CN115312194A

CN115312194A - Physiological data analysis system, method, device and storage medium

Info

Publication number: CN115312194A
Application number: CN202210942317.1A
Authority: CN
Inventors: 冷赫
Original assignee: Shanghai Yingyida Medical Instrument Co ltd; Inventec Appliances Shanghai Corp; Inventec Appliances Pudong Corp; Inventec Appliances Corp
Current assignee: Shanghai Yingyida Medical Instrument Co ltd; Inventec Appliances Shanghai Corp; Inventec Appliances Pudong Corp; Inventec Appliances Corp
Priority date: 2022-08-08
Filing date: 2022-08-08
Publication date: 2022-11-08

Abstract

The invention provides a physiological data analysis system, a method, a device and a storage medium, wherein the system comprises: the data acquisition module is used for acquiring historical measurement values of at least one physiological characteristic of the testee and acquiring real-time measurement values of at least one physiological characteristic of the testee; the model generation module is used for constructing a physiological state evaluation model of the measured person based on the historical measurement values; and the state evaluation module is used for evaluating the real-time measurement value based on the physiological state evaluation model and acquiring the real-time physiological state of the tested person. The invention solves the problem of individual difference of the evaluation standard by constructing the physiological state evaluation model which is specific to each tested person, and improves the accuracy of the physiological state evaluation.

Description

Physiological data analysis system, method, device and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a physiological data analysis system, method, device, and storage medium.

Background

Nowadays, people pay more and more attention to physiological health, and methods for evaluating physiological status are endless. For example, the physiological status of a subject can be evaluated according to HRV (heart rate variability) data of the subject, and the evaluation criterion is usually calibrated based on big data. However, the measured data of different subjects in various states may vary depending on the race, constitution, occupation, sex, age, psychological factors, and the like. Even if doctors intervene to adjust the evaluation standard, not enough doctors can observe and analyze all people, and human subjective factors influence judgment.

In the case of adopting a standardized evaluation standard obtained based on big data calibration, erroneous judgment may be caused to the physiological state of the subject. For example, the subject a obtains a complete HRV measurement report after the measurement is completed, and the physiological status of the subject is evaluated by using the unified evaluation standard in the database, and all the results are shown to be normal on the report. In fact the normal HRV value in a unified assessment standard is too high for the subject to be at risk of neurasthenia and requires an early medical visit. And the wrong HRV report can cause the subject to delay hospitalization. For another example, the subject B obtained a complete HRV measurement report after the measurement, and at this time, the physiological status was evaluated by using the unified evaluation criteria in the database, and the report showed that the heart rate variability energy value was too low, and the patient took some methylphenidate to activate the activity of the nerve after hospitalization. In fact, this heart rate variability energy is a normal range for subject B, and a wrong dose may cause a malfunction of the autonomic nervous system.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the invention and therefore may include information that does not constitute prior art that is already known to a person of ordinary skill in the art.

Disclosure of Invention

In view of the problems in the prior art, an object of the present invention is to provide a physiological data analysis system, method, device and storage medium, which construct a physiological status assessment model specific to each subject, and improve the accuracy of physiological status assessment.

The embodiment of the invention provides a physiological data analysis method, which comprises the following steps:

the data acquisition module is used for acquiring historical measurement values and calibration physiological states of at least one physiological characteristic of the tested person and acquiring real-time measurement values of at least one physiological characteristic of the tested person;

the model generation module is used for constructing a physiological state evaluation model of the measured person based on the historical measured values and the calibrated physiological state; and

and the state evaluation module is used for evaluating the real-time measurement value based on the physiological state evaluation model and acquiring the real-time physiological state of the tested person.

In some embodiments, the physiological status includes a level of at least one physiological status indicator, and the data acquisition module is configured to acquire, by a physiological indicator measurement device, historical measurement values of a physiological characteristic of the subject in a plurality of scenes, a plurality of modes, and/or a plurality of time points, and acquire a calibration level of the physiological status indicator corresponding to the historical measurement values.

In some embodiments, the calibration level of the physiological status indicator is a calibration level obtained by self-evaluation of the historical measurement values by the subject, or a calibration level obtained by manual evaluation of the historical measurement values by a doctor.

In some embodiments, the physiological state assessment model includes a range of measured values of the physiological characteristic corresponding to respective levels of each physiological state indicator;

the model generation module is used for constructing the physiological state evaluation model of the testee by adopting the following steps:

calculating the average value and standard deviation of the measured values of the corresponding historical measured values for the calibration level of each physiological state index;

and calculating the measurement value range of the physiological characteristics corresponding to each grade of each physiological state index based on the measurement value average value and the measurement value standard deviation corresponding to each calibration grade.

In some embodiments, for each physiological state indicator, the model generation module calculates the range of the measured value of the physiological characteristic corresponding to each level by:

for a physiological state index, the range of the initial measurement value of the ith grade is set as (x) _i1 ，x _i2 ) Wherein x is _i1 Mean of measurements-standard deviation of measurements, x, equal to the ith level _i2 The mean of the measurements equal to the ith rank + standard deviation of the measurements, i ∈ (1,n), n being the total number of ranks;

the standard deviation of the measured values of the respective levels is adjusted so that, for each two adjacent levels, the maximum value of the measured value of the preceding level is equal to the minimum value of the measured value of the following level.

In some embodiments, the model generation module is further configured to calculate, for each physiological status indicator, a measurement value range of a level without measurement record according to a preset calculation method according to a measurement value range of an existing level after calculating the measurement value range of the physiological characteristic corresponding to each level.

In some embodiments, further comprising:

and the improvement suggestion module is used for acquiring a preset standard physiological state evaluation model, comparing the physiological state evaluation model of the tested person with the standard physiological state evaluation model to obtain a comparison difference value of each physiological state index, generating an improvement suggestion corresponding to the physiological state index based on the corresponding comparison difference value for each physiological state index, and pushing the improvement suggestion to the tested person.

In some embodiments, the physiological state assessment model is a model established based on machine learning, the physiological state assessment model configured to output a prediction level of a physiological state indicator based on a measured value of an input physiological characteristic.

In some embodiments, the model generation module is configured to construct the physiological state assessment model of the subject by:

constructing an initial physiological state evaluation model;

inputting the historical measurement values as sample input data into the initial physiological state evaluation model;

acquiring the prediction grade of the physiological state index output by the initial physiological state evaluation model;

and optimally training the initial physiological state evaluation model based on the prediction grade and the calibration grade of the physiological state index to obtain a trained physiological state evaluation model.

In some embodiments, the physiological characteristic comprises at least one of a heart rate characteristic, a respiration characteristic, a body temperature characteristic, and a blood vessel characteristic; and/or the presence of a gas in the gas,

the physiological status indicator includes at least one of a stress indicator, an emotional indicator, a cardiopulmonary function indicator, a cardiac load indicator, a sympathetic activity indicator, and a parasympathetic activity indicator.

In some embodiments, after the data acquisition module acquires the historical measurement values of at least one physiological characteristic of the subject, the data acquisition module is further used for uploading the historical measurement values of the subject to a cloud; and/or the presence of a gas in the gas,

and the model generation module is used for uploading the physiological state evaluation model of the testee to a cloud after the physiological state evaluation model of the testee is constructed.

In some embodiments, after acquiring the real-time physiological status of the subject, the method further includes the following steps:

judging whether the real-time physiological state of the tested person meets a preset warning condition or not;

if yes, warning information is sent out.

The embodiment of the invention also provides a physiological data analysis method, which comprises the following steps:

the data acquisition module acquires a historical measurement value and a calibrated physiological state of at least one physiological characteristic of the measured person;

the model generation module is used for constructing a physiological state evaluation model of the measured person based on the historical measurement values and the calibrated physiological state;

the data acquisition module acquires a real-time measurement value of at least one physiological characteristic of the testee;

and the state evaluation module evaluates the real-time measurement value based on the physiological state evaluation model to acquire the real-time physiological state of the measured person.

An embodiment of the present invention further provides a physiological data analysis device, including:

a processor;

a memory having stored therein executable instructions of the processor;

wherein the processor is configured to perform the steps of the physiological data analysis method via execution of the executable instructions.

Embodiments of the present invention further provide a computer-readable storage medium for storing a program, which when executed by a processor implements the steps of the physiological data analysis method.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

The physiological data analysis system, method, equipment and storage medium of the invention have the following beneficial effects:

the invention firstly constructs the physiological state evaluation model which is exclusive to the tested person based on the historical physiological data of the tested person, and then evaluates the real-time physiological data of the tested person based on the physiological state evaluation model which is exclusive to the tested person to obtain the real-time physiological state, thereby solving the problem of individual difference of the evaluation standard and improving the accuracy of physiological state evaluation.

Drawings

Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.

FIG. 1 is a schematic diagram of a physiological data analysis system according to an embodiment of the present invention;

FIG. 2 is a flow chart of a physiological data analysis method according to an embodiment of the present invention;

FIG. 3 is a flow chart of a method for constructing a physiological status assessment model of a subject according to an embodiment of the present invention;

FIG. 4 is a flow diagram of generating an improvement suggestion according to an embodiment of the invention;

FIG. 5 is a flow chart of another embodiment of the present invention for constructing a physiological condition assessment model of the subject;

FIG. 6 is a schematic structural diagram of a physiological data analysis device according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the steps. For example, some steps may be decomposed, and some steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

In the present invention, physiological data refers to a measurement of at least one physiological characteristic. The physiological characteristics can be measured by the existing measuring method, such as measuring heart rate characteristics through an electrocardio electrode, measuring body temperature and blood vessel characteristics through infrared rays, and the like. The invention provides a physiological data analysis system which can effectively and accurately evaluate the physiological state of a measured person based on the measured physiological data.

As shown in fig. 1, in an embodiment of the present invention, the physiological data analysis system includes:

the data acquisition module M100 is used for acquiring historical measurement values and a calibrated physiological state of at least one physiological characteristic of the testee and acquiring real-time measurement values of at least one physiological characteristic of the testee;

in this embodiment, the physiological characteristics include at least one of a heart rate characteristic, a respiration characteristic, a body temperature characteristic and a blood vessel characteristic, the heart rate characteristic may include, for example, a heart rate value, a heart rate interval, a heart rate variation energy value and the like, the respiration characteristic may include, for example, a respiration rate, a respiration interval and the like, the body temperature characteristic may include, for example, a body temperature value, a body temperature variation trend and the like, and the blood vessel characteristic may include, for example, a blood vessel hardness and the like, and the system of the present invention may be applied to analysis of physiological data of one physiological characteristic and also applied to analysis of physiological data of two or more physiological characteristics;

in this embodiment, the physiological state comprises a rating of at least one physiological state indicator, and thus the nominal physiological state is a nominal rating of at least one physiological state indicator; the calibration grade of the physiological state index is a calibration grade obtained by self-evaluation of a measured value by a measured person on a historical measured value, for example, after a measured value of the measured person is obtained, the measured person is prompted to input a physiological state when measurement is performed on a screen of a medical measuring device, if pressure is input for three levels when measurement is performed, the pressure is recorded for three levels as the calibration physiological state of the measured value, or the calibration physiological state can be calibrated by a doctor end, for example, the measured value can be sent to a doctor end knowing the body state of the measured person, and the physiological state corresponding to the measured value is calibrated by the doctor; when a plurality of mental state indexes exist, the calibration mental state of each measured value also comprises calibration levels of the plurality of mental state indexes, for example, a three-level mental state index and a two-level mental state index are calibrated for one measurement; the following will specifically describe the calibration level of the physiological status indicator as an example of a calibration level obtained by the self-evaluation of the measured value by the measured person;

the model generation module M200 is used for constructing a physiological state evaluation model of the measured person based on the historical measurement values and the calibrated physiological state; and

the state evaluation module M300 is configured to evaluate the real-time measurement value based on the physiological state evaluation model, and obtain a real-time physiological state of the subject, that is, a real-time level of at least one physiological state indicator of the subject.

In this embodiment, the physiological state indicator includes at least one of a stress indicator, an emotion indicator, a cardiopulmonary function indicator, a cardiac load indicator, a sympathetic activity indicator, and a parasympathetic activity indicator, and is not limited to the types listed herein. Taking the example that the physiological status index includes the pressure index, the pressure index can be divided into five levels, and the real-time physiological status of the subject acquired by the status evaluation module M300 includes a certain level of the pressure index.

Different levels of the psychological state index may reflect different physiological states of the subject. For example, when the stress index is graded as 1-2, the heartbeat is about 60-70, the psychological state is relaxed, and the overall psychological function is younger. When the level of the stress index is 4-5, the heartbeat is about 110-130, the psychological state is relatively tired, and the whole physiological function is obviously aged. For another example, when the mood index is rated 1-2, the parasympathetic activity is active and the psychological state is low, suggesting that there is more exercise and more intake of non-delicate carbohydrates. When the grade of the emotion index is 4-5, parasympathetic nerve activity is low, and psychological state is high. More rest and less caffeine intake are recommended.

According to the invention, firstly, the data acquisition module M100 and the model generation module M200 are used for constructing the physiological state evaluation model which is dedicated to the testee based on the historical physiological data of the testee, then the data acquisition module M100 and the state evaluation module M300 are used for evaluating the real-time physiological data of the testee based on the physiological state evaluation model which is dedicated to the testee, so that the real-time physiological state is obtained, the problem of individual difference existing in the evaluation standard is solved, and the accuracy of physiological state evaluation is improved. The physiological data analysis system of the invention can be applied to mobile terminals, such as mobile phones, tablet computers, notebook computers and the like, can also be applied to devices such as desktops, servers and the like, or can also be applied to medical measurement devices.

Optionally, after the data acquisition module M100 acquires the historical measurement value of at least one physiological characteristic of the subject, the data acquisition module M is further configured to upload the historical measurement value of the subject to a cloud, and a user may directly acquire the historical measurement value of the subject from the cloud. The historical measurement values stored in the cloud can also be provided for facilities in hospitals, nursing homes, nursing centers or nursing villages to be retrieved and monitored. The testee or other users can access the cloud through the APP or the browser of the mobile terminal such as a mobile phone to check the historical measurement value of the testee.

Optionally, after the model generation module M200 constructs the physiological state assessment model of the subject, the model generation module M is further configured to upload the physiological state assessment model of the subject to a cloud, and a user may directly obtain the physiological state assessment model customized for the subject from the cloud, and when the user replaces a used medical measurement device, the user may directly obtain the physiological state assessment model from the cloud and store the physiological state assessment model locally, without repeating the construction process of the physiological state assessment model.

As shown in fig. 2, the present invention further provides a physiological data analysis method, which adopts the working process of the physiological data system, and the method comprises the following steps:

s100: the data acquisition module acquires a historical measurement value and a calibrated physiological state of at least one physiological characteristic of the measured person;

s200: the model generation module is used for constructing a physiological state evaluation model of the measured person based on the historical measurement values and the calibrated physiological state;

s300: the data acquisition module acquires a real-time measurement value of at least one physiological characteristic of the testee;

s400: the state evaluation module evaluates the real-time measurement value based on the physiological state evaluation model to obtain the real-time physiological state of the measured person.

The method comprises the steps of S100 and S200, constructing a physiological state evaluation model dedicated to a tested person based on historical physiological data of the tested person, and then evaluating the real-time physiological data of the tested person based on the physiological state evaluation model dedicated to the tested person through the steps S300 and S400 to obtain the real-time physiological state, so that the problem that evaluation standards have individual differences is solved, the accuracy of physiological state evaluation is improved, the tested person can evaluate the physical and mental health of the tested person according to the obtained physiological state result, and whether life habits or doctors need to be adjusted or hospitalized is judged and also provided for doctors, and the physical and mental health of the tested person is evaluated by the doctors to judge whether medication is needed.

The physiological data analysis system and method of the invention can be applied to mobile terminals, such as mobile phones, tablet computers, notebook computers and the like, can also be applied to devices such as desktops, servers and the like, or can also be applied to medical measurement devices. The physiological data analysis system and method will be specifically described below by taking an example in which the system and method are applied to a medical measurement device.

In this embodiment, in step S100, the acquiring, by the data acquisition module, historical measurement values of at least one physiological characteristic of the subject includes: the method comprises the steps of collecting historical measurement values of physiological characteristics of a measured person under a plurality of scenes, a plurality of modes and/or a plurality of time points through a physiological index measuring device, and obtaining calibration levels of physiological state indexes corresponding to the historical measurement values. The plurality of scenarios here may comprise different preset motion states (e.g. running, walking, etc.), different measurement states (standing, sitting, etc.), etc. For example, various measurement instructions may be displayed on a screen of the medical measurement device or played through a speaker, such as "please measure after moving for one minute", "please measure while standing", etc., to guide the subject to perform the measurement of the physiological data in different scenes. In addition, the physical state of the tested person can be acquired in a questionnaire mode, for example, whether the tested person has physical discomfort phenomena such as cold, headache and the like can be determined in the questionnaire mode. The plurality of time points may include, for example, morning, noon, afternoon, and the like.

In this embodiment, the physiological state assessment model includes a range of measured values of the physiological characteristic corresponding to the respective level of each physiological state indicator. For example, for a pressure index, when five levels are assigned, the physiological state assessment model includes a first-level measurement value range, a second-level measurement value range, a third-level measurement value range, a fourth-level measurement value range, and a fifth-level measurement value range of the pressure index.

After determining the measurement value range of the physiological characteristic corresponding to each physiological state of the subject, in step S400, when the state evaluation module evaluates the real-time measurement values based on the physiological state evaluation model, the state evaluation module determines which level of the measurement value range of the physiological state index the measurement value of each physiological characteristic falls into, so as to determine the real-time physiological state. For example, the physiological characteristics include heart rate variability energy value, and the measurement value range of the ith grade of the pressure index is (x) _i1 ，x _i2 ) Wherein x is _i1 Is the minimum value, x, of the measured value of the ith level _i2 For example, when the pressure index is divided into five levels, and n is 5, the value of i may be 1, 2, 3, 4, and 5. When the currently measured real-time heart rate variability energy value falls within the measurement value range of the third grade of the pressure index, the current physiological state is the pressure index with three grades. The physiological state is divided into different grades, and the measurement value ranges of the different grades are set, so that the current grade of the tested person can be quickly determined, and the evaluated grade can assist the tested person, a doctor or a nurse to quickly judge whether the tested person needs to receive urgent treatment or needs to seek medical advice as soon as possible.

In this embodiment, the step S400: after the state evaluation module acquires the real-time physiological state of the testee, the method also comprises the following steps:

if the alarm information is sent, specifically, sending the alarm information may be that the medical measuring equipment sends an acoustic/optical alarm signal, or that the medical measuring equipment pushes the alarm information to a doctor end, a measured person terminal, a measured person relative terminal, or the like.

The preset warning condition may include a level of the physiological index that needs to be warned, for example, it is preset that a warning is given when the level of the pressure index is four or five. Then, when the real-time physiological status of the subject is acquired as the pressure index of three levels through the step S400, it is considered as a normal status, and after the real-time physiological status of the subject is acquired as the pressure index of four levels through the step S400, a warning message is issued.

As shown in fig. 3, in step S200, the model generating module is configured to construct the physiological state evaluation model of the subject by:

s210: calculating the average value and standard deviation of the measured values of the corresponding historical measured values for the calibration level of each physiological state index;

for example, for the third level of the stress indicator, obtaining all the measured values of the heart rate variability energy calibrated as the third level of the stress indicator, then calculating the mean value and standard deviation of the measured values, for the second level of the emotion indicator, obtaining all the measured values of the heart rate variability energy calibrated as the second level of the emotion indicator, then calculating the mean value and standard deviation of the measured values;

s220: and calculating the measurement value range of the physiological characteristics corresponding to each grade of each physiological state index based on the measurement value average value and the measurement value standard deviation corresponding to each calibration grade. The calibrated physiological state is the actual physiological state which best accords with the tested person, and the measurement value range of the physiological characteristics obtained based on the calibrated physiological state and the corresponding historical measurement value is the physiological state evaluation model which is specially owned by the tested person.

In this embodiment, in step S220, for each physiological status indicator, the model generation module calculates the measurement value range of the physiological characteristic corresponding to each level by using the following steps:

for a physiological state index, the range of the initial measurement value of the ith grade is set as (x) _i1 ，x _i2 ) Wherein x is _i1 Mean of measurements-standard deviation of measurements, x, equal to the ith grade _i2 The mean of the measurements equal to the ith rank + standard deviation of the measurements, i ∈ (1,n), n being the total number of ranks;

It should be understood that if the result of adding the corresponding standard deviation to the average value of the measured values corresponding to the previous physiological state indicator level is not equal to the result of subtracting the corresponding standard deviation from the average value of the measured values corresponding to the next physiological state indicator level, a range of values for which the pressure indicator cannot be evaluated may be present between the ranges of measured values corresponding to the two pressure indicator levels. Thus, by adjusting the measurement value standard deviation, the result of adding the corresponding measurement value standard deviation to the measurement value average corresponding to the previous physiological state indicator level is equal to the result of subtracting the corresponding measurement value standard deviation from the measurement value average corresponding to the next physiological state indicator level.

Table 1 below shows measurement data measured 11 times for the same subject. The physiological state including five levels of stress indexes and the physiological characteristics including heart rate variability energy are taken as an example for explanation. As can be seen from table 1, there is a large error in using the prior art uniform evaluation criteria and the calibrated pressure indicator rating for the same measured value. As can be seen in table 1, the historical measurements corresponding to a nominal pressure index rating of 2 are 2.51, 1.24, 1.96. The mean value and standard deviation of the measured values of the second level of the pressure index are the mean value and standard deviation of 2.51, 1.24 and 1.96. A nominal pressure index rating of 3 corresponds to measurements of 5.25, 6.35, 4.78, 7.46, 6.27. The mean value and standard deviation of the measured values of the three levels of the pressure index are the mean values and standard deviations of 5.25, 6.35, 4.78, 7.46 and 6.27. The array corresponding to the pressure index is [0,3,6.5,10,15,20] obtained by adopting the existing evaluation mode, wherein the range of the first-level measurement value of the pressure index is 0-3, the range of the second-level measurement value of the pressure index is 3-6.5, the range of the third-level measurement value of the pressure index is 6.5-10, the range of the fourth-level measurement value of the pressure index is 10-15, and the range of the fifth-level measurement value of the pressure index is 15-20. And the array corresponding to the pressure index corrected by the calibration pressure index grade is [0,1,3.9,7.6,11.2,14.8].

TABLE 1

Number of tests	Rating pressure indicators	Measured value	Using existing assessment ratings
				1	3	5.25	2
2	5	11.55	4
				3	3	6.35	2
4	2	2.51	1
				5	3	4.78	2
6	4	8.54	3
				7	3	7.46	3
8	2	1.24	2
				9	2	1.96	2
10	4	9.55	4
				11	3	6.27	3

For example, if the average value of the measured values of the three stages of the pressure indicator is a1, the standard deviation of the measured values is b1, the average value of the measured values of the four stages of the pressure indicator is a2, and the standard deviation of the measured values is b2, and if the range of the measured values of the three stages of the pressure indicator is (a 1-b1, a1+ b 1), and the range of the measured values of the four stages of the pressure indicator is (a 2-b2, a2+ b 2), the maximum value a1+ b1 of the measured values of the three stages of the pressure indicator is different from the minimum value a2-b2 of the measured values of the four stages of the pressure indicator, and all the ranges of the measured values cannot be covered, therefore, the standard deviation of the measured values of the three stages of the pressure indicator is b1', the range of the measured values of the four stages of the pressure indicator is (a 1-b1', a1+ b2', a2+ b2 '), and the range of the measured values of the three stages of the pressure indicator is b2', and the range of the measured values of the three stages can be matched with the four stages, and similarly, the three stages of the pressure indicator, the combined level, the three stages of the pressure indicator, the five levels, and the maximum value of the two adjacent stages can be adjusted, and the maximum value of the two levels can be equal to the next two adjacent measured values.

In this embodiment, there may be a case that the historical physiological data of the subject may not cover all levels, for example, after the physiological data of the subject is collected for a period of time, it only includes the physiological data whose nominal physiological state is the first level, the third level, the fourth level and the fifth level of the stress indicator, and the physiological data of the second level of the stress indicator is absent, and a preset calculation method is required to obtain the measurement value range of the second level of the stress indicator. Therefore, the model generation module is further configured to calculate, for each physiological status indicator, the measurement value range of the physiological characteristic corresponding to each grade, and then calculate, according to the measurement value range of the existing grade and according to a preset calculation method, the measurement value range of the grade without measurement record. Therefore, after calculating the measurement value range of the physiological characteristic corresponding to each level for each physiological status index in step S220, the method further includes the following steps:

judging whether a grade without a measurement record exists;

if yes, calculating the measurement value range of the grade which is not measured and recorded according to the preset calculation method according to the existing measurement value range of the grade.

For example, in the absence of a secondary pressure indicator measurement range, a secondary pressure indicator measurement range may be obtained from the primary and tertiary pressure indicator measurement ranges, with the maximum pressure indicator measurement value at the primary level being the minimum pressure indicator measurement value, and the minimum pressure indicator measurement value at the tertiary level being the maximum pressure indicator measurement value. Interpolation or other means may be used to obtain a range of measurements for an unknown level intermediate existing levels in the absence of a range of measurements for multiple levels.

The following table 2 shows the comparison result of the physiological data analysis method of the present invention and the evaluation of the physiological status of the subject using the unified evaluation criteria in the prior art. The physiological state including five levels of pressure indexes and the physiological characteristics including heart rate variation energy are taken as examples for explanation, and 10 testees are respectively measured. As can be seen from the following table 2, after the evaluation method of the present invention is adopted, compared with the evaluation method in the prior art, the evaluation accuracy of the pressure index grade is greatly improved.

TABLE 2

In this embodiment, the step S100: after the historical measured value of at least one physiological characteristic of the tested person is collected, the method also comprises the following steps:

and uploading the historical measured value of the tested person to a cloud terminal.

Furthermore, during the use process of the medical measuring equipment, the physiological state evaluation model of the measured person can be further perfected and optimized according to the accumulated measuring data and the physiological state evaluated each time. For example, the measurement of the physiological characteristic and the evaluation of the physiological state may be performed periodically or aperiodically, obtaining measurements and physiological states at different points or intervals of time. If the evaluation result is not accurate, the correction can be performed manually, or the correction can be performed when the evaluation result is judged to be not accurate by a doctor according to the measured value. And adding the measured value of the last month into the historical physiological data when each month starts, taking the corresponding physiological state as a calibration physiological state, and recalculating the measured value range of each grade of each physiological state, namely realizing intelligent learning and dynamic adjustment of the physiological state evaluation model.

Further, whether the physiological status of the subject is improved or not can be judged at intervals according to the physiological status evaluation result of the subject, and a reasonable improvement suggestion can be given according to the latest physiological status evaluation result.

In this embodiment, the physiological data analysis system further includes an improvement suggestion module, configured to generate an improvement suggestion corresponding to the physiological status indicator according to the physiological status evaluation model of the subject and the standard physiological status evaluation model, and push the improvement suggestion to the subject.

As shown in fig. 4, specifically, the improvement suggestion module is configured to generate an improvement suggestion by the following steps:

s230: acquiring a preset standard physiological state evaluation model;

s240: comparing the physiological state evaluation model of the tested person with the standard physiological state evaluation model to obtain a comparison difference value of each physiological state index;

for example, the standard physiological status evaluation model of the athlete comprises the measurement value ranges of the levels of the stress indicator, the physiological status evaluation model of the tested person comprises the measurement value ranges of the levels of the stress indicator, the two are compared, and the comparison difference value of each physiological status indicator comprises the difference value of the measurement value ranges of the levels of the stress indicator;

s250: for each physiological state index, judging whether the tested person needs to improve the physiological state index or not based on the corresponding comparison difference value;

for example, if the difference between the measurement value range of each level of the stress index of the measured person and the standard physiological state evaluation model is small, it indicates that the measured person is closer to the standard state and does not need to be improved, and if the difference is large, it indicates that the measured person needs to improve the stress bearing capacity;

s260: if the physiological state index needs to be improved, generating an improvement suggestion corresponding to the physiological state index, and pushing the improvement suggestion to the tested person, wherein the pushing to the tested person can be displayed on a display screen of the medical measuring equipment or pushed to a terminal device used by the tested person.

The generated improvement suggestion can be a suggestion aiming at each physiological state index, such as suggesting that the tested person walks for half an hour regularly, and more protein is ingested, so that the physiological state evaluation model of the tested person is closer to the standard physiological state evaluation model.

The present invention has been described above only as an example of a method of constructing a physiological state evaluation model of a subject based on the historical measurement values, but the present invention is not limited thereto. In other alternative embodiments, the physiological state assessment model may be constructed in other ways. For example, other calculation methods may be employed to determine the measurement value ranges for the various levels of the various physiological state indicators. For another example, the physiological condition evaluation model is constructed as a machine learning-based physiological condition evaluation model, and the predicted real-time physiological condition can be acquired by using the physiological data of the subject as input data. Because the model construction needs a large amount of data support, a basic model can be trained based on big data, and then the model is optimally trained by adopting historical physiological data of a single testee, so that a physiological state evaluation model special for each testee is obtained.

The following describes an implementation of the physiological data analysis system and method according to another embodiment when the physiological state assessment model is a model established based on machine learning.

In this further embodiment, the physiological state assessment model is a model established based on machine learning. The physiological state assessment model is configured to output a predicted level of a physiological state indicator based on an input measurement of a physiological characteristic. For example, the physiological state index is heart rate variability energy, the physiological state index is a stress index, and the output of the model is a prediction grade of the stress index.

In this further embodiment, the physiological state comprises a rating of at least one physiological state indicator, and the nominal physiological state is therefore a nominal rating of at least one physiological state indicator. The calibration grade of the physiological state index is the calibration grade obtained by self-evaluation of the measured value to the historical measured value by the measured person, or the calibration grade can be calibrated by a doctor end. The following description will specifically take the calibration level of the physiological status indicator as an example of the calibration level obtained by the subject self-evaluating the historical measurement values. As shown in fig. 5, in the step S100, the acquiring of the historical measurement values of at least one physiological characteristic of the subject by the data acquiring module includes S110': the method comprises the steps of collecting historical measurement values of physiological characteristics of a measured person under a plurality of scenes, a plurality of modes and/or a plurality of time points through a physiological index measuring device, and obtaining calibration levels of physiological state indexes corresponding to the historical measurement values.

In this another embodiment, the constructing the physiological state assessment model in step S200 includes: training a machine learning model according to the historical measured values and the calibration levels of the physiological state indexes, outputting the prediction levels of the physiological state indexes by the machine learning model during training, calculating a loss function according to the calibration levels and the prediction levels, and iteratively training the machine learning model based on the loss function until the loss function values meet preset requirements.

In this another embodiment, as shown in fig. 5, in step S200, the model generation module is configured to construct the physiological state assessment model of the subject by the following steps:

s210': constructing an initial physiological state evaluation model, for example, model architectures such as a convolutional neural network model and a residual error network model can be adopted, but the invention is not limited thereto;

s220': inputting the historical measurement values as sample input data into the initial physiological state evaluation model;

s230': acquiring the prediction grade of the physiological state index output by the initial physiological state evaluation model;

s240': a loss function is optimized and constructed based on the prediction grade and the calibration grade of the physiological state index, a loss function value obtained through calculation of the loss function is the estimation accuracy rate of the physiological state estimation model to the grade of the physiological state index, the smaller the loss function value is, the higher the estimation accuracy rate is, the larger the loss function value is, and the lower the estimation accuracy rate is;

s250': judging whether the loss function value is smaller than a preset threshold value or not;

if not, S260': optimizing model parameters of the initial physiological state assessment model, and then continuing to step S220';

if so, S270': and obtaining the trained physiological state evaluation model, storing the model in the local area, and further uploading the model to the cloud.

In one embodiment, the historical measurement values may be divided into a training set and a test set, the training physiological state assessment model is optimized by using the historical measurement values of the training set and the calibration levels of the corresponding physiological state indexes, then the prediction accuracy of the physiological state assessment model is evaluated by using the test set, and if the accuracy cannot reach a predetermined standard, the model parameters are further adjusted until the prediction accuracy meets the requirements.

Also, in this other embodiment, the step S400: after the state evaluation module acquires the real-time physiological state of the tested person, the method further comprises the following steps:

Further, in this embodiment, steps S220 'to S270' may be executed again after the history data is increased. That is, the physiological state evaluation model can be further optimized as the user measurement data increases during the use of the corresponding medical measurement device. For example, the user may correct the real-time physiological state after measuring the real-time physiological state according to his own evaluation or a doctor evaluation. And adding the measured value corresponding to the correction and the corrected physiological state into a training set again, and optimally training the physiological state evaluation model. Therefore, real-time dynamic adjustment of the personalized physiological state evaluation model is realized. Other parts of the contents of the other embodiment may adopt the corresponding technical contents of the embodiments shown in fig. 1 to 4, and are not described herein again.

The embodiment of the invention also provides physiological data analysis equipment, which comprises a processor; a memory having stored therein executable instructions of the processor; wherein the processor is configured to perform the steps of the physiological data analysis method via execution of the executable instructions.

As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.

An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 6. The electronic device 600 shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention. The electronic device 600 may be, for example, a terminal device such as a mobile phone or a tablet computer connected to the medical measurement module, or a medical measurement device integrated with a medical measurement function.

As shown in fig. 6, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 that connects the various system components (including the storage unit 620 and the processing unit 610), a display unit 640, and the like.

Wherein the memory unit stores program code that can be executed by the processing unit 610 such that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention as described in the physiological data analysis method section described above in this specification. For example, the processing unit 610 may perform the steps as shown in fig. 1.

The storage unit 620 may include readable media in the form of volatile storage units, such as a random access memory unit (RAM) 6201 and/or a cache storage unit 6202, and may further include a read-only memory unit (ROM) 6203.

The memory unit 620 may also include programs/utilities 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 630 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any device (e.g., router, modem, etc.) that enables the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. Although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, to name a few.

In the physiological data analysis apparatus, the program in the memory implements the steps of the physiological data analysis method when executed by the processor, and therefore, the apparatus can also obtain the technical effects of the physiological data analysis method.

Embodiments of the present invention further provide a computer-readable storage medium for storing a program, which when executed by a processor implements the steps of the physiological data analysis method. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the invention described in the physiological data analysis method section above of this specification, when the program product is executed on the terminal device.

Referring to fig. 7, a program product 800 for implementing the above method according to an embodiment of the present invention is shown, which can employ a portable memory and include a program code, and can be executed on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The program in the computer storage medium implements the steps of the physiological data analysis method when executed by a processor, and therefore, the computer storage medium can also achieve the technical effects of the physiological data analysis method.

The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.

Claims

1. A physiological data analysis system, comprising:

2. The physiological data analysis system according to claim 1, wherein the physiological status comprises a grade of at least one physiological status indicator, and the data acquisition module is configured to acquire historical measurement values of the physiological characteristic of the subject under multiple scenes, multiple modes and/or multiple time points through a physiological indicator measurement device, and obtain a calibration grade of the physiological status indicator corresponding to the historical measurement values.

3. The physiological data analysis system according to claim 2, wherein the calibration level of the physiological status indicator is a calibration level obtained by a subject evaluating the historical measurement values by himself or a calibration level obtained by a doctor evaluating the historical measurement values by himself.

4. The physiological data analysis system of claim 2, wherein the physiological state assessment model comprises a range of measured values of the physiological characteristic corresponding to a respective level of each physiological state indicator;

5. The physiological data analysis system of claim 4, wherein for each physiological state indicator, the model generation module calculates the range of measured values of the physiological characteristic for each level using the following steps:

for a physiological status index, the range of the initial measurement value of the ith grade is set as (x) _i1 ，x _i2 ) Wherein x is _i1 Mean of measurements-standard deviation of measurements, x, equal to the ith level _i2 The mean of the measurements equal to the ith rank + standard deviation of the measurements, i ∈ (1,n), n being the total number of ranks;

6. The physiological data analysis system according to claim 5, wherein the model generation module is further configured to calculate the measurement value range of the grade without measurement record according to a preset calculation method according to the existing measurement value range of the grade after calculating the measurement value range of the physiological characteristic corresponding to each grade for each physiological status indicator.

7. The physiological data analysis system of claim 5, further comprising:

8. The physiological data analysis system of claim 2, wherein the physiological state assessment model is a model built based on machine learning, the physiological state assessment model configured to output a predicted level of a physiological state indicator based on an input measured value of a physiological characteristic.

9. The physiological data analysis system of claim 8, wherein the model generation module is configured to construct the physiological state assessment model of the subject by:

constructing an initial physiological state evaluation model;

10. The physiological data analysis system of claim 2, wherein the physiological characteristic comprises at least one of a heart rate characteristic, a respiration characteristic, a body temperature characteristic, and a blood vessel characteristic; and/or the presence of a gas in the atmosphere,

the physiological state index includes at least one of a stress index, an emotion index, a cardiopulmonary function index, a cardiac load index, a sympathetic activity index, and a parasympathetic activity index.

11. The physiological data analysis system of claim 1, wherein the data acquisition module is further configured to upload the historical measurement values of the subject to a cloud after acquiring the historical measurement values of at least one physiological characteristic of the subject; and/or the presence of a gas in the gas,

12. The physiological data analysis system of claim 1, further comprising the following steps after acquiring the real-time physiological status of the subject:

if yes, warning information is sent out.

13. A physiological data analysis method characterized by using the physiological data analysis system according to any one of claims 1 to 12, the method comprising the steps of:

the model generation module is used for constructing a physiological state evaluation model of the measured person based on the historical measured values and the calibrated physiological state;

the data acquisition module acquires a real-time measurement value of at least one physiological characteristic of a testee;

14. A physiological data analysis device, comprising:

a processor;

a memory having stored therein executable instructions of the processor;

wherein the processor is configured to perform the steps of the physiological data analysis method of claim 13 via execution of the executable instructions.

15. A computer-readable storage medium storing a program which, when executed by a processor, performs the steps of the physiological data analysis method of claim 13.