscle tension level is as follows: For any patient, the peak amplitude of the pelvic floor muscle electromyography signal corresponding to the patient’s maximum voluntary contraction of the pelvic floor muscles for a preset duration is taken as the patient’s maximum voluntary contraction amplitude. For any preset time period of the patient, the ratio of the peak amplitude of the pelvic floor electromyography signal to the maximum voluntary contraction amplitude within that preset time period is taken as the muscle tension level corresponding to that preset time period of the patient.

4. The control system for vaginal irrigation and dilation based on multimodal data as described in claim 1, characterized in that, The method for obtaining the degree of pH influence is as follows: The average of the maximum and minimum pH values ​​within the normal vaginal pH range is used as the normal reference pH value. The difference between the maximum pH value within the normal vaginal pH range and the normal reference pH value is used as the pH tolerance level; The difference between the current patient's pH value at each moment and the normal reference pH value is taken as the degree of pH deviation at each moment for the current patient. For any given moment in the current patient's life, the ratio of the degree of pH deviation to the pH tolerance at that moment is taken as the degree of pH abnormality for that patient at that moment. When the pH value abnormality exceeds the preset abnormality threshold, the variance of the pH value difference between all two adjacent times within the preset neighborhood time period is obtained as the degree of pH value change of the current patient at that time. The difference between the degree of pH abnormality and the preset abnormality threshold is taken as the first difference; The result of normalizing the product of the first difference and the degree of pH change is taken as the degree of pH influence on the current patient at that moment; When the pH value abnormality is less than or equal to the preset abnormality threshold, 0 is taken as the pH impact level of the current patient at that moment.

5. The control system for vaginal irrigation and dilation based on multimodal data as described in claim 1, characterized in that, The method for obtaining the flow rate adjustment weight is as follows: The end time of each preset time period for the current patient is taken as the target time for the current patient; the degree of electromyographic influence corresponding to each preset time period for the current patient is taken as the degree of electromyographic influence at each target time for the current patient. A two-dimensional coordinate system is constructed with the degree of pH influence as the horizontal axis and the degree of electromyography influence as the vertical axis. Based on the coordinates of the electromyographic and pH effects at each target time point in the initial phase, the initial state muscle analysis values ​​of the current patient are obtained in the two-dimensional coordinate system. Based on the coordinates of the electromyographic and pH effects at each target time point during the flushing and dilation phase of the current patient up to the current time, the current muscle analysis value of the current patient is obtained in a two-dimensional coordinate system; where the current time must be within the flushing and dilation phase of the current patient. Based on the difference between the current muscle analysis value and the initial muscle analysis value, obtain the dynamic reference weights for the current patient's last target time up to the current time. The product of the dynamic reference weight at the last target time of the current patient up to the current time and the degree of electromyographic influence is used as the first regulatory factor; The product of the dynamic reference weight negative correlation result up to the current time, the last target time of the current patient, and the degree of pH influence is used as the second regulatory factor; The sum of the first and second regulatory factors is used as the flow rate adjustment weight for the current patient's last target time up to the current moment.

6. The control system for vaginal irrigation and dilation based on multimodal data as described in claim 5, characterized in that, The method for obtaining the initial state muscle analysis values ​​is as follows: The coordinates of the degree of electromyography and pH influence of the current patient at each target time in the initial stage are used as the initial coordinates in the two-dimensional coordinate system. The principal component analysis algorithm is used to obtain the line corresponding to the initial coordinate point, which is then used as the initial reference line. The slope of the initial reference line is used as the initial muscle analysis value for the current patient.

7. The control system for vaginal irrigation and dilation based on multimodal data as described in claim 5, characterized in that, The method for obtaining the current muscle analysis value is as follows: By performing curve fitting on the coordinate points corresponding to the electromyographic and pH effects at each target time point during the flushing and dilation phase of the current patient up to the current time in the two-dimensional coordinate system, a reference curve is obtained. The first derivative of the coordinate point corresponding to the last target time of the current patient in the reference curve is used as the current muscle analysis value of the current patient.

8. The control system for vaginal irrigation and dilation based on multimodal data as described in claim 5, characterized in that, The method for obtaining the dynamic reference weight is as follows: The result of normalizing the difference between the current muscle analysis value and the initial muscle analysis value is used as the dynamic reference weight up to the current time, which is the last target time of the current patient.

9. A control system for vaginal irrigation and dilation based on multimodal data as described in claim 5, characterized in that, The method for real-time control of the irrigation flow rate during the current patient's vaginal irrigation and dilation process based on flow rate adjustment weights is as follows: The product of the flow rate adjustment weight and the irrigation flow rate data up to the current time and the last target time of the current patient is used as the corrected irrigation flow rate data up to the current time and the last target time of the current patient, and the irrigation flow rate is controlled in real time during the vaginal irrigation and dilation process of the current patient.

10. A control system for vaginal irrigation and dilation based on multimodal data as described in claim 1, characterized in that, The method for obtaining the matched historical patients is as follows: Each patient's basic information is converted into a vector, which serves as the feature vector for each patient. The cosine similarity between the feature vectors of the current patient and each historical patient is obtained and used as the similarity score; among them, historical patients are those who did not suffer damage during vaginal irrigation and dilation. When the similarity is greater than the preset similarity threshold, the corresponding historical patient will be used as the current patient's matched historical patient.

Citation Information

Patent Citations

  • Intelligent gastric tube

    CN109846715A

  • Pelvic floor rehabilitation training method based onbiologicalfeedback

    CN113769268A

  • Control system for in-vivo flushing of endoscope

    CN120304762A