CN116687390A - User fat reduction effect estimation method and system based on intelligent sports shoe analysis - Google Patents
User fat reduction effect estimation method and system based on intelligent sports shoe analysis Download PDFInfo
- Publication number
- CN116687390A CN116687390A CN202310344500.6A CN202310344500A CN116687390A CN 116687390 A CN116687390 A CN 116687390A CN 202310344500 A CN202310344500 A CN 202310344500A CN 116687390 A CN116687390 A CN 116687390A
- Authority
- CN
- China
- Prior art keywords
- information
- pressure
- stride
- user
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000000694 effects Effects 0.000 title claims abstract description 112
- 230000009467 reduction Effects 0.000 title claims abstract description 67
- 238000004458 analytical method Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000036541 health Effects 0.000 claims abstract description 50
- 238000013210 evaluation model Methods 0.000 claims abstract description 43
- 238000011156 evaluation Methods 0.000 claims abstract description 28
- 230000001603 reducing effect Effects 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 17
- 238000010276 construction Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 12
- 210000000577 adipose tissue Anatomy 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 abstract description 3
- 230000033001 locomotion Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010030 laminating Methods 0.000 description 1
- 150000002632 lipids Chemical class 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1036—Measuring load distribution, e.g. podologic studies
- A61B5/1038—Measuring plantar pressure during gait
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
Abstract
The application provides a user fat reduction effect estimation method and system based on intelligent sports shoe analysis, which relate to the technical field of data analysis and are used for acquiring the running steps and health sign information sets of a user and acquiring a plurality of pressure information sets through a pressure sensing module; the method comprises the steps of obtaining a plurality of stride information through a step counting analysis module, inputting the stride information into a unit step dividing model, obtaining a plurality of unit step sets of a plurality of unit step types, obtaining a plurality of sub-step numbers of the unit step types, inputting the sub-step sets into a fat reduction effect evaluation model, and obtaining a fat reduction effect evaluation result.
Description
Technical Field
The application relates to the technical field of data analysis, in particular to a user fat reduction effect estimation method and system based on intelligent sports shoe analysis.
Background
The development of the sports shoes is continuously expanded along with the activity range, the activity space and the activity state of people to adapt to the demands of users, and along with the rising of various novel projects, the performance demands of people on the sports shoes are gradually increased, wherein the fat reducing effect is one of the performance indexes of the sports shoes, the intelligent sports shoes can automatically detect professional sports data, and the fat reducing effect is evaluated based on the detected real-time sports data. At present, the fat reducing effect is judged mainly by monitoring various body index parameters in real time, and data comprehensive evaluation is carried out to determine the actual fat reducing effect, so that the current evaluation method has a certain technical flaw and affects the final estimation result.
In the prior art, the estimation method for the fat reducing effect is more traditional, the source data has insufficient degree of differentiation, and the data estimation flow is not strict enough, so that the estimation result has a certain deviation compared with the actual result.
Disclosure of Invention
The application provides a user fat-reducing effect estimation method and system based on intelligent sports shoe analysis, which are used for solving the technical problems that in the prior art, the method for estimating the fat-reducing effect is more traditional, the degree of source data is insufficient, the data estimation flow is not strict enough, and a certain deviation exists between the estimation result and the actual result.
In view of the above problems, the present application provides a method and a system for estimating the user's fat-reducing effect based on intelligent sports shoe analysis.
In a first aspect, the present application provides a method for estimating a user's fat reduction effect based on intelligent sports shoe analysis, the method comprising:
when a user uses the intelligent sports shoes to run, the step counting analysis module and the pressure sensing module are used for acquiring the step number of running of the user;
acquiring multiple types of health sign information of the user, and acquiring a health sign information set;
the pressure sensing module is used for acquiring multiple types of information of pressure generated by each step in running of the user and acquiring multiple pressure information sets;
the step counting analysis module is used for obtaining the steps of each step in running of the user and obtaining a plurality of step information;
inputting the pressure information sets and the stride information into a unit stride division model to obtain a plurality of unit stride sets of a plurality of unit stride types, and obtaining a plurality of sub-numbers of the unit stride types, wherein the sum of the sub-numbers is the stride number;
inputting the sub-numbers and the health sign information set into a fat-reducing effect evaluation model to obtain a fat-reducing effect evaluation result of the running exercise currently completed by the user.
In a second aspect, the present application provides a user fat reduction effect estimation system based on intelligent sports shoe analysis, the system comprising:
the step number acquisition module is used for acquiring the step number of running of the user through the step counting analysis module and the pressure sensing module when the user uses the intelligent sports shoes to run;
the system comprises a physical sign information acquisition module, a physical sign information acquisition module and a user identification module, wherein the physical sign information acquisition module is used for acquiring multiple types of physical sign information of the user and acquiring a physical sign information set;
the pressure information acquisition module is used for acquiring multiple types of information of pressure generated by each step in running of the user through the pressure sensing module to acquire multiple pressure information sets;
the stride information acquisition module is used for acquiring stride of each step in running of the user through the step counting analysis module to acquire a plurality of stride information;
the model analysis module is used for inputting the pressure information sets and the stride information into a unit step division model, obtaining a plurality of unit step sets of a plurality of unit step types, and obtaining a plurality of sub-step numbers of the unit step types, wherein the sum of the sub-step numbers is the step number;
the result acquisition module is used for inputting the sub-numbers and the health sign information set into a fat reduction effect evaluation model to obtain a fat reduction effect evaluation result of the running exercise currently completed by the user.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
according to the user fat reduction effect estimation method based on intelligent sports shoe analysis, when a user uses the intelligent sports shoe to run, the step counting analysis module and the pressure sensing module are used for obtaining the running step number of the user; acquiring multiple types of health sign information of the user, and acquiring a health sign information set; the pressure sensing module is used for acquiring multiple types of information of pressure generated by each step in running of the user and acquiring multiple pressure information sets; the step counting analysis module is used for obtaining the steps of each step in running of the user and obtaining a plurality of step information; the multiple pressure information sets and the multiple stride information are input into a unit stride division model to obtain multiple unit stride sets of multiple unit stride types, multiple sub-step numbers of the multiple unit stride types are obtained, the multiple pressure information sets and the multiple stride information are input into a fat reduction effect evaluation model to obtain a fat reduction effect evaluation result of running exercise currently completed by a user, the technical problems that an evaluation method for the fat reduction effect is more traditional, the degree of source data is insufficient, a data evaluation flow is not strict enough, a certain deviation exists in the evaluation result compared with the actual situation are solved, and the dimension refinement and the pertinence modeling of the source data to be evaluated are carried out to improve the pertinence of the evaluation direction and realize efficient and accurate fat reduction effect evaluation.
Drawings
FIG. 1 is a schematic flow chart of a method for estimating the effect of reducing fat of a user based on analysis of intelligent sports shoes;
FIG. 2 is a schematic diagram showing a process for obtaining a plurality of pressure information sets in a user fat-reducing effect estimation method based on intelligent sports shoe analysis;
FIG. 3 is a schematic diagram showing the flow of obtaining the result of estimating the effect of reducing fat in the method for estimating the effect of reducing fat of a user based on analysis of intelligent sports shoes;
fig. 4 is a schematic structural diagram of a user fat reduction effect estimating system based on intelligent sports shoe analysis.
Reference numerals illustrate: the device comprises a step number acquisition module 11, a sign information acquisition module 12, a pressure information acquisition module 13, a stride information acquisition module 14, a model analysis module 15 and a result acquisition module 16.
Description of the embodiments
The application provides a method and a system for estimating the fat reducing effect of a user based on intelligent sports shoe analysis, which are used for acquiring the running steps of the user and a health sign information set, and acquiring a plurality of pressure information sets through a pressure sensing module; the method comprises the steps of obtaining a plurality of stride information through a step counting analysis module, inputting a plurality of pressure information sets and a plurality of stride information into a unit stride division model, obtaining a plurality of unit stride sets of a plurality of unit stride types, obtaining a plurality of sub-step numbers of the unit stride types, inputting the sub-step numbers into a fat reduction effect evaluation model, and obtaining a fat reduction effect evaluation result.
Examples
As shown in fig. 1, the present application provides a method for estimating a user's fat-reducing effect based on analysis of an intelligent sports shoe, the method is applied to an intelligent sports shoe, the intelligent sports shoe includes a pressure sensing module and a step counting analysis module, the method includes:
step S100: when a user uses the intelligent sports shoes to run, the step counting analysis module and the pressure sensing module are used for acquiring the step number of running of the user;
specifically, the development of the sports shoes is continuously expanded along with the activity range, activity space and activity state of people to adapt to the demands of users, and along with the rising of various novel projects, the performance demands of people on the sports shoes are gradually increased, wherein the fat-reducing effect is one of the performance indexes of the sports shoes. Specifically, through carrying out shoe body state perception, carry out the motion and start and stop the judgement, when the user uses intelligent sports shoes carries out running motion, based on the pressure sensing module carries out shoe body pressure-bearing measurement to carry out the landing determination in the user running process, based on the gyroscope in the step analysis module of calculating and instrument in prior art such as gravity induction obtains running step number, confirms the step number that the user runs, through carrying out real-time perception, can ensure to obtain the actual laminating degree of step number.
Step S200: acquiring multiple types of health sign information of the user, and acquiring a health sign information set;
further, the step S200 of the present application further includes the steps of:
step S210: collecting age information, weight information, height information and body fat rate information of the user;
step S220: the health sign information set is generated based on the age information, weight information, height information, and body fat rate information.
Specifically, the physical state of the user is an energy efficiency influence factor of fat reduction, and the difference of the physical states can cause deviation of the fat reduction effect under the same exercise data. And acquiring various body data of the user, including the age information, the weight information, the height information and the body fat rate information, wherein the acquired information is a plurality of body function parameters, and performing targeted analysis and judgment based on the actual physical sign state of the user, so that the final fat reduction estimation result and the fitting degree of the user can be effectively ensured. And integrating the age information, the weight information, the height information and the body fat rate information, correlating with the user, and generating the health sign information set. And the health sign information set is used as auxiliary information for evaluation and analysis, so that the accuracy of an estimation result can be further improved.
Step S300: the pressure sensing module is used for acquiring multiple types of information of pressure generated by each step in running of the user and acquiring multiple pressure information sets;
further, as shown in fig. 2, the pressure sensing module obtains multiple types of information of pressure generated by each step in running of the user, and obtains multiple pressure information sets, and step S300 of the present application further includes:
step S310: the pressure sensing module is used for acquiring pressure positions of pressure generated by each step in running of the user and acquiring a plurality of pressure position information;
step S320: acquiring the pressure of pressure generated by each step in running of the user, and acquiring a plurality of pieces of pressure information;
step S330: acquiring pressure duration time of pressure generated by each step in running of the user, and acquiring a plurality of pieces of pressure duration information;
step S340: the plurality of pressure information sets are generated based on the plurality of pressure position information, the plurality of pressure magnitude information, the plurality of pressure duration information, and the number of steps.
Specifically, when the user runs based on the intelligent sports shoes, due to the difference of sports data of each step, certain deviation exists in corresponding sports energy efficiency. And carrying out pressure-bearing data sensing of each step of the intelligent sports shoe based on the pressure sensing module, carrying out specific acquisition statistics based on the pressure position, the pressure size and the pressure duration, and further carrying out data summarization and normalization to generate the plurality of pressure information sets.
Specifically, the pressure sensing module is a functional module for sensing the pressure of the running process, determines the bearing points of the intelligent sports shoes in the running process of the user, and generates a plurality of pressure position information by determining the bearing positions of each step in the running process of the user and sequencing the bearing positions based on time sequences due to slight differences of the bearing points, the bearing sizes and the bearing duration of each step caused by different running postures of running at different speeds. Similarly, determining the pressure of each step in the running process of the user, and performing time sequence integration to generate the pressure information; and determining the duration time of pressure generated by each step in the running process of the user as the pressure duration information. The pressure position information and the pressure size information are in one-to-one correspondence with the pressure duration information, and the data value of the pressure position information and the pressure size information is consistent with the step number. And carrying out time sequence association correspondence on the pressure position information, the pressure size information and the pressure duration information and the step number to generate a plurality of pressure data sequences as the pressure information sets, and gradually and sequentially carrying out pressure bearing data acquisition, so that the data deviation of real-time acquisition data can be reduced, and the accuracy of a data source to be evaluated is improved.
Step S400: the step counting analysis module is used for obtaining the steps of each step in running of the user and obtaining a plurality of step information;
step S500: inputting the pressure information sets and the stride information into a unit stride division model to obtain a plurality of unit stride sets of a plurality of unit stride types, and obtaining a plurality of sub-numbers of the unit stride types, wherein the sum of the sub-numbers is the stride number;
specifically, the step counting analysis module is a functional module for performing real-time exercise step number data metering, and in one embodiment, further obtains the step of running of the user. Illustratively, the step number is obtained by the prior art such as a gyroscope and gravity sensing, the running distance is positioned by the positioning function in the prior art, and the distance of each step is calculated and obtained as the stride. And synchronously determining the stride of each step along with the advancing of the motion progress of the user, and carrying out time sequence regulation on the stride, so as to generate the stride information, namely the distance data set of each step.
Further, the unit step division model is constructed, and the unit step division model comprises a plurality of decision units, namely a step decision unit and a plurality of pressure decision units, which are respectively used for carrying out targeted decision analysis according to the step, the pressure size information, the pressure duration information and the pressure position information. Inputting the pressure information sets and the stride information into the unit step division model, analyzing by a decision unit corresponding to matching through information identification division, determining the motion condition of each step based on an analysis result, dividing the motion condition into unit steps of different types, and obtaining the unit step types and sub-step numbers contained in the unit step types, wherein the sum of the sub-step numbers is the step number. The running intensity corresponding to the unit steps of different types is different, for example, the running intensity corresponding to the unit steps with large pressure, short pressure duration and large stride is more intense, and the fat reducing effect is good. And a plurality of decision units are constructed to carry out data decision judgment, so that the follow-up targeted analysis on unit step refinement results is facilitated, and the accuracy of the final estimation results is ensured.
Further, the step S500 of inputting the pressure information sets and the stride information into a unit step division model to obtain a plurality of unit step sets of a plurality of unit step types and a plurality of sub-numbers of the unit step types, and further includes:
step S510: based on the running sample data, acquiring a plurality of sample stride information, a plurality of sample pressure size information, a plurality of sample pressure duration information and a plurality of sample pressure position information, and acquiring a plurality of unit step types;
step S520: constructing a stride decision unit based on the plurality of sample stride information;
step S530: constructing a plurality of pressure decision units based on the plurality of sample pressure magnitude information, the plurality of sample pressure duration information and the plurality of sample pressure position information;
step S540: connecting the stride decision unit with the plurality of pressure decision units to obtain the unit stride division model;
step S550: inputting the plurality of pressure information sets and the plurality of stride information into the plurality of pressure decision units and the stride decision units to obtain the plurality of unit stride sets and the plurality of sub-numbers.
Further, based on the plurality of sample stride information, a stride decision unit is constructed, and step S520 of the present application further includes:
step S521: constructing a plurality of layers of stride division decision nodes based on the plurality of pieces of sample stride information, wherein each layer of stride division decision nodes carries out classification decision on the input stride information;
step S522: and obtaining the stride decision unit based on the multi-layer stride division decision node.
Specifically, a predetermined time interval, that is, a collection time range of sample data, is set, and running record data collection is performed on the user as the sample data based on the predetermined time interval. And taking the stride, the pressure size, the pressure duration and the pressure position as information extraction dimensions, extracting multidimensional data of each stride from the sample data, acquiring the plurality of sample stride information, the plurality of sample pressure size information, the plurality of sample pressure duration information and the plurality of sample pressure position information, judging the running intensity based on the data, and defining a multi-level data interval so as to configure the plurality of unit stride types, for example, the larger the pressure is, the shorter the duration is, the larger the unit stride intensity is, and the fat reduction energy efficiency is larger. And further determining a multi-level decision node based on the plurality of sample stride information, and constructing the stride decision unit.
Specifically, the multi-layer stride dividing decision node is constructed according to the plurality of sample stride information, a plurality of sample stride information in the plurality of sample stride information is selected at random, based on a decision tree algorithm, the sample stride information is configured for each layer stride dividing decision node as a threshold for data dividing decision, each layer stride dividing decision node can perform two-class dividing decision on the input stride information, the input stride information is divided into one class and the other class which are larger than the threshold in the layer stride dividing decision node, and the two-class result is input into the stride dividing decision node of the upper layer to continue the two-class dividing decision. For example, the median of the stride information of a plurality of samples may be sequentially taken as a hierarchical decision threshold, and two classifications of the stride information may be performed layer by layer, so as to finally determine a plurality of decision data sets, where each decision data set includes a stride information section, each section corresponds to a stride level, and further each step is divided into different unit steps according to the stride, and the more decision data sets obtained by dividing are, the more corresponding division results are accurate. And carrying out hierarchical linking association on the multi-layer stride division decision nodes to form the stride decision unit. The stride decision unit makes a data decision based on a qualitative decision mechanism so as to improve the data decision efficiency and accuracy.
Further, based on the pressure information of the plurality of samples, a pressure decision unit is constructed and used for carrying out decision attribution analysis of the pressure; constructing a pressure duration decision unit based on the pressure duration information of the plurality of samples, wherein the pressure duration decision unit is used for carrying out decision attribution analysis of the pressure duration; and constructing a pressure position decision unit based on the pressure position information of the plurality of samples, wherein the pressure position decision unit is used for carrying out decision analysis of the pressure position, and integrating and summarizing the pressure size decision unit, the pressure duration decision unit and the pressure position decision unit to generate the plurality of pressure decision units. The construction method and the operation mechanism of the pressure decision units and the stride decision units are the same, and only specific function differences exist. And connecting the stride decision unit with the plurality of pressure decision units, for example, sequentially connecting a top layer division decision node and a bottom layer division decision node of each decision unit, and generating the unit stride division model.
And inputting the multiple pressure information sets and the multiple stride information into the unit stride division model, performing multi-level division of matching data based on the multiple pressure decision units and the stride decision units by using decision units corresponding to data identification matching, determining multiple decision results and summarizing and judging, dividing multiple unit strides contained in a whole period of movement based on the multiple decision results and summarizing and judging, obtaining multiple unit stride sets, namely multiple unit stride groups, and determining multiple sub-numbers contained in each unit stride set. The decision analysis of the motion data is carried out through the unit step division model, so that the accuracy and objectivity of a decision result can be effectively ensured, corresponding decision units are constructed aiming at different data dimensions, the pertinence of the data analysis can be ensured, and the decision efficiency is improved.
Step S600: inputting the sub-numbers and the health sign information set into a fat-reducing effect evaluation model to obtain a fat-reducing effect evaluation result of the running exercise currently completed by the user.
Further, as shown in fig. 3, the multiple sub-numbers and the health sign information set are input into a fat-reducing effect evaluation model to obtain a fat-reducing effect evaluation result of the running exercise currently completed by the user, and step S600 of the present application further includes:
step S610: based on running fat reduction data of a plurality of sample users, acquiring a plurality of sample health sign information sets, a plurality of sample sub-step number sets and a plurality of sample fat reduction effect levels;
step S620: the plurality of sample health sign information sets, the plurality of sample sub-step number sets and the plurality of sample lipid-lowering effect grades are used as construction data to construct the lipid-lowering effect evaluation model;
step S630: inputting the sub-numbers and the health sign information set into the fat-reducing effect evaluation model to obtain the fat-reducing effect grade of the user as the fat-reducing effect evaluation result.
Specifically, running fat reduction data of the plurality of sample users are collected by performing big data investigation statistics. Based on the running fat-reducing data, extracting age information, weight information, height information and body fat rate information of the plurality of sample users, and carrying out information association to generate a plurality of information strings as a plurality of sample health sign information sets; extracting the plurality of sample sub-step number sets, namely a summary data set of unit step types and covering sub-step numbers in data corresponding to the plurality of sample users; and based on the fat reduction evaluation standard, defining a multi-stage fat reduction effect, evaluating the plurality of sample users, and obtaining the fat reduction effect grades of the plurality of samples.
Wherein the plurality of sample health sign information sets, the plurality of sample sub-step sets, the plurality of sample lipid-lowering effect levels and the plurality of sample users are in one-to-one correspondence and are used as construction data, wherein the plurality of sample health sign information sets and the plurality of sample sub-step sets are decision information, the plurality of sample lipid-lowering effect levels are decision results, and carrying out information association connection, generating the fat reduction effect evaluation model through model training verification, inputting the plurality of sub-numbers and the plurality of health sign information sets into the fat reduction effect evaluation model, determining the fat reduction effect grade of the user through data identification matching, and carrying out model output, and taking the grade as the fat reduction effect evaluation result. The judgment of the fat reducing effect is carried out by collecting the actual fat reducing data training model, so that the universality and the accuracy of a model analysis mechanism can be ensured, and the fat reducing effect evaluation result is ensured to be consistent with the actual result. According to the embodiment of the application, the fat reducing effect is evaluated according to the number of different unit steps and the sign of the user, and the higher the number of unit steps with high strength is, the better the fat reducing effect is.
Further, the step S620 of constructing the fat-reducing effect evaluation model using the plurality of sample health sign information sets, the plurality of sample sub-step number sets, and the plurality of sample fat-reducing effect levels as construction data further includes:
step S621: marking data of the plurality of sample health sign information sets, the plurality of sample sub-step number sets and the plurality of sample fat reduction effect levels, and dividing the data to obtain a training set, a verification set and a test set;
step S622: based on a BP neural network, constructing the fat-reducing effect evaluation model, wherein the input data of the fat-reducing effect evaluation model is a health sign information set and sub-numbers of a plurality of step unit types, and the output data is a fat-reducing effect grade;
step S623: performing supervision training on the fat reduction effect evaluation model by adopting the training set until the fat reduction effect evaluation model converges or the accuracy reaches a preset requirement;
step S624: and verifying and testing the fat reducing effect evaluation model by adopting the verification set and the test set, and obtaining the fat reducing effect evaluation model if the accuracy rate meets the preset requirement.
Specifically, the plurality of sample health sign information sets, the plurality of sample sub-step number sets and the plurality of sample fat-reducing effect levels are used as construction data to carry out data generic labeling, so that the follow-up rapid data identification and distinguishing are facilitated. And taking the sample health sign information set and the sample sub-step number set of the same sample user as source data to be evaluated, and carrying out information association on the corresponding lipid reduction effect level as an evaluation result so as to define a data dividing proportion, and dividing the construction data into the training set, the verification set and the test set based on the data dividing proportion. And establishing the fat reduction effect evaluation model based on a primary framework of a BP neural network determination model, wherein input data of the fat reduction effect evaluation model is the sub-number of the health sign information set and the step unit types, and output data is the fat reduction effect grade. Inputting the training set into the fat reduction effect evaluation model for supervision training, further inputting the verification set and the test set into the fat reduction effect evaluation model after training, performing correction and judgment on a model output result and the fat reduction effect level in input data so as to determine the model output accuracy, setting a preset requirement of the accuracy, for example, 99%, and when the accuracy accords with the preset requirement, indicating that the evaluation mechanism of the current model is better, and taking the current model as the finally determined fat reduction effect evaluation model; and when the accuracy rate does not meet the preset requirement, adjusting the data dividing proportion or adjusting the content of the data dividing result, and re-performing model training, verification and test until the accuracy rate of the model reaches the standard.
In one possible embodiment, after obtaining the evaluation result of the fat reducing effect of the user, the weight and body fat level data of the user can be obtained through detection means such as a weight scale and a body fat scale in the prior art, and the data are continuously fed back to the personal end and the intelligent sports terminal according to a certain frequency in combination with the evaluation result of the fat reducing effect, wherein the personal end is the user end, and the intelligent sports terminal is the sports teacher end of the user, so that a new exercise scheme can be formulated in a further targeted manner, the exercise quantity of the user can be adjusted, and the exercise health level of the user can be improved.
Examples
Based on the same inventive concept as the user fat reduction effect estimation method based on intelligent sports shoe analysis in the foregoing embodiments, as shown in fig. 4, the present application provides a user fat reduction effect estimation system based on intelligent sports shoe analysis, the system comprising:
the step number acquisition module 11 is used for acquiring the step number of running of the user through the step counting analysis module and the pressure sensing module when the user uses the intelligent sports shoes to run;
the physical sign information acquisition module 12 is used for acquiring multiple types of physical sign information of the user and acquiring a physical sign information set;
the pressure information acquisition module 13 is used for acquiring multiple types of information of pressure generated by each step in running of the user through the pressure sensing module to acquire multiple pressure information sets;
a stride information obtaining module 14, where the stride information obtaining module 14 is configured to obtain, through the step counting analysis module, a stride of each step in running of the user, and obtain a plurality of stride information;
the model analysis module 15 is configured to input the multiple pressure information sets and the multiple stride information into a unit stride division model, obtain multiple unit stride sets of multiple unit stride types, and obtain multiple sub-numbers of the multiple unit stride types, where a sum of the multiple sub-numbers is the stride number;
the result obtaining module 16 is configured to input the plurality of sub-numbers and the health sign information set into a fat reduction effect evaluation model, and obtain a fat reduction effect evaluation result of the running exercise currently completed by the user.
Further, the system further comprises:
the information acquisition module is used for acquiring age information, weight information, height information and body fat rate information of the user;
the information generation module is used for generating the health sign information set based on the age information, the weight information, the height information and the body fat rate information.
Further, the system further comprises:
the pressure position acquisition module is used for acquiring the pressure position of pressure generated by each step in running of the user through the pressure sensing module to acquire a plurality of pressure position information;
the pressure acquisition module is used for acquiring the pressure of pressure generated by each step in running of the user and acquiring a plurality of pieces of pressure information;
the pressure duration acquisition module is used for acquiring the pressure duration time of pressure generated by each step in running of the user and acquiring a plurality of pieces of pressure duration information;
the pressure information generation module is used for generating the pressure information sets based on the pressure position information, the pressure size information, the pressure duration information and the step number.
Further, the system further comprises:
the type acquisition module is used for acquiring a plurality of sample stride information, a plurality of sample pressure size information, a plurality of sample pressure duration information and a plurality of sample pressure position information based on running sample data, and acquiring the plurality of unit step types;
the stride decision unit construction module is used for constructing a stride decision unit based on the plurality of sample stride information;
the pressure decision unit construction module is used for constructing a plurality of pressure decision units based on the plurality of sample pressure size information, the plurality of sample pressure duration information and the plurality of sample pressure position information;
the model acquisition module is used for connecting the stride decision unit and the pressure decision units to obtain the unit stride division model;
the parameter information acquisition module is used for inputting the pressure information sets and the stride information into the pressure decision units and the stride decision units to obtain the unit stride sets and the sub-step numbers.
Further, the system further comprises:
the decision node construction module is used for constructing multi-layer stride dividing decision nodes based on the plurality of sample stride information, and each layer stride dividing decision node carries out classification decision on the input stride information;
and the stride decision unit acquisition module is used for acquiring the stride decision unit based on the multi-layer stride dividing decision nodes.
Further, the system further comprises:
the sample data acquisition module is used for acquiring a plurality of sample health sign information sets, a plurality of sample sub-step number sets and a plurality of sample fat reduction effect grades based on running fat reduction data of a plurality of sample users;
the model construction module is used for constructing the fat reduction effect evaluation model by adopting the plurality of sample health sign information sets, the plurality of sample sub-step number sets and the plurality of sample fat reduction effect grades as construction data;
and the evaluation result determining module is used for inputting the plurality of sub-numbers and the health sign information set into the fat reduction effect evaluation model to obtain the fat reduction effect grade of the user as the fat reduction effect evaluation result.
Further, the system further comprises:
the sample dividing module is used for marking data of the plurality of sample health sign information sets, the plurality of sample sub-step number sets and the plurality of sample fat reduction effect levels and dividing the data to obtain a training set, a verification set and a test set;
the fat-reducing effect evaluation model construction module is used for constructing the fat-reducing effect evaluation model based on a BP neural network, wherein input data of the fat-reducing effect evaluation model are a health sign information set and sub-numbers of a plurality of step unit types, and output data are fat-reducing effect grades;
the model training module is used for performing supervision training on the fat reduction effect evaluation model by adopting the training set until the fat reduction effect evaluation model converges or the accuracy reaches a preset requirement;
the model checking module is used for checking and testing the fat reducing effect evaluation model by adopting the checking set and the testing set, and if the accuracy rate meets the preset requirement, the fat reducing effect evaluation model is obtained.
Through the foregoing detailed description of a method for estimating a user's fat-reducing effect based on intelligent sports shoe analysis, those skilled in the art can clearly know a method and a system for estimating a user's fat-reducing effect based on intelligent sports shoe analysis in this embodiment, and for the device disclosed in the embodiment, since the device corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The method is characterized by being applied to an intelligent sports shoe, wherein the intelligent sports shoe comprises a pressure sensing module and a step counting analysis module, and the method comprises the following steps:
when a user uses the intelligent sports shoes to run, the step counting analysis module and the pressure sensing module are used for acquiring the step number of running of the user;
acquiring multiple types of health sign information of the user, and acquiring a health sign information set;
the pressure sensing module is used for acquiring multiple types of information of pressure generated by each step in running of the user and acquiring multiple pressure information sets;
the step counting analysis module is used for obtaining the steps of each step in running of the user and obtaining a plurality of step information;
inputting the pressure information sets and the stride information into a unit stride division model to obtain a plurality of unit stride sets of a plurality of unit stride types, and obtaining a plurality of sub-numbers of the unit stride types, wherein the sum of the sub-numbers is the stride number;
inputting the sub-numbers and the health sign information set into a fat-reducing effect evaluation model to obtain a fat-reducing effect evaluation result of the running exercise currently completed by the user.
2. The method of claim 1, wherein obtaining multiple types of health sign information for the user, obtaining a set of health sign information, comprises:
collecting age information, weight information, height information and body fat rate information of the user;
the health sign information set is generated based on the age information, weight information, height information, and body fat rate information.
3. The method of claim 1, wherein obtaining, by the pressure sensing module, multiple types of information for generating pressure for each step in running by the user, and obtaining multiple sets of pressure information, comprises:
the pressure sensing module is used for acquiring pressure positions of pressure generated by each step in running of the user and acquiring a plurality of pressure position information;
acquiring the pressure of pressure generated by each step in running of the user, and acquiring a plurality of pieces of pressure information;
acquiring pressure duration time of pressure generated by each step in running of the user, and acquiring a plurality of pieces of pressure duration information;
the plurality of pressure information sets are generated based on the plurality of pressure position information, the plurality of pressure magnitude information, the plurality of pressure duration information, and the number of steps.
4. The method of claim 1, wherein inputting the plurality of sets of pressure information and the plurality of stride information into a unit stride division model, obtaining a plurality of unit stride sets for a plurality of unit stride types, and obtaining a plurality of sub-numbers for a plurality of unit stride types, comprises:
based on the running sample data, acquiring a plurality of sample stride information, a plurality of sample pressure size information, a plurality of sample pressure duration information and a plurality of sample pressure position information, and acquiring a plurality of unit step types;
constructing a stride decision unit based on the plurality of sample stride information;
constructing a plurality of pressure decision units based on the plurality of sample pressure magnitude information, the plurality of sample pressure duration information and the plurality of sample pressure position information;
connecting the stride decision unit with the plurality of pressure decision units to obtain the unit stride division model;
inputting the plurality of pressure information sets and the plurality of stride information into the plurality of pressure decision units and the stride decision units to obtain the plurality of unit stride sets and the plurality of sub-numbers.
5. The method of claim 4, wherein constructing a stride decision unit based on the plurality of sample stride information comprises:
constructing a plurality of layers of stride division decision nodes based on the plurality of pieces of sample stride information, wherein each layer of stride division decision nodes carries out classification decision on the input stride information;
and obtaining the stride decision unit based on the multi-layer stride division decision node.
6. The method of claim 1, wherein inputting the plurality of sub-numbers and the set of health sign information into a fat reduction effect assessment model to obtain a fat reduction effect assessment result of the running exercise currently completed by the user comprises:
based on running fat reduction data of a plurality of sample users, acquiring a plurality of sample health sign information sets, a plurality of sample sub-step number sets and a plurality of sample fat reduction effect levels;
the plurality of sample health sign information sets, the plurality of sample sub-step number sets and the plurality of sample lipid-lowering effect grades are used as construction data to construct the lipid-lowering effect evaluation model;
inputting the sub-numbers and the health sign information set into the fat-reducing effect evaluation model to obtain the fat-reducing effect grade of the user as the fat-reducing effect evaluation result.
7. The method of claim 6, wherein constructing the lipid-lowering effect assessment model using the plurality of sample health sign information sets, the plurality of sample sub-number sets, and the plurality of sample lipid-lowering effect levels as construction data comprises:
marking data of the plurality of sample health sign information sets, the plurality of sample sub-step number sets and the plurality of sample fat reduction effect levels, and dividing the data to obtain a training set, a verification set and a test set;
based on a BP neural network, constructing the fat-reducing effect evaluation model, wherein the input data of the fat-reducing effect evaluation model is a health sign information set and sub-numbers of a plurality of step unit types, and the output data is a fat-reducing effect grade;
performing supervision training on the fat reduction effect evaluation model by adopting the training set until the fat reduction effect evaluation model converges or the accuracy reaches a preset requirement;
and verifying and testing the fat reducing effect evaluation model by adopting the verification set and the test set, and obtaining the fat reducing effect evaluation model if the accuracy rate meets the preset requirement.
8. The utility model provides a user's fat reduction effect estimation system based on intelligent sports shoes analysis which characterized in that includes pressure sensing module and meter step analysis module, the system includes:
the step number acquisition module is used for acquiring the step number of running of the user through the step counting analysis module and the pressure sensing module when the user uses the intelligent sports shoes to run;
the system comprises a physical sign information acquisition module, a physical sign information acquisition module and a user identification module, wherein the physical sign information acquisition module is used for acquiring multiple types of physical sign information of the user and acquiring a physical sign information set;
the pressure information acquisition module is used for acquiring multiple types of information of pressure generated by each step in running of the user through the pressure sensing module to acquire multiple pressure information sets;
the stride information acquisition module is used for acquiring stride of each step in running of the user through the step counting analysis module to acquire a plurality of stride information;
the model analysis module is used for inputting the pressure information sets and the stride information into a unit step division model, obtaining a plurality of unit step sets of a plurality of unit step types, and obtaining a plurality of sub-step numbers of the unit step types, wherein the sum of the sub-step numbers is the step number;
the result acquisition module is used for inputting the sub-numbers and the health sign information set into a fat reduction effect evaluation model to obtain a fat reduction effect evaluation result of the running exercise currently completed by the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310344500.6A CN116687390A (en) | 2023-04-03 | 2023-04-03 | User fat reduction effect estimation method and system based on intelligent sports shoe analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310344500.6A CN116687390A (en) | 2023-04-03 | 2023-04-03 | User fat reduction effect estimation method and system based on intelligent sports shoe analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116687390A true CN116687390A (en) | 2023-09-05 |
Family
ID=87826550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310344500.6A Pending CN116687390A (en) | 2023-04-03 | 2023-04-03 | User fat reduction effect estimation method and system based on intelligent sports shoe analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116687390A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117435932A (en) * | 2023-12-21 | 2024-01-23 | 广州中科医疗美容仪器有限公司 | Parameter control method and system for fat reducing equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101669814A (en) * | 2008-09-08 | 2010-03-17 | 广州盛华信息技术有限公司 | Shoe and human body physical sign monitoring system |
| CN104091080A (en) * | 2014-07-14 | 2014-10-08 | 中国科学院合肥物质科学研究院 | Intelligent bodybuilding guidance system and closed-loop guidance method thereof |
| CN105004453A (en) * | 2015-08-04 | 2015-10-28 | 安德润普科技开发（深圳）有限公司 | Pressure monitoring method and pressure monitoring system for intelligent pressure pads |
| US20160007885A1 (en) * | 2007-10-15 | 2016-01-14 | Alterg, Inc. | Method of gait evaluation and training with differential pressure system |
| CN106725503A (en) * | 2016-11-21 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | A kind of healthy corrective shoes based on Internet of Things, sport monitoring device and method |
| US20180192935A1 (en) * | 2015-06-29 | 2018-07-12 | Lg Electronics Inc. | Portable device and physical strength evaluation method thereof |
| CN115719645A (en) * | 2021-08-27 | 2023-02-28 | 华为技术有限公司 | Health management method and system and electronic equipment |
-
2023
- 2023-04-03 CN CN202310344500.6A patent/CN116687390A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160007885A1 (en) * | 2007-10-15 | 2016-01-14 | Alterg, Inc. | Method of gait evaluation and training with differential pressure system |
| CN101669814A (en) * | 2008-09-08 | 2010-03-17 | 广州盛华信息技术有限公司 | Shoe and human body physical sign monitoring system |
| CN104091080A (en) * | 2014-07-14 | 2014-10-08 | 中国科学院合肥物质科学研究院 | Intelligent bodybuilding guidance system and closed-loop guidance method thereof |
| US20180192935A1 (en) * | 2015-06-29 | 2018-07-12 | Lg Electronics Inc. | Portable device and physical strength evaluation method thereof |
| CN105004453A (en) * | 2015-08-04 | 2015-10-28 | 安德润普科技开发（深圳）有限公司 | Pressure monitoring method and pressure monitoring system for intelligent pressure pads |
| CN106725503A (en) * | 2016-11-21 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | A kind of healthy corrective shoes based on Internet of Things, sport monitoring device and method |
| CN115719645A (en) * | 2021-08-27 | 2023-02-28 | 华为技术有限公司 | Health management method and system and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117435932A (en) * | 2023-12-21 | 2024-01-23 | 广州中科医疗美容仪器有限公司 | Parameter control method and system for fat reducing equipment |
| CN117435932B (en) * | 2023-12-21 | 2024-03-01 | 广州中科医疗美容仪器有限公司 | Parameter control method and system for fat reducing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2535615C2 (en) | Determining user energy consumption | |
| JP2001202265A5 (en) | ||
| CN116687390A (en) | User fat reduction effect estimation method and system based on intelligent sports shoe analysis | |
| CN109856515A (en) | A kind of direct current cables state of insulation judgment method and system | |
| CN109299380A (en) | Exercise personalized recommendation method in online education platform based on multidimensional characteristic | |
| CN111415720B (en) | Training auxiliary method and device based on multiple data acquisition | |
| CN107767191A (en) | A kind of method based on medical big data prediction medicine sales trend | |
| CN116484307B (en) | Cloud computing-based intelligent ring remote control method | |
| CN113701825B (en) | Body-building facility abnormity detection method and system based on artificial intelligence | |
| CN106295805A (en) | Human body maximal oxygen uptake evaluation methodology based on BP neutral net and application thereof | |
| CN106037703A (en) | Cardiorespiratory endurance indirect testing method based on intelligent exercise bicycle | |
| CN116224112A (en) | XGBoost model-based battery impedance spectrum frequency importance analysis method | |
| KR101483218B1 (en) | Activity diagnosis apparatus | |
| KR102151610B1 (en) | Smart fitness system for reducing service quality deviation | |
| Sumida et al. | Smartphone-based heart rate prediction for walking support application | |
| CN117352114B (en) | Recommendation method and system of psychological assessment scale based on clustering algorithm | |
| CN114943707B (en) | Fine cornea deformation identification method and device based on pixel-level cornea biomechanics parameters | |
| CN115774803B (en) | Visual identification method and system for physical examination site | |
| EP4113374A1 (en) | Multi-modal few-shot learning device for user identification using walking pattern based on deep learning ensemble | |
| CN117591354A (en) | Application quality detection method and system for programmable keys | |
| CN111879415B (en) | Temperature measurement management method, device and system | |
| CN114864086A (en) | Disease prediction method based on lung function report template | |
| Yamazaki et al. | Preliminary evaluation of fatigue level estimation by gait sensor | |
| CN117133057A (en) | Physical exercise counting and illegal action distinguishing method based on human body gesture recognition | |
| CN114863166A (en) | Image classification method based on uncertainty measurement and fundus image classification method |
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 |