CN111986774B - Sport prescription generation and monitoring guidance system based on data analysis - Google Patents

Sport prescription generation and monitoring guidance system based on data analysis Download PDF

Info

Publication number
CN111986774B
CN111986774B CN202010652416.7A CN202010652416A CN111986774B CN 111986774 B CN111986774 B CN 111986774B CN 202010652416 A CN202010652416 A CN 202010652416A CN 111986774 B CN111986774 B CN 111986774B
Authority
CN
China
Prior art keywords
exercise
user
prescription
users
sports
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010652416.7A
Other languages
Chinese (zh)
Other versions
CN111986774A (en
Inventor
王磊
徐鹏飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian University of Technology
Original Assignee
Xian University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xian University of Technology filed Critical Xian University of Technology
Priority to CN202010652416.7A priority Critical patent/CN111986774B/en
Publication of CN111986774A publication Critical patent/CN111986774A/en
Application granted granted Critical
Publication of CN111986774B publication Critical patent/CN111986774B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Theoretical Computer Science (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses a sports prescription generation and monitoring guidance system based on data analysis, which comprises an intelligent equipment module for collecting information and guiding a user; the data transmission interface module is used for data interaction; the user information analysis module is used for evaluating the physical development level, the exercise capacity and the health condition of the user; the exercise prescription construction module is used for generating a personalized exercise prescription suitable for a user according to the user information acquired by the user information analysis module and the system exercise data; the exercise monitoring and guiding module is used for monitoring and guiding the exercise of the user; the exercise effect prediction module is used for predicting the exercise effect of the user according to the current exercise record of the user and the exercise data of other users in the system. The invention improves the fit and practicability of the system sports prescription and improves the adaptability of the system sports prescription to the user and the sports enthusiasm of the user.

Description

Sport prescription generation and monitoring guidance system based on data analysis
Technical Field
The invention belongs to the technical field of data analysis and exercise fitness, and relates to an exercise prescription generation and monitoring guidance system based on data analysis.
Background
Along with the development of social economy in China, the living standard of people is gradually improved, and the demands of people on body building are also increasing. Under the advocations of novel concepts such as 'healthy life', 'happy and alive', body-building culture is gradually changed into a mainstream life style, and 'body-building' becomes an important scene entrance of a third space outside work and living. The development of the mobile internet has promoted the development of sports industry, and although the current body-building platform system can help people to exercise and body-building, there are still many problems: 1. most of the exercise schemes provided by the traditional exercise platform are defined exercise video courses, and reasonable and personalized exercise schemes cannot be formulated for users according to the conditions of the users; 2. the traditional exercise platform system is mainly used for displaying exercise skills and monitoring exercise heart rate through an exercise watch and a bracelet, so that the current exercise heart rate range of the user cannot be reasonably controlled when the user does not have heart rate monitoring equipment, and the exercise can not be guided according to an exercise scheme in combination with exercise monitoring; 3. the traditional body-building platform system cannot automatically adjust the exercise scheme according to exercise feedback of an exerciser, and cannot evaluate exercise effects generated by the exercise scheme regularly; 4. the traditional body-building platform system lacks effective utilization of motion data of other sportsmen in the platform, ignores the value of the accumulated motion data, and leads to poor pertinence and practicality of a motion scheme generated by the system, and the control performance of the system on the motion process, the motion effect and the motion feedback adjustment of a user is also weak.
Disclosure of Invention
The invention aims to provide a sports prescription generation and monitoring guidance system based on data analysis, which solves the problem that a traditional body-building platform in the prior art cannot provide a personalized body-building scheme according to the conditions of a user.
The technical scheme adopted by the invention is that the exercise prescription generation and monitoring guidance system based on data analysis comprises an intelligent equipment module for collecting information and guiding a user; the data transmission interface module is used for data interaction; the user information analysis module is used for evaluating the physical development level, the exercise capacity and the health condition of the user; the exercise prescription construction module is used for generating a personalized exercise prescription suitable for a user according to the user information acquired by the user information analysis module and the system exercise data; the exercise monitoring and guiding module is used for monitoring and guiding the exercise of the user; the exercise effect prediction module is used for predicting the exercise effect of the user according to the current exercise record of the user and the exercise data of other users in the system.
The invention is also characterized in that:
The smart device module includes a smart phone and a device capable of monitoring heart rate.
The user information analysis module firstly acquires the interests and hobbies of the user, the moving targets and the usable sports equipment information, then writes the information into the database, and evaluates the physical development level, the movement capability and the health condition of the user according to the information.
The sport prescription construction module is used for constructing sport prescriptions and specifically comprises selection of standard prescriptions of a prescription library, fine adjustment of the standard prescriptions and checking of personalized prescriptions.
The selection of standard prescriptions of the prescription library is specifically implemented according to the following steps:
step 1, screening out standard exercise prescriptions meeting requirements according to exercise targets, usable sports equipment, hobbies and diseases from a prescription library and a keyword matching technology, and putting the standard prescriptions obtained by screening into a prescription set;
and 2, screening standard sports prescriptions with relatively good sports effects according to the system sports data and a sports effect analysis method, and providing the standard sports prescriptions for users to select.
The fine adjustment of the standard prescription is specifically carried out according to the following steps:
step 1, constructing a user set using a current standard exercise prescription;
step 2, calculating the similarity between the user and the users in the set according to the physical development level and the exercise capacity of the user, and removing the users with the similarity lower than a threshold value;
Step 3, removing users with average weekly completion degrees lower than 70% in the set according to the exercise records of the users using the current standard exercise prescriptions;
step 4, if a certain amount of users do not reach the set, dividing a movement intensity interval and a movement time interval of a standard prescription into 5 subintervals, selecting a corresponding subinterval according to a movement capacity level measured by the user, randomly selecting movement intensity and movement time in the interval in the corresponding subinterval, selecting a movement frequency closest to a user peripheral frequency expectation in a movement frequency interval specified by the prescription according to the requirement of the user on the weekly movement frequency, and then carrying out step six; if a certain amount of users exist in the set, performing a step five;
step 5, determining the average motion intensity and motion time of the user according to the user motion data in the set;
step 6, if the exercise type of the exercise prescription is running, calculating the relation between the running speed and the exercise intensity, obtaining the average running speed of the user according to the average exercise intensity combination model relation obtained in the step four, and then putting the average running speed into the exercise prescription which is finely adjusted currently as a reference of exercise guidance;
and 7, delivering the trimmed standard prescription to a personalized prescription verification unit for verification.
The verification of the personalized prescription is specifically implemented according to the following steps:
step 1, checking whether the intensity, time and frequency of the exercise prescription after fine adjustment are within a set range of a standard prescription;
step 2, checking whether a user has a disease forbidden by a prescription in a mobile phone questionnaire mode;
step 3, determining a standard sport prescription to which the finely-adjusted personalized prescription belongs, then searching all personalized prescriptions generated according to the current standard prescription, and storing the personalized prescriptions into a personalized prescription set;
step 4, sequentially searching users using prescriptions in the personalized prescription set, wherein the average weekly completion degree of the users is more than 70% in the use process, and storing the users in the prescription user set;
step 5, calculating the similarity between the current user and the users in the prescription user set according to the physical development level and the exercise capacity of the user, and removing the users with the similarity lower than a threshold value in the prescription user set;
step 6, respectively adjusting the exercise heart rate percentage and the exercise time of the personalized prescriptions of the current user by 3%, 15% and 3% and 15% on the basis of the original values, secondly acquiring the personalized exercise prescriptions used by the users in the prescription user set, then judging whether the acquired exercise heart rate percentage and exercise time of the personalized prescriptions are in the previously adjusted up and down intervals, and whether the weekly exercise frequency of the prescriptions is equal to the weekly frequency of the personalized exercise prescriptions of the current user, and if the weekly exercise frequency is equal in the intervals, storing the prescriptions in a similar prescription set;
Step 7, if a certain amount of individual prescriptions exist in the similar prescription set, respectively averaging the exercise effect generated by the individual prescriptions and the exercise score of the user and performing a step eight; if a certain amount of personalized prescriptions do not exist in the set, the step eight is skipped to execute the step nine;
step 8, obtaining all other users similar to the user in the system according to the physical development level and the exercise capacity of the user, screening the users with exercise records meeting the requirements and consistent exercise targets, determining the exercise effect and the exercise score of the screened users, if the average value of the exercise effect and the exercise score determined in the step seven is greater than 60% of the total number of the screened users, checking, if the average value of the exercise effect and the exercise score determined in the step seven is between 30% and 60% of the total number of the screened users, inquiring the opinion of the users to determine whether the user passes, and if the average value of the exercise effect and the exercise score determined in the step seven is below 30% of the total number of the screened users, checking not to pass;
step 9, if the problem exists in the inspection process in the step, returning inspection information to regenerate the prescription; and if no problem exists, issuing the prescription to the user.
The exercise monitoring guidance module comprises an accurate monitoring guidance and a fuzzy monitoring guidance, wherein the accurate monitoring guidance acquires the heart rate of a user through equipment for monitoring the heart rate so as to conduct guidance, and the fuzzy monitoring guidance comprises a guidance which can be monitored by an exercise characteristic mobile phone of the user and a guidance which cannot be monitored by the exercise characteristic mobile phone of the user.
The prescription evaluation content of the sports prescription evaluation module comprises evaluation of a user on a prescription and evaluation of a system on a sports effect, wherein the evaluation of the user on the prescription is that the system acquires the evaluation of the user on the sports prescription in a mobile phone questionnaire mode, the sports effect evaluation of the sports prescription evaluation module is that the user carries out self-evaluation according to the steps formulated by the system and fills in evaluation data, the system compares the acquired evaluation data with the last evaluation data of the user, so that the sports effect of the stage is obtained, and the system carries out fine adjustment of the prescription or change of the prescription through comprehensive evaluation after the evaluation of the user on the sports prescription and the sports effect of the user are acquired.
The motion effect prediction module is used for predicting the motion effect of the user through a similarity calculation-based motion effect prediction method according to the current motion record of the user and the motion data of other users in the system platform, then comprehensively improving and comprehensively reducing the motion completion degree of each current user motion record, respectively predicting the motion effect of the motion record after the motion completion degree is comprehensively improved and the motion record after the motion completion degree is comprehensively reduced, and finally displaying the prediction result to the user in a line graph mode, so that the user can intuitively know the motion effect in different motion states, the user can conveniently make a motion decision, and meanwhile, the motion enthusiasm of the user can be improved.
The beneficial effects of the invention are as follows:
(1) The invention can combine the target hobbies, physical conditions, exercise capacity and equipment facilities of the user to make a personalized exercise prescription with strong adaptability for each user, changes the single and indiscriminate prescription generation mode of the body-building platform system at the present stage, and improves the fitting degree of the exercise prescription of the system and the user;
(2) The invention changes the exercise monitoring guidance mode of the current body-building platform, so that the exercise monitoring guidance is not just the record of the exercise process, but can give out reminding guidance in the exercise process of the user according to the exercise intensity and the exercise time specified by the exercise prescription. Meanwhile, for users without moving a bracelet or a sports watch, the system can also utilize the user motion data in the platform to enable the mobile phone sensor to monitor the approximate heart rate interval of the user motion so as to conduct motion guidance, and for the motion which cannot be monitored by the mobile phone sensor, the corresponding relation between the subjective fatigue degree and the motion effect is measured by utilizing a questionnaire so as to conduct motion guidance. Compared with the prior art, the scheme can provide more reasonable exercise guidance for the user when the user does not have heart rate monitoring equipment;
(3) According to the invention, the exercise prescriptions can be perfected or replaced by combining the exercise records of the users and the platform exercise data through the staged prescription evaluation and exercise effect evaluation, so that the generated exercise prescriptions are more suitable for the exercise habits of the users and better adapt to the change of the physique of the users. Compared with the existing scheme, the adaptability of the sports prescriptions to users is improved, meanwhile, the diversity of the sports prescriptions is increased, and the effectiveness and pertinence of the sports prescriptions generated by the system are higher and higher along with the continuous increase of the users of the system and the continuous accumulation of sports data;
(4) The invention can predict the motion effect of the user according to the motion record of the user, and respectively predict the conditions lower than the current completion degree and higher than the current completion degree, and the user can intuitively know the motion effect of the user through the prediction line diagram, so that the user can conveniently make a motion decision, and the motion enthusiasm of the user can be improved;
(5) The invention adopts a self-adaptive adjustment mechanism on the whole structure, continuously modifies prescription contents through the step-by-step motion prescription evaluation, and gradually adapts to various conditions of users. In the running process of the system, along with the continuous accumulation of exercise data and the continuous increase of the diversity of personalized exercise prescriptions, the model effectiveness and accuracy of the system in three links of personalized prescription formulation, exercise monitoring guidance and exercise effect prediction of users are gradually improved, better exercise experience is brought to users without body-building coaches, intelligent body-building equipment and various body-building instruments, and the service level of a body-building system platform is improved.
Drawings
FIG. 1 is a system diagram of a system for generating and monitoring instructions for a athletic prescription based on data analysis in accordance with the present invention;
FIG. 2 is a schematic flow chart of a method for evaluating a prescription of a sports prescription generation and monitoring guidance system and perfecting the prescription after evaluation based on data analysis;
FIG. 3 is a schematic diagram of a process for generating and guiding a sports prescription based on a data analysis and a system for monitoring and guiding a sports prescription according to the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
The invention relates to a sports prescription generation and monitoring guidance system based on data analysis, which is particularly used for aerobic sports, as shown in fig. 1, and comprises an intelligent equipment module, a data transmission interface module, a user information analysis module, a sports prescription construction module, a sports monitoring guidance module, a sports prescription evaluation module and a sports effect prediction module; the intelligent equipment module is operated in the mobile phone of the user, other modules are operated in the cloud server, and data interaction between the intelligent equipment module and other modules of the cloud server is performed through the data transmission interface module.
The equipment of smart machine module includes the smart mobile phone, can monitor heart rate exercise bracelet, can monitor the exercise wrist-watch of heart rate, and wherein the effect of smart mobile phone includes: the heart rate of the exercise bracelet or the exercise watch is obtained by utilizing the Bluetooth of the mobile phone, the exercise data is collected by utilizing a GPS sensor, an acceleration sensor and a gyroscope in the mobile phone, the exercise process of the user is guided by utilizing a message reminding mode, and the user interacts with the server data by utilizing a visual interface.
The data transmission interface module is a bridge for the user client to interact data with the server, and the user client realizes the interaction of data with the server by calling the interface of the data transmission interface module and transmitting related parameters.
The user information analysis module is used for evaluating the physical development level, exercise capacity and health condition of the user, acquiring the interests and hobbies of the user, the moving targets and the information of usable sports equipment, and writing the information into the database. Wherein, the basic information of the age, sex, height, weight, chest circumference, waistline, hip circumference, heart rate in quiet time and the like of the user is measured by the user under the prompt of the system and the form is filled in; the user's hobbies, moving objects and usable sports equipment generate complex options for the user to select according to the types of sports, sports effects and equipment required by sports contained in all prescriptions in the current prescription library; the health condition of the user is evaluated whether the user is in a sub-health state or not in a mobile phone questionnaire mode, and the disease condition of the user is inquired; the exercise capacity test of the user is that the user performs one-minute push-up test, one-minute supine and rising test, 12-minute running test and step test under the prompt of the system, and the test result is filled in the mobile phone client.
After the user information analysis module obtains various information of the user, the physical development level and the exercise capacity of the user are evaluated; the physical development level evaluation indexes comprise: body Mass Index (BMI), waist-to-hip circumference ratio, vickers index; wherein, the body mass index=weight (kg)/(height ≡2 (m), the body mass index is less than 17.5 is emaciation, 17.5-24 is normal range, more than or equal to 24 is overweight, more than or equal to 28 is obesity; waist-hip ratio = waist/hip, male lower than 0.9 is normal, higher than 0.9 is too high, female lower than 0.8 is normal, higher than 0.8 is too high; the Wilker index is = [ weight (kg) +chest circumference (cm) ]/[ height (cm) ]. 100. After calculation, the physical morphological development of the user is evaluated according to the Wilker index evaluation table; and performing poor, general, medium, good and excellent grades according to the obtained test data and the standard evaluation table, wherein the poor score, the general score, the medium score, the good score and the excellent score are obtained in a one-to-one, two-to-three, four-to-four and five-to-five mode, adding all the exercise ability evaluation scores to average, and grading the overall exercise ability of the user according to the average.
The personalized exercise prescription building module is used for generating a personalized exercise prescription suitable for a user according to the user information obtained by the user information analysis module and the exercise data of the system, and the building process comprises the following steps: selection of standard prescriptions of a prescription library, fine adjustment of the standard prescriptions and checking of personalized prescriptions.
The selection process of the standard prescriptions of the prescription library comprises the following steps:
step one: screening out standard exercise prescriptions meeting the requirements according to the training targets, usable sports equipment, interests and diseases from a prescription library and a keyword matching technology, and putting the standard prescriptions obtained by screening into a prescription set;
step two: if the number of standard prescriptions in the prescription set is 0, deleting the screening conditions of the sports equipment which are interested in and can be used one by one, then rescreening until the number of standard prescriptions in the prescription set is not 0, informing a screening process to a user, if the screened prescription set is still empty after deleting both conditions, reminding the user to replace an exercise target, and rescreening after replacing the target; if the number of standard prescriptions in the screened prescription set is more than 3, obtaining a user group which uses the standard prescriptions in the current prescription set and meets the prescription requirements in the use process, calculating the similarity between the user and the user group according to the exercise capacity and the physical development level of the user, and finally selecting 3 standard prescriptions with the similarity being more than a threshold value and the best evaluating effect of the user prescription for selection of the user, wherein the similarity calculation adopts the mode of [0070 ]; if the number of prescriptions in the standard prescriptions set after screening is more than 0 and less than or equal to 3, the user is directly enabled to select the standard prescriptions. As shown in table 1 below, the content information of the standard sports prescription;
Table 1 standard athletic prescription information
The fine tuning process of the standard prescription includes:
step one: constructing a set of users using the current standard sports prescription;
step two: calculating the similarity between the user and the users in the set according to the physical development level and the exercise capacity of the user, and removing the users with the similarity lower than a threshold value;
the similarity calculation formula is as follows:ω i weight p for each similar attribute i For the i-th similar attribute value of the current user, q i Ith similar attribute value, x, for other users of the system i Maximum and maximum value existing in the system for the ith similar attributeDifference of small value, x i The unreasonable values should be removed and all the values sorted from large to small in the calculation process, and the maximum value is selected by the average value of the first 4% attribute values, the minimum value is selected by the average value of the last 4% attribute values, x i The purpose is to make the similarity attribute values of each calculation between 0 and 1, so as to reasonably arrange the weight omega i The method comprises the steps of carrying out a first treatment on the surface of the The threshold value can be selected and debugged through experiments according to the data accurately monitored, or the system ranks similarity values from low to high and then selects the nth threshold value as the threshold value, and a second method can be selected to determine the threshold value after the system accumulates a large number of users; for example, in the fat-reducing and slimming exercise, body Mass Index (BMI), waist-hip circumference ratio, virve index, pulse in quiet time, age, 12-minute running test time, step test evaluation index, one-minute supine-sit-up test number and one-minute push-up test number can be selected as similar attributes, n is equal to 8, omega, p, q and x are also 8, after the users with inconsistent sexes and dissimilar ages are removed, the similarity between the current user and other users in the set is calculated according to a formula and is screened;
Step three: removing users with an average weekly completion of less than 70% from the collection according to the user's athletic records using the current standard athletic prescription;
step four: if a certain amount of users are not reached in the set, dividing a movement intensity interval and a movement time interval of a standard prescription into 5 subintervals, selecting a corresponding subinterval according to movement capacity (5 levels in total) measured by the users, randomly selecting movement intensity and movement time in the interval in the corresponding subinterval, selecting a movement frequency closest to a user peripheral frequency expectation in a movement frequency interval specified by the prescription according to the requirement of the users on the weekly movement frequency, and then carrying out a step six; if a certain amount of users exist in the set, performing a step five;
step five: weighting and averaging the weekly motion quantity according to the motion effect scores of the users in the set to obtain the weekly average motion quantity of the current user; weighting and averaging the weekly average motion intensity according to the motion effect scores of the users in the set to obtain the weekly average motion intensity of the current user; then obtaining average movement time according to the average movement amount and the average movement intensity of each week; and the exercise intensity of the prescription is mainly represented by an exercise heart rate percentage interval;
Wherein the exercise amount is only one intermediate parameter, and is mainly used for calculating the exercise intensity and exercise time of a prescription, and the exercise amount = exercise heart rate percentage x effective exercise time and exercise heart rate percentageThe effective exercise time is the total time reaching the heart rate interval specified by the prescription in the exercise process after the user is warmed up, and the average heart rate in the exercise is the average heart rate in the effective exercise time process; the calculation formula of the maximum heart rate of the user is as follows: 205.8-0.685 x age; the average motion amount of the user is calculated as: />Wherein g i 、g j Score for athletic performance of similar users, m i The amount of motion (resulting from the calculation) for the i-th similar user; the calculation formula of the average motion intensity of the user is as follows:wherein g i 、g j Scoring the athletic performance of similar users, i i Average exercise heart rate percentage for similar users; the calculation formula of the average movement time of the user is +.>Writing the exercise intensity and the exercise time into an exercise prescription, inquiring the exercise feeling of a user according to the previous three times of the prescription exercise after the prescription verification is passed, performing prescription fine adjustment again if not suitable, and judging whether to perform prescription fine adjustment or change after the prescription evaluation is completed if suitable;
Step six: if the exercise prescription type is running, removing the user with fuzzy monitoring in the current user set, obtaining the relation between the running speed and the exercise intensity in a polynomial regression mode, obtaining the average running speed of the user according to the average exercise intensity obtained in the step four and combining a polynomial regression model, and writing the average running speed into the newly adjusted exercise prescription as a reference of exercise guidance;
the polynomial regression model training process is as follows, and a polynomial function is defined: y (x) =ω 0 +ω 1 x 1 +ω 2 x 2 2 +ω 3 x 3 3 X is the heart rate percentage of the user during exercise, y is the running speed of the user, and in order to calculate the parameter omega, letThen y=xw, X is a sample matrix of exercise heart rate percentages for similar users, samples in the sample matrix are average values of exercise heart rate percentages corresponding to the same running speed in 5 exercise processes, so that Y n Is the true value of the corresponding running speed, Y n For the model predictive value, the error function isAnd deriving the following steps: />Let derivative equal to 0, find: w= (X T X) -1 X T T, taking W into y (x) to obtain a polynomial regression model, and inputting the exercise heart rate percentage to obtain the average running speed of the user;
step seven: and delivering the adjusted standard prescriptions to a personalized prescription verification unit for verification. As shown in table 2 below, the content information for the post-fine-tuning personalized sports prescription is provided.
Table 2 personalized prescription information
The personalized prescription verification is used for detecting whether the personalized exercise prescription after fine adjustment is abnormal in model data, unsafe and poor in exercise effect, and the process comprises the following steps:
step one: checking whether the intensity, time and frequency of the exercise prescription after fine adjustment are within the set range of the standard prescription;
step two: checking whether the user has a prescription forbidden disease or not in a mobile phone questionnaire mode;
step three: determining a standard sport prescription to which the fine-tuned personalized prescription belongs, then searching all personalized prescriptions generated according to the current standard prescription, and storing the personalized prescriptions into a personalized prescription set;
step four: sequentially searching users using prescriptions in the personalized prescription set, wherein the average weekly completion degree of the users is more than 70% in the use process, and storing the users in the prescription user set;
step five: calculating the similarity between the current user and the users in the prescription user set according to the physical development level and the exercise capacity of the user, and removing the users with the similarity lower than a threshold value in the prescription user set;
step six: firstly, respectively adjusting the exercise heart rate percentage and the exercise time of a current user personalized prescription by 3%, 15% and 3% and 15% on the basis of original setting, secondly, acquiring the personalized exercise prescription used by the user in a prescription user set, wherein the personalized exercise prescription used by the user belongs to the prescription in the personalized prescription set established in the third step, then judging whether the acquired exercise heart rate percentage and exercise time of the personalized prescription are in a previously adjusted up and adjusted down interval, and whether the weekly exercise frequency of the prescription is equal to the weekly frequency of the personalized exercise prescription of the current user, and if the weekly exercise frequency is equal in the interval, storing the prescription in a similar prescription set;
Step seven: if a certain amount of individual prescriptions exist in the similar prescription set, respectively averaging the exercise effect generated by the individual prescriptions and the exercise score of the user and performing the step eight; if a certain amount of personalized prescriptions do not exist in the set, the step eight is skipped to execute the step nine;
step eight: obtaining all other users similar to the user in the system according to the physical development level and the exercise capacity of the user, screening the users with exercise records meeting the requirements and the exercise targets being consistent, determining the exercise effect and the exercise score of the screened users, if the average value of the exercise effect and the exercise score determined in the step seven is greater than 60% of the total number of the screened users, checking, if the average value of the exercise effect and the exercise score determined in the step seven is between 30% and 60% of the total number of the screened users, inquiring the opinion of the users to determine whether the opinion of the users passes, and if the average value of the exercise effect and the exercise score determined in the step seven is below 30% of the total number of the screened users, checking not to pass;
step nine: if the problem exists in the inspection process in the steps, returning inspection information to regenerate the prescription; if no problem exists, issuing a prescription to the user;
The exercise monitoring guidance module is used for monitoring and guiding exercise of a user, and in order to more effectively utilize exercise data and adapt to more body-building crowds, the exercise monitoring guidance mode is divided into accurate monitoring guidance and fuzzy monitoring guidance; accurately monitoring and requiring a user to wear a designated sports watch or sports bracelet, acquiring and recording the heart rate of the user in the sports process through the sports watch or sports watch, and giving vibration and voice reminding through a smart phone if the sports heart rate exceeds or falls below 3% of the prescribed heart rate or the time exceeds or falls below 15% of the prescribed sports time;
the fuzzy monitoring guidance comprises a user's movement characteristic mobile phone monitorable guidance and a user's movement characteristic mobile phone non-monitorable guidance; for example, the key running characteristics of running can be obtained by using a mobile phone sensor, including running speed, swing arm frequency, pace and running time, so that the running type of a user's running prescription is running, the monitoring guidance mode of a user's no-running watch and no-running bracelet is a running characteristic mobile phone monitorable guidance in the invention, the mobile phone monitorable guidance mode of the running characteristic cannot be used for detecting the running characteristics of the user by using the mobile phone sensor for the running of the types such as badminton, table tennis, swimming and the like, and if the user selects the prescription and the user's no-running watch and no-running watch is a monitoring guidance mode of the running characteristic mobile phone monitorable guidance in the invention;
The motion characteristic mobile phone can monitor and guide motion characteristics through a sensor in the smart phone, after the motion characteristics monitored by the mobile phone are obtained, the motion characteristics are converted into corresponding motion heart rates through a mapping relation between the motion characteristics and heart rate percentages of a polynomial regression model, and the motion heart rate calculated by the mapping relation is subjected to fine adjustment by combining subjective motion feeling of a user in the previous 3 times of motion monitoring, and then if the motion heart rate of the user in motion exceeds or falls below 3% of a prescription specified heart rate or the time exceeds or falls below 15% of the prescription specified motion time, vibration and voice reminding are given through the smart phone, and the polynomial regression model adopts the process of [0075] to carry out model training;
the mobile phone monitoring-free guidance of the movement characteristics is that subjective movement feeling, subjective fatigue degree after movement and movement time in the movement process of a user are obtained through a mobile phone questionnaire, wherein the subjective fatigue degree of the obtained user can be selected from self feeling, complexion, perspiration, respiration and movement, and the subjective movement feeling can be selected from extremely relaxed, very relaxed, somewhat laborious, very laborious, feeling of exhaustion and the like, and in order to ensure that all users have a unified standard, detailed description of each option of the subjective movement feeling and the subjective fatigue degree should be given; for example, subjective feeling is easily described as feeling of walking and dressing indoors; the self-perception of moderate fatigue is: tiredness, leg soreness, etc., complexion: relatively red, perspiration: more, breathe: remarkably quickens, acts: heavy pace, etc.; after subjective motor feeling and subjective fatigue degree in the motor process of a user are obtained, the subjective feeling and the subjective fatigue degree are scored according to a system scoring table, then other users of a system which are similar to the current user in physical development level and motor ability and are accurately monitored in a motor monitoring mode are searched, and further system users of which the difference of different individual motor prescriptions generated by the current user and the other users of the system according to the same standard motor prescriptions in the motor heart rate percentage is not more than 3% and the difference of the motor time is not more than 15% are screened, if the number of the screened system users meeting the requirements is more than 15, the subjective motor feeling scores after the users are subjected to averaging, and the relatively most suitable subjective motor feeling scores are obtained; if the screened system users meeting the requirements do not exceed 15, obtaining a mapping relation between the exercise heart rate percentage and the subjective exercise feeling score by using a polynomial regression model for the exercise records accurately monitored in a monitoring mode, obtaining an exercise feeling score which is more suitable for the current prescription according to the exercise heart rate percentage and the mapping relation specified by the prescription, firstly judging whether the difference between the subjective exercise feeling score of the user and the subjective exercise feeling score calculated by the system exceeds 1 in the process of monitoring guidance of the exercise characteristic mobile phone, reminding the user to reduce or increase the exercise intensity if the difference exceeds 1, then judging whether the difference between the exercise time and the time specified by the prescription exceeds 15%, reminding the user to reduce or increase the exercise time if the difference exceeds 15%, finally judging whether the exercise feeling score after the exercise of the user is equal to the fatigue grade specified by the prescription or not, if the difference is smaller than the fatigue grade specified by the prescription, then selecting to appropriately increase the exercise intensity or the exercise time according to the exercise time of the exercise feeling score of the user and the subjective exercise time of the user if the fatigue grade of the user is larger than the fatigue grade specified by the prescription, and giving the subjective exercise feeling score of the user and the subjective exercise feeling score of the user if the user is only recommended to the user through the exercise guidance if the fatigue grade specified by the subjective exercise evaluation of the prescription.
The exercise prescription evaluation module is used for evaluating whether the current exercise prescription is suitable for the current user, the prescription evaluation content comprises evaluation of the prescription by the user and evaluation of the exercise effect by the system, and the evaluation period of the prescription is set according to the prescription regulation period; the system acquires the evaluation of the user on the exercise prescription in a mobile phone questionnaire mode, and acquires the exercise effect of the user in a mode of guiding the user to perform self-effect evaluation; the system performs fine adjustment of the prescription or modification of the prescription through comprehensive evaluation after acquiring the evaluation of the exercise prescription by the user and the exercise effect of the user; the implementation process is shown in a third diagram, wherein the fifth step, the sixth step and the seventh step are exemplary steps of fine tuning the prescription, the eighth step, the ninth step and the tenth step are exemplary steps of changing the prescription, and fine tuning or changing operation on the original prescription is determined by the fourth step.
Step one: the platform reminds the user to perform the step prescription evaluation;
step two: filling a prescription evaluation questionnaire by a user, and completing the test by the user according to the test step;
the evaluation of the user on the prescription is to acquire the exercise intensity feeling, exercise duration feeling, weekly exercise frequency feeling and prescription score of the current prescription by using a mobile phone questionnaire mode, wherein each questionnaire has 5 choices; the exercise intensity sensation, the exercise duration sensation, and the exercise frequency sensation are interrogated from five levels, low, appropriate, high, and given a detailed explanation of each definition, the exercise prescription score is scored from 1 score to 5 scores for the user. In order to evaluate the exercise effect of the user, the user needs to perform self-evaluation according to the steps formulated by the system, the system evaluates the exercise effect of the user according to the evaluation result, for example, the aim of the user is to enhance the heart-lung capacity, the user can perform the self-evaluation by adopting a 12-minute running and step test method, the test steps are generated by the smart phone in the evaluation process, and the user only needs to complete various tests according to the test steps;
Step three: uploading evaluation information of the prescription by the user and a user evaluation result to a server through an intelligent equipment module;
step four: the exercise evaluation module judges the operation mode of the current exercise prescription;
after the exercise prescription evaluation module obtains the evaluation of the user on the exercise prescription and the evaluation result of the user, the exercise prescription evaluation module obtains the difference between the current test result and the last test result, and obtains the exercise effect of the user at the stage; then the motion prescription evaluation module firstly screens motion records of all users in the system, removes motion records which are inconsistent with the current user motion targets and have a weekly average completion degree of less than 70%, compares the motion records with the motion effects of the users according to the scheduled staged motion effect experience values of the prescriptions if the screened motion records are less than 500, sorts the motion effect scores of the motion records in the same motion stage if the screened motion records are more than 500, and determines the positions of the staged motion effects of the users in the sorting; judging whether the periodic exercise effect is lower than 35% of users or whether the periodic exercise effect experience value is lower than 3 score or whether the user scores the exercise prescription, if any one of the conditions is met, inquiring whether the user changes the exercise prescription, entering the step eight if the user selects to change the prescription, and entering the step five if the user selects not to change the prescription; if the conditions are not met, and the user periodic exercise effect exceeds 75% or exceeds the exercise effect experience value preset by the prescription, and the user does not adjust the exercise prescription of the user if the exercise intensity, duration and frequency evaluation are all moderate; otherwise, performing fine adjustment processing on the exercise prescription of the user according to the exercise effect and questionnaire evaluation, and entering a step five;
Step five: gradually adjusting the exercise intensity, the exercise time and the exercise frequency of each week of the current prescription according to the prescription evaluation of the user;
the adjusting mode is that the exercise heart rate percentage of the exercise intensity is increased or decreased by 1 percent each time, the exercise time is increased or decreased by 5 percent each time on the basis of the original time, the exercise frequency is increased or decreased by 1 each time on the basis of the original frequency, the addition and subtraction are judged according to the evaluation of the user on the exercise prescription, and the user considers that the exercise prescription is high and low, and the exercise prescription is added and is suitable; obtaining all adjustable prescription parameters in the standard prescription specified parameter range in a cyclic traversal mode, writing each adjusted parameter into the prescription and storing the parameters into a prescription set;
step six: searching a motion effect mean value generated according to the adjusted motion prescription according to the motion record in the platform;
traversing the adjusted prescription set, searching for a motion record generated by using a prescription similar to the prescription in the set from all the motion records of the platform, removing the motion record with the average completion degree lower than 70%, if the rest of the motion records are more than 100, solving the average value of the motion effect generated by the motion record, and if the rest of the motion records are less than 100, directly performing the next traversal process; if the average value exists in the traversal process and the average value is higher than 45% of the stepwise exercise effect in the platform, marking and recording each parameter of the adjusted prescription; the prescriptions similar to prescriptions in the set are prescriptions which generate movement records in the platform and the standard prescriptions according to the prescriptions after adjustment in the set are consistent, the difference of the movement intensities of the two prescriptions is less than 1%, the difference of the movement time is less than 5%, and the movement frequency is consistent;
Step seven: judging whether a mark record exists after traversing the prescription set;
after judging, if mark records with the average effect value higher than 45% exist in the traversal, selecting prescription parameters with good movement effect and the movement intensity, movement time and movement frequency meeting the requirements of users in the records, and if mark records do not exist in the traversal, increasing and decreasing the prescription parameters within the movement intensity, movement time and movement frequency range specified by the prescription according to the evaluation; in general, if the user evaluates the exercise intensity to be slightly higher and lower, the exercise intensity can be reduced and increased by 2% -7%, if the user evaluates the exercise time to be slightly higher and lower, the exercise time can be reduced and increased by 5% -25%, and if the user evaluates the exercise frequency to be slightly higher and lower, the weekly exercise frequency can be reduced and increased by 1%; further if the user evaluates as high and low, continuing to decrease and increase outside a slightly high and slightly low maximum range; wherein, the adjustment cannot exceed the minimum and maximum values of the parameter range specified by the standard sport prescription in any way; step eleven, checking and releasing the prescription after the fine adjustment is finished;
step eight: obtaining the exercise intensity, time and frequency range expected by the user according to the prescription evaluation and the exercise prescription before modification;
If the user selects to change the sports prescription in the fourth step, the step eight is directly carried out to start changing the sports prescription, and in the process of changing the sports prescription, in order to better adapt to the sports of the user, the sports strength, time and frequency range expected by the user are firstly obtained according to the prescription evaluation and the sports prescription which is not changed; in general, if the user evaluation exercise intensity is slightly higher and lower, the exercise intensity is respectively reduced and increased by 2% to 7% on the basis of the original prescription as a range of the user expected exercise intensity, if the user evaluation exercise time is slightly higher and lower, the exercise time is reduced and increased by 5% to 25% on the basis of the original prescription as a range of the user expected exercise time, and if the user evaluation exercise frequency is slightly higher and lower, the weekly exercise frequency is reduced and increased by 1 on the basis of the original prescription as a range of the user expected weekly exercise frequency; further, if the user evaluates to be high and low, taking the minimum and maximum values of the slightly high and slightly low maximum range values and the prescription requirements as the movement strength, time and frequency range expected by the user; wherein, the minimum and maximum values of the parameter range specified by the standard exercise prescription cannot be exceeded regardless of the exercise intensity, time and frequency range expected by the user;
Step nine: the user re-picks the standard prescription;
the implementation mode of generating the standard prescriptions for the users is basically consistent with the selection process of the standard prescriptions of the prescription library under the sport prescription construction module, but the standard prescriptions according to the original personalized prescriptions are removed in the standard prescription selection process;
step ten: fine-tuning the selected standard exercise prescription in combination with the exercise intensity, exercise time and exercise frequency range expected by the user;
the implementation of fine tuning the standard prescription re-selected by the user is similar to the fine tuning process [0066] of the standard prescription implemented by the sports prescription fine tuning unit under the sports prescription building module; the difference is that a condition that the movement intensity, movement time and movement frequency in the set are not in the range expected by the user is added in the step three [0070] for realizing standard prescription fine adjustment of the movement prescription fine adjustment unit according to the movement record of the user, and in the step four [0071], if a certain amount of users are not reached in the set, the movement intensity, movement time and movement frequency of the user prescription are selected in the movement intensity, movement time and movement frequency range expected by the movement of the user;
step eleven, checking and releasing the fine-tuned exercise prescription;
Whether after fine tuning of the original sports prescription or after fine tuning of the changed sports prescription, any sports prescription to be issued needs to be checked in a prescription check and issue unit, so as to prevent the problems of abnormal model data, unsafe and poor sports effect of the issued prescription.
The motion effect prediction unit is used for predicting the motion effect of the user according to the current motion record of the user and the motion data of other users in the system platform through the motion effect prediction method based on the similarity calculation, then comprehensively improving and comprehensively reducing the motion completion degree of the current user motion record each time, respectively predicting the motion effect of the motion record after comprehensively improving the motion completion degree each time and the motion record after comprehensively reducing the motion completion degree each time, and finally displaying the prediction result to the user in a line diagram mode, so that the user can intuitively know the motion effect in different motion states, the user can conveniently make motion decisions, and meanwhile, the motion enthusiasm of the user can be improved; in order to make effect prediction more accurate and effective, in the invention, motion effect prediction is only carried out on a motion record generated by a motion monitoring mode for accurate monitoring, and the implementation process comprises the following steps:
Step one: acquiring a motion record of a current user, calculating the average completion degree of the motion of the user every week and the average completion degree of the motion every time in a week, and judging whether the motion state of the user is stable or not;
the motion effect prediction of the user takes one period of the prescription as a prediction node, the motion record in the current prescription period of the user should be selected in the process of acquiring the motion record of the user, namely, the motion record from the starting time of the prescription period to the current time of the user should be selected, and at least two complete-cycle motion records exist; after the motion record is acquiredThe average completion of each movement of the user and the average completion of each movement within a week are calculated, wherein,the effective exercise time is the exercise time accumulated by the heart rate percentage of the user exercise in the exercise process of the user and the heart rate percentage prescribed by the prescription which are different by not more than 3 percent, after calculation is completed, judging whether the motion state of the user is stable or not according to the motion record of the user, if the difference between the maximum value and the minimum value of the average completion degree of each motion in a circle in the motion record is more than 20% or the difference between the maximum value and the minimum value of the average completion degree of each motion in a circle is more than 20%, indicating that the motion state of the user is unstable, the invention does not give the approximate prediction of the motion effect, otherwise, indicating that the motion state of the user in the current stage is stable, and can give the approximate prediction of the motion effect;
Step two: acquiring motion records generated in the motion process of other users in the platform system according to the motion records of the current user;
firstly, searching motion records generated by other users of the system under the conditions that the motion intensity is not more than 2%, the motion time is not more than 5% and the weekly motion frequency is equal, which are generated by the personalized prescriptions generated by fine tuning the standard prescriptions which are the same as the standard prescriptions used by the current user, from platform system data, putting the motion records which are accurately monitored in a monitoring mode into a motion record set, and then removing the motion records with unstable motion states in the motion record set;
step three: constructing a similar movement effect set;
calculating the similarity of the current user and the user generating the motion records in the motion record set on the physical development level and the motion capability, and removing the similarity in the motion record set greater than a threshold valueA user generated motion record of (a); then, calculating the similarity between the motion records in the record set and the current motion records of the user respectively, and storing the motion records with the similarity smaller than a threshold value in the motion record set into a similar motion effect set; wherein, the user similarity can be [0069 ] ]The similarity calculation formula is used for calculating, and the similarity of the motion records can be measured by using the deviation degree of the average completion degree of each motion in a circle between the two motion records and the deviation degree of the average completion degree of each motion in a circle between the two motion records; the average deviation degree calculation formula of the average completion degree of each movement in a circle between the two movement records can beThe average deviation calculation formula of the "average completion of weekly movements" between the two movement records may be +.>Wherein E is the average deviation of the average completion degree of each movement in a circle between two movement records, W is the average deviation of the average completion degree of each movement between two movement records, n is the complete number of the current user movement records, u i Record for the current user movement the i-th complete week 'average completion of each movement in a week' o i "average completion of every movement in a week" for the ith complete week, z, is recorded for movements in the movement record set i Record "average completion of weekly movements" for the ith complete week, c, for current user movements i "average completion of weekly movements" for the ith complete week for movement records within the movement record set; if |E| <5% and |W|<5% indicates that the motion records are similar, otherwise, the motion records are dissimilar, the threshold value can be adjusted according to the size of the motion data quantity in the platform, the smaller the threshold value, the more accurate the prediction is, but the higher the requirement on the data quantity of the platform system is, and the threshold value can be adjusted up and down on the basis of 5% of the prediction rate and the prediction accuracy of the platform;
step four: calculating the rough movement effect of the user according to the similar movement effect set;
after the similar motion effect set is obtained, if the set is empty, motion effect prediction is not given, or a threshold value of similarity can be increased to regain the similar motion effect set so as to increase the platform prediction rate; if the set is not empty, acquiring motion effects of different motion periods of motion records in the set, and respectively according to formulasObtaining the approximate exercise effect of the current user under different prescription periods, wherein R l A predicted value of the motion effect representing the first period after the user predicting period starts, n is the record number of the motion records in the similar motion effect set for completing the evaluation of the motion effect of the first period, and u i 、u j Representing similarity values of the ith and jth motion records and the current user motion record and u i ＝|W i |+|E i |、u j ＝|W j |+|E j |、u i ≥0.001、u j ≥0.001，r i Representing the exercise effect produced by the ith record corresponding to the n records,/for each record>It can be understood that r i The higher the similarity value between the motion records in the set and the current user motion record, the lower the similarity between the motion records in the set and the current user motion record is, because the motion effect prediction is performed according to the motion effect generated by all similar motion records, therefore, the overall influence of the motion effect generated by the lower similarity of the motion records on the prediction of the motion effect of the current user should be lower, so that +.>The higher the similarity of the motion records is, the higher the overall influence of the motion effect generated by the motion record on the motion effect prediction of the current user is; the method is compared with the methodThe prediction accuracy is improved by using the mean value or the method for predicting the user motion effect by using a single motion record;
step five: displaying the predicted result of the user movement effect to the user in a line graph mode;
after the motion effect prediction is performed according to the current motion record of the user, the motion completion degree of the current motion record of the user can be increased and decreased by 10% each time, and then the motion effect prediction is performed on the motion record with the increased and decreased motion completion degree each time respectively; the motion enthusiasm of users can be improved by predicting the motion effect of the motion state which keeps the current motion state, comprehensively improves the motion state of the completion degree of each motion and comprehensively reduces the motion state of the completion degree of each motion, and comparing and displaying the prediction effects under different motion states by combining the line graph;
The flow of the personalized exercise prescription and exercise guidance method generated according to the user moving object and the user self condition is shown in figure 3;
step 1: registering and logging in a user;
step 2.1: the user selects a moving object, wherein the moving object is various moving effects contained in a prescription of the prescription library;
step 2.2: the user fills in personal information, physical questionnaires and health questionnaires according to the self situation;
step 2.3: the user selects sports hobbies and available sports equipment, wherein the alternative sports hobbies are various sports types contained in the prescription library prescription, and the alternative sports equipment is various equipment required by the prescription library prescription sports;
step 3: the user tests physical quality and exercise capacity according to the system prompt, performs one-minute push-up test, one-minute supine and rising test, 12-minute running test, step test and the like under the prompt of the platform system, and fills the test result into the mobile phone client;
step 4: the platform system selects 3 most suitable standard sports prescriptions for the user from a prescription library by utilizing a standard prescription screening unit of a sports prescription construction module according to the sports targets, physique, diseases, sports hobbies and sports equipment of the user;
Step 5: the user selects a favorite standard exercise prescription from 3 standard prescriptions screened by a platform system;
step 6: the platform system utilizes the sports prescription fine-tuning unit of the sports prescription construction module to fine-tune the standard sports prescription selected by the user according to the physique of the user and the system sports data;
step 7: the platform system performs personalized prescription verification on the fine-tuned sports prescriptions by utilizing a prescription verification issuing unit of the sports prescription construction module, and issues the sports prescriptions to users after the prescription verification is successful;
step 8: for the sports prescriptions just released by the platform system, a user needs to judge the fatigue degree after the sports of the user when performing the previous three sports according to the new prescriptions, after the sports fatigue degree of the user is obtained by utilizing a mobile phone questionnaire, if the fatigue degree assessment meets the prescription requirements, the prescriptions are proper, and if the fatigue degree assessment does not meet the prescription requirements, the prescriptions are finely adjusted or changed;
step 9: the system monitors the movement of the user through the movement monitoring and guiding module and guides the user according to the movement prescription;
step 10: the system evaluates the sports prescriptions through a sports prescription evaluation module;
Step 11: judging whether the sports prescription is effective or not according to the prescription evaluation result of the sports prescription evaluation module and meeting the user requirement; if the sports prescription is valid and meets the user requirement, the sports prescription is not changed and the sports of the next period is directly started; otherwise, performing fine adjustment or prescription change on the sports prescription according to the evaluation result, and then re-checking and releasing the fine adjustment or changed sports prescription to start the sports in a new period.
According to the exercise prescription generation and monitoring guidance system based on data analysis, which is provided by the invention, the generation mode of an indifferent exercise scheme among users of a traditional exercise platform and the exercise monitoring guidance mode of the traditional exercise platform are changed by utilizing exercise data accumulated by users of the platform, an exercise prescription theory and a data analysis technology, so that the fit and practicability of the exercise prescription of the system are improved; and the adaptability of the system sports prescription to the user and the sports enthusiasm of the user are improved through the sports prescription evaluation and the sports effect prediction of the user. The invention brings better exercise experience to users without body-building coaches, intelligent body-building equipment and various body-building instruments, and improves the service level of a system platform.

Claims (7)

1. The exercise prescription generation and monitoring guidance system based on data analysis is characterized by comprising an intelligent equipment module for collecting information and guiding a user; the data transmission interface module is used for data interaction; the user information analysis module is used for evaluating the physical development level, the exercise capacity and the health condition of the user; the exercise prescription construction module is used for generating a personalized exercise prescription suitable for a user according to the user information acquired by the user information analysis module and the system exercise data; the exercise monitoring and guiding module is used for monitoring and guiding the exercise of the user; the exercise effect prediction module is used for predicting the exercise effect of the user according to the current exercise record of the user and the exercise data of other users in the system;
the exercise prescription construction module is used for constructing exercise prescriptions, and specifically comprises selection of standard prescriptions of a prescription library, fine adjustment of the standard prescriptions and checking of personalized prescriptions;
the fine adjustment of the standard prescription is specifically implemented according to the following steps:
step 1, constructing a user set using a current standard exercise prescription;
step 2, calculating the similarity between the user and the users in the set according to the physical development level and the exercise capacity of the user, and removing the users with the similarity lower than a threshold value;
Step 3, removing users with average weekly completion degrees lower than 70% in the set according to the exercise records of the users using the current standard exercise prescriptions;
step 4, if a certain amount of users do not reach the set, dividing a movement intensity interval and a movement time interval of a standard prescription into 5 subintervals, selecting a corresponding subinterval according to a movement capacity level measured by the user, randomly selecting movement intensity and movement time in the interval in the corresponding subinterval, selecting a movement frequency closest to a user peripheral frequency expectation in a movement frequency interval specified by the prescription according to the requirement of the user on the weekly movement frequency, and then carrying out step six; if a certain amount of users exist in the set, performing a step five;
step 5, determining the average motion intensity and motion time of the user according to the user motion data in the set;
step 6, if the exercise type of the exercise prescription is running, calculating the relation between the running speed and the exercise intensity, obtaining the average running speed of the user according to the average exercise intensity combination model relation obtained in the step four, and then putting the average running speed into the exercise prescription which is finely adjusted currently as a reference of exercise guidance;
step 7, delivering the fine-tuned standard prescription to a personalized prescription verification unit for verification;
The verification of the personalized prescription is specifically implemented according to the following steps:
step 1, checking whether the intensity, time and frequency of the exercise prescription after fine adjustment are within a set range of a standard prescription;
step 2, checking whether a user has a disease forbidden by a prescription in a mobile phone questionnaire mode;
step 3, determining a standard sport prescription to which the finely-adjusted personalized prescription belongs, then searching all personalized prescriptions generated according to the current standard prescription, and storing the personalized prescriptions into a personalized prescription set;
step 4, sequentially searching users using prescriptions in the personalized prescription set, wherein the average weekly completion degree of the users is more than 70% in the use process, and storing the users in the prescription user set;
step 5, calculating the similarity between the current user and the users in the prescription user set according to the physical development level and the exercise capacity of the user, and removing the users with the similarity lower than a threshold value in the prescription user set;
step 6, respectively adjusting the exercise heart rate percentage and the exercise time of the personalized prescriptions of the current user by 3%, 15% and 3% and 15% on the basis of the original values, secondly acquiring the personalized exercise prescriptions used by the users in the prescription user set, then judging whether the acquired exercise heart rate percentage and exercise time of the personalized prescriptions are in the previously adjusted up and down intervals, and whether the weekly exercise frequency of the prescriptions is equal to the weekly frequency of the personalized exercise prescriptions of the current user, and if the weekly exercise frequency is equal in the intervals, storing the prescriptions in a similar prescription set;
Step 7, if a certain amount of individual prescriptions exist in the similar prescription set, respectively averaging the exercise effect generated by the individual prescriptions and the exercise score of the user and performing a step eight; if a certain amount of personalized prescriptions do not exist in the set, the step eight is skipped to execute the step nine;
step 8, obtaining all other users similar to the user in the system according to the physical development level and the exercise capacity of the user, screening the users with exercise records meeting the requirements and consistent exercise targets, determining the exercise effect and the exercise score of the screened users, if the average value of the exercise effect and the exercise score determined in the step seven is greater than 60% of the total number of the screened users, checking, if the average value of the exercise effect and the exercise score determined in the step seven is between 30% and 60% of the total number of the screened users, inquiring the opinion of the users to determine whether the user passes, and if the average value of the exercise effect and the exercise score determined in the step seven is below 30% of the total number of the screened users, checking not to pass;
step 9, if the problem exists in the inspection process in the step, returning inspection information to regenerate the prescription; and if no problem exists, issuing the prescription to the user.
2. The athletic prescription generation and monitoring guidance system of claim 1, wherein the smart device module comprises a smart phone and a device capable of monitoring heart rate.
3. The system according to claim 1, wherein the user information analysis module obtains user interest, moving object, and usable sports equipment information, and writes the information into the database, and evaluates the physical development level, the exercise ability, and the health condition of the user according to the information.
4. The system for generating and monitoring and guiding a sports prescription based on data analysis according to claim 1, wherein said prescription library standard prescription is selected by the following steps:
step 1, screening out standard exercise prescriptions meeting requirements according to exercise targets, usable sports equipment, hobbies and diseases from a prescription library and a keyword matching technology, and putting the standard prescriptions obtained by screening into a prescription set;
and 2, screening standard sports prescriptions with relatively good sports effects according to the system sports data and a sports effect analysis method, and providing the standard sports prescriptions for users to select.
5. The system of claim 1, wherein the exercise monitoring guidance module comprises an accurate monitoring guidance and a fuzzy monitoring guidance, the accurate monitoring guidance is used for obtaining the heart rate of the user through a heart rate monitoring device so as to conduct guidance, and the fuzzy monitoring guidance comprises a guidance that the exercise characteristic mobile phone of the user can monitor and a guidance that the exercise characteristic mobile phone of the user cannot monitor.
6. The system for generating and monitoring and guiding a sports prescription based on data analysis according to claim 1, wherein the prescription evaluation content of the sports prescription evaluation module comprises evaluation of a user on the prescription and evaluation of a system on a sports effect, the evaluation of the user on the prescription is that the system obtains the evaluation of the user on the sports prescription in a mobile phone questionnaire mode, the sports effect evaluation of the sports prescription evaluation module is that the user carries out self evaluation according to the steps formulated by the system and fills in evaluation data, the system compares the obtained evaluation data with the last evaluation data of the user so as to obtain the sports effect of the stage, and the system carries out fine adjustment of the prescription or modification of the prescription through comprehensive evaluation after obtaining the evaluation of the user on the sports effect of the sports prescription and the sports effect of the user.
7. The system for generating, monitoring and guiding a movement prescription based on data analysis according to claim 1, wherein the movement effect prediction module predicts the movement effect of the user by combining the current movement record of the user with the movement data of other users in the system platform through a movement effect prediction method based on similarity calculation, then comprehensively improves and comprehensively reduces the completion degree of each movement of the current user movement record, predicts the movement effect of the movement record after comprehensively improving the completion degree of each movement and the movement record after comprehensively reducing the completion degree of each movement respectively, finally displays the prediction result to the user through a line graph, so that the user can intuitively know the movement effect under different movement states, and is convenient for making movement decisions, and meanwhile, the enthusiasm of the movement of the user can be improved.
CN202010652416.7A 2020-07-08 2020-07-08 Sport prescription generation and monitoring guidance system based on data analysis Active CN111986774B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010652416.7A CN111986774B (en) 2020-07-08 2020-07-08 Sport prescription generation and monitoring guidance system based on data analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010652416.7A CN111986774B (en) 2020-07-08 2020-07-08 Sport prescription generation and monitoring guidance system based on data analysis

Publications (2)

Publication Number Publication Date
CN111986774A CN111986774A (en) 2020-11-24
CN111986774B true CN111986774B (en) 2023-09-12

Family

ID=73439022

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010652416.7A Active CN111986774B (en) 2020-07-08 2020-07-08 Sport prescription generation and monitoring guidance system based on data analysis

Country Status (1)

Country Link
CN (1) CN111986774B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112836105B (en) * 2021-02-05 2022-05-24 浙江工业大学 Large-scale student aerobic capacity clustering method based on movement physiological characterization fusion

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011025075A1 (en) * 2009-08-28 2011-03-03 (주)누가의료기 Exercise prescription system
US8639650B1 (en) * 2003-06-25 2014-01-28 Susan Pierpoint Gill Profile-responsive system for information exchange in human- and device-adaptive query-response networks for task and crowd management, distributed collaboration and data integration
CN107767955A (en) * 2017-10-18 2018-03-06 北京大学第三医院 A kind of Personalized motion target heart rate design system and its application method
CN108364674A (en) * 2018-02-22 2018-08-03 国家体育总局体育科学研究所 A kind of intelligent body-building guidance method and system using exercise prescription
CN110706777A (en) * 2019-09-30 2020-01-17 康纪明 Personalized exercise amount recommendation system and method
CN111145908A (en) * 2019-12-26 2020-05-12 糖医生健康管理南京有限公司 Health assessment comprehensive information service platform

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8639650B1 (en) * 2003-06-25 2014-01-28 Susan Pierpoint Gill Profile-responsive system for information exchange in human- and device-adaptive query-response networks for task and crowd management, distributed collaboration and data integration
WO2011025075A1 (en) * 2009-08-28 2011-03-03 (주)누가의료기 Exercise prescription system
CN107767955A (en) * 2017-10-18 2018-03-06 北京大学第三医院 A kind of Personalized motion target heart rate design system and its application method
CN108364674A (en) * 2018-02-22 2018-08-03 国家体育总局体育科学研究所 A kind of intelligent body-building guidance method and system using exercise prescription
CN110706777A (en) * 2019-09-30 2020-01-17 康纪明 Personalized exercise amount recommendation system and method
CN111145908A (en) * 2019-12-26 2020-05-12 糖医生健康管理南京有限公司 Health assessment comprehensive information service platform

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
The exercise prescription for enhancing overall health of midlife and older women;Miriam J. Woodward 等;Maturitas;全文 *

Also Published As

Publication number Publication date
CN111986774A (en) 2020-11-24

Similar Documents

Publication Publication Date Title
TWI650713B (en) Customized training advice
CN108905170B (en) Effective movement evaluation method based on cardiopulmonary endurance level and RPE feedback and device for implementing method
EP2063966B1 (en) System for training optimisation
CN109637625B (en) Self-learning fitness plan generation system
CN108364674A (en) A kind of intelligent body-building guidance method and system using exercise prescription
CN114822763A (en) Personalized exercise prescription recommendation method driven by exercise data
Pyne Interpreting the results of fitness testing
CN102213957A (en) Control method, and device and system for providing virtual private sport coach
CN104699928A (en) Physique development assessment model for 3-15 years-old children
CN103294921A (en) Intelligent management method and system for fitness sports
US8996446B2 (en) Sensory testing data analysis by categories
CN104083174A (en) Exercise ability evaluation model
CN109922719A (en) For quantifying system, the method and computer program of the physical fatigue of object
US20230181058A1 (en) System and method for estimating cardiorespiratory fitness
CN111986774B (en) Sport prescription generation and monitoring guidance system based on data analysis
JP4646019B2 (en) Daily life / exercise support system for the elderly
CN111544853A (en) Physical index evaluation method and equipment in running exercise
Gallo et al. Power road-derived physical performance parameters in junior, under-23, and professional road cycling climbers
US20220249911A1 (en) Physical training system with machine learning-based training programs
CN112349413A (en) Long-distance exercise training load analysis system
Boullosa et al. The fine-tuning approach for training monitoring
CN111370089A (en) Sports training system
Kramer How to develop a Grand Slam winner...: physical and psychological skills in Dutch junior tennis players
Geneau et al. The Relationship Between Lower-Body Force–Time Variables and Skating Performance in Female Ice Hockey Players
CN108600361A (en) A kind of sports monitoring method and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant