WO2019228418A1

WO2019228418A1 - Physical state detection method and system based on gait recognition device

Info

Publication number: WO2019228418A1
Application number: PCT/CN2019/089080
Authority: WO
Inventors: 陈涛; 袁宏永; 陈建国; 苏国锋; 孙占辉
Original assignee: 北京辰安科技股份有限公司; 清华大学
Priority date: 2018-05-31
Filing date: 2019-05-29
Publication date: 2019-12-05
Also published as: CN108742637A; CN108742637B

Abstract

A physical state detection method and system (400) based on a gait recognition device. The gait recognition device (410) is built in a cavity of an insole or a sole, and comprises a pressure sensor used to detect the pressure in the cavity. The detection method comprises: periodically sampling pressure measurement data output by the pressure sensor (S110); determining the change law of the pressure in the cavity according to the collected pressure measurement data (S120); recognizing gait information of a pedestrian according to the collected pressure measurement data and the change law of the pressure (S130), the gait information comprising the state of the foot falling to the ground, the stride frequency, the consistency of the paces, and the walking mode; and analyzing the state of the foot falling to the ground, the stride frequency, the consistency of paces, and the walking mode according to the preset detection rules to detect the gait-related physical state information (S140). The method can detect the pedestrian's physical state at any time and conveniently by means of the gait information, and facilitate users to conveniently grip the pedestrian's physical state, thereby improving the user experience.

Description

Body state detection method and detection system based on gait recognition device

Cross-reference to related applications

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on May 31, 2018, with application number 201810549509.X, and with the invention name "body state detection method and detection system based on gait recognition device", all of which are The contents are incorporated herein by reference.

Technical field

The present application relates to the field of body state detection, and in particular, to a body state detection method based on a gait recognition device and a body state detection system.

Background technique

With the development of society, the pace of people's life is gradually accelerating. When people understand their physical health, they usually need to go to the hospital or experience center station to use professional equipment to detect. This detection method, for the user, not only needs to spend a lot of time queuing up for medical examinations, but also costs a certain amount of money, making the detection method of the user's physical health state more complicated and the user experience poor. Therefore, how to detect the user's body state based on a simple measurement device has become an urgent problem.

Summary of the Invention

The purpose of this application is to solve at least one of the above-mentioned technical problems.

For this reason, a first object of the present application is to propose a body state detection method based on a gait recognition device. The method can detect the pedestrian's physical state at any time and conveniently through the gait information, which is convenient for the user to understand the physical health of the pedestrian, and improves the user experience.

The second object of the present application is to propose a physical state detection system.

In order to achieve the above object, a body state detection method based on a gait recognition device according to an embodiment of the first aspect of the present application, the gait recognition device is built in a cavity of an insole or a sole, and the gait recognition device includes a device for detecting The detection method of the air pressure sensor of the air pressure in the cavity includes: periodically sampling the air pressure measurement data output by the air pressure sensor; determining the law of air pressure change in the cavity according to the collected air pressure measurement data; The collected air pressure measurement data and the air pressure change rule are used to identify pedestrian gait information, wherein the gait information includes a foot tribe land state, a step frequency, a front-to-back consistency index, and a walking manner, wherein, the The before and after consistency index refers to the characteristics of the pressure change of the foot tribe, and the characteristics include the waveform of the pressure value, the maximum, minimum, and variance of the pressure, and the mean value; and the state of the foot tribe according to a preset detection rule. , Cadence, inconsistency indicators, and walking styles to analyze body state information related to gait.

In order to achieve the above object, the body state detection system provided by the embodiment of the second aspect of the present application includes a gait recognition device and a detection device, wherein the gait recognition device is built in the cavity of the insole or sole, and the gait recognition The device includes an air pressure sensor for detecting the air pressure in the cavity, and the gait recognition device is configured to periodically sample the air pressure measurement data output by the air pressure sensor, and determine the cavity according to the collected air pressure measurement data. The law of air pressure change in the body, and the gait information of the pedestrian is identified according to the collected air pressure measurement data and the air pressure change law, wherein the gait information includes the state of the foot tribe, the step frequency, and the consistency Indicator and walking method, wherein the front-to-back consistency indicator refers to a characteristic of a change in air pressure value at the foot tribe, and the characteristic includes a waveform of the air pressure value, a maximum air pressure value, a minimum air pressure value, a variance of the air pressure value, and an average value; the detection device For the foot tribe land state, step frequency, front-to-back consistency index, and walking method according to preset detection rules Line analysis to detect the correlation with the gait of the body status information.

According to the body state detection method and the body state detection system based on the gait recognition device according to the embodiments of the present application, the air pressure measurement data output by the air pressure sensor can be sampled periodically, wherein the air pressure sensor is built into the cavity of the insole or sole Inside the body, and determine the pressure change rule in the cavity according to the collected pressure measurement data, and identify the gait information of the pedestrian according to the collected pressure measurement data and the pressure change rule, and according to a preset The detection rule analyzes the gait information to detect body state information related to the gait. That is, the gait information of the pedestrian is recognized by the gait recognition device placed in the cavity of the insole or the sole, and based on the analysis and processing of the gait information, the body health state information related to the gait can be obtained at any time and conveniently. Detecting the physical status of pedestrians, facilitating users to understand the physical health of pedestrians, and improving the user experience.

In addition, the pressure sensor is placed in the cavity of the insole or the sole, and the cavity is compressed and deformed when walking. The pressure inside the cavity changes, and the change is more significant. The measurement value detected by the pressure sensor changes significantly, similar to the amplifier amplification. The change process of the foot tribe land and kicking feet makes the change of the air pressure measurement value further reflect the gait change. Then, while using the air pressure sensor to measure the air pressure, the pedestrian's gait information is directly identified through the air pressure measurement data. The sensor information, and the recognition of gait information through the change of air pressure, improve the recognition accuracy and improve the user experience.

Additional aspects and advantages of the present application will be given in part in the following description, part of which will become apparent from the following description, or be learned through practice of the present application.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

FIG. 1 is a flowchart of a body state detection method based on a gait recognition device according to an embodiment of the present application; FIG.

2 is a diagram illustrating an example of a waveform of pressure measurement data detected by a pressure sensor according to an embodiment of the present application;

3 is a flowchart of a body state detection method based on a gait recognition device according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a body state detection system according to an embodiment of the present application.

Detailed ways

Hereinafter, embodiments of the present application are described in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary, and are intended to explain the present application, and should not be construed as limiting the present application.

The following describes a body state detection method and a body state detection system based on a gait recognition device according to an embodiment of the present application with reference to the drawings.

FIG. 1 is a flowchart of a body state detection method based on a gait recognition device according to an embodiment of the present application. As shown in FIG. 1, the body state detection method based on a gait recognition device may include:

S110. Sampling the air pressure measurement data output by the air pressure sensor periodically.

It should be noted that, in the embodiment of the present application, the gait recognition device may include an air pressure sensor. The air pressure sensor may sensitively detect changes in air pressure, and the air pressure sensor is built into the cavity of the insole (or sole). In this way, when a person walks, the size of the cavity in which the air pressure sensor is placed changes due to the squeeze between the foot and the insole (or sole). The air pressure in the cavity will change significantly as the human body walks. There is an obvious change in air pressure caused by the foot tribal land. When the foot is vacated, the air pressure value returns to normal because the cavity is not deformed. Therefore, this application uses this air pressure change pulse signal to accurately record the foot tribal land. , Vacant state, and derivation of gait information such as the number of steps of the human body, the step frequency, the landing state, the vacant state, the walking style, and the forward and backward consistency indicators. Among them, the forward and backward consistency indicators refer to the changes in air pressure when the tribal land is full. The characteristics may include, but are not limited to, waveforms of pressure values, maximum, minimum, pressure variance, mean, and other characteristic information.

First, the air pressure measurement data detected by the air pressure sensor while the pedestrian is walking can be collected periodically. For example, the air pressure measurement data detected by the air pressure sensor when a pedestrian is walking may be collected every 5 seconds, and the sampling time may be 10 seconds. In other words, every 5 seconds, air pressure measurement data detected by the air pressure sensor within 10 seconds can be collected.

S120. Determine a pressure change rule in the cavity according to the collected pressure measurement data.

Optionally, according to all the collected air pressure measurement data, a change law of the air pressure in the cavity during the acquisition time period is determined. For example, the relationship between air pressure and time can be used to represent the law of air pressure change. For example, as shown in FIG. 2, the collected air pressure measurement data detected by the air pressure sensor while the pedestrian is walking is represented by a correspondence graph between air pressure and time, and the change in air pressure in the cavity can be determined through the correspondence graph. Regularity, for example, the air pressure change in the E time period shown in FIG. 2 is large, and the air pressure change in the F time period is relatively stable.

S130. Identify the gait information of the pedestrian according to the collected pressure measurement data and the pressure change rule. In the embodiment of the present application, the gait information may include, but is not limited to, the state of the foot tribe, the step frequency, Before and after consistency indicators and walking methods.

Optionally, certain algorithmic processing can be performed on the collected air pressure measurement data and the air pressure change rule to obtain pedestrian gait information, such as landing and flying states (also referred to as landing and flying times), step frequency, Before and after consistency indicators, walking style, landing strength, etc. As an example, as shown in FIG. 3, the specific implementation process of identifying the gait information of the pedestrian according to the collected air pressure measurement data and the air pressure change rule may include:

S310. Determine the foot status of the pedestrian at each sampling time according to the collected air pressure measurement data, wherein the foot status includes a landing status and a flying status;

Optionally, determine the air pressure value P _k at the current sampling time from the collected air pressure measurement data, and calculate the difference between the current air pressure value P _k and the normal air pressure value P _N at the current sampling time, If the absolute value of the difference is greater than the target threshold, determine that the foot state of the pedestrian at the current sampling time is a landing state; if the absolute value of the difference is less than the target threshold, determine the pedestrian The foot state at the current sampling time is a vacated state.

It can be understood that when a pedestrian is walking, the foot can be divided into a grounded state and a vacated state. When the foot tribe land, touching the ground and kicking the feet are a continuous process. There is a large change in air pressure, which appears to increase or decrease rapidly, as shown in Figure 2. Among them, the time period E can be regarded as a landing state, and the time period F can be regarded as a foot empty state.

For example, in this example, assuming that the sampling time is k, the pressure value P _k of the current sampling time k can be determined from the collected pressure measurement data, and the pressure value P _k of the current sampling time _k and the current The difference between the normal air pressure value P _N at the sampling time is compared with the target threshold T _p . For example, if the absolute value of the difference is greater than the target threshold T _p , it can be determined that the pedestrian is in the current The foot state at the sampling time is a landing state; if the absolute value of the difference is smaller than the target threshold value T _p , it is determined that the foot state of the pedestrian at the current sampling time is a vacated state. Wherein, in the embodiment of the present application, the normal pressure value at the sampling time is used to indicate the pressure value that is stable and lasts for a certain period of time during the sampling time; the target threshold value T _p can be calculated by the following formula: T _p = 3 to 5 σ, where σ is the mean square error of the current normal pressure value, and T _p represents 3 to 5 times the mean square error σ of the normal pressure value at the current sampling time.

In this way, the absolute value of the difference between the air pressure value P _k and the normal air pressure value P _N at the current sampling time can be used as the determination value of the foot state at the current sampling time, and the size of the determination value and the target threshold value can be compared. Yes, and based on the comparison result, it is determined whether the foot state at the current sampling time is the landing state or the flying state.

S320. Calculate the step frequency of a pedestrian when walking according to the pressure change pattern, the pressure value waveform corresponding to the landing state, and the pressure value waveform corresponding to the vacated state;

Optionally, according to the pressure value waveform corresponding to the landing state, the pressure value waveform of the target landing state is found from the pressure change rule, wherein the target landing state is used to indicate that the cumulative time of the foot tribe land is greater than the first time A time threshold landing state, and an air pressure value waveform of a target empty state from the air pressure change rule according to the air pressure value waveform corresponding to the empty state, wherein the target empty state is used to indicate the time of foot empty A vacated state whose accumulated time is greater than a second time threshold; based on the pressure value waveform of the target landing state and the pressure value waveform of the target vacated state, determining that the target landing state and the target vacated state alternately appear from the pressure change rule. The number of steps of the pedestrian while walking is calculated according to the number of times that the target landing state and the target vacant state alternately appear. For example, if the number of times is one, that is, the number of steps is one step, and the number of times is five times, then the number of steps is five steps. After that, the use time of the air pressure sensor when the pedestrian is walking may be determined, and the step frequency of the pedestrian when walking is calculated according to the number of steps and the use time.

For example, as shown in FIG. 2, when a pedestrian is walking, the air pressure value output by the air pressure sensor will show a certain periodic law, which can be analyzed to obtain the number of walking steps. For example, assuming that the air pressure change rule in the cavity can be represented by the air pressure change waveform shown in FIG. 2, the air pressure change waveform shown in FIG. 2 can be analyzed and processed according to the waveform of the foot tribal land state and the vacated state to obtain walking. Steps M.

In this example, to avoid misjudgment, it is assumed that in one step cycle, the foot needs to have two states of landing and flying, and each state needs to meet a certain length of time. Assume that the accumulated time of the foot tribe land state is t _d , and let the accumulated time of the foot vacated state be t _t ; Let the foot tribe land or vacated state be represented by W, when the foot tribal land is W = 1, and the foot vacated W = 0 Suppose that the time thresholds of foot tribal land and vacant space are t _d1 (that is, the first time threshold) and t _t1 (that is, the second time threshold). The setting of the threshold can be obtained based on the analysis of pedestrians' various motion characteristics. Designed as an adaptive estimation mode. In practical applications, the current state of the foot tribe can be determined in real time, and the cumulative time t _d and t _{t for the} current step landing and vacation of the foot can be recorded in real time. The calculation method of the number of walking steps can be as follows:

Set two conditions:

Condition 1: W = 1 and t _d > t _d1 ;

Condition 2: W = 0 and t _t > t _t1 ;

If condition 1 and condition 2 are satisfied at the same time, it can be determined in real time that the current movement is a walking step, and the current number of walking steps is: M = M + 1. Then, the length of use of the air pressure sensor when the pedestrian is walking is determined. At this time, the step frequency of the pedestrian when walking can be calculated according to the current number of walking steps and the time currently used by the air pressure sensor.

S330. Obtain a consistency index before and after the pressure value according to the collected pressure measurement data.

The front-to-back consistency index mainly refers to characteristics of pressure changes when the foot tribe land includes, but is not limited to, characteristic information such as the waveform of the pressure, the maximum and minimum values of the pressure, the variance of the pressure, and the mean.

S340: Obtain a variation range of the air pressure value according to the collected air pressure measurement data;

Optionally, the maximum pressure and the minimum value of the pressure within a preset time are obtained from the collected pressure measurement data, wherein the preset time is used to indicate a walking time covering at least one step; calculating the preset The difference between the maximum value of the air pressure and the minimum value of the air pressure over time, and the difference is taken as the variation range of the air pressure value.

It can be understood that when pedestrians walk, they can be divided into multiple walking modes such as walking and running. They can also distinguish between slow walking and fast walking for walking, and distinguish between jogging and fast running for running. The walking intensity gradually increases. The intensity of the foot tribe gradually increases, the cavity deformation also gradually increases, and the magnitude of the change in the pressure value detected by the pressure sensor will also increase. Therefore, the pedestrian's Way of walking.

For example, when determining the variation range of the air pressure value, the difference between the maximum air pressure value and the minimum air pressure value over a period of time can be selected from the collected air pressure measurement data as the determination value of the walking mode. For example, assuming that the selected time period (that is, the above-mentioned preset time) is t, where t time needs to be able to cover at least one step of walking time, from the collected pressure measurement data, the current time of t can be selected to be within the time period of t The maximum value of the atmospheric pressure and the minimum value of the atmospheric pressure, and the difference between the maximum value of the atmospheric pressure and the minimum value of the atmospheric pressure is taken as the variation range of the atmospheric pressure value.

S350. Determine the walking mode of the pedestrian when walking according to the variation range of the air pressure value.

Optionally, when the variation range of the air pressure value is smaller than the first determination threshold, determining that the walking mode is slow walking; when the variation range of the air pressure value is greater than the first determination threshold and less than the second determination threshold , Determining that the walking mode is fast walking; determining that the walking mode is jogging when the variation range of the air pressure value is greater than the second determination threshold value and less than the third determination threshold value; When the third determination threshold is specified, it is determined that the walking mode is fast running.

For example, suppose that Pmax is the maximum value of air pressure during the time period t from the current moment, and let Pmin be the minimum value of air pressure during the time period t from the current moment, and the difference between the maximum pressure and the minimum pressure is: Pm = Pmax -Pmin, wherein the difference Pm is the variation range of the pressure value;

Through actual walking experiments, the Pm value range under different walking modes can be determined and set as the determination threshold for various walking modes, as follows:

If Pm <the first decision threshold Pm1, the walking method is slow walking; if Pm1 <Pm <the second decision threshold Pm2, the walking method is fast walking; if Pm2 <Pm <the third decision threshold Pm3, the walking method is Jog; if Pm> Pm3, the walking mode is fast running. Therefore, the variation range of the air pressure value output by the air pressure sensor can be matched with the determination threshold in various walking modes to identify the walking mode of the pedestrian when walking.

In summary, the gait information of the pedestrian can be obtained through the above steps S310 to S350, such as the foot tribe land state, the step frequency, the consistency index before and after the air pressure value, and the walking manner.

S140: Analyze the foot tribe's land state, step frequency, front-to-back consistency index, and walking mode according to preset detection rules to detect body state information related to gait.

Optionally, a type of body state detection for pedestrians is determined first, wherein the detection type includes a fatigue detection type, a body defect detection type, and the like. After that, a corresponding detection rule can be selected according to the type of body state detection. Then, from the corresponding detection rules, a reference waveform, a reference step frequency, and a reference consistency of the landing state of the pedestrian within the target time can be selected respectively. Indicators and reference walking methods. Then, the reference waveform of the landing state is matched with the waveform of the identified foot tribe land state, and the reference cadence is matched with the identified cadence, and the reference is consistent. Matching the sexual index with the identified consistency index, and matching the reference walking pattern with the identified walking pattern. Finally, the body state information of the pedestrian is determined according to the matching result.

For example, when the physical state detection type is a fatigue detection type, a corresponding detection rule may be selected first. After that, the waveform of the identified foot tribe land status can be matched with the reference waveform of the ground landing in the detection rule. For example, it is determined that the waveform of the identified foot tribe land changes with respect to the reference waveform. The trend is relatively slow; and, it is determined that the number of identified steps becomes smaller than the number of reference steps within a certain period of time, and the walking method identified based on the collected air pressure measurement data is not consistent with the reference walking method, For example, the identified walking mode is walking, and the reference walking corresponding to the collected air pressure measurement data should be fast walking. Therefore, according to the above three judgments, it can be determined that the pedestrian is currently walking in fatigue. status. That is, each parameter in the gait information can be matched with a reference value corresponding to each parameter described in the detection rule red to determine whether the pedestrian currently reaches a condition of fatigue status, and if so, can determine that the pedestrian is currently In a fatigue state, the pedestrian may be reminded of fatigue at this time.

As another example, when the physical state detection type is a physical defect detection type, it is assumed that a plurality of models are included in a detection rule corresponding to the physical defect detection type, wherein each model corresponds to a physical defect type. The model calculates and judges the identified gait information to determine the physical health status corresponding to the gait information, such as whether the pedestrian has a physical defect problem, and if so, determines which type of physical defect it belongs to. That is, the identified gait information may be estimated and predicted according to multiple models in the corresponding detection rule to obtain the type of physical defect corresponding to the identified gait information.

It can be understood that the phenomenon presented by the air pressure measurement data detected by the air pressure sensor when a pedestrian with a physical defect is walking is very different from the phenomenon presented by the air pressure measurement data detected by a normal person while walking. Therefore, the corresponding model of each type of body defect can be used to train its corresponding model. For example, a pedestrian with poliomyelitis sequelae can make the left and right foot fall frequency and step size different when walking, and can collect the pedestrian walking The air pressure measurement data detected by the air pressure sensor is used as training data to train a model for the type of body defect. In this way, in actual detection, the gait information actually recognized can be predicted according to a pre-trained model to obtain the current pedestrian. Type of body state.

It should be noted that the preset detection rules can be obtained based on actual experimental data. If a certain abnormal body state needs to be detected and judged, multiple sets of abnormal body state data can be collected to extract the waveform of the air pressure value, the maximum and minimum air pressure values. , Pressure value variance, mean value and other characteristic values. Based on these feature values, the value range of each feature value when the body is abnormal can be obtained, and the determination threshold of each feature value can be set. The joint judgment can be used to determine whether the body state is abnormal; or, machine learning algorithms can be used to The feature data of each sample is used to learn the original data or feature value data, and then the learned model parameters are used to predict whether the body state is abnormal.

According to the body state detection method based on the gait recognition device in the embodiment of the present application, the air pressure measurement data output by the air pressure sensor can be sampled periodically, wherein the air pressure sensor is built in the cavity of the insole or the sole of the shoe, and according to the acquisition The obtained air pressure measurement data determines the air pressure change law in the cavity, and according to the collected air pressure measurement data and the air pressure change law, recognizes the gait information of the pedestrian, and according to a preset detection rule, Gait information is analyzed to detect body state information related to gait. That is, the gait information of the pedestrian is recognized by the gait recognition device placed in the cavity of the insole or the sole, and based on the analysis and processing of the gait information, the body health state information related to the gait can be obtained at any time and conveniently. Detecting the physical status of pedestrians, facilitating users to understand the physical health of pedestrians, and improving the user experience.

In addition, the pressure sensor is placed in the cavity of the insole or the sole, and the cavity is compressed and deformed when walking. The pressure inside the cavity changes, and the change is more significant. The measurement value detected by the pressure sensor changes significantly, similar to the amplifier amplification. The change process of the foot tribe land and kicking feet makes the change of the air pressure measurement value further reflect the gait change, and then uses the air pressure sensor to measure the air pressure and directly recognize the pedestrian's gait information through the air pressure measurement data, making full use of the air pressure The sensor information, and the recognition of gait information through the change of air pressure, improve the recognition accuracy and improve the user experience.

Corresponding to the body state detection method based on the gait recognition device provided by the foregoing embodiments, an embodiment of the present application also proposes a body state detection system. The physical state detection methods provided by the foregoing embodiments correspond to each other. Therefore, the implementation of the foregoing physical state detection method is also applicable to the physical state detection system provided by this embodiment, and will not be described in detail in this embodiment. FIG. 4 is a schematic structural diagram of a body state detection system according to an embodiment of the present application. As shown in FIG. 4, the physical state detection system 400 may include a gait recognition device 410 and a detection device 420. The gait recognition device 410 is built in the cavity of the insole or the sole, and the gait recognition device 410 may include a pressure sensor for detecting the pressure inside the cavity.

The gait recognition device 410 may be configured to periodically sample the air pressure measurement data output by the air pressure sensor, determine the law of air pressure change in the cavity according to the collected air pressure measurement data, and according to the collected air pressure measurement The data and the pressure change rule identify the gait information of the pedestrian, wherein the gait information includes the foot tribe land state, the step frequency, the consistency index and the walking style;

The detection device 420 may be configured to analyze the foot tribe land state, step frequency, front-to-back consistency index, and walking mode according to a preset detection rule to detect body state information related to gait.

Optionally, in an embodiment of the present application, the gait recognition device 410 recognizes the gait information of the pedestrian according to the collected pressure measurement data and the pressure change rule. The specific implementation manner of the gait information may be as follows: The collected air pressure measurement data determines a foot state of the pedestrian at each sampling time, wherein the foot state includes a landing state and a vacated state; according to the law of air pressure change, the landing state corresponds to The air pressure value waveform and the air pressure value waveform corresponding to the vacated state are used to calculate the step frequency of the pedestrian when walking; obtain the consistency index before and after the air pressure value according to the collected air pressure measurement data; and according to the collected air pressure measurement The data acquires a variation range of the air pressure value; and determines a walking mode of the pedestrian when walking according to the variation range of the air pressure value.

In the embodiment of the present application, the gait recognition device 410 determines the foot state of the pedestrian at each sampling time according to the collected air pressure measurement data, and a specific implementation manner may be as follows: Determine the air pressure value P _k at the current sampling time in the air pressure measurement data; calculate the difference between the air pressure value P _k at the current sampling time and the normal air pressure value P _N at the current sampling time; if the absolute value of the difference is greater than A target threshold value, determine the foot state of the pedestrian at the current sampling time as a landing state; if the absolute value of the difference is less than the target threshold value, determine the foot of the pedestrian at the current sampling time The state is vacated.

In the embodiment of the present application, the gait recognition device 410 calculates the number of steps of the pedestrian when walking according to the pressure change rule, the pressure value waveform corresponding to the landing state, and the pressure value waveform corresponding to the vacant state. The specific implementation of the method can be as follows: according to the pressure value waveform corresponding to the landing state, find the pressure value waveform of the target landing state from the pressure change rule, wherein the target landing state is used to indicate the cumulative time of the foot tribe land time A landing state greater than a first time threshold; and an air pressure value waveform of a target empty state is found from the air pressure change rule according to the air pressure value waveform corresponding to the empty state, wherein the target empty state is used to indicate foot empty The cumulative state of time is greater than the second time threshold for the state of vacation; according to the pressure value waveform of the target landing state and the pressure value waveform of the target vacancy state, the target landing state and the target vacancy state are determined from the pressure change rule. The number of times of alternate appearance; the number of times of alternate appearance according to the target landing state and the target vacant state Calculating the number of steps of the pedestrian is walking; length when the air pressure during walking of the pedestrian is determined using a sensor; according to the number of steps and the use of long, when the calculated pitch pedestrian walking.

In the embodiment of the present application, the gait recognition device 410 obtains the variation range of the air pressure value according to the collected air pressure measurement data, and the specific implementation manner may be as follows: from the collected air pressure measurement data, a Maximum air pressure and minimum air pressure, wherein the preset time is used to indicate a walking time covering at least one step; calculating a difference between the maximum air pressure and the minimum air pressure within the preset time, and The difference is taken as the change range of the pressure value.

In the embodiment of the present application, the gait recognition device 410 may determine the walking mode of the pedestrian when walking according to the variation range of the air pressure value, and the specific implementation manner may be as follows: when the variation range of the air pressure value is less than the first determination threshold , Determining that the walking mode is slow walking; when the change in air pressure value is greater than the first determination threshold and less than the second determination threshold, determining that the walking mode is fast walking; when the pressure value changes When it is greater than the second determination threshold and is smaller than the third determination threshold, the walking mode is determined to be jogging; when the pressure value variation range is greater than the third determination threshold, the walking mode is determined to be fast running.

As an example, after obtaining the gait information identified by the gait recognition device 410, the detection device 420 may first determine a type of body state detection for the pedestrian, wherein the detection type includes a fatigue detection type and a physical defect detection. Type; the corresponding detection rule is selected according to the type of body state detection; from the detection rule, a reference waveform, a reference cadence, a reference consistency index before and after the landing state of a pedestrian within a target time, and Reference walking mode; matching the reference waveform of the landing state with the waveform of the identified foot tribal land state, matching the reference cadence with the identified cadence, and comparing the reference The front-to-back consistency index is matched with the identified front-to-back consistency index, and the reference walking manner is matched with the identified walking manner; and the physical state information of the pedestrian is determined according to the matching result.

According to the body condition detection system in the embodiment of the present application, the gait recognition device may periodically sample the pressure measurement data output by the pressure sensor, and determine the pressure change rule in the cavity according to the collected pressure measurement data, and Gait information of a pedestrian is identified according to the collected air pressure measurement data and the air pressure change rule. The detection device analyzes the gait information according to a preset detection rule to detect body state information related to the gait. That is, the gait information of the pedestrian is recognized by the gait recognition device placed in the cavity of the insole or the sole, and based on the analysis and processing of the gait information, the body health state information related to the gait can be obtained at any time and conveniently. Detecting the physical status of pedestrians, facilitating users to understand the physical health of pedestrians, and improving the user experience.

In the description of this application, it should be understood that the terms “first” and “second” are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "plurality" is at least two, for example, two, three, etc., unless it is specifically and specifically defined otherwise.

In the description of this specification, the description with reference to the terms “one embodiment”, “some embodiments”, “examples”, “specific examples”, or “some examples” and the like means specific features described in conjunction with the embodiments or examples , Structure, materials, or features are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and combine different embodiments or examples and features of the different embodiments or examples without conflicting one another.

Any process or method description in a flowchart or otherwise described herein can be understood as representing a module, fragment, or portion of code that includes one or more executable instructions for implementing a particular logical function or step of a process And, the scope of the preferred embodiments of the present application includes additional implementations, in which the functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved, which should It is understood by those skilled in the art to which the embodiments of the present application pertain.

The logic and / or steps represented in the flowchart or otherwise described herein, for example, a sequenced list of executable instructions that can be considered to implement a logical function, can be embodied in any computer-readable medium, For the instruction execution system, device, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from the instruction execution system, device, or device), or combine these instruction execution systems, devices, or devices Or equipment. For the purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections (electronic devices) with one or more wirings, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, because, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or other suitable Processing to obtain the program electronically and then store it in computer memory.

It should be understood that each part of the application may be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods may be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it may be implemented using any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

A person of ordinary skill in the art can understand that all or part of the steps carried by the methods in the foregoing embodiments may be implemented by a program instructing related hardware. The program may be stored in a computer-readable storage medium. The program is When executed, one or a combination of the steps of the method embodiment is included.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing module, or each unit may exist separately physically, or two or more units may be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

The aforementioned storage medium may be a read-only memory, a magnetic disk, or an optical disk. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on the present application. Those skilled in the art can interpret the above within the scope of the present application. Embodiments are subject to change, modification, substitution, and modification.

Claims

A body state detection method based on a gait recognition device, characterized in that the gait recognition device is built into a cavity of an insole or sole, and the gait recognition device includes an air pressure sensor for detecting the air pressure in the cavity The detection method includes the following steps:

Periodically sampling the air pressure measurement data output by the air pressure sensor;

Determining a variation rule of the air pressure in the cavity according to the collected air pressure measurement data;

Gait information of pedestrians is identified according to the collected air pressure measurement data and the air pressure change rule, wherein the gait information includes a foot tribe land state, a step frequency, a front-to-back consistency index, and a walking manner, wherein, The front-to-back consistency index refers to a characteristic of a change in pressure value when the foot tribe land is included, and the characteristics include a waveform of the pressure value, a maximum value, a minimum value, a variance, and a mean value of the pressure value;

Analyze the foot tribe ’s land state, step frequency, front-to-back consistency index, and walking style according to preset detection rules to detect body state information related to gait.
The method according to claim 1, wherein identifying the pedestrian gait information according to the collected air pressure measurement data and the air pressure change rule comprises:

Determining the foot state of the pedestrian at each sampling time according to the collected air pressure measurement data, wherein the foot state includes a landing state and a flying state;

Calculating the step frequency of the pedestrian when walking according to the pressure change rule, the pressure value waveform corresponding to the landing state, and the pressure value waveform corresponding to the flying state;

Obtaining a consistency index before and after the pressure value according to the collected pressure measurement data;

Acquiring a variation range of the air pressure value according to the collected air pressure measurement data;

A walking mode of the pedestrian when walking is determined according to a variation range of the air pressure value.
The method according to claim 2, wherein determining the foot state of the pedestrian at each sampling time according to the collected air pressure measurement data comprises:

Determine the air pressure value Pk at the current sampling time from the collected air pressure measurement data;

Calculating a difference between the pressure value Pk at the current sampling time and the normal pressure value PN at the current sampling time;

If the absolute value of the difference is greater than the target threshold, it is determined that the foot state of the pedestrian at the current sampling time is a landing state, wherein the target threshold Tp is a mean square error σ of a normal pressure value at the current sampling time. 3 to 5 times, the normal pressure value at the current sampling time is used to indicate the pressure value that is stable and lasts for a certain period of time within the current sampling time;

If the absolute value of the difference is smaller than the target threshold, it is determined that the foot state of the pedestrian at the current sampling time is a vacated state.
The gait recognition method according to claim 2, wherein the pedestrian is calculated when the pedestrian is walking according to the pressure change rule, the pressure value waveform corresponding to the landing state, and the pressure value waveform corresponding to the vacated state. Cadence, including:

According to the air pressure value waveform corresponding to the landing state, find the air pressure value waveform of the target landing state from the air pressure change rule, wherein the target landing state is used to indicate a landing where the cumulative time of the foot tribe land is greater than the first time threshold status;

According to the air pressure value waveform corresponding to the empty state, find the air pressure value waveform of the target empty state from the air pressure change rule, wherein the target empty state is used to indicate that the cumulative time of the foot empty time is greater than the second time threshold Flying state

Determining, according to the pressure value waveform of the target landing state and the pressure value waveform of the target flying state, the number of times that the target landing state and the target flying state alternately appear from the pressure change rule;

Calculating the number of steps of the pedestrian while walking according to the number of times that the target landing state and the target vacant state appear alternately;

Determining the use time of the air pressure sensor when the pedestrian is walking;

Calculate the step frequency of the pedestrian when walking according to the number of steps and the duration of use.
The gait recognition method according to claim 2, wherein acquiring the change range of the air pressure value according to the collected air pressure measurement data comprises:

Obtaining a maximum pressure and a minimum value of air pressure within a preset time from the collected air pressure measurement data, wherein the preset time is used to indicate a walking time covering at least one step;

Calculate a difference between the maximum value of the air pressure and the minimum value of the air pressure within the preset time, and use the difference as the variation range of the air pressure value.
The gait recognition method according to claim 2 or 5, wherein determining the walking mode of the pedestrian when walking according to the variation range of the air pressure value comprises:

When the variation range of the air pressure value is smaller than the first determination threshold, determining that the walking mode is slow walking;

When the variation range of the air pressure value is greater than the first determination threshold and less than the second determination threshold, determining that the walking mode is fast walking;

Determining that the walking mode is jogging when the variation range of the air pressure value is greater than the second determination threshold and smaller than the third determination threshold;

When the variation range of the air pressure value is greater than the third determination threshold, it is determined that the walking mode is fast running.
The method according to any one of claims 1 to 6, wherein the foot tribe land state, step frequency, consistency index, and walking method are analyzed according to a preset detection rule to detect and step State-related physical state information, including:

Determining a detection type of a physical state for the pedestrian, wherein the detection type includes a fatigue detection type and a body defect detection type;

Selecting the corresponding detection rule according to the physical state detection type;

From the detection rules, a reference waveform, a reference cadence, a reference consistency index, and a reference walking mode of the landing state of the pedestrian within the target time are respectively selected;

Matching the reference waveform of the landing state with the waveform of the identified foot tribal land state, matching the reference cadence with the identified cadence, and matching the pre- and post-reference consistency indicators Matching the identified front-to-back consistency index, and matching the reference walking manner with the identified walking manner;

The body state information of the pedestrian is determined according to the matching result.
A body state detection system, comprising a gait recognition device and a detection device, wherein:

The gait recognition device is built in a cavity of an insole or a sole, the gait recognition device includes an air pressure sensor for detecting the air pressure in the cavity, and the gait recognition device is for periodically detecting the air pressure sensor. The output air pressure measurement data is sampled, and the air pressure change rule in the cavity is determined according to the collected air pressure measurement data, and the gait information of the pedestrian is identified according to the collected air pressure measurement data and the air pressure change rule. Wherein, the gait information includes foot tribe land state, step frequency, front-to-back consistency index, and walking style, wherein the front-to-back consistency index refers to a characteristic of a change in air pressure value when the foot tribe land, and the feature includes air pressure The waveform of the value, the maximum and minimum pressure, the variance and mean value of the pressure;

The detection device is configured to analyze the foot tribe land state, step frequency, front-to-back consistency index, and walking mode according to a preset detection rule to detect body state information related to gait.
The system according to claim 8, wherein the gait recognition device is specifically configured to:

Determining the foot state of the pedestrian at each sampling time according to the collected air pressure measurement data, wherein the foot state includes a landing state and a flying state;

Calculating the step frequency of the pedestrian when walking according to the pressure change rule, the pressure value waveform corresponding to the landing state, and the pressure value waveform corresponding to the flying state;

Obtaining a consistency index before and after the pressure value according to the collected pressure measurement data;

Acquiring a variation range of the air pressure value according to the collected air pressure measurement data;

A walking mode of the pedestrian when walking is determined according to a variation range of the air pressure value.
The system according to claim 9, wherein the gait recognition device is specifically configured to:

Determine the air pressure value Pk at the current sampling time from the collected air pressure measurement data;

Calculating a difference between the pressure value Pk at the current sampling time and the normal pressure value PN at the current sampling time;

If the absolute value of the difference is greater than the target threshold, determining that the foot state of the pedestrian at the current sampling time is a landing state;

If the absolute value of the difference is smaller than the target threshold, it is determined that the foot state of the pedestrian at the current sampling time is a vacated state.
The system according to claim 9, wherein the gait recognition device is specifically configured to:

According to the air pressure value waveform corresponding to the landing state, find the air pressure value waveform of the target landing state from the air pressure change rule, wherein the target landing state is used to indicate a landing where the cumulative time of the foot tribe land is greater than the first time threshold status;

According to the air pressure value waveform corresponding to the empty state, find the air pressure value waveform of the target empty state from the air pressure change rule, wherein the target empty state is used to indicate that the cumulative time of the foot empty time is greater than the second time threshold Flying state

Determining, according to the pressure value waveform of the target landing state and the pressure value waveform of the target flying state, the number of times that the target landing state and the target flying state alternately appear from the pressure change rule;

Calculating the number of steps of the pedestrian while walking according to the number of times that the target landing state and the target vacant state appear alternately;

Determining the use time of the air pressure sensor when the pedestrian is walking;

Calculate the step frequency of the pedestrian when walking according to the number of steps and the duration of use.
The system according to claim 9, wherein the gait recognition device is specifically configured to:

Obtaining a maximum pressure and a minimum value of air pressure within a preset time from the collected air pressure measurement data, wherein the preset time is used to indicate a walking time covering at least one step;

Calculate a difference between the maximum value of the air pressure and the minimum value of the air pressure within the preset time, and use the difference as the variation range of the air pressure value.
The system according to claim 9 or 12, wherein the gait recognition device is specifically configured to:

When the variation range of the air pressure value is smaller than the first determination threshold, determining that the walking mode is slow walking;

When the variation range of the air pressure value is greater than the first determination threshold and less than the second determination threshold, determining that the walking mode is fast walking;

Determining that the walking mode is jogging when the variation range of the air pressure value is greater than the second determination threshold and smaller than the third determination threshold;

When the variation range of the air pressure value is greater than the third determination threshold, it is determined that the walking mode is fast running.
The system according to any one of claims 8 to 13, wherein the detection device is specifically configured to:

Determining a detection type of a physical state for the pedestrian, wherein the detection type includes a fatigue detection type and a body defect detection type;

Selecting the corresponding detection rule according to the physical state detection type;

From the detection rules, a reference waveform, a reference cadence, a reference consistency index, and a reference walking mode of the landing state of the pedestrian within the target time are selected respectively;

Matching the reference waveform of the landing state with the waveform of the identified foot tribal land state, matching the reference cadence with the identified cadence, and matching the pre- and post-reference consistency indicators Matching the identified front-to-back consistency index, and matching the reference walking manner with the identified walking manner;

The body state information of the pedestrian is determined according to the matching result.