CN116746933A - Multidimensional analysis method for pelvic floor muscle training data - Google Patents
Multidimensional analysis method for pelvic floor muscle training data Download PDFInfo
- Publication number
- CN116746933A CN116746933A CN202310976760.5A CN202310976760A CN116746933A CN 116746933 A CN116746933 A CN 116746933A CN 202310976760 A CN202310976760 A CN 202310976760A CN 116746933 A CN116746933 A CN 116746933A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- crowd
- muscle strength
- treatment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000003205 muscle Anatomy 0.000 title claims abstract description 109
- 238000012549 training Methods 0.000 title claims abstract description 52
- 210000003903 pelvic floor Anatomy 0.000 title claims abstract description 31
- 238000004458 analytical method Methods 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 18
- 208000024891 symptom Diseases 0.000 claims description 25
- 230000000694 effects Effects 0.000 claims description 15
- 238000011084 recovery Methods 0.000 claims description 13
- 238000013500 data storage Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 3
- 206010000210 abortion Diseases 0.000 claims 2
- 231100000176 abortion Toxicity 0.000 claims 2
- 230000008569 process Effects 0.000 abstract description 6
- 238000007405 data analysis Methods 0.000 abstract description 3
- 230000003797 telogen phase Effects 0.000 description 8
- 206010000234 Abortion spontaneous Diseases 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 208000015994 miscarriage Diseases 0.000 description 4
- 238000007634 remodeling Methods 0.000 description 4
- 230000000284 resting effect Effects 0.000 description 4
- 238000012358 sourcing Methods 0.000 description 4
- 208000000995 spontaneous abortion Diseases 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000001568 sexual effect Effects 0.000 description 3
- 230000002485 urinary effect Effects 0.000 description 3
- 206010010774 Constipation Diseases 0.000 description 2
- 208000004483 Dyspareunia Diseases 0.000 description 2
- 208000034347 Faecal incontinence Diseases 0.000 description 2
- 206010060891 General symptom Diseases 0.000 description 2
- 208000002193 Pain Diseases 0.000 description 2
- 208000000450 Pelvic Pain Diseases 0.000 description 2
- 206010046543 Urinary incontinence Diseases 0.000 description 2
- 206010046555 Urinary retention Diseases 0.000 description 2
- 206010046814 Uterine prolapse Diseases 0.000 description 2
- 206010046914 Vaginal infection Diseases 0.000 description 2
- 201000008100 Vaginitis Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 230000013872 defecation Effects 0.000 description 2
- 210000001035 gastrointestinal tract Anatomy 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000027939 micturition Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000036407 pain Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 201000010727 rectal prolapse Diseases 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000007493 shaping process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 206010011224 Cough Diseases 0.000 description 1
- 206010024419 Libido decreased Diseases 0.000 description 1
- 208000029549 Muscle injury Diseases 0.000 description 1
- 206010064229 Pelvic discomfort Diseases 0.000 description 1
- 208000012287 Prolapse Diseases 0.000 description 1
- 206010051873 Vaginal relaxation Diseases 0.000 description 1
- 206010071212 Vulvovaginal injury Diseases 0.000 description 1
- 206010000059 abdominal discomfort Diseases 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 230000036592 analgesia Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002757 inflammatory effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 210000000664 rectum Anatomy 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 206010041232 sneezing Diseases 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a multidimensional analysis method of pelvic floor muscle training data, and belongs to the technical field of data analysis. According to the invention, signals fed back by pelvic floor muscles are collected by hardware equipment and transmitted to APP through Bluetooth, the signals are collected by APP and then converted into muscle strength values, the muscle strength values are transmitted to cloud storage through a network, and mainly, combined multidimensional data analysis is carried out by combining data generated in the collection process of the muscle strength values and data of a user, personal data of the user are mainly recorded and transmitted to cloud storage by the user through APP, and muscle strength related data are collected and uploaded to APP by equipment and then transmitted to cloud storage. The generation of muscle force data is mainly realized by that APP sends out specific instructions according to a treatment scheme, and a user can train according to the training requirement of the scheme.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a multidimensional analysis method of pelvic floor muscle training data.
Background
With the continuous development of socioeconomic performance, people are increasingly concerned about how to protect body muscles. Most of the prior art is to analyze the muscle strength itself, and neglect human factors and environmental factors. In the same scheme, people of different ages, different postpartum stages or different degrees of pelvic floor muscle injury are used, the training effects are different, and a user can influence the training effect due to insufficient familiarity degree of training in initial training.
Therefore, a multi-dimensional analysis method capable of analyzing pelvic floor muscle training data with wider coverage and higher applicability is needed.
Disclosure of Invention
The invention aims to provide a multidimensional analysis method of pelvic floor muscle training data, which aims to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a multidimensional analysis method of pelvic floor muscle training data comprises the following steps:
s1, collecting relevant data of a user;
s2, classifying and counting the collected related data according to different dimensionalities;
s3, extracting a crowd data set matched with the user characteristics according to requirements on the basis of classification statistics;
s4, classifying the data in the crowd data set according to muscle strength grade;
s5, analyzing and obtaining the recovery effect of pelvic floor muscles under different treatment courses on the basis of the classified products.
In S1, the collecting of related data of different users is to collect related data through APP, and then use APP to call a data storage interface provided by a cloud server to store data. The basic data includes height, weight, age, marital status, number of births, miscarriage, time of last birthing miscarriage, region. The user fills corresponding data into the forms provided by the personal information page of the APP, and then the APP calls a data storage interface/userinfo/save provided by the cloud server to store the data. User demand and symptomatic conditions, general pelvic muscle training demands include prevention of pelvic floor problems, promotion of privacy health, shaping maintenance relaxation, repair of pelvic floor problems, general symptoms include urinary incontinence, urinary retention, fecal incontinence, constipation, reduced sexual experience, dyspareunia, front and rear wall distension, uterine prolapse, rectal prolapse, recurrent vaginitis, pelvic floor pain, chronic pelvic pain. The APP end provides two forms, one is related to the user's needs and used for recording the problem which the user wants to solve, and the other is related to the symptoms and used for knowing the problem of the pelvic floor muscles faced by the current user. The data of the two forms are respectively stored in the two data tables of the cloud through two interfaces/used/save and/user/save provided by the server. Training data, the user usually goes to treat along a regimen, one regimen has 15 courses, one course is 30 minutes, the user will first train the initial, the user will make some initial configuration, such as current value, channel usage number, APP will first record the muscle force values that the user produces by training the device for 30 minutes, these muscle force values usually have 5 phases consisting of forward rest phase, fast rest phase, slow rest phase, endurance test phase, backward rest phase. The APP end can provide a form for feedback data, the user can input the feedback information, and the satisfaction degree grade evaluation is carried out on the training process, and finally the training is carried out to obtain score data of each stage. The APP saves the part of data to the cloud through a back-end interface/user/feedback.
In S2, the collected data is classified and counted according to different dimensions, and the user data collected and stored in the cloud is classified and counted according to age, height, weight, area, wedding, post-partum stage and muscle strength stage. The ages are divided into five intervals, respectively less than 20 years old, 21 years old to 25 years old, 26 years old to 30 years old, 31 years old to 35 years old, 36 years old to 40 years old, and 41 years old to 50 years old;
the height interval is divided into an interval smaller than 150 cm, more than 150 cm, and a new interval from 150 cm, for example: 150 cm to 155 cm, 155 cm to 160cm, 160cm to 165cm, 165cm to 170 cm and 170 cm to 175 cm;
the weight interval is divided into a single interval of less than 40 kg, more than 40 kg, and a new interval every 5 kg from 40 kg, for example: 40 kg to 45 kg, 45 kg to 50 kg, 50 kg to 55 kg, 55 kg to 60 kg and 60 kg to 65 kg;
the division of the region section is performed in a manner of division in the form of the first letter of province, for example: (nj, js), (cd, sc), (sh, sh) and (bj, bj);
the wedding condition is divided into two sections, namely a non-bred section and a bred section; the post-partum is divided into six intervals of less than 42 days, 42 days to 180 days, half year to one year, one year to three years, three years to ten years and more than ten years respectively;
the muscle strength stage score is divided into five sections, namely a front resting stage score, a fast muscle stage score, a slow muscle stage score, a endurance stage score and a rear resting stage score;
the demands are divided into five sections, namely, the expected muscle strength grade A, the expected muscle strength grade B, the expected muscle strength grade C, the expected muscle strength grade D and the expected muscle strength grade E, and different crowds are divided according to different symptoms.
In S3, extracting different user characteristic data sets is to analyze out data sets meeting the conditions by setting different range query conditions, and then to acquire intersections of the different data sets to obtain the user characteristic data sets. All training data are analyzed, training related data of all users are taken out, polling calculation is carried out, when the muscle strength is increased from D to C, n1 treatment courses are used on average, the number of people for the increase is 90%, and the current is 70ma and 90%. The muscle strength value is increased to B, n2 courses of treatment are used on average, the number of people to be increased is 85%, m3 courses of treatment are used for the muscle strength to A, and the number of people to be increased is 80%. The user is calculated to perform n1 courses of treatment, the muscle strength level is restored to the C level with 90% probability, the user is trained for n2 courses of treatment with the current of 70ma accounting for 80%, the muscle strength level is restored to the B level with 90% probability, the user is trained for m3 courses of treatment, and the muscle strength level is restored to the A level with 90% probability.
In S4, classifying crowd data according to muscle strength levels, firstly collecting crowd with the same characteristics, classifying different crowd according to different characteristics, putting all the characteristic crowd belonging to user basic data together to obtain crowd conforming to the user basic data, putting all the characteristic crowd belonging to user demands and symptom conditions together to obtain crowd conforming to the user demands and symptom conditions, putting all the characteristic crowd belonging to training data together to obtain crowd conforming to the training data, putting all the characteristic crowd belonging to feedback data together to obtain crowd conforming to the feedback data, and obtaining crowd data conforming to the user characteristic values; the crowd of user basic data, the crowd of user demands and symptom conditions, the crowd of training data and the crowd of feedback data are put together, and intersection sets are taken at the same time to obtain all feature matching target user crowd; and finally, classifying the target user groups according to the muscle strength grade.
In S5, the recovery effect of pelvic floor muscles under different courses of treatment is that the recovery effective rate of each course of treatment is obtained by analyzing the ratio of the number of people with the muscle strength grade lifting ratio in different courses of treatment to the number of people in the course of treatment, the crowd data of the recovery effect in each course of treatment and the crowd data of the muscle strength grade lifting span are extracted, the ratio of people using different courses of treatment in the crowd is calculated, the effective rate of the courses of treatment is obtained, and the distribution situation of the course of treatment scheme in the crowd is obtained.
Compared with the prior art, the invention has the following beneficial effects: the invention has the advantages that the data surface of the analyzed and covered data is wider, massive multidimensional data can more objectively and truly reflect the training condition of a group, so that universal prediction results are obtained, the user is promoted to insist to do training, the analysis from muscle strength per se is somewhat covered, the analysis results cannot be obtained better and accurately, the single data reflects only one group of data of individuals, the conditions among individuals are quite different, and on the contrary, the multidimensional characteristic data and the case users with more data can obtain universal and objective guidance.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method for multidimensional analysis of pelvic floor training data in accordance with the present invention;
fig. 2 is a schematic flow chart of a multidimensional analysis method of pelvic floor muscle training data according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions: a multidimensional analysis method of pelvic floor muscle training data comprises the following steps:
s1, collecting relevant data of a user;
s2, classifying and counting the collected related data according to different dimensionalities;
s3, extracting a crowd data set matched with the user characteristics according to requirements on the basis of classification statistics;
s4, classifying the data in the crowd data set according to muscle strength grade;
s5, analyzing and obtaining the recovery effect of pelvic floor muscles under different treatment courses on the basis of the classified products.
In S1, the relevant data of the collected user is collected through the APP, and then the APP calls a data storage interface provided by the cloud server to store the data. The basic data includes height, weight, age, marital status, number of births, miscarriage, time of last birthing miscarriage, region. The user fills corresponding data into the forms provided by the personal information page of the APP, and then the APP calls a data storage interface/userinfo/save provided by the cloud server to store the data. User demand and symptomatic conditions, general pelvic muscle training demands include prevention of pelvic floor problems, promotion of privacy health, shaping maintenance relaxation, repair of pelvic floor problems, general symptoms include urinary incontinence, urinary retention, fecal incontinence, constipation, reduced sexual experience, dyspareunia, front and rear wall distension, uterine prolapse, rectal prolapse, recurrent vaginitis, pelvic floor pain, chronic pelvic pain. The APP end provides two forms, one is related to user requirements and used for recording the problem to be solved by the user, and the other is related to symptoms and used for knowing the problem of pelvic floor muscles faced by the current user. The data of the two forms are respectively stored in the two data tables of the cloud through two interfaces/used/save and/user/save provided by the server. Training data, the user usually goes to treat along a regimen, one regimen has 15 courses, one course is 30 minutes, the user will first train the initial, the user will make some initial configuration, such as current value, channel usage number, APP will first record the muscle force values that the user produces by training the device for 30 minutes, these muscle force values usually have 5 phases consisting of forward rest phase, fast rest phase, slow rest phase, endurance test phase, backward rest phase. The APP end can provide a form for feedback data, the user can input the feedback information, and the satisfaction degree grade evaluation is carried out on the training process, and finally the training is carried out to obtain score data of each stage. The APP saves the part of data to the cloud through a back-end interface/user/feedback.
In S2, the collected data is classified and counted according to different dimensions, and the user data collected and stored in the cloud is classified and counted according to age, height, weight, area, wedding, post-partum stage and muscle strength stage. The ages are divided into five intervals, respectively less than 20 years old, 21 years old to 25 years old, 26 years old to 30 years old, 31 years old to 35 years old, 36 years old to 40 years old, and 41 years old to 50 years old;
the height interval is divided into an interval smaller than 150 cm, more than 150 cm, and a new interval from 150 cm, for example: 150 cm to 155 cm, 155 cm to 160cm, 160cm to 165cm, 165cm to 170 cm and 170 cm to 175 cm;
the weight interval is divided into a single interval of less than 40 kg, more than 40 kg, and a new interval every 5 kg from 40 kg, for example: 40 kg to 45 kg, 45 kg to 50 kg, 50 kg to 55 kg, 55 kg to 60 kg and 60 kg to 65 kg;
the division of the region section is performed in a manner of division in the form of the first letter of province, for example: (nj, js), (cd, sc), (sh, sh) and (bj, bj);
the wedding condition is divided into two sections, namely a non-bred section and a bred section; the post-partum is divided into six intervals of less than 42 days, 42 days to 180 days, half year to one year, one year to three years, three years to ten years and more than ten years respectively;
the muscle strength stage score is divided into five sections, namely a front resting stage score, a fast muscle stage score, a slow muscle stage score, a endurance stage score and a rear resting stage score;
the demands are divided into five sections, namely, the expected muscle strength grade A, the expected muscle strength grade B, the expected muscle strength grade C, the expected muscle strength grade D and the expected muscle strength grade E, and different crowds are divided according to different symptoms.
In S3, extracting different user characteristic data sets is to analyze out data sets meeting the conditions by setting different range query conditions, and then to acquire intersections of the different data sets to obtain the user characteristic data sets. All training data are analyzed, training related data of all users are taken out, polling calculation is carried out, when the muscle strength is increased from D to C, n1 treatment courses are used on average, the number of people for the increase is 90%, and the current is 70ma and 90%. The muscle strength value is increased to B, n2 courses of treatment are used on average, the number of people to be increased is 85%, m3 courses of treatment are used for the muscle strength to A, and the number of people to be increased is 80%. The user is calculated to perform n1 courses of treatment, the muscle strength level is restored to the C level with 90% probability, the user is trained for n2 courses of treatment with the current of 70ma accounting for 80%, the muscle strength level is restored to the B level with 90% probability, the user is trained for m3 courses of treatment, and the muscle strength level is restored to the A level with 90% probability.
In S4, classifying crowd data according to muscle strength levels, firstly collecting crowd with the same characteristics, classifying different crowd according to different characteristics, putting all the characteristic crowd belonging to user basic data together to obtain crowd conforming to the user basic data, putting all the characteristic crowd belonging to user demands and symptom conditions together to obtain crowd conforming to the user demands and symptom conditions, putting all the characteristic crowd belonging to training data together to obtain crowd conforming to the training data, putting all the characteristic crowd belonging to feedback data together to obtain crowd conforming to the feedback data, and obtaining crowd data conforming to the user characteristic values; the crowd of user basic data, the crowd of user demands and symptom conditions, the crowd of training data and the crowd of feedback data are put together, and intersection sets are taken at the same time to obtain all feature matching target user crowd; and finally, classifying the target user groups according to the muscle strength grade.
In S5, the recovery effect of pelvic floor muscles under different courses of treatment is that the recovery effective rate of each course of treatment is obtained by analyzing the ratio of the number of people with the muscle strength grade lifting ratio in different courses of treatment to the number of people in the course of treatment, the crowd data of the recovery effect in each course of treatment and the crowd data of the muscle strength grade lifting span are extracted, the ratio of people using different courses of treatment in the crowd is calculated, the effective rate of the courses of treatment is obtained, and the distribution situation of the course of treatment scheme in the crowd is obtained.
Example 1:
first, collecting feature group data of a user:
{ Age, height, weight, region }, i.e., feature 1= { Age, height, weight, area };
{ demand, symptom }, i.e., feature 2= { seed, symptom };
{ wedding, post parturient }, i.e. Feature 3= { Married, postpartum }.
Secondly, solving a crowd data set where the single feature is located: feature1 (Age) =age (26, 30); feature1 (Height) =height (160 cm, 165 cm); and deducing a crowd data set in which all the features are located according to the sequence.
Solving a crowd data set where the requirements and symptoms are located: feed 2 (feed) =feed (a) U feed (B); feature2 (Symptom) =symptom (a) U Symptom (B); and deducing a crowd data set in which all the requirements and symptoms are located according to the sequence.
Calculate crowd data set for wedding and post partum: feature3 (maried) =maried (1, 1); feature3 (postpart) =postpart (42 d,180 d);
crowd data set at muscle strength stage: feature4 (Muscle 1) =muscle 1 (30, 40); feature4 (Muscle 2) =muscle 1 (40, 50); feature4 (Muscle 3) =muscle 1 (40, 50); feature4 (Muscle 4) =muscle 1 (50, 60); feature4 (Muscle 5) =muscle 1 (40, 50); feature4 (music) =music 1 (40, 50).
Solving a crowd data set where the training feedback level is located: feature5 (feed) =feed back (a)
Third, the muscle strength grade fraction was A, B, C, D, E, the average course data was n, and the current was ma. All crowd data meeting the user characteristic values (all characteristic matching are obtained) are obtained:
FeatureAll1 = Feature1(Age)∩ Feature1(Height)∩Feature1(Weight)∩Feature1(Area);FeatureAll2 = Feature2(Need)∩Feature2(Symptom);FeatureAll3 = Feature3(Married)∩Feature3(Symptom);FeatureAll4 = Feature4(Muscle1)∩Feature3(Muscle1)∩Feature4(Muscle2)∩Feature4(Muscle3)∩Feature4(Muscle4)∩Feature4(Muscle5)∩Feature4(Muscle);FeatureAll5 = Feature4(FeedBack)
and putting all the crowd data which accord with the user characteristic values together to obtain intersection, and obtaining crowd data of all the target user with the characteristic matching:
FeatureAll = FeatureAll1 ∩ FeatureAll2 ∩ FeatureAll3 ∩ FeatureAll4 ∩ FeatureAll5 ={u1, u2, u3, u4, u5, u6, u7…un}
obtaining the total number of target crowd: n= sum (FeatureAll)
Fourth, the target user group is improved and divided according to the muscle strength level:
To(D)= {u1, u2, u3, u4, u5, u6, u7…un}
To(C)= {u1, u2, u3, u4, u5, u6, u7…un}
To(B)= {u1, u2, u3, u4, u5, u6, u7…un}
To(A)= {u1, u2, u3, u4, u5, u6, u7…un}
average values of treatment course data of all users To (D), to (C), to (B), to (a) were obtained:
N1 = AVG(To(D) = (a1 + a2 + a3 + a4 + a5 + …an) / n
N2 = AVG(To(C) = (a1 + a2 + a3 + a4 + a5 + …an) / n
N3 = AVG(To(B) = (a1 + a2 + a3 + a4 + a5 + …an) / n
N4 = AVG(To(A) = (a1 + a2 + a3 + a4 + a5 + …an) / n
the predicted value comprises two categories, wherein the first category is the average value of treatment courses used by all people promoted to a specific grade, the second category is the proportion of the number of people promoted to a (D, C, B, A) grade, the proportion of the number of people is matched with the proportion of all people, and the predicted value is obtained according to the target user group:
raising to level D, and using N1 treatment courses on average; the duty cycle sum (To (D))/N;
raising to level C, and using N2 courses on average; the duty cycle sum (To (C))/N;
lifting to a grade B, and averaging the average data of the treatment courses of all users for N3 treatment courses; the duty cycle sum (To (B))/N;
raising to grade A, and using N4 treatment courses on average; the duty cycle sum (To (A))/N.
Further distinguished by current:
Ma(To(D),70)={u1, u2, u3, u4, u5, u6, u7…,un}
Ma(To(D),80)={u1, u2, u3, u4, u5, u6, u7…,un}
…
obtaining a predicted value:
lifting to a level D, using 70ma; the duty ratio N (Ma (To (D), 70))/N
Lifting to a level D, and using 80ma; the duty ratio N (Ma (To (D), 80))/N
…
The predicted course data is mainly used for showing how long the user needs to achieve the improvement effect, and gives the user feedback of training information, so that the user can know the recovery condition of using the current course according to the feedback.
The actual operation process can select partial characteristic matching, and the characteristics comprise: age, height, weight, symptoms, wedding, post partum.
After the predicted value is obtained, treatment effect analysis is carried out, and the initial muscle strength grade C and the following users are put into an analysis group set:
U(C)= {u1, u2, u3, u4, u5, u6, u7…un}
U(D)= {u1, u2, u3, u4, u5, u6, u7…un}
U(E)= {u1, u2, u3, u4, u5, u6, u7…un}
grouping the data of each group according to muscle strength stage:
U(C,Muscle1(30,40)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(C,Muscle1(40,50)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(C,Muscle1(50,60)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(C,Muscle1(60,70)) = {u1, u2, u3, u4, u5, u6, u7…un}
…
U(C,Muscle5(30,40)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(C,Muscle5(40,50)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(C,Muscle5(50,60)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(C,Muscle5(60,70)) = {u1, u2, u3, u4, u5, u6, u7…un}
…
U(D,Muscle1(30,40)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(D,Muscle1(40,50)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(D,Muscle1(50,60)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(D,Muscle1(60,70)) = {u1, u2, u3, u4, u5, u6, u7…un}
…
U(E,Muscle1(30,40)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(E,Muscle1(40,50)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(E,Muscle1(50,60)) = {u1, u2, u3, u4, u5, u6, u7…un}
U(E,Muscle1(60,70)) = {u1, u2, u3, u4, u5, u6, u7…un}
polling obtains the rehabilitation regimen data set used by the analysis group users: f= { sourcing 1, sourcing 2, sourcing 3, … sourcing n }.
The rehabilitation regimen is as follows:
postnatal pelvic floor rehabilitation, indications: post-partum pelvic floor maintenance/conventional pelvic floor maintenance;
privacy tightening, indication: vaginal relaxation/vaginal blowing/hyposexuality/asexual climax, etc.;
privacy relaxation, indications: vaginoses/vaginal overstresses/disharmony of sexual life, etc.;
urinary remodeling (relaxed), indication: urine leakage occurs when abdominal pressure increases such as coughing/sneezing/laughing;
urinary remodeling (active type), indication: urgent urination/frequent urination at night (more than 1 time per night) and the like are difficult to control;
urinary remodeling (mixed mode), indication: the two conditions exist simultaneously to generate the urine leakage;
pelvic support remodeling, indications: prolapse/vaginal anterior and posterior wall/pelvic organ distension of bladder/rectum etc.;
intestinal tract dredging (relaxation type), indication: no sense of inconvenience/feeling of inexhaustibility after defecation, etc.;
intestinal tract dredging (tension type), indication: laborious/uncomfortable/less frequent defecation, etc.;
private analgesia, indications: pelvic discomfort/private discomfort (non-inflammatory/vaginal injury)/lower abdominal discomfort, and the like.
Solving the crowd number of each group of target users:
Total(C) = sum(U(C))
Total(D) = sum(U(D))
Total(E) = sum(U(E))
respectively taking 1 course of post-treatment muscle strength data of the batch of users, and acquiring user data sets of corresponding lifting proportions at each stage:
c class group users, the muscle strength is respectively improved in a stage:
U1(C,Muscle1,10%)= {u1, u2, u3, u4, u5, u6, u7…un}
U1(C,Muscle1,20%)= {u1, u2, u3, u4, u5, u6, u7…un}
…
U1(C,Muscle1,100%)= {u1, u2, u3, u4, u5, u6, u7…un}
c class group users, the muscle strength two stages are respectively improved in proportion:
U1(C,Muscle2,10%)= {u1, u2, u3, u4, u5, u6, u7…un}
U1(C,Muscle2,20%)= {u1, u2, u3, u4, u5, u6, u7…un}
…
U1(C,Muscle2,100%)= {u1, u2, u3, u4, u5, u6, u7…un}
c class group users, the three stages of muscle strength are respectively improved in proportion:
U1(C,Muscle3,10%)= {u1, u2, u3, u4, u5, u6, u7…un}
U1(C,Muscle3,20%)= {u1, u2, u3, u4, u5, u6, u7…un}
…
U1(C,Muscle3,100%)= {u1, u2, u3, u4, u5, u6, u7…un}
c class group user, four stages of muscle strength each lifting proportion
U1(C,Muscle4,10%)= {u1, u2, u3, u4, u5, u6, u7…un}
U1(C,Muscle4,20%)= {u1, u2, u3, u4, u5, u6, u7…un}
…
U1(C,Muscle4,100%)= {u1, u2, u3, u4, u5, u6, u7…un}
C class group users, the four stages of muscle strength are respectively improved in proportion:
U1(C,Muscle4,10%)= {u1, u2, u3, u4, u5, u6, u7…un}
U1(C,Muscle4,20%)= {u1, u2, u3, u4, u5, u6, u7…un}
…
U1(C,Muscle4,100%)= {u1, u2, u3, u4, u5, u6, u7…un}
c class group users, the proportion of each lifting in the muscle strength five-stage is improved:
U1(C,Muscle4,10%)= {u1, u2, u3, u4, u5, u6, u7…un}
U1(C,Muscle4,20%)= {u1, u2, u3, u4, u5, u6, u7…un}
…
U1(C,Muscle4,100%)= {u1, u2, u3, u4, u5, u6, u7…un}
obtaining the data duty ratio of each group to obtain the treatment effective rate of each group:
B1(c1,10%) = Sum(U1(C,Muscle1,10%)) / SUM(U1(C))
B1(c1,20%) = Sum(U1(C,Muscle1,20%)) / SUM(U1(C))
…
B5(c5,100%) = Sum(U1(C,Muscle1,100%)) / SUM(U1(C))
wherein B1 (C1, 10%) represents a user initial grade of C, 1 session training was performed, the value of muscle strength phase 1 was increased by 10% of the user's duty cycle, and so on.
And then obtaining the overall effective rate of each group:
Total(B1)=B1(c1,10%)+ B1(c1,20%)+ ... B1(c1,100%)
the relation represents the sum of all the ratios of 10% and 20% …% of the initial muscle strength C for 1 course of treatment, i.e. the initial muscle strength C grade, for 1 course of treatment, the overall effective rate of treatment.
Polling all effective users, and obtaining the user duty ratio of the corresponding scheme:
Course1 = {u1, u2 …un}
Course2 = {u1, u2 …un}
Course3 = {u1, u2 …un}
B(Course1)= sum(course1) / Total(C)
B(Course2)= sum(course2) / Total(C)
B(Course3)= sum(course3) / Total(C)
the user proportion of the scheme can reflect the treatment tendency of the user on one hand, and the effect of the scheme is reflected on the other hand, and parameters of all treatment items in the scheme are optimized through guiding the reverse direction of the effect.
The efficiency of D, E is obtained in the same manner.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A multidimensional analysis method of pelvic floor muscle training data is characterized in that:
s1, collecting relevant data of a user;
s2, classifying and counting the collected related data according to different dimensionalities;
s3, extracting a crowd data set matched with the user characteristics according to requirements on the basis of classification statistics;
s4, classifying the crowd data set according to muscle strength grades;
s5, analyzing and obtaining the recovery effect of pelvic floor muscles under different treatment courses on the basis of the classified products.
2. The method for multidimensional analysis of pelvic training data of claim 1, wherein:
in S1, the relevant data of the collected user is collected through the APP, and then the APP calls a data storage interface provided by the cloud server to store the data.
3. The method for multidimensional analysis of pelvic training data of claim 2, wherein:
the related data comprises user basic data, user demands, symptom conditions, training data and feedback data; the user basic data comprises height, weight, age, marital status, delivery times, abortion conditions, latest delivery abortion time and region, the user requirements refer to pelvic floor muscle training requirements, the symptom conditions refer to user own symptoms, the training data comprises treatment course time, initial configuration and muscle strength values, and the feedback data comprises feedback information, satisfaction degree grade evaluation and score of each stage.
4. The method for multidimensional analysis of pelvic training data of claim 2, wherein:
the method comprises the steps that an APP is used for calling a data storage interface provided by a cloud server to store data, specifically, the APP is used for calling the data storage interface/usenfo/save provided by the cloud server for user basic data, the user requirement is stored in a data table of the cloud through the interface/userned/save provided by a server, the symptom is stored in the data table of the cloud through the interface/usersick/save provided by the server, and the feedback data is stored in the cloud through a back-end interface/user/feedback.
5. The method for multidimensional analysis of pelvic training data of claim 1, wherein:
in S2, the classifying and counting the collected related data according to different dimensions is performed by classifying and counting the collected related data stored in the cloud according to age, height, weight, area, wedding, post-natal stage, muscle strength stage score, demand, symptom and training feedback level.
6. The method for multidimensional analysis of pelvic training data of claim 5, wherein:
in S3, the crowd data set is extracted by setting different range query conditions, analyzing the data set meeting the conditions according to the range query conditions, and finally acquiring intersections of the different data sets to obtain the crowd data set.
7. The method for multidimensional analysis of pelvic training data of claim 1, wherein:
in S4, the crowd data set is classified according to the muscle strength grade, the muscle strength grade is classified into five grades of ABCDE, the crowd with the muscle strength grade a and B is removed, and the rest crowd is classified according to the muscle strength grade to which the rest crowd belongs.
8. The method for multidimensional analysis of pelvic training data of claim 1, wherein:
in S5, the recovery effect of pelvic floor muscles under different courses of treatment is that the recovery effective rate of each course of treatment is obtained by analyzing the ratio of the number of people with the muscle strength grade lifting ratio in different courses of treatment to the number of people in the course of treatment, the crowd data of the recovery effect in each course of treatment and the crowd data of the muscle strength grade lifting span are extracted, the ratio of people using different courses of treatment in the crowd is calculated, the effective rate of the courses of treatment is obtained, and the distribution situation of the course of treatment scheme in the crowd is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310976760.5A CN116746933A (en) | 2023-08-04 | 2023-08-04 | Multidimensional analysis method for pelvic floor muscle training data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310976760.5A CN116746933A (en) | 2023-08-04 | 2023-08-04 | Multidimensional analysis method for pelvic floor muscle training data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116746933A true CN116746933A (en) | 2023-09-15 |
Family
ID=87948064
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310976760.5A Pending CN116746933A (en) | 2023-08-04 | 2023-08-04 | Multidimensional analysis method for pelvic floor muscle training data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116746933A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117473328A (en) * | 2023-12-26 | 2024-01-30 | 南京麦豆健康科技有限公司 | Big data-based vaginal relaxation assessment training system and method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107822648A (en) * | 2017-09-07 | 2018-03-23 | 华南理工大学 | A kind of non-intrusion type intelligence basin bottom rehabilitation system |
CN111899840A (en) * | 2020-07-30 | 2020-11-06 | 南京麦豆健康管理有限公司 | Pelvic floor muscle training system and training method |
CN112204671A (en) * | 2018-05-30 | 2021-01-08 | 国际商业机器公司 | Personalized device recommendation for active health monitoring and management |
CN112509697A (en) * | 2020-12-04 | 2021-03-16 | 南京大学 | Multi-module intelligent health management information system |
CN115040843A (en) * | 2022-07-19 | 2022-09-13 | 惠州优朵科技有限公司 | Intelligent dynamic adjustment method based on pelvic floor muscle training |
-
2023
- 2023-08-04 CN CN202310976760.5A patent/CN116746933A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107822648A (en) * | 2017-09-07 | 2018-03-23 | 华南理工大学 | A kind of non-intrusion type intelligence basin bottom rehabilitation system |
CN112204671A (en) * | 2018-05-30 | 2021-01-08 | 国际商业机器公司 | Personalized device recommendation for active health monitoring and management |
CN111899840A (en) * | 2020-07-30 | 2020-11-06 | 南京麦豆健康管理有限公司 | Pelvic floor muscle training system and training method |
CN112509697A (en) * | 2020-12-04 | 2021-03-16 | 南京大学 | Multi-module intelligent health management information system |
CN115040843A (en) * | 2022-07-19 | 2022-09-13 | 惠州优朵科技有限公司 | Intelligent dynamic adjustment method based on pelvic floor muscle training |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117473328A (en) * | 2023-12-26 | 2024-01-30 | 南京麦豆健康科技有限公司 | Big data-based vaginal relaxation assessment training system and method |
CN117473328B (en) * | 2023-12-26 | 2024-03-15 | 南京麦豆健康科技有限公司 | Big data-based vaginal relaxation assessment training system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dumoulin et al. | Pelvic floor muscle training versus no treatment, or inactive control treatments, for urinary incontinence in women | |
Braekken et al. | Pelvic floor function is independently associated with pelvic organ prolapse | |
Nygaard et al. | Lifetime physical activity and female stress urinary incontinence | |
CN116746933A (en) | Multidimensional analysis method for pelvic floor muscle training data | |
Rogers et al. | Sexual function in women with and without urinary incontinence and/or pelvic organ prolapse | |
Hollien et al. | Longitudinal research on adolescent voice change in males | |
Hundley et al. | A comparison of perineometer to brink score for assessment of pelvic floor muscle strength | |
Townsend et al. | Physical activity and incident urinary incontinence in middle-aged women | |
Rivalta et al. | Urinary incontinence and sport: first and preliminary experience with a combined pelvic floor rehabilitation program in three female athletes | |
Dechow et al. | Body condition scores and dairy form evaluations as indicators of days open in US Holsteins | |
Tegerstedt et al. | A short-form questionnaire identified genital organ prolapse | |
Ahmadi et al. | The hidden epidemic of urinary incontinence in women: a population-based study with emphasis on preventive strategies | |
Hartmann | Chronic vulvar pain from a physical therapy perspective | |
Manrique et al. | Assessment of pelvic floor anatomy for male-to-female vaginoplasty and the role of physical therapy on functional and patient-reported outcomes | |
Tosun et al. | Do stages of menopause affect the outcomes of pelvic floor muscle training? | |
Dufour et al. | Enhancing pelvic health: optimizing the services provided by primary health care teams in Ontario by integrating physiotherapists | |
Mazor et al. | Factors associated with response to anorectal biofeedback therapy in patients with fecal incontinence | |
Vasey et al. | Sexual reward via vulvar, perineal, and anal stimulation: a proximate mechanism for female homosexual mounting in Japanese macaques | |
Bradley et al. | Bowel symptoms in women planning surgery for pelvic organ prolapse | |
Sampselle | Behavioral intervention: the first-line treatment for women with urinary incontinence | |
Bø et al. | Which women do pelvic floor muscle exercises six months’ postpartum? | |
Ghafar et al. | Size of urogenital hiatus as a potential risk factor for emptying disorders after pelvic prolapse repair | |
Wang et al. | The self-report fecal incontinence and constipation questionnaire in patients with pelvic-floor dysfunction seeking outpatient rehabilitation | |
Thompson et al. | Continence nursing: A whole person approach | |
Kim et al. | Association between birth‐related factors and periodontitis in women: Korea National Health and Nutrition Examination Survey 2013–2018 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230915 |