WO2020220403A1

WO2020220403A1 - Fatigue state detection method, apparatus and device, and storage medium

Info

Publication number: WO2020220403A1
Application number: PCT/CN2019/087430
Authority: WO
Inventors: 王作第
Original assignee: 深圳六合六医疗器械有限公司
Priority date: 2019-04-30
Filing date: 2019-05-17
Publication date: 2020-11-05
Also published as: CN110236571A

Abstract

A fatigue state detection method, apparatus and device (100), and a storage medium. The method comprises: obtaining pulse point data of a person to be detected (S10); generating a pulse waveform according to collected pulse point data (S20); obtaining fatigue characteristic parameters by calculation according to a maximum point and a minimum point of the pulse waveform (S30); normalizing the fatigue characteristic parameters to obtain fatigue parameters (S40); and determining a fatigue state grade of said person according to the correspondence between the fatigue parameters obtained by normalization and a preset fatigue state grade (S50). The method can obtain the change trend of the fatigue state by calculation, and achieve an early warning function for the fatigue status of the person to be detected.

Description

Fatigue state detection method, device, equipment and storage medium

Technical field

The invention relates to the field of detection, in particular to a fatigue state detection method, device, equipment and storage medium.

Background technique

Today's social health is a hot topic that people are most concerned about, but there is no time to manage their health in busy work. In particular, some physical conditions, such as fatigue, some people’s physical conditions are very good, that is, when they show fatigue, they can’t detect any diseases after going to the hospital for physical examination. With the passage of time, the whole person gradually became more negative, and at the same time, the negative effects gradually showed up, seriously affecting work and life. If you can detect this situation early, prevent and manage your health early, you can completely avoid this development. However, the existing fatigue detection methods have low accuracy of the calculated fatigue state and cannot meet the higher requirements of people. Therefore, we need to propose improvements to the existing fatigue state detection methods.

Summary of the invention

The technical problem to be solved by the present invention is to provide a fatigue state detection method, device, equipment and storage medium, aiming to improve the detection accuracy of the fatigue state.

In order to solve the above technical problems, the technical solution adopted by the present invention is: a fatigue state detection method, the fatigue state detection method includes:

Obtain the pulse point data of the examinee;

Generate pulse waveform according to the collected pulse point data;

Calculate the fatigue characteristic parameters according to the maximum point and minimum point of the pulse waveform;

Normalize fatigue characteristic parameters to obtain fatigue parameters;

According to the corresponding relationship between the normalized fatigue parameter and the preset fatigue state level, the fatigue state level of the test subject is determined.

Further, the fatigue characteristic parameters include blood flow velocity, blood vessel radius, velocity, peripheral resistance of blood vessels, the amplitude of each heart beat, heartbeat interval, heartbeat interval, segment cut point, layer cut point, time sequence corresponding point .

Further, the calculation of fatigue characteristic parameters according to the acquired pulse waveform data specifically includes:

Calculate the blood flow velocity and integrate a segment of the pulse waveform; calculate the numerical point velocity according to the sampling frequency, the velocity of the numerical point is inversely proportional to the blood flow velocity;

Calculating a blood vessel radius, the blood vessel radius being a proportional coefficient of the maximum value and the minimum value of the pulse waveform;

Calculating a rate, the rate being the rate of change of the velocity of the pulse point data on the pulse waveform;

Calculate the peripheral resistance, which is the ratio of the descending isthmus point and the extreme point of the pulse waveform;

Calculate the beat amplitude of each heart beat, where the beat amplitude of each heart beat is the maximum value of the pulse waveform;

Calculate the line gap, where the line gap is the line connecting the extreme points of every two beats;

Calculate the heartbeat interval, the heartbeat interval being the minimum interval of every two heart beats;

Calculating a segmented tangent point, where the segmented tangent point is a value of a segmentation point that divides a continuous pulse waveform into 8 segments;

Calculating a layered cut point, where the layered cut point is a value obtained by dividing each of the 8 segments into 7 small segments;

Calculate the time sequence corresponding point, the time sequence corresponding point is the time sequence of the stored standard value, which is used for comparison with the newly collected value.

Further, the fatigue characteristic parameters further include plane tangent points, differential threshold points, and cardiac output; the calculation of the fatigue characteristic parameters based on the acquired pulse waveform data also includes:

Calculate the plane tangent point, where the plane tangent point is a point where the pulse waveform can equally divide the area of both sides;

Calculate the difference threshold point, the difference threshold point being the maximum point and the minimum point of each heart beat.

To calculate the stroke volume, the calculation formula is: sv=(0.283/(k*k))(Ps-Pd)*T;

Among them, k=(Ps-Pm)/(Ps-Pd), T is the cardiac cycle, Ps is the maximum value, Pd is the minimum value, and Pm is the value of the descending isthmus point.

Further, the blood flow velocity includes the velocity from the heart to the brain and the velocity from the heart to the limbs; the fatigue state detection method further includes analyzing fatigue based on the blood flow velocity to the brain and the blood flow velocity to the limbs The state is used to verify whether the fatigue state of the testee matches the preset fatigue state level, and if it does not match, the fatigue parameter is recalculated.

Further, the fatigue detection method further includes determining whether the systolic blood pressure and the diastolic blood pressure increase when the blood flow velocity to the brain is greater than a preset value, and if so, determining that the fatigue status level of the subject is increased.

Further, before generating the pulse waveform according to the collected pulse point data, the step of data screening is further included, specifically;

Determine whether the pulse data point is within the preset error interval. If it is, the pulse data point is valid data; if it is not, the data is invalid data; invalid data is eliminated.

A fatigue state detection device, which includes:

The data acquisition module is used to acquire the pulse point data of the test subject;

Waveform generation module, used to generate pulse waveform according to the collected pulse point data;

The characteristic parameter calculation module is used to calculate the fatigue characteristic parameters according to the maximum and minimum points of the pulse waveform;

The normalization module is used to normalize the fatigue characteristic parameters to obtain the fatigue parameters;

The fatigue level determination module is used to determine the fatigue level of the test subject according to the corresponding relationship between the normalized fatigue parameter and the preset fatigue level.

A fatigue state detection device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, and the processor implements any of the above when the computer program is executed Fatigue state detection method.

A storage medium storing a computer program, and the computer program includes program instructions that, when executed by a processor, cause the processor to execute the fatigue state detection method described in any one of the above items.

The technical effect of the present invention is that the pulse waveform is formed by collecting the pulse point data of the examinee, the fatigue characteristic parameters are calculated according to the maximum point and the minimum point of the pulse waveform, and the fatigue parameters are obtained after normalization. , According to the corresponding relationship between the fatigue parameters and the fatigue level, the fatigue state level of the examinee is obtained; this method can analyze and calculate the change trend of the fatigue state more accurately, and can play an early warning function of the fatigue state of the examinee.

Description of the drawings

The specific structure of the present invention will be described in detail below with reference to the drawings.

FIG. 1 is a flowchart of a fatigue state detection method according to a specific embodiment of the present invention;

Fig. 2 is a block diagram of a fatigue state detection device according to a specific embodiment of the present invention;

Figure 3 is a pulse waveform diagram of a specific embodiment of the present invention;

Among them, Ps: maximum value point; Pd: minimum value point; Pm: lower middle gorge point.

Detailed ways

In order to describe in detail the technical content, structural features, achieved objectives and effects of the present invention, the following is a detailed description in conjunction with the embodiments and accompanying drawings.

Referring to Fig. 1, a specific embodiment of the present invention is: a fatigue state detection method, the fatigue state detection method includes:

S10. Obtain pulse point data of the person to be tested;

S20: Generate a pulse waveform according to the collected pulse point data;

S30. Calculate the fatigue characteristic parameters according to the maximum point and minimum point of the pulse waveform;

S40. Normalize the fatigue characteristic parameters to obtain the fatigue parameters;

S50: Determine the fatigue state level of the test subject according to the corresponding relationship between the normalized fatigue parameter and the preset fatigue state level.

Among them, the mathematical method of normalization is: for example, a set (2,3,4,5) has four numbers, after normalization, 2+3+4+5=14; the new set obtained is (2 /14, 3/14, 4/14, 5/14), the maximum sum of the new set values is 1; then the fatigue parameter is obtained by summing the ratio between the new value and the maximum value.

In this embodiment, the pulse waveform is formed by collecting the pulse point data of the subject, and the fatigue characteristic parameters are calculated according to the maximum and minimum points of the pulse waveform, and the fatigue parameters are obtained after normalization. The corresponding relationship between the fatigue parameters and the fatigue level obtains the fatigue state level of the test subject; this method can analyze and calculate the change trend of the fatigue state more accurately, and can play an early warning role for the fatigue state of the test subject.

Preferably, the fatigue characteristic parameters include blood flow velocity, blood vessel radius, velocity, peripheral resistance of blood vessels, the amplitude of each heart beat, heartbeat interval, heartbeat interval, segmented cut point, layered cut point, and time sequence corresponding point .

In a specific embodiment, the calculation of fatigue characteristic parameters based on the acquired pulse waveform data specifically includes:

Referring to Figure 3, calculate the peripheral resistance, the peripheral resistance is the ratio of the descending isthmus point and the extreme point of the pulse waveform;

In this example, the time length of the pulse point data for each test is 90 seconds, including more than 40,000 data points. The fatigue characteristic parameters above can be calculated every time the pulse data points of about 400 are passed, so it can be calculated More than a dozen sets of fatigue characteristic parameters, through linear normalization of more than a dozen sets of fatigue characteristic parameters, where there are more data in the fuzzy statistical distribution, the data at this position is selected as the analysis data, which can make the calculated results more accurate.

In a specific embodiment, the fatigue characteristic parameters further include plane tangent points, differential threshold points, and cardiac output; the calculation of the fatigue characteristic parameters based on the acquired pulse waveform data further includes:

Refer to Figure 3 to calculate stroke volume, the calculation formula is: sv=(0.283/(k*k))(Ps-Pd)*T;

In a specific embodiment, the blood flow speed includes the speed from the heart to the brain and the speed from the heart to the extremities; the fatigue state detection method further includes, according to the blood flow speed to the brain and the blood flow to the extremities Speed, the fatigue state is analyzed to verify whether the fatigue state of the test subject matches the preset fatigue state level, and if it does not match, the fatigue parameter is recalculated.

In a specific embodiment, the fatigue state detection method further includes determining whether the blood pressure systolic and diastolic blood pressure increases when the blood flow velocity to the brain is greater than a preset value, and if so, determining the fatigue of the subject The status level rises.

In a specific embodiment, before generating the pulse waveform according to the collected pulse point data, the step of data screening is further included, specifically:

In this embodiment, because some of the collected pulse point data is problematic, we select the sample size to filter out the data that meets our analysis. The specific screening method: consider the limit of 285 output points per stroke of the heart and the sampling frequency The maximum limit is 485, and the qualification rate is greater than or equal to 12. On this basis, the data model parameters are selected again, so that the accuracy can be improved by at least 30%.

Referring to FIG. 2, a fatigue state detection device, the fatigue state detection device 100 includes:

The data acquisition module 10 is used to acquire the pulse point data of the test subject;

The waveform generation module 20 is used to generate a pulse waveform according to the collected pulse point data;

The characteristic parameter calculation module 30 is used to calculate the fatigue characteristic parameter according to the maximum value point and the minimum value point of the pulse waveform;

The normalization module 40 is used to normalize the fatigue characteristic parameters to obtain the fatigue parameters;

The fatigue level determining module 50 is used to determine the fatigue level of the test subject according to the corresponding relationship between the normalized fatigue parameter and the preset fatigue level.

In a specific embodiment, the characteristic parameter calculation module 30 is specifically configured to:

In a specific embodiment, the fatigue characteristic parameters further include plane tangent points, difference threshold points, and cardiac output; the characteristic parameter calculation module 30 is also used to:

In a specific embodiment, the blood flow speed includes the speed from the heart to the brain and the speed from the heart to the extremities; the fatigue state detection device 100 further includes a fatigue level verification module, which is used to verify the blood flow to the brain according to The speed and the blood flow speed to the limbs are analyzed, and the fatigue state is analyzed to verify whether the fatigue state of the test subject matches the preset fatigue state level. If it does not match, the fatigue parameters are recalculated.

In a specific embodiment, the fatigue state detection device 100 further includes a blood pressure monitoring module, which is used to determine whether the systolic and diastolic blood pressure has increased when the blood flow velocity to the brain is greater than a preset value, and if so, It is determined that the fatigue level of the test subject has increased.

In a specific embodiment, the fatigue state detection device 100 further includes a data screening module for determining whether the pulse data point is within a preset error interval before generating the pulse waveform according to the collected pulse point data, and if so, The pulse data point is valid data; if it is not, the data is invalid data; invalid data is eliminated.

Here, the first and second... only represent the distinction between their names, and do not mean that their importance and position are different.

Here, up, down, left, right, front, and back only represent their relative positions and not their absolute positions. The above are only the embodiments of the present invention, and do not limit the scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the description and drawings of the present invention, or directly or indirectly applied to other related technologies In the same way, all fields are included in the scope of patent protection of the present invention.

Claims

A fatigue state detection method, characterized in that: the fatigue state detection method includes:

Obtain the pulse point data of the examinee;

Generate pulse waveform according to the collected pulse point data;

Calculate the fatigue characteristic parameters according to the maximum point and minimum point of the pulse waveform;

Normalize fatigue characteristic parameters to obtain fatigue parameters;

According to the corresponding relationship between the normalized fatigue parameter and the preset fatigue state level, the fatigue state level of the test subject is determined.
The fatigue detection method according to claim 1, wherein the fatigue characteristic parameters include blood flow velocity, blood vessel radius, velocity, peripheral resistance of blood vessels, amplitude of each heart beat, heartbeat interval, heartbeat interval, Segment tangent points, hierarchical tangent points, and time sequence corresponding points.
The fatigue state detection method according to claim 2, wherein the calculation of the fatigue characteristic parameters according to the acquired pulse waveform data specifically includes:

Calculate the blood flow velocity and integrate a segment of the pulse waveform; calculate the numerical point velocity according to the sampling frequency, the velocity of the numerical point is inversely proportional to the blood flow velocity;

Calculating a blood vessel radius, the blood vessel radius being a proportional coefficient of the maximum value and the minimum value of the pulse waveform;

Calculating a rate, the rate being the rate of change of the velocity of the pulse point data on the pulse waveform;

Calculate the peripheral resistance, which is the ratio of the descending isthmus point and the extreme point of the pulse waveform;

Calculate the beat amplitude of each heart beat, where the beat amplitude of each heart beat is the maximum value of the pulse waveform;

Calculate the line gap, where the line gap is the line connecting the extreme points of every two beats;

Calculate the heartbeat interval, the heartbeat interval being the minimum interval of every two heart beats;

Calculating a segmented tangent point, where the segmented tangent point is a value of a segmentation point that divides a continuous pulse waveform into 8 segments;

Calculating a layered cut point, where the layered cut point is a value obtained by dividing each of the 8 segments into 7 small segments;

Calculate the time sequence corresponding point, the time sequence corresponding point is the time sequence of the stored standard value, which is used for comparison with the newly collected value.
The fatigue state detection method according to claim 2, wherein the fatigue characteristic parameters further include plane tangent points, differential threshold points, and cardiac output; the fatigue characteristic parameters are calculated according to the acquired pulse waveform data. include,

Calculate the plane tangent point, where the plane tangent point is a point where the pulse waveform can equally divide the area of both sides;

Calculate the difference threshold point, the difference threshold point being the maximum point and the minimum point of each heart beat.

To calculate the stroke volume, the calculation formula is: sv=(0.283/(k*k))(Ps-Pd)*T;

Among them, k=(Ps-Pm)/(Ps-Pd), T is the cardiac cycle, Ps is the maximum value, Pd is the minimum value, and Pm is the value of the descending isthmus point.
The fatigue detection method according to claim 3, wherein the blood flow speed includes the speed of the blood flow from the heart to the brain and the speed of the heart to the limbs; the fatigue detection method further comprises, according to the flow to the brain The blood flow velocity and the blood flow velocity to the extremities are analyzed to verify the fatigue state of the test subject to verify whether the fatigue state matches the preset fatigue state level, and if it does not match, the fatigue parameters are recalculated.
5. The fatigue state detection method according to claim 5, characterized in that: the fatigue state detection method further comprises, when the blood flow velocity to the brain is greater than a preset value, judging whether the systolic and diastolic blood pressure increase, If yes, it is determined that the fatigue state level of the test subject has risen.
The fatigue state detection method according to claim 1, characterized in that: before generating the pulse waveform according to the collected pulse point data, it further comprises a step of data screening, specifically;

Determine whether the pulse data point is within the preset error interval. If it is, the pulse data point is valid data; if it is not, the data is invalid data; invalid data is eliminated.
A fatigue state detection device, characterized in that: the fatigue state detection device includes:

The data acquisition module is used to acquire the pulse point data of the test subject;

Waveform generation module, used to generate pulse waveform according to the collected pulse point data;

The characteristic parameter calculation module is used to calculate the fatigue characteristic parameters according to the maximum and minimum points of the pulse waveform;

The normalization module is used to normalize the fatigue characteristic parameters to obtain the fatigue parameters;

The fatigue level determination module is used to determine the fatigue level of the test subject according to the corresponding relationship between the normalized fatigue parameter and the preset fatigue level.
A fatigue state detection device, which is characterized in that it includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor. The processor executes the computer program as claimed in the claims. The fatigue state detection method described in any one of 1 to 7.
A storage medium, characterized in that: the storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes any one of claims 1 to 7 The fatigue state detection method described in item.