Individual height prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses an individual height prediction method and device, electronic equipment and a storage medium, and relates to the technical field of height prediction, and the method comprises the steps: S1, obtaining the growth time interval of an individual, determining a genetic prediction height value in each growth time point, drawing a first height curve which is the trend of age-genetic height, and determining the growth time interval of the individual; determining a basic growth coefficient corresponding to the first height curve; s2, the actually measured height value of the individual in each growth time interval is determined, a second height curve is determined, the second height curve is the age-height trend, and a first feedback coefficient corresponding to the second height curve is determined; s3, acquiring a weight-height trend set in the database as a third height curve, and determining a growth disturbance coefficient of the individual at each time point according to the weight-height trend; s4, comparing the obtained first growth curve, the second growth curve and the third growth curve, and determining an actual prediction value of individual growth; and the height prediction accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of height prediction, and in particular to a method, device, electronic device and storage medium for predicting individual height. Background Art

[0002] The growth and development of adolescents and children is the focus of parents' attention, and height is one of the most concerned indicators. Parents can infer their growth and development from their height. The traditional method of predicting the height of adolescents and children is to refer to the standard height comparison table for adolescents and children issued by the state. However, this comparison table is a statistical product and cannot well reflect the differences in growth of each individual. In addition to referring to the standard height comparison table for adolescents and children, the height of adolescents and children can also be predicted through the height genetic formula. This method takes into account the impact of the acquired environment on the height of adolescents and children.

[0003] For example, Chinese patent publication number CN112182067A discloses a method, device, electronic device and storage medium for predicting individual height, the method comprising: obtaining individual height prediction parameters; obtaining preset standard height data according to the individual height prediction parameters; fitting a reference height prediction curve and a height change amplitude curve according to the preset standard height data; determining a first height prediction curve according to the individual height prediction parameters, the reference height prediction curve and the height change amplitude curve. The embodiment of the present invention realizes the prediction of individual height, so that any individual can obtain a height prediction curve that conforms to their current development situation, so that individual height prediction has both universality and personalization.

[0004] However, the existing technology only identifies the amplitude of height change when considering height changes to determine the height that can be predicted at this time, ignoring the individual's own weight and growth values ​​in different environments. As a result, the final curve cannot reflect the differences in individual environment, weight, etc., which reduces the personalization effect and causes an increase in height prediction errors. Summary of the invention

[0005] The embodiments of the present application solve the problem of reduced personalization effect of height prediction in the prior art by providing an individual height prediction method, device, electronic device and storage medium, and improve the accuracy of height prediction.

[0006] The present application embodiment provides a method for predicting individual height, including: S1, obtaining the growth time interval of the individual, determining the genetic predicted height value at each growth time point, drawing a first height curve, the first height curve is the trend of age-genetic height, and determining the basic growth coefficient corresponding to the first height curve; S2, determining the measured height value of the individual in each growth time interval, determining a second height curve, the second height curve is the age-height trend, and determining a first feedback coefficient corresponding to the second height curve; S3, obtaining the weight-height trend set in the database as the third height curve, and determining the growth disturbance coefficient of the individual at each time point according to the weight-height trend; S4, comparing the first growth curve, the second growth curve, and the third growth curve to determine an actual estimated value of the individual growth.

[0007] An individual height prediction device, comprising: Genetic height prediction module: used to predict the genetic height value of an individual in each growth time interval based on the height of the parents and the individual's environmental characteristics, and draw the first height curve; Measured height feedback module: used to calculate the first feedback coefficient and draw the second height curve based on the measured height value of the individual in each growth time interval; Weight-height relationship analysis module: used to determine the growth disturbance coefficient of an individual at each time point based on the weight-height trend, and draw a third height curve; Comprehensive evaluation module: used to compare the first height curve, the second height curve and the third height curve, comprehensively consider the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, and obtain the actual estimated value of individual growth.

[0008] An electronic device comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in an individual height prediction method as described in any one of the above items are executed.

[0009] A storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps in any one of the above-mentioned methods for predicting an individual's height are executed.

[0010] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By comprehensively considering multiple factors such as genetics, actual measurements and weight-height relationship, the accuracy of height prediction has been significantly improved, providing a more reliable basis for individual height management.

[0011] By taking genetics and actual measured height into consideration and introducing the weight-height relationship, height assessment is made more comprehensive and detailed, and can more accurately reflect the actual development of an individual's height.

[0012] By integrating information from multiple dimensions such as genetic height prediction, actual height feedback and weight-height relationship analysis, a comprehensive evaluation mechanism is established to more comprehensively evaluate the development of individual height and provide parents and doctors with more accurate height management. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 The figure is a schematic diagram of a flow chart of a method for predicting individual height of the present invention.

[0014] Figure 2 Schematic diagram of the flow of step S1 of a method for predicting individual height of the present invention.

[0015] Figure 3 Schematic diagram of the flow of step S3 of a method for predicting individual height of the present invention.

[0016] Figure 4 The figure is a system schematic diagram of an individual height prediction device of the present invention.

[0017] Figure 5 The present invention is a schematic diagram of an electronic device for predicting individual height.

[0018] In the figure: 1000, electronic device; 1001, processor; 1002, memory. DETAILED DESCRIPTION

[0019] To facilitate the understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.

[0020] It should be noted that the terms “vertical”, “horizontal”, “up”, “down”, “left”, “right” and similar expressions used in this document are only for illustrative purposes and do not represent the only implementation method.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more related listed items.

[0022] like Figure 1 As shown, the present application provides a method for predicting individual height, including: S1, obtain the individual's growth time interval, determine the genetic predicted height value at each growth time point, draw a first height curve, the first height curve is the trend of age-genetic height, and determine the basic growth coefficient corresponding to the first height curve.

[0023] S2, determining the actual height value of the individual in each growth time interval, determining a second height curve, the second height curve is the age-height trend, and determining a first feedback coefficient corresponding to the second height curve.

[0024] S3, obtaining the weight-height trend set in the database as the third height curve, and determining the growth disturbance coefficient of the individual at each time point according to the weight-height trend.

[0025] S4, comparing the first growth curve, the second growth curve, and the third growth curve to determine an actual estimated value of the individual growth.

[0026] like Figure 2 As shown, the method of determining the trend of age-genetic height in step S1 includes: S11, determine the height of the parents corresponding to the individual, take the height of the parents as the independent variable, take the individual's environmental characteristics as the control variable, and determine the genetically predicted height value of the individual in each growth time interval.

[0027] At the same time, the growth time interval can be set according to the calculation requirements. The growth time interval can be set in the form of 1 month, 3 months, 6 months, 1 year, 3 years, etc., or any of the above time periods can be selected as needed, and the height curve can be judged in the form of equal or unequal intervals, so that the growth of height in different intervals can be judged according to the required interval range.

[0028] Therefore, the genetically predicted height value at each time point in the first height curve is expressed as: ; in, represents the genetically predicted height value, represents the intercept term, and Represents the father's height and the mother's height respectively, and Respectively represent the influence coefficients of father's height and mother's height on genetic height, represents the control variable, represents the coefficient of the control variable, represents the error term.

[0029] The control variables set above are expressed as parameters such as nutritional level and health status. The control variables are determined by using a preset scale to determine the scores of the corresponding control variables, and multiple first height curves are generated in turn according to different input control variables. The generated first height curves are fitted according to the obtained genetic predicted height values, and the similarity between the first height curves is determined. The two first height curves with the greatest similarity are weighted averaged in turn until all the first height curves are weighted averaged. The first height curve with the largest value after weighted averaging is used as the first height curve to determine the trend of age-genetic height; the weight set when the first height curve is weighted averaged is the relative importance of the current control variable among all control variables.

[0030] The scale definition of the control variables is as follows: Nutrition level (N): from 0 to 10 points, where 0 indicates extreme malnutrition and 10 indicates very adequate nutrition; Health status (H): from 0 to 10 points, where 0 indicates very unhealthy and 10 indicates very healthy; Exercise habits (E): from 0 to 10 points, where 0 indicates almost no exercise and 10 indicates frequent high-intensity exercise.

[0031] Preset scale scores: For each control variable, a scale score can be set according to the actual situation; for example: Nutrition level (N): calculated based on diet diary and nutritional intake; Health status (H): based on physical examination report and medical history; Exercise habits (E): calculated based on daily activity recorded by wearable devices.

[0032] Example of scores for control variables: Suppose there is a child whose control variable scores are as follows: nutrition level (N): 8; health status (H): 7; exercise habits (E): 9.

[0033] Next, we need to generate multiple first height curves based on the scores of these control variables. Each control variable corresponds to a trend curve of height growth. It can be assumed that these curves reflect the height growth trend under different control variable levels.

[0034] Suppose three height curves are generated based on nutritional level, health status, and exercise habits; it can be assumed that each curve represents the expected height growth pattern under that control variable.

[0035] Curve N: Height growth curve when nutrition level is 8.

[0036] Curve H: Height growth curve when health status is 7.

[0037] Curve E: Height growth curve when the exercise habit is 9.

[0038] Determine the genetic height value: Assume that the genetic height value of the child has been calculated to be 170 cm.

[0039] Next, these three curves need to be fitted to the genetic height values ​​to determine their similarity to the genetic height values.

[0040] The similarity of each curve to genetic height can be calculated using a correlation coefficient or other similarity measure.

[0041] For example, if correlation coefficients are used, the correlation coefficients between curves N, H, and E and genetic height are 0.85, 0.78, and 0.90, respectively.

[0042] Now, the weight of each curve will be determined according to the relative importance of the control variables. You can assume that the weights of these control variables are as follows: Nutrition level (N): 0.4; Health status (H): 0.3; Exercise habits (E): 0.3.

[0043] Next, the two curves with the greatest similarity will be weighted averaged according to these weights to determine the final first height curve.

[0044] The similarity between curve N and genetic height is 0.85, and the weight is 0.4.

[0045] The similarity between curve H and genetic height is 0.78, and the weight is 0.3.

[0046] Curve E has a similarity of 0.90 to genetic height and a weight of 0.3.

[0047] The two curves with the greatest similarity are curve N and curve E, so these two curves will be weighted and averaged first.

[0048] The first step is weighted averaging.

[0049] Weighted similarity: (0.85∗0.4)+(0.90∗0.3)=0.34+0.27=0.61; after this step, a new height curve is obtained, and its similarity with the genetic height is 0.61.

[0050] The second step is weighted averaging.

[0051] Next, this new curve is weightedly averaged with curve H.

[0052] Weighted similarity: (0.61∗0.7)+(0.78∗0.3)=0.427+0.234=0.661; Here, it is assumed that all control variables are weighted and averaged once, and finally a first height curve with a similarity of 0.661 to the genetic height is obtained.

[0053] The final first height curve represents the height growth trend that the child is most likely to follow, taking into account all control variables.

[0054] S12, determining the basic growth value of the individual in each growth time interval according to the genetically predicted height value, and obtaining the basic growth coefficient according to the obtained basic growth value and the genetically predicted height value.

[0055] When determining the height inheritance of an individual, determine the mean and standard deviation of the individual in each growth time interval in the first height curve, and obtain the basic growth coefficient of the individual in each growth time interval by summing the mean and standard deviation of the individual in each growth time interval.

[0056] Preferably, when obtaining the basic growth coefficient, the minimum point in each growth time interval in the first height curve is obtained, the average of the minimum point and the adjacent points is used as the basic growth value, and the ratio of the basic growth value to the average value of the genetically predicted height value in the growth time interval is used as the set basic growth coefficient.

[0057] Therefore, the basic growth coefficient can be expressed as: ; in, is the basic growth coefficient, is the average value of the basic growth value. It is the standard value of basic growth value. represents the standard deviation of genetically predicted height values; Represents the control coefficient of the growth time interval.

[0058] The basic growth coefficient can help understand the relationship between an individual's actual growth rate and genetic expectations at different growth stages. If the coefficient is close to 1, it means that the individual's growth rate is roughly consistent with genetic expectations; if the coefficient is greater than 1, it means that the individual's growth rate exceeds genetic expectations; if the coefficient is less than 1, it means that the individual's growth rate is lower than genetic expectations.

[0059] In step S2, the implementation method for the age-height trend is to calculate the first feedback coefficient of the individual's height growth based on the individual's actual measured height values ​​in each growth time interval.

[0060] When calculating the first feedback coefficient, the actual measured height values ​​are obtained, and the integral value of the cumulative deviation between the actual measured height values ​​and the genetically predicted height values ​​in each growth time interval and the ratio of the deviation change rate that changes with time are calculated to obtain the feedback gain corresponding to the growth time interval. Based on the obtained feedback gain, the first feedback coefficient is obtained.

[0061] The feedback gain is expressed as: ; in, is the feedback gain, represents the proportional gain, represents the weight of the cumulative deviation of height in the i-th growth time interval, represents the cumulative deviation of height in the ith growth time interval, Represents the time interval between growth time intervals, It represents the ratio of the deviation change rate of the i-th growth time interval, The differential gain that represents the ratio of the rate of change of the deviation.

[0062] The integral value of the cumulative deviation of height is expressed as the sum of the deviation values ​​of the measured height values ​​and the genetically predicted height values ​​in different time periods. The deviation change rate ratio is expressed as the proportional value of the change in the growth deviation value of the individual's measured height values ​​over time. The time interval between the growth time intervals is expressed in the form of a proportional value to quantify the comprehensive cumulative deviation of the cumulative deviation in the corresponding growth time interval.

[0063] The set proportional gain value is expressed as follows: the proportional gain of the current growth time interval is the product of the proportional gain of the previous growth time interval and the actual height value, that is, the proportional gain setting value is related to the current measured height value. The larger the actual height value, the larger the set proportional gain. The setting range of the proportional gain is 0 to 1. Ultimately, the calculated feedback gain can represent the deviation between the current predicted height and the actual height, and identify the main changes in these deviations.

[0064] When the feedback gain value is large, it means that when analyzing the current second height curve, more attention is paid to the response to the deviation between the height and the predicted value, that is, the adjustment of the height prediction based on the current measured height value is larger; when the feedback gain value is small, it means that the difference between the current height and the predicted value is small, and a smaller correction can be made, that is, the adjustment range is smaller.

[0065] Based on the obtained feedback gain, the implementation method of obtaining the first feedback coefficient is: The maximum value of the feedback gain of the current individual is obtained, and the growth time interval corresponding to the maximum value of the feedback gain is determined as the first interval, and the growth time interval adjacent to the first interval is taken as the second interval. The slope value of the second height curve at each point in the first interval and the second interval is calculated, and the trend of the slope value changing with time is obtained to determine whether there is an extreme value point in the first interval; if there is an extreme value point in the first interval, based on the obtained extreme value point, the feedback gain of all points in the first interval is superimposed with the extreme value point in the first interval to obtain a feedback superposition value; when the feedback superposition value is greater than the first preset value, the feedback superposition value is output as the first feedback coefficient; if the feedback superposition value is less than or equal to the first preset value, the feedback superposition value in the second interval is calculated, and the feedback superposition values ​​of two adjacent second intervals are compared to obtain a feedback deviation value, and the feedback superposition value of the second interval corresponding to the minimum value of the feedback deviation value is used as the output first feedback coefficient; if there is no extreme value point in the first interval, the average value of the adjacent second feedback superposition values ​​is used as the output first feedback coefficient.

[0066] The feedback superposition value is calculated by weighting the values ​​of all points in the interval according to the value of the extreme point and averaging them. When performing weighted averaging, all points are weighted averaged in turn according to their distance from the extreme point. The distance between points is obtained by calculating the Euclidean distance between the two points in the coordinate system.

[0067] Suppose there is an individual whose actual height values ​​at different growth time periods and predicted height values ​​based on genetic factors are recorded; specifically, suppose there are three growth time periods, namely 3-6 years old, 6-9 years old and 9-12 years old, his height is measured in each time period, and the deviation from the predicted height is calculated.

[0068] Calculate the integral value of the cumulative deviation and the ratio of the rate of change: 3-6 years old: The cumulative deviation is 2 cm, the time interval is 3 years, and the deviation change rate ratio is 0.5.

[0069] 6-9 years old: The cumulative deviation is 5 cm, the time interval is 3 years, and the deviation change rate ratio is 0.7.

[0070] 9-12 years old: The cumulative deviation is 3 cm, the time interval is 3 years, and the deviation change rate ratio is 0.4.

[0071] Calculate the feedback gain: Using the given formula, a feedback gain value can be calculated for each growth time interval. Assume that the proportional gain has an initial value of 0.5 and is adjusted as the measured height increases.

[0072] Determine the first feedback coefficient: Assume that the feedback gain in the 6-9 age range is the largest, so it is the first range.

[0073] The adjacent growth time intervals of 3-6 years old and 9-12 years old are the second interval.

[0074] Calculate the slope of the height curve in the ranges of 6-9 years old, 3-6 years old, and 9-12 years old, and observe the trend.

[0075] Assume that there is an extreme point in the 6-9 age range.

[0076] The feedback superposition value is calculated, and if it is greater than a first preset value (eg, 1.0), it is output as a first feedback coefficient.

[0077] Effects and benefits: Improved accuracy: By considering the cumulative deviation and change rate of height in different growth time intervals, the height prediction model can be adjusted more accurately to make it more consistent with the individual's actual growth.

[0078] Personalized adjustment: The calculation of feedback gain and first feedback coefficient takes into account the individual's actual growth data, making height prediction more personalized and improving the accuracy and practicality of the prediction.

[0079] Dynamic adjustment: As time goes by and the individual's actual height changes, the proportional gain and feedback gain will be adjusted accordingly, so that the height prediction model can adapt to the dynamic changes of individual growth.

[0080] Wide application: This method is not only suitable for the prediction of children's height, but can also be extended to other fields that require prediction and adjustment based on time series data, such as weight management, disease progression prediction, etc.

[0081] like Figure 3 As shown, in step S3, the processing method for the weight-height trend is: S31, clustering the third height curves of the individuals according to the ratio of weight to height, and successively determining the mean height of the individuals at each time point within the range of each weight to height ratio; and determining the first similarity of the third height curves under different weights.

[0082] The first similarity is calculated by comparing the third height curves under different weights, taking the height values ​​of the third height curve at each time point in turn, and calculating the Pearson correlation coefficient of the third height curve as the first similarity of the current third height curve.

[0083] S32, determining a second similarity of a third height curve according to an initial time of the individual development time.

[0084] The processing method for the second similarity is to determine the initial nodes of all the third height curves. The set initial nodes are determined by obtaining the initial time point of the individual development time. At the same time, the individual development time set at this time is marked in advance, and the time point when the individual meets the normal development speed is used as the initial time of the individual development time; according to the initial nodes of the third height curve, the Pearson correlation coefficient of the height value of the third height curve at the initial nodes is calculated to obtain the second similarity of the third height curve.

[0085] S33, obtaining a growth disturbance coefficient of the third height curve according to the first correlation and the second correlation of the third height curve.

[0086] The growth disturbance coefficient is expressed as: ; in, represents the growth disturbance coefficient at the jth time point, and represents the adjustment factor, which is used to control the influence of the first similarity and the second similarity on the growth disturbance coefficient; represents the first similarity, represents the second similarity, represents the actual height of the individual at the jth time point, Represents the genetically predicted height value of an individual at the jth time point.

[0087] All The average value of the total is used as the growth disturbance coefficient of the current output .

[0088] It is assumed that the third height curve has been acquired, and the first similarity and the second similarity have been calculated.

[0089] Assume that the height value of the third height curve at the age of 2 is 90 cm, the height value at the age of 4 is 100 cm, the height value at the age of 6 is 110 cm, the height value at the age of 8 is 120 cm, and the height value at the age of 10 is 130 cm.

[0090] Assume that the first similarity S1=0.95.

[0091] Assume that the second similarity S2=0.90.

[0092] Assume that the actual height data of the individual is: Height 95cm at 2 years old.

[0093] Height 105cm at age 4.

[0094] Height 115cm at age 6.

[0095] Height 125cm at age 8.

[0096] Height 135cm at age 10.

[0097] Assume adjustment factors β = 0.1 and τ = 0.05.

[0098] Calculate the adjusted growth disturbance coefficient: For 2 years old, the adjusted growth disturbance coefficient C1 is: C1≈0.05.

[0099] For 4 years old, the adjusted growth disturbance coefficient C2 is: C2≈0.0455.

[0100] For age 6, the adjusted growth disturbance coefficient C3 is: C3≈0.0418.

[0101] For the age of 8, the adjusted growth disturbance coefficient C4 is: C4≈0.0389.

[0102] For the age of 10, the adjusted growth disturbance coefficient C5 is: C5≈0.0368.

[0103] Through the above steps, the growth disturbance coefficient can be adjusted according to the first similarity and the second similarity to reflect the degree of deviation between the individual height growth trend and similar individuals. The adjusted growth disturbance coefficient can be used to evaluate the degree of deviation between the individual height growth trend and the group average level, and further analysis and adjustment of the prediction model can be carried out accordingly. Please note that the values ​​and parameters provided here are all hypothetical and need to be adjusted according to specific data in actual applications.

[0104] At this point, you can know the differences in different age groups when adjusting for different age groups and related weight and height ratios. Ultimately, the growth disturbance coefficient, the first feedback coefficient, and the basic growth coefficient will be comprehensively processed to obtain the method of predicting adjustments when predicting height.

[0105] Therefore, the actual evaluation value obtained in step S4 is expressed as follows: after normalizing the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, the actual evaluation value is calculated: ; in, represents the actual evaluation value, Indicates the basic growth coefficient, represents the first feedback coefficient, represents the growth disturbance coefficient, , and Respectively represent the mean of the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, , and Respectively represent the standard deviation of the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, , and They respectively represent the weights of the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient.

[0106] Based on the actual evaluation value obtained, we can understand the predicted value that the individual can adjust by considering the different changes in the individual height curve to determine the height value that the individual may eventually reach.

[0107] like Figure 4 As shown, the present application provides an individual height prediction device, comprising: Genetic height prediction module: used to predict the genetic height value of an individual in each growth time period based on the height of the parents and the individual's environmental characteristics, and draw the first height curve.

[0108] Measured height feedback module: used to calculate the first feedback coefficient and draw the second height curve based on the measured height value of the individual in each growth time interval.

[0109] Weight-height relationship analysis module: used to determine the growth disturbance coefficient of the individual at each time point based on the weight-height trend, and draw a third height curve.

[0110] Comprehensive evaluation module: used to compare the first height curve, the second height curve and the third height curve, comprehensively consider the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, and obtain the actual estimated value of individual growth.

[0111] The genetic height prediction module inputs: parents' height, individual environmental characteristics; outputs: genetically predicted height value, first height curve, basic growth coefficient.

[0112] The measured height feedback module inputs: measured height value, genetic predicted height value; outputs: first feedback coefficient, second height curve.

[0113] The weight-height relationship analysis module inputs: weight value, height value; outputs: growth disturbance coefficient, third height curve.

[0114] Comprehensive evaluation module input: basic growth coefficient, first feedback coefficient, growth disturbance coefficient; output: actual evaluation value.

[0115] like Figure 5As shown, the present application provides an electronic device 1000, including a processor 1001 and a memory 1002, wherein the memory 1002 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 1001, the steps in any of the above methods are executed. Through the above technical solution, the processor 1001 and the memory 1002 are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanisms (not shown), and the memory 1002 stores a computer program executable by the processor. When the electronic device 1000 is running, the processor 1001 executes the computer program to execute the method in any optional implementation of the above embodiment to achieve the following functions: predict the genetic height value of the individual in each growth time interval based on the height of the parents and the environmental characteristics of the individual, and draw a first height curve; calculate the first feedback coefficient based on the measured height value of the individual in each growth time interval, and draw a second height curve; determine the growth disturbance coefficient of the individual at each time point according to the weight-height trend, and draw a third height curve; compare the first height curve, the second height curve and the third height curve, and comprehensively consider the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient to obtain the actual estimated value of the individual's growth.

[0116] The present application provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in any of the above methods are executed. Through the above technical solution, when the computer program is executed by the processor, the method in any optional implementation of the above embodiment is executed to achieve the following functions: predict the genetic height value of the individual in each growth time interval based on the height of the parents and the environmental characteristics of the individual, and draw a first height curve; calculate the first feedback coefficient based on the measured height value of the individual in each growth time interval, and draw a second height curve; determine the growth disturbance coefficient of the individual at each time point according to the weight-height trend, and draw a third height curve; compare the first height curve, the second height curve and the third height curve, and comprehensively consider the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient to obtain the actual estimated value of the individual's growth.

[0117] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting individual height, characterized in that: include: S1, obtaining the growth time interval of the individual, determining the genetic predicted height value at each growth time point, drawing a first height curve, the first height curve is the trend of age-genetic height, and determining the basic growth coefficient corresponding to the first height curve; S2, determining the measured height value of the individual in each growth time interval, determining a second height curve, the second height curve is the age-height trend, and determining a first feedback coefficient corresponding to the second height curve; S3, obtaining the weight-height trend set in the database as the third height curve, and determining the growth disturbance coefficient of the individual at each time point according to the weight-height trend; S4, comparing the first growth curve, the second growth curve, and the third growth curve to determine an actual estimated value of the individual growth.

2. A method for predicting individual height as claimed in claim 1, characterized in that: The processing method in step S1 includes: S11, determine the height of the parents corresponding to the individual, take the height of the parents as the independent variable, take the environmental characteristics of the individual as the control variable, and determine the genetically predicted height value of the individual in each growth time interval; S12, determining the basic growth value of the individual in each growth time interval according to the genetically predicted height value, and obtaining the basic growth coefficient according to the obtained basic growth value and the genetically predicted height value.

3. A method for predicting individual height as claimed in claim 2, characterized in that: The basic growth coefficient can be expressed as: ； in, is the basic growth coefficient, is the average value of the basic growth value. It is the standard value of basic growth value. represents the standard deviation of genetically predicted height values; Represents the control coefficient of the growth time interval.

4. A method for predicting individual height as claimed in claim 1, characterized in that: The implementation method of step S2 is to calculate a first feedback coefficient of the individual's height growth based on the measured height values ​​of the individual in each growth time interval; When calculating the first feedback coefficient, the actual measured height values ​​are obtained, and the integral value of the cumulative deviation between the actual measured height values ​​and the genetically predicted height values ​​in each growth time interval and the ratio of the deviation change rate that changes with time are calculated to obtain the feedback gain corresponding to the growth time interval. Based on the obtained feedback gain, the first feedback coefficient is obtained.

5. The method for predicting individual height according to claim 1, wherein: The processing method in step S3 is: S31, clustering the third height curves of the individuals according to the weight-to-height ratio, and sequentially determining the mean height of the individuals at each time point within the range of each weight-to-height ratio; and determining the first similarity of the third height curves under different weights; S32, determining a second similarity of a third height curve according to the initial time of the individual development time; S33, obtaining a growth disturbance coefficient of the third height curve according to the first correlation and the second correlation of the third height curve.

6. A method for predicting individual height as claimed in claim 5, characterized in that: The growth disturbance coefficient is expressed as: ； in, represents the growth disturbance coefficient at the jth time point, and represents the adjustment factor, which is used to control the influence of the first similarity and the second similarity on the growth disturbance coefficient; represents the first similarity, represents the second similarity, represents the actual height of the individual at the jth time point, Represents the genetically predicted height value of an individual at the jth time point.

7. A method for predicting individual height as claimed in claim 1, characterized in that: The actual evaluation value obtained in step S4 is expressed as follows: after normalizing the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, the actual evaluation value is calculated: ； in, represents the actual evaluation value, Indicates the basic growth coefficient, represents the first feedback coefficient, represents the growth disturbance coefficient, , and Respectively represent the means of the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, , and Respectively represent the standard deviation of the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, , and They respectively represent the weights of the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient.

8. An individual height prediction device, using an individual height prediction method as claimed in claim 1, characterized in that: include: Genetic height prediction module: used to predict the genetic height value of an individual in each growth time interval based on the height of the parents and the individual's environmental characteristics, and draw the first height curve; Measured height feedback module: used to calculate the first feedback coefficient and draw the second height curve based on the measured height value of the individual in each growth time interval; Weight-height relationship analysis module: used to determine the growth disturbance coefficient of an individual at each time point based on the weight-height trend, and draw a third height curve; Comprehensive evaluation module: used to compare the first height curve, the second height curve and the third height curve, comprehensively consider the basic growth coefficient, the first feedback coefficient and the growth disturbance coefficient, and obtain the actual estimated value of individual growth.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method for predicting an individual height as described in any one of claims 1 to 7 are executed.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method for predicting an individual height as described in any one of claims 1 to 7 are performed.

Images