CN111436940B

CN111436940B - Gait health assessment method and device

Info

Publication number: CN111436940B
Application number: CN202010202430.7A
Authority: CN
Inventors: 高伟东; 杨益娜
Original assignee: Beijing University of Posts and Telecommunications
Current assignee: Beijing University of Posts and Telecommunications
Priority date: 2020-03-20
Filing date: 2020-03-20
Publication date: 2021-11-09
Anticipated expiration: 2040-03-20
Also published as: CN111436940A

Abstract

The embodiment of the invention provides a gait health assessment method and device. The method comprises the following steps: acquiring a gait pressure signal, and identifying a gait phase by adopting a fuzzy logic inference rule based on the gait pressure signal; recording the phase sequence of the gait phase; calculating the gait phase duration and the overall gait cycle according to the phase sequence interval; counting abnormal gait cycles deviating from standard gait according to medical standard phase duration based on a standard gait sequence of a Perry model; and obtaining an abnormal cycle proportion based on the abnormal gait cycle and the overall gait cycle, and taking the abnormal cycle proportion as a gait health evaluation basis. The embodiment of the invention applies a fuzzy logic reasoning system in the gait phase detection process to realize stable and continuous gait phase detection, adopts trapezoidal and triangular membership functions in the output membership function, does not preset to form an individual gait phase sequence, fully considers the internal difference of individual gait, and is suitable for the gait evaluation requirements of various crowds.

Description

Gait health assessment method and device

Technical Field

The invention relates to the technical field of biological feature recognition, in particular to a gait health assessment method and device.

Background

Walking is one of the most common daily activities, and the health and degree of gait can reflect the health condition of human body to a certain extent. Gait analysis is to record and analyze human body kinematics information and dynamics information, and aims to quantitatively analyze factors of lower limb control functions in the walking process. Accurate gait phase identification is the basis for analyzing individual gait, determines gait cycle and phase and duration in the cycle, and can effectively reflect the health condition of gait.

The existing gait analysis method comprises the following steps:

(1) and (3) qualitative analysis: the method is mainly applied to rehabilitation patients, depends on qualitative analysis of experienced clinicians, and assessment of patient rehabilitation is easily affected subjectively;

(2) quantitative analysis of large-scale equipment: large gait analysis systems such as an infrared light spot catcher, a force measuring platform, a surface electromyograph and the like have high precision and complete functions, but are high in price, limited by places and spaces and difficult to popularize under the condition of shortage of medical resources;

(3) low-cost, miniaturized, portable gait analysis system: the existing low-cost, small-sized and portable gait analysis system mainly utilizes a threshold method, only can realize basic gait cycle segmentation, but the reasonable threshold size is difficult to determine; in addition, the existing gait analysis method is only suitable for specific people, the phase sequence of human gait is preset according to experience, and the internal difference of individual gait cannot be fully considered.

Disclosure of Invention

The embodiment of the invention provides a gait health assessment method and a gait health assessment device, which are used for solving the defects that the gait assessment method in the prior art is easily influenced subjectively, is low in precision, excessively depends on complex instruments, does not consider individual difference and the like.

In a first aspect, an embodiment of the present invention provides a gait health assessment method, including:

acquiring a gait pressure signal, and identifying a gait phase by adopting a fuzzy logic inference rule based on the gait pressure signal;

recording the phase sequence of the gait phase;

calculating gait phase duration and overall gait cycle according to the phase sequence interval;

counting abnormal gait cycles deviating from standard gait according to medical standard phase duration based on a standard gait sequence of a Perry model;

and obtaining an abnormal cycle proportion based on the abnormal gait cycle and the overall gait cycle, and taking the abnormal cycle proportion as a gait health evaluation basis.

Preferably, the identifying the gait phase by using a fuzzy logic inference rule based on the gait pressure signal specifically includes:

selecting an input-output fuzzy set of the gait pressure signal;

defining an input and output membership function of the gait pressure signal;

designing the fuzzy logic inference rule based on the input and output fuzzy set and the input and output membership function, and establishing a fuzzy rule table according to the fuzzy logic inference rule;

performing preset operation on input and output variables of the gait pressure signals based on the fuzzy logic reasoning rule to obtain fuzzy reasoning result aggregation;

and aggregating the fuzzy reasoning results to perform defuzzification processing to obtain the gait phase.

Preferably, the selecting the input and output fuzzy set of the gait pressure signal specifically includes:

inputting an analog voltage value corresponding to the gait pressure signal acquired by an ADC (analog-to-digital converter), and outputting a gait phase value;

the gait phase value corresponds to a gait cycle, the gait cycle comprises a standing phase and a swinging phase, the standing phase comprises a first touchdown phase, a bearing reaction phase, a support phase middle phase, a support phase end phase and a swinging early phase, and the swinging phase comprises a swinging phase early phase, a swinging phase middle phase and a swinging phase end phase.

Preferably, the defining an input-output membership function of the gait pressure signal specifically includes:

fuzzifying the analog voltage value by adopting a sigmoid membership function, and dividing the analog voltage value into a first input fuzzy set and a second input fuzzy set, wherein the analog voltage value is in a preset voltage interval range;

fuzzifying the first touchdown period and the swing phase by adopting a trapezoidal membership function, and fuzzifying the bearing reaction period, the support phase middle period, the support phase final period and the swing early period by adopting a triangular membership function to obtain an output variable, wherein the output variable is in a preset output variable interval range and corresponds to the output variable at preset intervals.

Preferably, the designing the fuzzy logic inference rule based on the input-output fuzzy set and the input-output membership function, and establishing a fuzzy rule table according to the fuzzy logic inference rule specifically includes:

designing the fuzzy logic inference rule according to the first input fuzzy set, the second input fuzzy set and the output variable, and constructing the fuzzy rule table based on the fuzzy logic inference rule;

and defining a fuzzy inference rule matrix to represent the fuzzy inference rule based on the fuzzy inference rule.

Preferably, the performing a preset operation on the input and output variables of the gait pressure signal based on the fuzzy logic inference rule to obtain a fuzzy inference result aggregate specifically includes:

substituting the input and output variables into the input and output membership function to obtain membership;

obtaining a triggered rule by combining the fuzzy rule table according to the membership degree;

obtaining the reliability of the rule precondition through the preset operation;

performing the preset operation on the input and output variables based on the rule precondition credibility to obtain rule credibility;

and extracting a union of a plurality of rule reasoning results based on the rule credibility, wherein the union is used as the fuzzy reasoning result aggregation.

Preferably, the aggregating the fuzzy inference result and performing defuzzification processing to obtain the gait phase specifically includes:

and aggregating the fuzzy inference results by adopting an average maximum value method to perform defuzzification processing to obtain the gait phase.

In a second aspect, an embodiment of the present invention provides a gait health assessment apparatus, including:

the acquisition and identification module is used for acquiring gait pressure signals and identifying gait phases by adopting a fuzzy logic reasoning rule based on the gait pressure signals;

the recording module is used for recording the phase sequence of the gait phase;

the calculating module is used for calculating the gait phase duration and the overall gait cycle according to the phase sequence interval;

the statistical module is used for counting abnormal gait cycles deviating from standard gait according to medical standard phase duration based on a standard gait sequence of a Perry model;

and the processing module is used for obtaining an abnormal cycle proportion based on the abnormal gait cycle and the overall gait cycle, and taking the abnormal cycle proportion as a gait health evaluation basis.

In a third aspect, an embodiment of the present invention provides an electronic device, including:

a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the gait health assessment methods when executing the program.

In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of any one of the gait health assessment methods.

The gait health assessment method and the device provided by the embodiment of the invention realize stable and continuous gait phase detection by applying the fuzzy logic reasoning system in the gait phase detection process, adopt trapezoidal and triangular membership functions in the output membership function, do not preset to form an individual gait phase sequence, fully consider the internal difference of individual gait, and are suitable for the gait assessment requirements of various crowds.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a block diagram of a wearable gait analysis system according to an embodiment of the invention;

FIG. 2 is a pressure sensor profile provided by an embodiment of the present invention;

fig. 3 is a flowchart of a gait health assessment method according to an embodiment of the invention;

fig. 4 is a schematic view of a gait phase model according to an embodiment of the invention:

fig. 5 is a structural diagram of a gait health assessment device according to an embodiment of the invention;

fig. 6 is a block diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The embodiment of the invention designs a gait health assessment method and a gait health assessment device aiming at the problem of human gait analysis and evaluation. The gait analysis needs to accurately divide the gait cycle, and the embodiment of the invention collects multiple paths of pressure signals through multiple paths of piezoelectric ceramic sensors, clearly identifies each gait phase by using a gait division algorithm, simultaneously records the duration of each gait phase, and further effectively evaluates the gait health condition through the gait analysis algorithm.

Fig. 1 is a structural diagram of a wearable gait analysis system according to an embodiment of the invention, and as shown in fig. 1, the wearable gait analysis system is composed of 8-channel pressure sensors, a digital-to-analog/analog-to-digital conversion unit (ADC), a Microcontroller (MCU) and a wireless communication module. The system is composed of three subsystems, which are respectively: the system comprises a signal acquisition subsystem, a signal analysis subsystem and a wireless communication subsystem.

The signal acquisition subsystem is composed of a pressure sensor and an ADC and is mainly responsible for acquiring signals of the pressure sensor, and the distribution of the pressure sensor is shown in figure 2, wherein the pressure sensors GRF1-GRF3 are positioned at the heel, the pressure sensors GRF4-GRF7 are positioned at the phalanges, and the pressure sensor GRF8 is positioned at the thumb.

The numeric value range of the pressure signal acquired by the pressure sensor is [0,4096 ]]Using the formula:

converting the digital pressure value into an analog voltage value, wherein the converted voltage value range is [0,3.3V ]]Here, 3.3V is only an example of the operating voltage, and for other voltage values, the embodiment of the present invention does not workAnd (4) limiting. And the wireless communication subsystem transmits the result calculated by the signal analysis subsystem to the smart phone or transmits the result to the background through the wireless base station. The manner of wireless communication includes, but is not limited to: bluetooth, WiFi, 4G, 5G.

The gait phase recognition and gait evaluation of the signal analysis subsystem, and related processing procedures are completed in a Microcontroller (MCU), including fuzzy logic reasoning, gait phase recognition and gait evaluation.

Fig. 3 is a flowchart of a gait health assessment method according to an embodiment of the invention, as shown in fig. 3, including:

s1, acquiring gait pressure signals, and recognizing gait phases by adopting a fuzzy logic reasoning rule based on the gait pressure signals;

s2, recording the phase sequence of the gait phase;

s3, calculating the gait phase duration and the overall gait cycle according to the phase sequence interval;

s4, based on the standard gait sequence of the Perry model, counting the abnormal gait cycle deviating from the standard gait according to the medical standard phase duration;

and S5, obtaining an abnormal cycle proportion based on the abnormal gait cycle and the overall gait cycle, and taking the abnormal cycle proportion as a gait health evaluation basis.

Specifically, the gait health assessment aims to construct a model capable of identifying the health of different human gaits, the phase sequence of forming specific individual gaits is not preset, the structural difference of the individual gaits is fully considered, the gait assessment is realized by measuring the 'symmetry' and the 'homogeneity' of the gaits, and the 'symmetry' measures the similarity between pressure signals generated by the left foot and the right foot in each step; "homogeneity" measures the timely repetition of the same pressure pattern between two steps. Thus, the evaluation of the individual gait can be performed based on the phase sequence in the gait cycle and the duration of each phase.

The steps for assessing whether gait is normal are as follows:

1) marking transitional gait events from one gait phase to another gait phase, namely gait phase identification;

2) the sequence of gait phases is recorded. The system does not preset the phase sequence of individual gait, only judges the current gait phase according to the pressure signal obtained by detection, and can clearly reflect the gait phase at each moment;

3) the gait phase duration is calculated. Taking the same gait phase interval of two times of the same side foot (such as the right foot) as a gait cycle, recording the gait phase duration, and comparing with the medical standard: IC accounts for about 2% of the gait cycle, LR accounts for about 10% of the gait cycle, MS accounts for about 19% of the gait cycle, TS accounts for about 19% of the gait cycle, PS accounts for about 12% of the gait cycle, and SW accounts for about 38% of the gait cycle;

4) gait sequence (IC) -proposed by Perry model>LR—>MS—>TS—>PS—>SW) is standard gait, the divided gait cycles which are different from the Perry model and the gait phase duration time obviously deviates from the medical standard shown in the step (3) are collectively called as abnormal gait cycles, and the abnormal cycles are as the following formula:

taking abnormal cycle ratio as the basis of gait health assessment.

The embodiment of the invention realizes stable and continuous gait phase detection by applying the fuzzy logic reasoning system in the gait phase detection process, does not preset to form an individual gait phase sequence, fully considers the internal difference of individual gait, and is suitable for the gait evaluation requirements of various crowds.

Based on the above embodiment, the identifying the gait phase by using the fuzzy logic inference rule based on the gait pressure signal specifically includes:

selecting an input-output fuzzy set of the gait pressure signal;

defining an input and output membership function of the gait pressure signal;

Specifically, the gait phase recognition is completed through fuzzy logic reasoning, and comprises the following steps: (1) selecting an input and output fuzzy set; (2) defining an input and output membership function; (3) establishing a fuzzy control table; (4) establishing a fuzzy control rule; (5) fuzzy reasoning; (6) and (4) defuzzification.

Based on any of the above embodiments, the selecting the input and output fuzzy set of the gait pressure signal specifically includes:

Specifically, the input is an analog voltage value corresponding to the ADC acquisition; the output is the gait phase value.

According to medical standards, for a particular lower limb (e.g. right limb), as shown in fig. 4, the gait cycle consists of a Stance phase (Stance) which accounts for about 60% of the entire gait cycle and a Swing phase (SW) which accounts for about 40% of the entire gait cycle. According to the Perry gait model, each gait cycle is divided into 8 phases, as shown in fig. 3, wherein 5 phases belong to the stance phase, which are: initial Contact (IC), Load Response (LR), Mid-support phase (MS), Terminal support phase (TS), and Pre-Swing Phase (PS); the 3 phases belong to the swing phase and are respectively: early Swing phase (Initial Swing), Mid Swing phase (Mid Swing), and end Swing phase (Terminal Swing), which are collectively referred to as SW.

The details of each gait phase are as follows:

IC: GRF1-GRF3 of the heel began to measure force.

LR: the lateral forefoot begins to contact the ground and GRF4-GRF5 begins to measure force.

MS: the medial forefoot begins to contact the ground and GRF6-GRF7 begins to measure force, and GRF8 may or may not measure force depending on gait.

TS: the center of gravity of the body moves forward and the heel no longer contacts the ground, i.e., GRF1-GRF3 no longer measures force.

PS: only the thumb and toe contact the ground, i.e. only GRF8 measures the force.

SW: the foot does not touch the ground and the GRF1-GRF8 signal remains 0.

The detection of 6 gait phases is realized by utilizing pressure signals, which are respectively as follows: IC. LR, MS, TS, PS and wobble phase SW.

Based on any of the above embodiments, the defining the input-output membership function of the gait pressure signal specifically includes:

Specifically, a sigmoid-type Membership Function (MF) is adopted to fuzzify each input variable (voltage value corresponding to a pressure value), and the pressure is divided into 2 fuzzy sets: l (corresponding to membership function 1, MF1), S (corresponding to membership function 2, MF 2). L represents a large pressure value and S represents a small pressure value. Input variable value range: [0,3.3 ], i.e. the predetermined voltage interval, which is not limited in the embodiments of the present invention.

Adopt trapezoidal membership function and triangle-shaped membership function fuzzification each output variable (gait phase place), divide the gait phase place into 6 fuzzy sets: IC (corresponding to membership function 1, MF1), LR (corresponding to membership function 2, MF2), MS (corresponding to membership function 3, MF3), TS (corresponding to membership function 4, MF4), PS (corresponding to membership function 5, MF5), and SW (corresponding to membership function 6, MF 6). Wherein the triangular membership functions are special forms of trapezoidal membership functions. IC and SW adopt trapezoidal membership functions, and the rest adopt triangular membership functions. Presetting a value range of an output variable interval: [0, 12], the output value is 0-2 corresponding to the gait phase IC, i.e. 2 is a preset interval, and so on.

Based on any of the above embodiments, the designing the fuzzy logic inference rule based on the input-output fuzzy set and the input-output membership function, and establishing a fuzzy rule table according to the fuzzy logic inference rule specifically includes:

Specifically, a rule is designed according to the magnitude of the pressure value of the pressure sensor corresponding to each gait phase, and the larger the pressure value is (L), the higher the possibility of the position touching the ground is; the smaller the pressure value (S), the less likely this location is to touch down. In the embodiment of the present invention, there are 8 input variables in total, and each variable has 2 possible linguistic values (L is large, S is small), so that 2 may be formed⁸256 fuzzy inference rules.

The fuzzy rule takes the form of if … then, for example rule 10 is of the form: if (GRF1 is S) AND (GRF2 is S) AND (GRF3 is S) AND (GRF4 is S) AND (GRF5 is S) AND (GRF6 is S) AND (GRF7 is S) AND (GRF8 is S) the gate-phase (gait phase) is SW. The specific expression form of the fuzzy rule is complicated, and a fuzzy inference rule matrix is used for replacing the fuzzy inference rule matrix in programming, for example, the rule 10 corresponds to the rule matrix [ 22222222611 ].

Here, the fuzzy inference rule list matrix should follow the following principle: if the system has m inputs and n outputs, the first m vector elements in the rule structure correspond to the 1 st to m inputs and the next n columns correspond to the n outputs. The first column of elements is the membership function pointer associated with input1 (L for 1, S for 2,/for 0), the m +1 column of elements is the membership function pointer associated with output1 (1 for IC, 2 for LR, 3 for MS, 4 for TS, 5 for PS, 6 for SW), and so on. The (m + n + 1) th column is a weight value (usually, 1) related to the rule, AND the (m + n + 2) th column specifies a rule connection method (1 represents an AND relationship, AND 2 represents an OR relationship). The number of rows is equal to the number of rules that need to be added. The fuzzy rule table is shown in table 1:

TABLE 1

Based on any one of the above embodiments, the performing a preset operation on the input and output variables of the gait pressure signal based on the fuzzy logic inference rule to obtain a fuzzy inference result aggregate specifically includes:

The step of aggregating the fuzzy inference results to perform defuzzification processing to obtain the gait phase specifically includes:

Specifically, the fuzzy inference process adopted by the embodiment of the invention specifically comprises the following steps:

1) rule matching: and substituting the pressure value of the sole measured by the current pressure sensor into the membership function to obtain the corresponding membership degree.

2) Rule triggering: and obtaining the triggered rule by combining a fuzzy inference rule table according to the membership degree.

3) Rule premise reasoning: within the same rule, the reliability of the rule preconditions is obtained through the AND relation between the preconditions.

4) Reasoning of each rule: and (4) carrying out AND operation on the input and the output to obtain the reliability of the rule.

5) Fuzzy system output aggregation: and taking a union set of the reasoning results of all the rules to obtain fuzzy reasoning result aggregation.

6) Defuzzification: the fuzzy system needs to defuzzify the output to obtain an accurate inference result, and a mean maximum value method (mom) is adopted for defuzzification.

Fig. 5 is a structural diagram of a gait health assessment device according to an embodiment of the invention, as shown in fig. 5, including: an acquisition identification module 51, a recording module 52, a calculation module 53, a statistic module 54 and a processing module 55; wherein:

the acquiring and identifying module 51 is configured to acquire a gait pressure signal and identify a gait phase by using a fuzzy logic inference rule based on the gait pressure signal; the recording module 52 is configured to record a phase sequence of the gait phases; the calculating module 53 is configured to calculate the gait phase duration and the overall gait cycle according to the phase sequence interval; the statistic module 54 is used for counting abnormal gait cycles deviating from standard gait according to medical standard phase duration based on a standard gait sequence of the Perry model; the processing module 55 is configured to obtain an abnormal cycle proportion based on the abnormal gait cycle and the overall gait cycle, and use the abnormal cycle proportion as a gait health evaluation basis.

The device system provided in the embodiment of the present invention is configured to execute the corresponding method, and a specific implementation manner of the device system is consistent with that of the method.

Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may call logic instructions in the memory 630 to perform the following method: acquiring a gait pressure signal, and identifying a gait phase by adopting a fuzzy logic inference rule based on the gait pressure signal; recording the phase sequence of the gait phase; calculating gait phase duration and overall gait cycle according to the phase sequence interval; counting abnormal gait cycles deviating from standard gait according to medical standard phase duration based on a standard gait sequence of a Perry model; and obtaining an abnormal cycle proportion based on the abnormal gait cycle and the overall gait cycle, and taking the abnormal cycle proportion as a gait health evaluation basis.

In addition, the logic instructions in the memory 630 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the transmission method provided in the foregoing embodiments when executed by a processor, and for example, the method includes: acquiring a gait pressure signal, and identifying a gait phase by adopting a fuzzy logic inference rule based on the gait pressure signal; recording the phase sequence of the gait phase; calculating gait phase duration and overall gait cycle according to the phase sequence interval; counting abnormal gait cycles deviating from standard gait according to medical standard phase duration based on a standard gait sequence of a Perry model; and obtaining an abnormal cycle proportion based on the abnormal gait cycle and the overall gait cycle, and taking the abnormal cycle proportion as a gait health evaluation basis.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A gait health assessment apparatus, characterized by comprising:

the step of identifying the gait phase by adopting a fuzzy logic reasoning rule based on the gait pressure signal specifically comprises the following steps:

selecting an input-output fuzzy set of the gait pressure signal;

defining an input and output membership function of the gait pressure signal;

aggregating the fuzzy inference results to perform defuzzification processing to obtain the gait phase;

the selecting the input and output fuzzy set of the gait pressure signal specifically comprises:

the gait phase value corresponds to a gait cycle, the gait cycle comprises a standing phase and a swinging phase, the standing phase comprises a first touchdown phase, a bearing reaction phase, a support phase middle phase, a support phase end phase and a swinging early phase, and the swinging phase comprises a swinging phase early phase, a swinging phase middle phase and a swinging phase end phase;

the step of defining the input and output membership function of the gait pressure signal specifically comprises the following steps:

fuzzifying the first touchdown period and the swing phase by adopting a trapezoidal membership function, and fuzzifying the bearing reaction period, the support phase middle period, the support phase end period and the swing early period by adopting a triangular membership function to obtain an output variable, wherein the output variable is in a preset output variable interval range and corresponds to the output variable at preset intervals;

the calculation module is used for calculating the gait phase duration and the overall gait cycle according to the phase sequence interval;

the processing module is used for obtaining an abnormal cycle proportion based on the abnormal gait cycle and the overall gait cycle, and taking the abnormal cycle proportion as a gait health evaluation basis;

the formula of the abnormal period ratio is as follows:

2. the gait health assessment device according to claim 1, wherein the designing the fuzzy logic inference rule based on the input-output fuzzy set and the input-output membership function, and establishing a fuzzy rule table according to the fuzzy logic inference rule, specifically comprises:

3. The gait health assessment device according to claim 1, wherein the preset operation is performed on the input and output variables of the gait pressure signal based on the fuzzy logic inference rule to obtain a fuzzy inference result aggregate, specifically comprising:

4. The gait health assessment device according to claim 1, wherein the step of aggregating the fuzzy inference results to perform defuzzification processing to obtain the gait phase comprises: