A deep squat 1RM resistance training effect prediction method, system and storage medium

Abstract

The present application relates to a kind of deep squat 1RM resistance training effect prediction method, system and storage medium, comprising: the data corresponding to each first independent variable index of any subject and the percentage of deep squat 1RM training change are obtained as a training sample, obtain the training data set containing multiple training samples, based on stepwise linear regression method and training data set, the first independent variable index that meets preset significance condition is determined as target independent variable index, and the prediction model of the percentage of deep squat 1RM training change and multiple target independent variable indexes is constructed;The specific data corresponding to all target independent variable indexes of the trainee are obtained and input into prediction model, and the prediction value of the percentage of deep squat 1RM training change of the trainee is obtained.The present application improves the prediction accuracy, provides support for the trainee to provide accurate training scheme, and also lays a foundation for subsequent discussion on the mechanism that exercise is beneficial to health.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of training effect prediction, in particular to a deep squat 1RM resistance training effect prediction method, system and storage medium. BACKGROUND

[0002] Resistance training is an effective method to increase muscle strength and improve muscle function. In the research of precise fitness guidance program, the prediction model composed of phenomics indicators such as initial value of strength, muscle content and muscle thickness can only explain 40.9% to 42.5% of the difference in training effect of the maximum repetition (1RM), which indicates that there are other important factors affecting the training effect. It has been proved that genetic factors alone or in interaction with training significantly affect the difference in individual response to exercise training. The study based on candidate genes shows that 2.1% of the 1RM training effect can be attributed to the ACTN3 gene. However, training effect is a complex trait determined by multiple genetic markers, and with the deepening of research, it is difficult for the candidate gene method to meet the needs of the development of precise exercise fitness program.

[0003] Genome-wide association analysis (GWAS) is a commonly used method to study the genetic diversity of phenotypes. Polygenic score is the weighted sum of the effects of alleles related to the phenotype. The polygenic score developed on the basis of GWAS can predict the genetic effect of individual phenotype occurrence or probability from the whole genome perspective, so it is speculated that the construction of a comprehensive model combining genomics and phenomics indicators will improve the prediction effect of the model. However, due to the large resource demand of GWAS research, so far, the candidate gene method is still the main research method for genetic factors of muscle strength training effect. Both genomic and phenomic indicators explain the individual difference in training effect, so it is urgent to screen genetic markers of training effect from the level of GWAS, and solve the problems existing in the prior art from the perspective of multiple omics such as phenomics. SUMMARY

[0004] To solve the above technical problems, the present application provides a deep squat 1RM resistance training effect prediction method, system and storage medium.

[0005] The technical scheme of a deep squat 1RM resistance training effect prediction method of the present application is as follows:

[0006] Before performing the deep squat 1RM resistance training, the initial value of the deep squat 1RM of each subject is obtained, and after performing the deep squat 1RM resistance training, the training value of the deep squat 1RM of each subject is obtained, and the training change percentage of the deep squat 1RM of each subject is obtained according to the initial value of the deep squat 1RM and the training value of the deep squat 1RM of each subject;

[0007] The specific data corresponding to each first independent variable index of any subject and the squat 1RM training change percentage of the any subject are obtained before squat 1RM resistance training, as a training sample, to obtain a training data set containing multiple training samples, wherein the squat 1RM initial value is at least included in all first independent variable indexes;

[0008] Based on the stepwise linear regression method and the training data set, the first independent variable index meeting the preset significance condition is determined as the target independent variable index, and a target prediction model of the squat 1RM training change percentage and multiple target independent variable indexes is constructed.

[0009] Before squat 1RM resistance training, the specific data corresponding to all target independent variable indexes of the to-be-trained subject are input into the target prediction model to obtain the target prediction value of the squat 1RM training change percentage of the to-be-trained subject.

[0010] The beneficial effects of the squat 1RM resistance training effect prediction method of the present application are as follows:

[0011] The method of the present application constructs a squat 1RM training effect prediction model by the stepwise linear regression method, which improves the prediction accuracy, provides support for providing accurate training programs for the trainer, and lays a foundation for subsequent exploration of the mechanism that exercise is beneficial to health.

[0012] On the basis of the above-mentioned scheme, the squat 1RM resistance training effect prediction method of the present application can be further improved as follows.

[0013] Further, the multiple first independent variable indexes further include: original trunk muscle content, original whole body fat content and multiple first single nucleotide polymorphism sites.

[0014] Further, the multiple target independent variable indexes include: the squat 1RM initial value, the original trunk muscle content, the original whole body fat content and multiple target single nucleotide polymorphism sites; the step of determining the first independent variable index meeting the preset significance condition as the target independent variable index comprises:

[0015] Each single nucleotide polymorphism site meeting the preset significance condition is determined as a target single nucleotide polymorphism site.

[0016] Further, the plurality of target single nucleotide polymorphism sites comprises: a first target single nucleotide polymorphism site, a second target single nucleotide polymorphism site, a third target single nucleotide polymorphism site, a fourth target single nucleotide polymorphism site, a fifth target single nucleotide polymorphism site, a sixth target single nucleotide polymorphism site, a seventh target single nucleotide polymorphism site, an eighth target single nucleotide polymorphism site, and a ninth target single nucleotide polymorphism site; and the target prediction model is: y = 104.74 - 0.778x1 + 11.227x2 + 8.012x3 - 9.144x4 + 21.139x5 - 7.75x6 - 7.613x7 + 9.304x8 + 12.469x9 - 6.063x 10 - 0.001x 11 + 0.001x 12 ;

[0017] wherein y is a target prediction value of the to-be-trained person, x1 is a deep squat 1RM initial value of the to-be-trained person, x2 is an assignment value of the first target single nucleotide polymorphism site of the to-be-trained person, x3 is an assignment value of the second target single nucleotide polymorphism site of the to-be-trained person, x4 is an assignment value of the third target single nucleotide polymorphism site of the to-be-trained person, x5 is an assignment value of the fourth target single nucleotide polymorphism site of the to-be-trained person, x6 is an assignment value of the fifth target single nucleotide polymorphism site of the to-be-trained person, x7 is an assignment value of the sixth target single nucleotide polymorphism site of the to-be-trained person, x8 is an assignment value of the seventh target single nucleotide polymorphism site of the to-be-trained person, x9 is an assignment value of the eighth target single nucleotide polymorphism site of the to-be-trained person, and x 10 is an assignment value of the ninth target single nucleotide polymorphism site of the to-be-trained person, x 11 is an original whole body fat content of the to-be-trained person, x 12 is an original trunk muscle content of the to-be-trained person.

[0018] wherein when the genotype of any single nucleotide polymorphism site is AA, the assignment value of the any single nucleotide polymorphism site is 0; when the genotype of any single nucleotide polymorphism site is Aa, the assignment value of the any single nucleotide polymorphism site is 1; and when the genotype of any single nucleotide polymorphism site is aa, the assignment value of the any single nucleotide polymorphism site is 2.

[0019] Further, the step of obtaining a deep squat 1RM training change percentage of each subject according to the deep squat 1RM initial value and the deep squat 1RM training value of each subject comprises:

[0020] According to a preset formula, a squat 1RM initial value of any subject and a squat 1RM training value of the subject, a squat 1RM change percentage of the subject is obtained until a squat 1RM change percentage of each subject is obtained, wherein the preset formula is: Delta a is the squat 1RM change percentage of the subject, a2 is the squat 1RM training value of the subject, and a1 is the squat 1RM initial value of the subject.

[0021] The technical scheme of the squat 1RM resistance training effect prediction system of the application is as follows:

[0022] It comprises a first processing module, a second processing module, a construction module and a prediction module.

[0023] The first processing module is used to obtain a squat 1RM initial value of each subject before squat 1RM resistance training, obtain a squat 1RM training value of each subject after squat 1RM resistance training, and obtain a squat 1RM training change percentage of each subject according to the squat 1RM initial value and the squat 1RM training value of each subject.

[0024] The second processing module is used to obtain specific data corresponding to each first independent variable index of any subject and the squat 1RM training change percentage of the subject before squat 1RM resistance training, take the data as a training sample, obtain a training data set containing multiple training samples, and at least include a squat 1RM initial value in all first independent variable indexes.

[0025] The construction module is used to determine a first independent variable index meeting a preset significance condition as a target independent variable index based on a stepwise linear regression method and the training data set, and construct a target prediction model of a squat 1RM training change percentage and multiple target independent variable indexes.

[0026] The prediction module is used to input specific data corresponding to all target independent variable indexes of a subject to be trained into the target prediction model to obtain a target prediction value of a squat 1RM training change percentage of the subject to be trained before squat 1RM resistance training.

[0027] The squat 1RM resistance training effect prediction system of the application has the following beneficial effects:

[0028] The system of the application constructs a squat 1RM training effect prediction model by a stepwise linear regression method, improves prediction accuracy, provides support for providing a precise training scheme for a trainer, and lays a foundation for subsequent exploration of mechanisms of sports benefiting health.

[0029] On the basis of the above scheme, the squat 1RM resistance training effect prediction system of the present application can be further improved as follows.

[0030] Further, the plurality of first independent variable indicators further include: original trunk muscle content, original whole body fat content, and a plurality of first single nucleotide polymorphism sites.

[0031] Further, the plurality of target independent variable indicators include: the squat 1RM initial value, the original trunk muscle content, the original whole body fat content, and a plurality of target single nucleotide polymorphism sites; the step of determining the first independent variable indicator meeting the preset significance condition as the target independent variable indicator includes:

[0032] Each single nucleotide polymorphism site meeting the preset significance condition is determined as a target single nucleotide polymorphism site.

[0033] Further, the plurality of target single nucleotide polymorphism sites include: a first target single nucleotide polymorphism site, a second target single nucleotide polymorphism site, a third target single nucleotide polymorphism site, a fourth target single nucleotide polymorphism site, a fifth target single nucleotide polymorphism site, a sixth target single nucleotide polymorphism site, a seventh target single nucleotide polymorphism site, an eighth target single nucleotide polymorphism site, and a ninth target single nucleotide polymorphism site; the target prediction model is: y=104.74-0.778×x1+11.227×x2+8.012×x3-9.144×x4+21.139×x5-7.75×x6-7.613×x7+9.304×x8+12.469×x9-6.063×x 10 -0.001×x 11 +0.001×x 12 ;

[0034] Wherein, y is the target prediction value of the trainee, x1 is the squat 1RM initial value of the trainee, x2 is the assignment value of the first target single nucleotide polymorphism site of the trainee, x3 is the assignment value of the second target single nucleotide polymorphism site of the trainee, x4 is the assignment value of the third target single nucleotide polymorphism site of the trainee, x5 is the assignment value of the fourth target single nucleotide polymorphism site of the trainee, x6 is the assignment value of the fifth target single nucleotide polymorphism site of the trainee, x7 is the assignment value of the sixth target single nucleotide polymorphism site of the trainee, x8 is the assignment value of the seventh target single nucleotide polymorphism site of the trainee, x9 is the assignment value of the eighth target single nucleotide polymorphism site of the trainee, x 10 is the assignment value of the ninth target single nucleotide polymorphism site of the trainee, x 11 is the original whole body fat content of the trainee, x12 The original trunk muscle mass of the trainee;

[0035] Specifically, when the genotype of any single nucleotide polymorphism (SNP) site is AA, the value of any SNP site is 0; when the genotype of any SNP site is Aa, the value of any SNP site is 1; and when the genotype of any SNP site is aa, the value of any SNP site is 2.

[0036] The technical solution of the invented storage medium is as follows:

[0037] The storage medium stores instructions that, when read by a computer, cause the computer to execute the steps of a method for predicting the effect of 1RM resistance training in squats, as described in this invention. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating a method for predicting the effect of 1RM resistance training in squats according to an embodiment of the present invention.

[0039] Figure 2 This is a schematic diagram of a squat 1RM resistance training effect prediction system according to an embodiment of the present invention. Detailed Implementation

[0040] like Figure 1 As shown, an embodiment of the present invention provides a method for predicting the effect of squat 1RM resistance training, comprising the following steps:

[0041] S1. Before performing squat 1RM resistance training, obtain the initial squat 1RM value for each subject. After performing squat 1RM resistance training, obtain the squat 1RM training value for each subject. Based on the initial squat 1RM value and the squat 1RM training value for each subject, obtain the percentage change in squat 1RM training for each subject.

[0042] The initial squat 1RM value is the squat 1RM value before resistance training. The training squat 1RM value is the depth 1RM value after resistance training. The percentage change in squat 1RM after training is the degree of change between the initial squat 1RM value and the training squat 1RM value.

[0043] It's important to note that absolute muscle strength is defined as "the maximum weight that can be lifted in one repetition." In sports science, this is defined as "1RM (one-repetition maximum)." The squat 1RM represents the maximum weight that can be lifted using a squatting motion, signifying the strength of the lower limb muscles.

[0044] It should be noted that the 1RM squat test uses a strength training rack, barbell, and standardized weight plates. The process for collecting the squat 1RM value is as follows: ① Predict the subject's initial squat 1RM value based on their subjective feeling, and perform 5-10 squats with 40% of the initial predicted squat 1RM value as a warm-up; ② Rest for 1 minute after warm-up; ③ Increase the warm-up weight by 15-20 kg, and ask the subject to complete 3-5 squats as the first test; ④ After the first test, rest for 2-4 minutes, and increase the load in step ③ by 15-20 kg, so that the subject can complete approximately 2-3 squats; ⑤ Rest for 2-4 minutes, and repeat step ④, allowing the subject to attempt the initial predicted squat 1RM value; ⑥ If the subject successfully completes the test, continue to increase the load according to step ⑤ until the subject cannot successfully complete one squat under the new load; ⑦ Rest for 2-4 minutes, reduce the load by 5-10 kg, and continue testing. This process of increasing or decreasing the load continues until the subject can complete one 1RM with good technique. The initial squat 1RM value is usually determined within 5 attempts.

[0045] It should be noted that in this embodiment, the squat 1RM resistance training program was identical for each subject. The specific training program was as follows: resistance training intervention was conducted using a Smith machine. Squats were performed at 70% of 1RM load for 5 sets of 10 repetitions each, with a 2-minute rest between sets; twice a week for 12 weeks. 1RM testing was conducted every 4 weeks to determine the new training load to accommodate changes in strength gains. Moderate to high-intensity activities were avoided for the first 3 days of data collection. The post-intervention testing was conducted 72 hours after the last exercise session, and both pre- and post-intervention tests were completed within one week.

[0046] S2. Before conducting squat 1RM resistance training, acquire and use the specific data corresponding to each first independent variable index of any subject, as well as the percentage change of squat 1RM training of any subject, as a training sample to obtain a training dataset containing multiple training samples, wherein all first independent variable indices include at least the initial value of squat 1RM.

[0047] The primary independent variable indicators, in addition to the initial squat 1RM value, include: raw trunk muscle mass, raw total body fat mass, and multiple first single nucleotide polymorphism (SNP) sites. Each training sample includes: a subject's initial squat 1RM value, percentage change in squat 1RM after training, raw trunk muscle mass, raw total body fat mass, and multiple SNP sites. The training dataset includes training samples for each subject.

[0048] The original trunk muscle mass was defined as the trunk muscle mass of the subject before performing 1RM squat resistance training. The original total body fat mass was defined as the total body fat mass of the subject before performing 1RM squat resistance training. Single nucleotide polymorphisms (SNPs) were identified. The number of SNPs was 4,929,604.

[0049] It should be noted that body composition is an indicator reflecting the proportional characteristics of the internal structure of the human body. In this embodiment, the body composition indicators used are trunk muscle content and total body fat content as the first independent variable. The specific data collection process is as follows: Dual-energy X-ray absorptiometry (DEXA) is used to test the subject's body composition. Specifically, ① the instrument is preheated and calibrated beforehand, ensuring that the subject has not undergone a barium meal examination, radioactive isotope injection, or injection or oral contrast agents for CT or MRI examinations within the past 7 days. ② The instrument is preheated and calibrated beforehand. The subject is required to fast, remove clothing and items that may affect the test results, and begin the examination in a supine position. ③ Using enCORE (2011) software, the subject's basic parameters are input, and the scanning gantry scans layer by layer from head to toe to obtain the subject's body composition data, including fat content and muscle content of the upper limbs, lower limbs, trunk, and whole body. The original trunk muscle content and original total body fat content of the subject are then obtained from this data.

[0050] It should be noted that the process for collecting the first single nucleotide polymorphism site is as follows:

[0051] (I) DNA Extraction and Quality Control: 5 ml of venous blood was drawn from the subjects, and DNA was extracted from the venous blood using a magnetic bead-based blood genomics extraction kit. DNA concentration and purity were detected using Nanodrop 2000, and DNA integrity was assessed by gel electrophoresis. The required DNA concentration was greater than 100 ng / μl, the sample OD value (260 / 280) was greater than 1.8, and the main band on the gel electrophoresis was clear with no degradation bands.

[0052] (II) Whole Genome Detection and Quality Control: DNA samples that passed quality control were used for whole-genome genotyping and data format conversion using the Infinium microarray. Using 1000 Genomes Phase 3 V5 (GRCh37 / hg19) whole-genome data of Chinese individuals as a reference template, genotyping was performed using the impute2 method (filling filter condition: info ≥ 0.98). Plink 1.9 software was used for quality control of the microarray data. Quality control criteria included: excluding data with ① minimum allele frequency less than 5% (maf < 0.05) and ② data not conforming to Hardy–Weinberg equilibrium (HWE) (p > 1 × 10⁻⁶). -5 ); ③ Single nucleotide polymorphisms (SNPs) with a genotype deletion rate exceeding 10%; ④ Individuals with a genotype deletion rate exceeding 10%. After genotype filling, the number of first single nucleotide polymorphism sites retained through quality control was 4,929,604.

[0053] S3. Based on the stepwise linear regression method and the training dataset, the first independent variable indicator that meets the preset significance condition is determined as the target independent variable indicator, and a target prediction model is constructed for the percentage change in squat 1RM training and multiple target independent variable indicators.

[0054] Among them, multiple target independent variable indicators include: initial squat 1RM value, original trunk muscle mass, original whole body fat mass, and multiple target single nucleotide polymorphism sites.

[0055] Regarding the pre-defined significance criteria, it should be noted that the final target SNPs were selected stepwise. Specifically, Plink software was used for statistical analysis first, followed by SPSS software, with different significance criteria for each. ① When using Plink 1.9 software, 179 SNPs (second SNPs) were selected from 4,929,604 SNPs (first SNPs). The second independent variable at this point included the 179 second SNPs, initial squat 1RM values, raw trunk muscle mass, and raw total body fat percentage. The pre-defined significance criteria at this point were: the significance level p < 5 × 10 for any of the first independent variables. -5② When using SPSS software, 12 SNPs were screened from 179 SNPs (second single nucleotide polymorphism sites), and then 9 (target single nucleotide polymorphism sites) were screened from the 12 SNPs. The second target independent variable indicators at this time include the 9 target single nucleotide polymorphism sites, the initial value of squat 1RM, the original trunk muscle content and the original whole body fat content. The preset significance condition at this time is: the significance level of any second independent variable indicator is p<0.05.

[0056] S4. Before conducting squat 1RM resistance training, obtain and input the specific data corresponding to all target independent variable indicators of the trainee into the target prediction model to obtain the target predicted value of the percentage change in the trainee's squat 1RM training.

[0057] The target prediction model is used to obtain the predicted percentage change in squat 1RM obtained by the trainee during resistance training. The dependent variable of the target prediction model is the percentage change in squat 1RM, and the independent variables are the initial squat 1RM value, the original trunk muscle mass, the original total body fat mass, and multiple target single nucleotide polymorphism sites.

[0058] It should be noted that the process of constructing a target prediction model using the stepwise linear regression method and the training sample set is an existing technology, which will not be elaborated on here.

[0059] Preferably, the step of determining the first independent variable indicator that meets the preset significance condition as the target independent variable indicator includes:

[0060] Each single nucleotide polymorphism site that meets the preset significance criteria is identified as a target single nucleotide polymorphism site.

[0061] Among them, the target prediction model obtained by stepwise linear regression includes 9 single nucleotide polymorphism sites.

[0062] Preferably, the plurality of target single nucleotide polymorphism (SNP) sites include: a first target SNP site, a second target SNP site, a third target SNP site, a fourth target SNP site, a fifth target SNP site, a sixth target SNP site, a seventh target SNP site, an eighth target SNP site, and a ninth target SNP site.

[0063] The target single nucleotide polymorphism (SNP) sites are: rs79634566, rs36115704, rs11315123, rs34287953, rs7814353, rs2594781, rs11256179, rs3831759, and rs12587270.

[0064] The target prediction model is: y = 104.74 - 0.778 × x1 + 11.227 × x2 + 8.012 × x3 - 9.144 × x4 + 21.139 × x5 - 7.75 × x6 - 7.613 × x7 + 9.304 × x8 + 12.469 × x9 - 6.063 × x 10 -0.001×x 11 +0.001×x 12 Where y is the target predicted value of the trainee, x1 is the initial squat 1RM value of the trainee, x2 is the assigned value of the first target single nucleotide polymorphism (SNP) site (rs79634566) of the trainee, x3 is the assigned value of the second target SNP site (rs36115704) of the trainee, x4 is the assigned value of the third target SNP site (rs11315123) of the trainee, and x5 is the assigned value of the fourth target SNP site (rs11315123). The values ​​assigned to the following sites are: x34287953, x6 is the value assigned to the fifth target single nucleotide polymorphism (SNP) site (rs7814353), x7 is the value assigned to the sixth target SNP site (rs2594781), x8 is the value assigned to the seventh target SNP site (rs11256179), and x9 is the value assigned to the eighth target SNP site (rs3831759). 10 Assigning a value to the ninth target single nucleotide polymorphism site (rs12587270) of the trainee, x 11 x represents the original total body fat percentage of the trainee. 12 This refers to the original trunk muscle mass of the trainee.

[0065] Specifically, when the genotype of any single nucleotide polymorphism (SNP) site is AA, the value of any SNP site is 0; when the genotype of any SNP site is Aa, the value of any SNP site is 1; and when the genotype of any SNP site is aa, the value of any SNP site is 2.

[0066] In the target prediction model, as shown in Table 1, B represents the standardized coefficient (the coefficient of each target independent variable in the formula); Beta: unstandardized coefficient; Sig represents the significance p-value, which is statistically significant in the model when p < 0.05 and should be retained; the coefficient R... 2 Also known as goodness of fit or coefficient of determination, it represents the explanatory power of the independent variable on the dependent variable; the adjusted coefficient R0 2 Similar to the coefficient R 2 Adjusted coefficient R 2 The influence of sample size (n) and the number of target independent variable indicators (k) in the regression were considered. Tolerance and variance inflation factor (VIF) were used together as collinearity statistics. Generally, the tolerance is not less than 0.1 and the VIF (the reciprocal of the tolerance) is not greater than 10, which can indicate that there is no collinearity among the independent variables (the model needs to satisfy the condition that there is no collinearity among the independent variables).

[0067] Table 1:

[0068] Target independent variable B Beta Sig. coefficient R 2 ]]> adjusted coefficient R 2 ]] Tolerance VIF Constant 104.74 0.001 squat 1 RM initial value (x1) -0.778 -0.699 0.001 0.402 0.398 0.38 2.63 a first target single nucleotide polymorphism site (x2) 11.227 0.18 0.001 0.085 0.082 0.923 1.083 second target single nucleotide polymorphism site (x3) 8.012 0.157 0.001 0.065 0.063 0.895 1.118 a third target single nucleotide polymorphism site (x4) -9.144 -0.188 0.001 0.053 0.052 0.918 1.089 a fourth target single nucleotide polymorphism site (x5) 21.139 0.184 0.001 0.06 0.058 0.869 1.15 Fifth target single nucleotide polymorphism site (x6) -7.75 -0.152 0.001 0.032 0.032 0.94 1.064 Sixth target single nucleotide polymorphism site (x7) -7.613 -0.16 0.001 0.026 0.025 0.972 1.029 Seventh target single nucleotide polymorphism site (x8) 9.304 0.148 0.001 0.018 0.017 0.86 1.162 Eighth target single nucleotide polymorphism site (x9) 12.469 0.152 0.001 0.02 0.02 0.912 1.097 a ninth target single nucleotide polymorphism site (x 10 )]]> -6.063 -0.125 0.002 0.013 0.012 0.925 1.081 Original whole body fat content (x 11 )]]> -0.001 -0.131 0.003 0.009 0.008 0.798 1.254 Original trunk muscle content (x 12 )]]> 0.001 0.166 0.006 0.011 0.011 0.413 2.421

[0069] Preferably, the step of obtaining the percentage change in squat 1RM training for each subject based on their initial squat 1RM value and training squat 1RM value includes:

[0070] Based on a preset formula, the initial squat 1RM value and training squat 1RM value of any subject, the percentage change in squat 1RM for any given subject is obtained, and this process is repeated until the percentage change in squat 1RM for each subject is obtained. The preset formula is as follows: Δa is the percentage change in squat 1RM for any subject, a2 is the squat 1RM training value for any subject, and a1 is the initial squat 1RM value for any subject.

[0071] In this embodiment, a training sample set was obtained by conducting squat 1RM resistance training on 193 subjects. A Pearson correlation test was performed on the actual calculated percentage change in squat 1RM training for each subject and the percentage change in squat 1RM training predicted by the model. The correlation coefficient r = 0.89, indicating a good correlation. Furthermore, a Bland-Altman consistency test was performed on the actual calculated percentage change in squat 1RM training for each subject and the percentage change in squat 1RM training predicted by the model. It was found that 183 of the 193 training samples were within the consistency bound, accounting for 94.82%, indicating that the error between the actual calculated percentage change in squat 1RM training and the percentage change in squat 1RM training predicted by the model is small, and the consistency is good.

[0072] In addition, this embodiment may also include:

[0073] S5. When the target predicted value of the trainee is less than the preset threshold, the training plan for the trainee's squat 1RM resistance training is modified, and S1 is executed again based on the modified training plan until the target predicted value of the trainee is greater than or equal to the preset threshold. Then, the modified training plan is determined as the target training plan so that the trainee can perform squat 1RM resistance training according to the target training plan.

[0074] The technical solution in this embodiment constructs a prediction model for the 1RM training effect of squats using the stepwise linear regression method. While improving the accuracy of prediction, it provides support for trainees to develop precise training plans and lays the foundation for subsequent exploration of the mechanisms by which exercise is beneficial to health.

[0075] like Figure 2 As shown, an embodiment of the present invention provides a squat 1RM resistance training effect prediction system 200, which includes: a first processing module 210, a second processing module 220, a construction module 230, and a prediction module 240.

[0076] The first processing module 210 is used to: obtain the initial value of squat 1RM for each subject before squat 1RM resistance training, and obtain the squat 1RM training value for each subject after squat 1RM resistance training, and obtain the percentage change in squat 1RM training for each subject based on the initial value and training value of squat 1RM for each subject.

[0077] The second processing module 220 is used to: before performing squat 1RM resistance training, acquire and use the specific data corresponding to each first independent variable index of any subject, as well as the percentage change of squat 1RM training of any subject, as a training sample to obtain a training dataset containing multiple training samples, wherein all first independent variable indices include at least the initial value of squat 1RM.

[0078] The construction module 230 is used to: determine the first independent variable indicator that meets the preset significance condition as the target independent variable indicator based on the stepwise linear regression method and the training dataset, and construct a target prediction model of the percentage change in squat 1RM training and multiple target independent variable indicators.

[0079] The prediction module 240 is used to: before performing squat 1RM resistance training, acquire and input the specific data corresponding to all target independent variable indicators of the trainee into the target prediction model to obtain the target predicted value of the percentage change in the trainee's squat 1RM training.

[0080] Preferably, the multiple first independent variable indicators also include: raw trunk muscle content, raw total body fat content, and multiple first single nucleotide polymorphism sites.

[0081] Preferably, the multiple target independent variable indicators include: the initial value of squat 1RM, the original trunk muscle mass, the original whole body fat mass, and multiple target single nucleotide polymorphism sites; the step of determining the first independent variable indicator that meets the preset significance condition as the target independent variable indicator includes:

[0082] Each single nucleotide polymorphism site that meets the preset significance criteria is identified as a target single nucleotide polymorphism site.

[0083] Preferably, the plurality of target single nucleotide polymorphism (SNP) sites include: a first target SNP site, a second target SNP site, a third target SNP site, a fourth target SNP site, a fifth target SNP site, a sixth target SNP site, a seventh target SNP site, an eighth target SNP site, and a ninth target SNP site; the target prediction model is: y = 104.74 - 0.778 × x1 + 11.227 × x2 + 8.012 × x3 - 9.144 × x4 + 21.139 × x5 - 7.75 × x6 - 7.613 × x7 + 9.304 × x8 + 12.469 × x9 - 6.063 × x 10 -0.001×x 11 +0.001×x 12 ;

[0084] Where y is the target predicted value of the trainee, x1 is the initial squat 1RM value of the trainee, x2 is the assigned value of the first target single nucleotide polymorphism (SNP) site of the trainee, x3 is the assigned value of the second target SNP site of the trainee, x4 is the assigned value of the third target SNP site of the trainee, x5 is the assigned value of the fourth target SNP site of the trainee, x6 is the assigned value of the fifth target SNP site of the trainee, x7 is the assigned value of the sixth target SNP site of the trainee, x8 is the assigned value of the seventh target SNP site of the trainee, x9 is the assigned value of the eighth target SNP site of the trainee, and x... 10 Assigning a value to the ninth target single nucleotide polymorphism site of the trainee, x 11 x represents the original total body fat percentage of the trainee. 12 The original trunk muscle mass of the trainee;

[0085] Specifically, when the genotype of any single nucleotide polymorphism (SNP) site is AA, the value of any SNP site is 0; when the genotype of any SNP site is Aa, the value of any SNP site is 1; and when the genotype of any SNP site is aa, the value of any SNP site is 2.

[0086] The technical solution in this embodiment constructs a prediction model for the 1RM training effect of squats using the stepwise linear regression method. While improving the accuracy of prediction, it provides support for trainees to develop precise training plans and lays the foundation for subsequent exploration of the mechanisms by which exercise is beneficial to health.

[0087] The parameters and steps for each module to perform their respective functions in the squat 1RM resistance training effect prediction system 200 described above in this embodiment can be referred to the parameters and steps in the embodiment of the squat 1RM resistance training effect prediction method above, and will not be repeated here.

[0088] An embodiment of the present invention provides a storage medium, comprising: the storage medium storing instructions, which, when a computer reads the instructions, cause the computer to execute steps such as a method for predicting the effect of 1RM resistance training in squats. For details, please refer to the parameters and steps in the embodiment of the method for predicting the effect of 1RM resistance training in squats described above, which will not be repeated here.

[0089] Those skilled in the art will know that the present invention can be implemented as a method, system, and storage medium.

[0090] Therefore, the present invention can be implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present invention can also be implemented as a computer program product contained in one or more computer-readable media, which contains computer-readable program code. Any combination of one or more computer-readable media can be used. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Although embodiments of the invention have been shown and described above, it is to be understood that these embodiments are exemplary and should not be construed as limiting the invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the invention.

Claims

1. A method of predicting the effect of resistance training on a deep squat 1RM, characterized by, The method comprises the following steps: Before deep squat 1RM resistance training is performed, an initial deep squat 1RM value of each subject is obtained, and after the deep squat 1RM resistance training is performed, a training deep squat 1RM value of each subject is obtained, and a training change percentage of the deep squat 1RM of each subject is obtained according to the initial deep squat 1RM value and the training deep squat 1RM value of each subject; Before deep squat 1RM resistance training is performed, specific data corresponding to each first independent variable index of any subject and the training change percentage of the deep squat 1RM of the any subject are obtained as a training sample, and a training data set comprising a plurality of training samples is obtained, wherein the first independent variable indexes at least include the initial deep squat 1RM value; Based on a stepwise linear regression method and the training data set, a first independent variable index meeting a preset significance condition is determined as a target independent variable index, and a target prediction model of the training change percentage of the deep squat 1RM and a plurality of target independent variable indexes is constructed; Before deep squat 1RM resistance training is performed, specific data corresponding to all target independent variable indexes of a subject to be trained is input into the target prediction model, and a target prediction value of the training change percentage of the deep squat 1RM of the subject to be trained is obtained.

2. The deep squat 1RM resistance training effect prediction method according to claim 1, characterized by, The plurality of first independent variable indexes further include an original trunk muscle content, an original whole body fat content and a plurality of first single nucleotide polymorphism sites.

3. The deep squat 1RM resistance training effect prediction method according to claim 2, characterized by, The plurality of target independent variable indexes include the initial deep squat 1RM value, the original trunk muscle content, the original whole body fat content and a plurality of target single nucleotide polymorphism sites; the step of determining the first independent variable index meeting the preset significance condition as the target independent variable index comprises: Each single nucleotide polymorphism site meeting the preset significance condition is determined as a target single nucleotide polymorphism site.

4. The deep squat 1RM resistance training effect prediction method according to claim 3, characterized by, The plurality of target single nucleotide polymorphism sites include a first target single nucleotide polymorphism site, a second target single nucleotide polymorphism site, a third target single nucleotide polymorphism site, a fourth target single nucleotide polymorphism site, a fifth target single nucleotide polymorphism site, a sixth target single nucleotide polymorphism site, a seventh target single nucleotide polymorphism site, an eighth target single nucleotide polymorphism site and a ninth target single nucleotide polymorphism site; and the target prediction model is: ； wherein y is a target prediction value of the to-be-trained person, is an initial value of the to-be-trained person's deep squat 1RM, is an assignment of the to-be-trained person's first target single nucleotide polymorphism site, is an assignment of the to-be-trained person's second target single nucleotide polymorphism site, is an assignment of the to-be-trained person's third target single nucleotide polymorphism site, is an assignment of the to-be-trained person's fourth target single nucleotide polymorphism site, is an assignment of the to-be-trained person's fifth target single nucleotide polymorphism site, is an assignment of the to-be-trained person's sixth target single nucleotide polymorphism site, is an assignment of the to-be-trained person's seventh target single nucleotide polymorphism site, is an assignment of the to-be-trained person's eighth target single nucleotide polymorphism site, is an assignment of the to-be-trained person's ninth target single nucleotide polymorphism site, is an original whole-body fat content of the to-be-trained person, is an original trunk muscle content of the to-be-trained person; When the genotype of any single nucleotide polymorphism site is AA, the assignment value of the any single nucleotide polymorphism site is 0; when the genotype of the any single nucleotide polymorphism site is Aa, the assignment value of the any single nucleotide polymorphism site is 1; and when the genotype of the any single nucleotide polymorphism site is aa, the assignment value of the any single nucleotide polymorphism site is 2.

5. The deep squat 1RM resistance training effect prediction method according to claim 4, characterized by, The step of obtaining the training change percentage of the deep squat 1RM of each subject according to the initial deep squat 1RM value and the training deep squat 1RM value of each subject comprises: According to a preset formula, a squat 1RM initial value of any subject and a squat 1RM training value of the subject, a squat 1RM change percentage of the subject is obtained until a squat 1RM change percentage of each subject is obtained; wherein the preset formula is: ; is the squat 1RM change percentage of the subject, is the squat 1RM training value of the subject, is the squat 1RM initial value of the subject.

6. A deep squat 1RM resistance training effect prediction system, characterized by, The method comprises the following steps: The method comprises the following steps: The first processing module, the second processing module, the construction module and the prediction module. The first processing module is configured to obtain the squat 1RM initial value of each subject before squat 1RM resistance training is performed, obtain the squat 1RM training value of each subject after squat 1RM resistance training is performed, and obtain the squat 1RM training change percentage of each subject according to the squat 1RM initial value and the squat 1RM training value of each subject. The second processing module is configured to obtain, before squat 1RM resistance training is performed, specific data corresponding to each first independent variable indicator of any subject and the squat 1RM training change percentage of the any subject as a training sample, and obtain a training data set containing multiple training samples, wherein the first independent variable indicators at least include the squat 1RM initial value. The construction module is configured to determine, based on a stepwise linear regression method and the training data set, the first independent variable indicators meeting a preset significance condition as target independent variable indicators, and construct a target prediction model of the squat 1RM training change percentage and multiple target independent variable indicators. The prediction module is configured to input specific data corresponding to all target independent variable indicators of a subject to be trained into the target prediction model before squat 1RM resistance training is performed, and obtain a target prediction value of the squat 1RM training change percentage of the subject to be trained.

7. The squat 1RM resistance training effect prediction system of claim 6, wherein, The multiple first independent variable indicators further include original trunk muscle content, original whole body fat content, and multiple first single nucleotide polymorphism sites.

8. The squat 1RM resistance training effect prediction system of claim 7, wherein, The multiple target independent variable indicators include the squat 1RM initial value, the original trunk muscle content, the original whole body fat content, and multiple target single nucleotide polymorphism sites; and the step of determining the first independent variable indicators meeting the preset significance condition as target independent variable indicators includes: Each single nucleotide polymorphism site meeting the preset significance condition is determined as a target single nucleotide polymorphism site.

9. The squat 1RM resistance training effect prediction system of claim 8, wherein, The multiple target single nucleotide polymorphism sites include a first target single nucleotide polymorphism site, a second target single nucleotide polymorphism site, a third target single nucleotide polymorphism site, a fourth target single nucleotide polymorphism site, a fifth target single nucleotide polymorphism site, a sixth target single nucleotide polymorphism site, a seventh target single nucleotide polymorphism site, an eighth target single nucleotide polymorphism site, and a ninth target single nucleotide polymorphism site; and the target prediction model is: ； wherein y is a target prediction value of the to-be-trained person, is an initial value of the deep squat 1RM of the to-be-trained person, is an assignment of the first target single nucleotide polymorphism site of the to-be-trained person, is an assignment of the second target single nucleotide polymorphism site of the to-be-trained person, is an assignment of the third target single nucleotide polymorphism site of the to-be-trained person, is an assignment of the fourth target single nucleotide polymorphism site of the to-be-trained person, is an assignment of the fifth target single nucleotide polymorphism site of the to-be-trained person, is an assignment of the sixth target single nucleotide polymorphism site of the to-be-trained person, is an assignment of the seventh target single nucleotide polymorphism site of the to-be-trained person, is an assignment of the eighth target single nucleotide polymorphism site of the to-be-trained person, is an assignment of the ninth target single nucleotide polymorphism site of the to-be-trained person, is an original whole-body fat content of the to-be-trained person, is an original trunk muscle content of the to-be-trained person; wherein, when the genotype of any single nucleotide polymorphism site is AA, the assignment value of the any single nucleotide polymorphism site is 0; when the genotype of the any single nucleotide polymorphism site is Aa, the assignment value of the any single nucleotide polymorphism site is 1; and when the genotype of the any single nucleotide polymorphism site is aa, the assignment value of the any single nucleotide polymorphism site is 2.

10. A storage medium, characterized by The storage medium has instructions stored therein, and when a computer reads the instructions, the computer performs the squat 1RM resistance training effect prediction method according to any one of claims 1 to 5.

Images