CN113261924A - Intelligent stroke early warning system and method - Google Patents

Abstract

The invention provides an intelligent early warning method and system for cerebral apoplexy, comprising the following steps: acquiring and processing an original pulse wave signal through a preset wearable device sensor, and determining a pulse characteristic point; transmitting the pulse characteristic points to a preset big data analysis platform, carrying out analysis calculation, determining sign data, transmitting the sign data to a preset artificial intelligence algorithm for analysis processing, and determining an analysis result; the analysis result is used for judging whether a stroke precursor exists in the object to be detected or not; based on a deep neural network learning algorithm, establishing a stroke premonitory pathology model by periodically collecting the analysis result and transmitting the analysis result to preset simulation equipment; and judging whether the sign data of the object to be detected is abnormal in real time according to the stroke occurrence premonitory pathology model, and carrying out abnormity reminding when the sign data is abnormal.

Description

Intelligent stroke early warning system and method

Technical Field

The invention relates to the technical field of pathological modeling and data simulation, in particular to an intelligent stroke early warning system and method.

Background

At present, the cerebral apoplexy is also called apoplexy and cerebrovascular accident, is an acute cerebrovascular disease, is a group of diseases of brain tissue damage caused by the fact that blood can not flow into the brain due to the sudden rupture of cerebral vessels or the blockage of blood vessels, and comprises ischemic stroke and hemorrhagic stroke, wherein the incidence rate of the ischemic stroke is higher than that of the hemorrhagic stroke, and accounts for 60 to 70 percent of the total number of the cerebral stroke. The occlusion and stenosis of internal carotid and vertebral arteries can cause ischemic stroke, which is more than 40 years old, more female, and more severe, can cause death

Disclosure of Invention

The invention provides an intelligent stroke early warning system and method, which aim to solve the problems in the background technology.

A stroke intelligent early warning method comprises the following steps:

acquiring and processing an original pulse wave signal through a preset wearable device sensor, and determining a pulse characteristic point;

transmitting the pulse characteristic points to a preset big data analysis platform, carrying out analysis calculation, determining sign data, transmitting the sign data to a preset artificial intelligence algorithm for analysis processing, and determining an analysis result; wherein,

the analysis result is used for judging whether the object to be detected has a cerebral apoplexy aura;

based on a deep neural network learning algorithm, establishing a stroke premonitory pathology model by periodically collecting the analysis result and transmitting the analysis result to preset simulation equipment;

and judging whether the sign data of the object to be detected is abnormal in real time according to the stroke occurrence premonitory pathology model, and carrying out abnormity reminding when the sign data is abnormal.

Preferably, through the wearing equipment sensor that predetermines, obtain and handle original pulse wave signal, confirm pulse characteristic point, include:

the method comprises the steps that pulse sign information of a to-be-detected object is detected regularly through a preset wearable device sensor, and an original pulse wave signal of the to-be-detected object is determined according to the pulse sign information;

denoising, baseline removing and wavelet decomposition are carried out on the original pulse wave signals, and preprocessed pulse wave signals are determined;

and acquiring and reconstructing pulse wave characteristic signal points according to the preprocessed pulse wave signals, and determining the pulse wave characteristic points.

Preferably, the transmitting the pulse feature points to a preset big data analysis platform, performing analysis calculation, determining sign data, transmitting the sign data to a preset artificial intelligence algorithm, performing analysis processing, and determining an analysis result includes:

acquiring pulse wave characteristic points, and transmitting the pulse wave characteristic points to a big data analysis platform;

analyzing and calculating to obtain sign data by analyzing the characteristics of the transmitted pulse wave signals on the basis of the big data analysis platform; wherein,

the physical sign data at least comprises heart rate data, blood pressure data and blood oxygen data;

and mining and screening the physical sign data of the user through a preset artificial intelligence algorithm, pushing out a corresponding treatment scheme, and determining an analysis result.

Preferably, the method for establishing a stroke premonitory pathology model based on the deep neural network learning algorithm by periodically collecting the analysis result and transmitting the analysis result to a preset simulation device comprises the following steps:

step 1: collecting and obtaining analysis result delta Re (delta t, hr, bp, spo, F (m)) periodically,

wherein Δ Re (Δ t, hr, bp, spo, f (m)) represents an analysis result which is periodically collected and acquired, hr represents heart rate data of a to-be-detected object, bp represents blood pressure data of the to-be-detected object, and spo represents blood oxygen data of the to-be-detected object; Δ t time period for the collection of the object to be detected, f (m) represents the analysis data for the object to be detected based on the pre-entered traditional Chinese medicine thinking treatment data and western medicine clinical archive data;

step 2: according to the analysis result, calculating a prediction analysis result in the simulation equipment, and determining a difference value between the analysis result and the prediction analysis result:

wherein,

represents the result of the i-th predictive analysis, Δ Re_iRepresenting the ith regularly acquired analysis result, n representing the total number of the acquired analysis results, i representing a natural number, i belongs to (1, n), MAE representing the average absolute error of the analysis results and the prediction analysis results, RMSE representing the root mean square error of the analysis results and the prediction analysis results, and MRE representing the average relative error of the analysis results and the prediction analysis results; w is a_iRepresenting the weight matrix corresponding to the ith analysis result, b_iRepresenting the bias vector corresponding to the analysis result;

and step 3: evaluating the difference to determine an evaluation result:

wherein H is an evaluation result;

and 4, step 4: when the average absolute error, the root mean square error and the average relative error simultaneously meet a preset threshold value, determining that the value of an evaluation result H is 1, and establishing a stroke premonitory pathology model based on a deep neural network learning algorithm;

and 5: and when the average absolute error, the root mean square error and the average relative error do not meet the preset threshold, determining that the value of the evaluation result H is 0, representing that the correlation degree of the historical analysis result and the real-time collected analysis result is too small, and performing exception prompting.

Preferably, the real-time judgment whether the sign data of the object to be detected is abnormal or not, and the abnormal reminding is performed when the sign data is abnormal, including:

acquiring a timing acquisition frequency, and acquiring state sign data of an object to be detected according to the timing acquisition frequency;

acquiring historical sign data, and calculating variance fluctuation values of state sign data and historical state data;

judging whether the body health state of the object to be detected is abnormal or not according to the variance fluctuation value based on the stroke premonitory pathology model, and generating a judgment result;

when the judgment result is abnormal, triggering a preset alarm, and carrying out distress prompt on the terminal equipment bound with the wearable equipment sensor in advance;

and when the judgment result is normal, storing the state sign data into a preset storage database.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

The utility model provides a cerebral apoplexy intelligence early warning system which characterized in that includes:

a feature extraction module: the device comprises a sensor, a pulse wave processing module, a pulse processing module and a pulse characteristic point acquiring module, wherein the sensor is used for acquiring and processing an original pulse wave signal through a preset intelligent device sensor and determining the pulse characteristic point;

a data analysis module: the pulse characteristic points are transmitted to a preset big data analysis platform and are analyzed and calculated to determine sign data, and the sign data are transmitted to a preset artificial intelligence algorithm to be analyzed and processed to determine an analysis result; wherein,

the analysis result is used for judging whether the object to be detected has a cerebral apoplexy aura;

establishing a pathological model module: the system is used for establishing a stroke premonitory pathology model by periodically acquiring the analysis result and transmitting the analysis result to preset simulation equipment based on a deep neural network learning algorithm;

a real-time monitoring module: and the system is used for judging whether the sign data of the object to be detected is abnormal in real time according to the stroke occurrence premonitory pathology model and carrying out abnormity reminding when the sign data is abnormal.

Preferably, the feature extraction module includes:

acquiring an original pulse wave signal unit: the device comprises a wearable device sensor, a pulse wave signal generator and a pulse wave signal generator, wherein the wearable device sensor is used for detecting pulse sign information of a to-be-detected object at regular time and determining an original pulse wave signal of the to-be-detected object according to the pulse sign information;

an original pulse wave signal processing unit: the system is used for denoising, baseline removing and wavelet decomposition of the original pulse wave signals and determining preprocessed pulse wave signals;

a pulse wave feature point reconstruction unit: and the pulse wave characteristic signal point acquisition and reconstruction unit is used for acquiring and reconstructing a pulse wave characteristic signal point according to the preprocessed pulse wave signal and determining the pulse wave characteristic point.

Preferably, the data analysis module includes:

a transmission unit: the device comprises a big data analysis platform, a data acquisition module, a data analysis module and a data analysis module, wherein the big data analysis platform is used for acquiring pulse wave characteristic points and transmitting the pulse wave characteristic points to the big data analysis platform;

an analysis unit: the big data analysis platform is used for analyzing and calculating the characteristics of the transmitted pulse wave signals to obtain sign data; wherein,

the physical sign data at least comprises heart rate data, blood pressure data and blood oxygen data;

an analysis unit: and mining and screening the physical sign data of the user through a preset artificial intelligence algorithm, pushing out a corresponding treatment scheme, and determining an analysis result.

Preferably, the module for establishing a pathology model includes: a periodic acquisition unit: for collecting and obtaining analysis results Delta Re (Delta t, hr, bp, spo, F (m)) periodically,

wherein Δ Re (Δ t, hr, bp, spo, f (m)) represents an analysis result which is periodically collected and acquired, hr represents heart rate data of a to-be-detected object, bp represents blood pressure data of the to-be-detected object, and spo represents blood oxygen data of the to-be-detected object; Δ t time period for the collection of the object to be detected, f (m) represents the analysis data for the object to be detected based on the pre-entered traditional Chinese medicine thinking treatment data and western medicine clinical archive data;

a difference value calculation unit: the device is used for calculating a prediction analysis result in the simulation equipment according to the analysis result and determining a difference value between the analysis result and the prediction analysis result:

wherein,

represents the result of the i-th predictive analysis, Δ Re_iRepresenting the ith regularly acquired analysis result, n representing the total number of the acquired analysis results, i representing a natural number, i belongs to (1, n), MAE representing the average absolute error of the analysis results and the prediction analysis results, RMSE representing the root mean square error of the analysis results and the prediction analysis results, and MRE representing the average relative error of the analysis results and the prediction analysis results; w is a_iRepresenting the weight matrix corresponding to the ith analysis result, b_iRepresenting the bias vector corresponding to the analysis result;

an evaluation unit: the device is used for evaluating the difference value and determining an evaluation result:

wherein H is an evaluation result;

establishing a pathological model unit: and when the average absolute error, the root mean square error and the average relative error simultaneously meet a preset threshold, determining that the value of the evaluation result H is 1, and establishing a stroke premonitory pathology model based on a deep neural network learning algorithm.

An abnormality presentation unit: and when the average absolute error, the root mean square error and the average relative error do not meet the preset threshold, determining that the value of the evaluation result H is 0, representing that the correlation degree of the historical analysis result and the real-time acquired analysis result is too small, and performing exception prompting.

Preferably, the real-time monitoring module includes:

status sign data unit: the system comprises a timing acquisition frequency acquisition unit, a data acquisition unit and a data acquisition unit, wherein the timing acquisition frequency acquisition unit is used for acquiring timing acquisition frequency and acquiring state sign data of an object to be detected according to the timing acquisition frequency;

variance fluctuation value unit: the system is used for acquiring historical sign data and calculating variance fluctuation values of the state sign data and the historical state data;

a judging unit: the system is used for judging whether the body health state of a to-be-detected object is abnormal or not according to the variance fluctuation value based on the stroke occurrence premonitory pathology model and generating a judgment result;

a judgment result abnormality unit: the alarm device is used for triggering a preset alarm when the judgment result is abnormal, and giving a help-seeking prompt to the terminal device pre-bound by the intelligent device sensor;

a judgment result normal unit: and the data processing module is used for storing the state sign data to a preset storage database when the judgment result is normal.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:

fig. 1 is a flow chart of a method of an intelligent stroke warning system according to an embodiment of the present invention;

fig. 2 is a block diagram of a system flow of an intelligent stroke warning system according to an embodiment of the present invention;

fig. 3 is a system flow chart of an intelligent stroke warning method according to an embodiment of the present invention.

Detailed Description

The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.

Example 1:

as shown in fig. 1, the present technical solution provides an intelligent stroke early warning method, including:

acquiring and processing an original pulse wave signal through a preset wearable device sensor, and determining a pulse characteristic point;

transmitting the pulse characteristic points to a preset big data analysis platform, carrying out analysis calculation, determining sign data, transmitting the sign data to a preset artificial intelligence algorithm for analysis processing, and determining an analysis result; wherein,

the analysis result is used for judging whether the object to be detected has a cerebral apoplexy aura;

based on a deep neural network learning algorithm, establishing a stroke premonitory pathology model by periodically collecting the analysis result and transmitting the analysis result to preset simulation equipment;

and judging whether the sign data of the object to be detected is abnormal in real time according to the stroke occurrence premonitory pathology model, and carrying out abnormity reminding when the sign data is abnormal.

The working principle of the technical scheme is as follows:

the embodiment of the invention provides an intelligent stroke early warning system and method, which comprises a feature extraction module, a data analysis module, a pathology model building module and a real-time monitoring module, wherein the feature extraction module is used for extracting feature information of a brain stroke; wherein,

the characteristic extraction module is used for acquiring an original pulse wave signal of a to-be-detected object through a preset wearable device sensor, determining original pulse wave information of the to-be-detected object, processing the original pulse wave signal, determining pulse characteristic points, wherein the pulse of a human body regularly beats along with the flow of heartbeat and blood, and different people or one person does not coincide before and after movement, so that the pulse characteristic points of the to-be-detected object are constructed by acquiring the original pulse wave signal of the to-be-detected object, the pulse characteristic points are transmitted to a preset big data analysis platform through the data analysis module and are analyzed and calculated, sign data are determined, and the sign data are transmitted to a preset artificial intelligence algorithm for analysis and processing, and an analysis result is determined; the analysis result is used for judging whether a stroke precursor exists in the object to be detected or not; the cerebral apoplexy is also called apoplexy and cerebrovascular accident, is an acute cerebrovascular disease, is a group of diseases caused by brain tissue damage due to the fact that blood cannot flow into the brain because of sudden rupture of cerebral vessels or blockage of blood vessels, and comprises ischemic stroke and hemorrhagic stroke, wherein the incidence rate of the ischemic stroke is higher than that of the hemorrhagic stroke, and accounts for 60% -70% of the total number of the cerebral stroke. The internal carotid artery and vertebral artery occlusion and stenosis can cause ischemic stroke, the age is more than 40 years old, more men than women and severe people can cause death, when the stroke occurs, abnormal phenomena such as arrhythmia, ischemia and the like are often accompanied, people can deduce the physiological condition of an object to be detected from the previous data of the object to be detected, so that a pathological model module is established based on a deep neural network learning algorithm, a premonitory pathological model of the stroke is established by regularly collecting the analysis result and transmitting the analysis result to preset simulation equipment, quantitative data of the object to be detected are collected, the influence of physical factors of the object to be detected is determined, whether the object to be detected has the risk of the stroke is judged, a corresponding pathological model is established, the whole process is established through a real-time monitoring module, and whether the physical sign data of the object to be detected are abnormal or not is judged in real time, and when the physical sign data is abnormal, performing abnormal reminding.

The beneficial effects of the above technical scheme are:

according to the technical scheme, the object to be detected acquires pulse wave data by wearing the morton early warning watch and uploads the pulse wave data to the data analysis platform, the platform fuses traditional Chinese medicine thinking and western medicine clinic together by using an artificial intelligence algorithm through acquired heart rate data and the like, and whether the object to be detected has potential stroke risks or not is analyzed according to an established stroke occurrence precursor pathological model. When cerebral apoplexy occurs, the brain apoplexy can be effectively treated within the gold treatment time, but the gold treatment time is short, and many people lose lives because of not being treated in time.

Example 2:

this technical scheme provides an embodiment, through the wearing equipment sensor of predetermineeing, acquire and handle original pulse wave signal, confirm the pulse characteristic point, include:

the method comprises the steps that pulse sign information of a to-be-detected object is detected regularly through a preset wearable device sensor, and an original pulse wave signal of the to-be-detected object is determined according to the pulse sign information;

denoising, baseline removing and wavelet decomposition are carried out on the original pulse wave signals, and preprocessed pulse wave signals are determined;

and acquiring and reconstructing pulse wave characteristic signal points according to the preprocessed pulse wave signals, and determining the pulse wave characteristic points.

The working principle of the technical scheme is as follows:

the feature extraction module of the technical scheme comprises an original pulse wave signal acquisition unit, an original pulse wave signal processing unit and a pulse wave feature point reconstruction unit; firstly, acquiring an original pulse wave signal of an object to be detected by an original pulse wave signal acquisition unit and a preset wearable device sensor; the wearable device sensor is an electronic device which can be worn on the wrist of an object to be detected, collects the pulse information of the object to be detected in real time, then carries out noise reduction, baseline removal and wavelet decomposition on the original pulse wave signal through an original pulse wave signal processing unit, determines a preprocessed pulse wave signal, and needs to process the original pulse wave signal only because the original pulse wave signal only comprises the dynamic pulse characteristic of the pulse, thereby obtaining the pulse rule of the pulse signal, determines a normal range through the personal information of the object to be detected, and needs to collect the personal information of the object to be detected because the pulse wave characteristics of the objects to be detected with different ages, sexes, heights and weights are not completely the same, calculates the pulse of the object to be detected, and determines the pulse characteristic point of the object to be detected, and then reconstructing pulse wave characteristic points according to the preprocessed pulse wave signals by a pulse wave characteristic point reconstruction unit.

The beneficial effects of the above technical scheme are:

according to the technical scheme, the pulse wave characteristic points of the object to be detected are reconstructed, so that the operation rule of the pulse wave signals of the object to be detected is determined, the pulse characteristic points of the object to be detected are flexibly reconstructed according to the pulse signal rules of the object to be detected with different physiques at different ages, the pulse characteristics of the object to be detected are determined, and safe and healthy real-time monitoring is timely performed.

Example 3:

the present solution provides an example of an implementation,

preferably, the transmitting the pulse feature points to a preset big data analysis platform, performing analysis calculation, determining sign data, transmitting the sign data to a preset artificial intelligence algorithm, performing analysis processing, and determining an analysis result includes:

acquiring pulse wave characteristic points, and transmitting the pulse wave characteristic points to a big data analysis platform;

analyzing and calculating to obtain sign data by analyzing the characteristics of the transmitted pulse wave signals on the basis of the big data analysis platform; wherein,

the physical sign data at least comprises heart rate data, blood pressure data and blood oxygen data;

and mining and screening the physical sign data of the user through a preset artificial intelligence algorithm, pushing out a corresponding treatment scheme, and determining an analysis result.

The working principle of the technical scheme is as follows:

the data analysis module comprises a transmission unit, an analysis unit and an analysis unit, wherein pulse wave characteristic points are obtained through the transmission unit at first and are transmitted to a big data analysis platform, so that pulse wave characteristic data are determined, then the sign data are obtained through analysis and calculation through the analysis unit based on the big data analysis platform and through analyzing the transmitted pulse wave signal characteristics, the exclusive data of a to-be-detected object are determined through analysis of the pulse wave signal characteristics in the whole process, wherein the sign data at least comprise heart rate data, blood pressure data and blood oxygen data, and finally the sign data are analyzed and processed through the analysis unit based on a preset artificial intelligence algorithm, so that an analysis result is determined; the artificial intelligence algorithm is characterized in that traditional Chinese medicine thinking and western medicine clinical archive data are input in advance, the traditional Chinese medicine thinking and western medicine clinical archive data cover a large number of traditional Chinese medicine and western medicine treatment schemes, traditional Chinese medicine and western medicine treatment is selected according to different conditions of an object to be detected, traditional Chinese medicine tends to medical treatment, the traditional Chinese medicine treatment process is slow and not aggressive, the western medicine treatment generally refers to treatment of a patient by performing a surgical operation at a crisis moment, condition selection is performed according to different conditions of the patient, therefore when the object to be detected is slightly premonitory, the object to be detected is reminded to go to a hospital to see a doctor and display the traditional Chinese medicine treatment scheme, when the risk of the object to be detected is high, an alarm is given, the relatives of the object to be detected are reminded to send the hospital emergency call, and the western medicine clinical treatment case is determined.

The beneficial effects of the above technical scheme are:

when the cerebral apoplexy takes place, can effective treatment in the gold treatment time, however the gold treatment time is shorter, many people lose life because of can not in time treating, this technical scheme passes through the integration of traditional chinese medical science thinking and western medicine clinical, not only having played at ordinary times health maintenance and suggestion to patient, and at the critical moment, carry out the crisis to patient and remind, establish corresponding pathological model, remind the terminal that the wearing equipment sensor that predetermines that waits to detect the object binds, in time rescue, the loss of property of people has been reduced, the sudden disease risk of waiting to detect the object has been reduced.

Example 4:

the technical scheme provides an embodiment, the method for establishing a stroke premonitory pathology model by periodically collecting the analysis result and transmitting the analysis result to preset simulation equipment based on a deep neural network learning algorithm comprises the following steps:

step 1: collecting and obtaining analysis result delta Re (delta t, hr, bp, spo, F (m)) periodically,

wherein Δ Re (Δ t, hr, bp, spo, f (m)) represents an analysis result which is periodically collected and acquired, hr represents heart rate data of a to-be-detected object, bp represents blood pressure data of the to-be-detected object, and spo represents blood oxygen data of the to-be-detected object; Δ t time period for the collection of the object to be detected, f (m) represents the analysis data for the object to be detected based on the pre-entered traditional Chinese medicine thinking treatment data and western medicine clinical archive data;

step 2: according to the analysis result, calculating a prediction analysis result in the simulation equipment, and determining a difference value between the analysis result and the prediction analysis result:

wherein,

represents the result of the i-th predictive analysis, Δ Re_iRepresenting the ith regularly acquired analysis result, n representing the total number of the acquired analysis results, i representing a natural number, i belongs to (1, n), MAE representing the average absolute error of the analysis results and the prediction analysis results, RMSE representing the root mean square error of the analysis results and the prediction analysis results, and MRE representing the average relative error of the analysis results and the prediction analysis results; w is a_iRepresenting the weight matrix corresponding to the ith analysis result, b_iRepresenting the bias vector corresponding to the analysis result;

and step 3: evaluating the difference to determine an evaluation result:

wherein H is an evaluation result;

and 4, step 4: when the average absolute error, the root mean square error and the average relative error simultaneously meet a preset threshold value, determining that the value of an evaluation result H is 1, and establishing a stroke premonitory pathology model based on a deep neural network learning algorithm;

and 5: and when the average absolute error, the root mean square error and the average relative error do not meet the preset threshold, determining that the value of the evaluation result H is 0, representing that the correlation degree of the historical analysis result and the real-time collected analysis result is too small, and performing exception prompting.

The working principle and the beneficial effects of the technical scheme are as follows:

the module for establishing a pathological model in the technical scheme regularly acquires and acquires an analysis result delta Re (delta t, hr, bp, spo, F (m)) through a regular acquisition unit, calculates a prediction analysis result in simulation equipment according to the analysis result by using a difference value calculation unit, determines a difference value between the analysis result and the prediction analysis result, evaluates the difference value through an evaluation unit, determines an evaluation result, and finally establishes a pathological model unit aiming at the evaluation result: and when the average absolute error, the root mean square error and the average relative error simultaneously meet a preset threshold, determining that the value of the evaluation result H is 1, and establishing a stroke premonitory pathology model based on a deep neural network learning algorithm. An abnormality presentation unit: and when the average absolute error, the root mean square error and the average relative error do not meet the preset threshold, determining that the value of the evaluation result H is 0, representing that the correlation degree between the historical analysis result and the real-time acquired analysis result is too small, performing exception prompting, reducing the risk of the evaluation result, reducing the risk loss of the established model, planning in advance, avoiding the risk of a rule, improving the modeling efficiency, reducing the modeling cost and improving the accuracy of modeling.

Example 5:

the technical scheme provides an embodiment, the method for judging whether the sign data of a to-be-detected object is abnormal in real time according to the stroke premonitory pathology model, and performing abnormity reminding when the sign data is abnormal includes:

acquiring a timing acquisition frequency, and acquiring state sign data of an object to be detected according to the timing acquisition frequency;

acquiring historical sign data, and calculating variance fluctuation values of state sign data and historical state data;

judging whether the body health state of the object to be detected is abnormal or not according to the variance fluctuation value based on the stroke premonitory pathology model, and generating a judgment result;

when the judgment result is abnormal, triggering a preset alarm, and carrying out distress prompt on the terminal equipment bound with the wearable equipment sensor in advance;

and when the judgment result is normal, storing the state sign data into a preset storage database.

The working principle and the beneficial effects of the technical scheme are as follows:

the real-time monitoring module comprises a state sign data unit, a variance fluctuation value unit, a judging result abnormal unit and a judging result normal unit, wherein the state sign data unit is used for acquiring a timing acquisition frequency, acquiring state sign data of an object to be detected according to the timing acquisition frequency, and determining the current body data of the object to be detected, and the variance fluctuation value unit: the system is used for acquiring historical sign data and calculating variance fluctuation values of the state sign data and the historical state data; the variance value is used for determining whether the body of the object to be detected has unstable and large difference, judging whether the health state of the object to be detected is abnormal or not according to the variance fluctuation value by the judging unit and generating a judging result, and is used for judging whether the body of the object to be detected is different from the body of the object to be detected in the past or not, and finally triggering a preset alarm and prompting the wearing device sensor to ask for help by the judging unit when the judging result is normal by the judging unit, and storing the state sign data to a preset storage database when the judging result is normal, so as to carry out characteristic statistics on the body of the object to be detected, and the technical scheme can also be based on the biological data of human body at the beginning by inputting the biological data of the body of the object to be detected in advance, when the wearing equipment sensor is not worn by the object to be detected, sudden cerebral apoplexy caused by the fact that body characteristic data of the object to be detected is not collected, so that the risk of the object to be detected is reduced, the object to be detected is protected by heavy safety guarantee, the sudden cerebral apoplexy of the object to be detected is avoided, and the loss of the body and property of people is reduced.

Example 6:

according to fig. 2, an intelligent early warning system for stroke is characterized by comprising:

a feature extraction module: the device comprises a sensor, a pulse wave processing module, a pulse processing module and a pulse characteristic point acquiring module, wherein the sensor is used for acquiring and processing an original pulse wave signal through a preset intelligent device sensor and determining the pulse characteristic point;

a data analysis module: the pulse characteristic points are transmitted to a preset big data analysis platform and are analyzed and calculated to determine sign data, and the sign data are transmitted to a preset artificial intelligence algorithm to be analyzed and processed to determine an analysis result; wherein,

the analysis result is used for judging whether the object to be detected has a cerebral apoplexy aura;

establishing a pathological model module: the system is used for establishing a stroke premonitory pathology model by periodically acquiring the analysis result and transmitting the analysis result to preset simulation equipment based on a deep neural network learning algorithm;

a real-time monitoring module: and the system is used for judging whether the sign data of the object to be detected is abnormal in real time according to the stroke occurrence premonitory pathology model and carrying out abnormity reminding when the sign data is abnormal.

The working principle of the technical scheme is as follows:

the embodiment of the invention provides an intelligent stroke early warning system and method, which comprises a feature extraction module, a data analysis module, a pathology model building module and a real-time monitoring module, wherein the feature extraction module is used for extracting feature information of a brain stroke; wherein,

the characteristic extraction module is used for acquiring an original pulse wave signal of a to-be-detected object through a preset wearable device sensor, determining original pulse wave information of the to-be-detected object, processing the original pulse wave signal, determining pulse characteristic points, wherein the pulse of a human body regularly beats along with the flow of heartbeat and blood, and different people or one person does not coincide before and after movement, so that the pulse characteristic points of the to-be-detected object are constructed by acquiring the original pulse wave signal of the to-be-detected object, the pulse characteristic points are transmitted to a preset big data analysis platform through the data analysis module and are analyzed and calculated, sign data are determined, and the sign data are transmitted to a preset artificial intelligence algorithm for analysis and processing, and an analysis result is determined; the analysis result is used for judging whether a stroke precursor exists in the object to be detected or not; the cerebral apoplexy is also called apoplexy and cerebrovascular accident, is an acute cerebrovascular disease, is a group of diseases caused by brain tissue damage due to the fact that blood cannot flow into the brain because of sudden rupture of cerebral vessels or blockage of blood vessels, and comprises ischemic stroke and hemorrhagic stroke, wherein the incidence rate of the ischemic stroke is higher than that of the hemorrhagic stroke, and accounts for 60% -70% of the total number of the cerebral stroke. The internal carotid artery and vertebral artery occlusion and stenosis can cause ischemic stroke, the age is more than 40 years old, more men than women and severe people can cause death, when the stroke occurs, abnormal phenomena such as arrhythmia, ischemia and the like are often accompanied, people can deduce the physiological condition of an object to be detected from the previous data of the object to be detected, so that a pathological model module is established based on a deep neural network learning algorithm, a premonitory pathological model of the stroke is established by regularly collecting the analysis result and transmitting the analysis result to preset simulation equipment, quantitative data of the object to be detected are collected, the influence of physical factors of the object to be detected is determined, whether the object to be detected has the risk of the stroke is judged, a corresponding pathological model is established, the whole process is established through a real-time monitoring module, and whether the physical sign data of the object to be detected are abnormal or not is judged in real time, and when the physical sign data is abnormal, performing abnormal reminding.

The beneficial effects of the above technical scheme are:

according to the technical scheme, the object to be detected acquires pulse wave data by wearing the morton early warning watch and uploads the pulse wave data to the data analysis platform, the platform fuses traditional Chinese medicine thinking and western medicine clinic together by using an artificial intelligence algorithm through acquired heart rate data and the like, and whether the object to be detected has potential stroke risks or not is analyzed according to an established stroke occurrence precursor pathological model. When cerebral apoplexy occurs, the brain apoplexy can be effectively treated within the gold treatment time, but the gold treatment time is short, and many people lose lives because of not being treated in time.

Example 7:

as shown in fig. 2, the present technical solution provides an embodiment, where the feature extraction module includes:

acquiring an original pulse wave signal unit: the device comprises a wearable device sensor, a pulse wave signal generator and a pulse wave signal generator, wherein the wearable device sensor is used for detecting pulse sign information of a to-be-detected object at regular time and determining an original pulse wave signal of the to-be-detected object according to the pulse sign information;

an original pulse wave signal processing unit: the system is used for denoising, baseline removing and wavelet decomposition of the original pulse wave signals and determining preprocessed pulse wave signals;

a pulse wave feature point reconstruction unit: and the pulse wave characteristic signal point acquisition and reconstruction unit is used for acquiring and reconstructing a pulse wave characteristic signal point according to the preprocessed pulse wave signal and determining the pulse wave characteristic point.

The working principle of the technical scheme is as follows:

the feature extraction module of the technical scheme comprises an original pulse wave signal acquisition unit, an original pulse wave signal processing unit and a pulse wave feature point reconstruction unit; firstly, acquiring an original pulse wave signal of an object to be detected by an original pulse wave signal acquisition unit and a preset wearable device sensor; the wearable device sensor is an electronic device which can be worn on the wrist of an object to be detected, collects the pulse information of the object to be detected in real time, then carries out noise reduction, baseline removal and wavelet decomposition on the original pulse wave signal through an original pulse wave signal processing unit, determines a preprocessed pulse wave signal, and needs to process the original pulse wave signal only because the original pulse wave signal only comprises the dynamic pulse characteristic of the pulse, thereby obtaining the pulse rule of the pulse signal, determines a normal range through the personal information of the object to be detected, and needs to collect the personal information of the object to be detected because the pulse wave characteristics of the objects to be detected with different ages, sexes, heights and weights are not completely the same, calculates the pulse of the object to be detected, and determines the pulse characteristic point of the object to be detected, and then reconstructing pulse wave characteristic points according to the preprocessed pulse wave signals by a pulse wave characteristic point reconstruction unit.

The beneficial effects of the above technical scheme are:

according to the technical scheme, the pulse wave characteristic points of the object to be detected are reconstructed, so that the operation rule of the pulse wave signals of the object to be detected is determined, the pulse characteristic points of the object to be detected are flexibly reconstructed according to the pulse signal rules of the object to be detected with different physiques at different ages, the pulse characteristics of the object to be detected are determined, and safe and healthy real-time monitoring is timely performed.

Example 8:

this technical solution provides an embodiment, and the data analysis module includes:

a transmission unit: the device comprises a big data analysis platform, a data acquisition module, a data analysis module and a data analysis module, wherein the big data analysis platform is used for acquiring pulse wave characteristic points and transmitting the pulse wave characteristic points to the big data analysis platform;

an analysis unit: the big data analysis platform is used for analyzing and calculating the characteristics of the transmitted pulse wave signals to obtain sign data; wherein,

the physical sign data at least comprises heart rate data, blood pressure data and blood oxygen data;

an analysis unit: and mining and screening the physical sign data of the user through a preset artificial intelligence algorithm, pushing out a corresponding treatment scheme, and determining an analysis result.

The working principle of the technical scheme is as follows:

the data analysis module comprises a transmission unit, an analysis unit and an analysis unit, wherein pulse wave characteristic points are obtained through the transmission unit at first and are transmitted to a big data analysis platform, so that pulse wave characteristic data are determined, then the sign data are obtained through analysis and calculation through the analysis unit based on the big data analysis platform and through analyzing the transmitted pulse wave signal characteristics, the exclusive data of a to-be-detected object are determined through analysis of the pulse wave signal characteristics in the whole process, wherein the sign data at least comprise heart rate data, blood pressure data and blood oxygen data, and finally the sign data are analyzed and processed through the analysis unit based on a preset artificial intelligence algorithm, so that an analysis result is determined; the artificial intelligence algorithm is characterized in that traditional Chinese medicine thinking and western medicine clinical archive data are input in advance, the traditional Chinese medicine thinking and western medicine clinical archive data cover a large number of traditional Chinese medicine and western medicine treatment schemes, traditional Chinese medicine and western medicine treatment is selected according to different conditions of an object to be detected, traditional Chinese medicine tends to medical treatment, the traditional Chinese medicine treatment process is slow and not aggressive, the western medicine treatment generally refers to treatment of a patient by performing a surgical operation at a crisis moment, condition selection is performed according to different conditions of the patient, therefore when the object to be detected is slightly premonitory, the object to be detected is reminded to go to a hospital to see a doctor and display the traditional Chinese medicine treatment scheme, when the risk of the object to be detected is high, an alarm is given, the relatives of the object to be detected are reminded to send the hospital emergency call, and the western medicine clinical treatment case is determined.

The beneficial effects of the above technical scheme are:

when the cerebral apoplexy takes place, can effective treatment in the gold treatment time, however the gold treatment time is shorter, many people lose life because of can not in time treating, this technical scheme passes through the integration of traditional chinese medical science thinking and western medicine clinical, not only having played at ordinary times health maintenance and suggestion to patient, and at the critical moment, carry out the crisis to patient and remind, establish corresponding pathological model, remind the terminal that the wearing equipment sensor that predetermines that waits to detect the object binds, in time rescue, the loss of property of people has been reduced, the sudden disease risk of waiting to detect the object has been reduced.

Example 9:

the technical solution provides an embodiment, wherein the module for establishing a pathological model includes: a periodic acquisition unit: for collecting and obtaining analysis results Delta Re (Delta t, hr, bp, spo, F (m)) periodically,

wherein Δ Re (Δ t, hr, bp, spo, f (m)) represents an analysis result which is periodically collected and acquired, hr represents heart rate data of a to-be-detected object, bp represents blood pressure data of the to-be-detected object, and spo represents blood oxygen data of the to-be-detected object; Δ t time period for the collection of the object to be detected, f (m) represents the analysis data for the object to be detected based on the pre-entered traditional Chinese medicine thinking treatment data and western medicine clinical archive data;

a difference value calculation unit: the device is used for calculating a prediction analysis result in the simulation equipment according to the analysis result and determining a difference value between the analysis result and the prediction analysis result:

wherein,

represents the result of the i-th predictive analysis, Δ Re_iRepresenting the ith regularly acquired analysis result, n representing the total number of the acquired analysis results, i representing a natural number, i belongs to (1, n), MAE representing the average absolute error of the analysis results and the prediction analysis results, RMSE representing the root mean square error of the analysis results and the prediction analysis results, and MRE representing the average relative error of the analysis results and the prediction analysis results; w is a_iRepresenting the weight matrix corresponding to the ith analysis result, b_iRepresenting the bias vector corresponding to the analysis result;

an evaluation unit: the device is used for evaluating the difference value and determining an evaluation result:

wherein H is an evaluation result;

establishing a pathological model unit: and when the average absolute error, the root mean square error and the average relative error simultaneously meet a preset threshold, determining that the value of the evaluation result H is 1, and establishing a stroke premonitory pathology model based on a deep neural network learning algorithm.

An abnormality presentation unit: and when the average absolute error, the root mean square error and the average relative error do not meet the preset threshold, determining that the value of the evaluation result H is 0, representing that the correlation degree of the historical analysis result and the real-time acquired analysis result is too small, and performing exception prompting.

The working principle and the beneficial effects of the technical scheme are as follows:

the module for establishing a pathological model in the technical scheme regularly acquires and acquires an analysis result delta Re (delta t, hr, bp, spo, F (m)) through a regular acquisition unit, calculates a prediction analysis result in simulation equipment according to the analysis result by using a difference value calculation unit, determines a difference value between the analysis result and the prediction analysis result, evaluates the difference value through an evaluation unit, determines an evaluation result, and finally establishes a pathological model unit aiming at the evaluation result: and when the average absolute error, the root mean square error and the average relative error simultaneously meet a preset threshold, determining that the value of the evaluation result H is 1, and establishing a stroke premonitory pathology model based on a deep neural network learning algorithm. An abnormality presentation unit: and when the average absolute error, the root mean square error and the average relative error do not meet the preset threshold, determining that the value of the evaluation result H is 0, representing that the correlation degree between the historical analysis result and the real-time acquired analysis result is too small, performing exception prompting, reducing the risk of the evaluation result, reducing the risk loss of the established model, planning in advance, avoiding the risk of a rule, improving the modeling efficiency, reducing the modeling cost and improving the accuracy of modeling.

Example 10:

this technical scheme provides an embodiment, real time monitoring module includes:

status sign data unit: the system comprises a timing acquisition frequency acquisition unit, a data acquisition unit and a data acquisition unit, wherein the timing acquisition frequency acquisition unit is used for acquiring timing acquisition frequency and acquiring state sign data of an object to be detected according to the timing acquisition frequency;

variance fluctuation value unit: the system is used for acquiring historical sign data and calculating variance fluctuation values of the state sign data and the historical state data;

a judging unit: the system is used for judging whether the body health state of a to-be-detected object is abnormal or not according to the variance fluctuation value based on the stroke occurrence premonitory pathology model and generating a judgment result;

a judgment result abnormality unit: the alarm device is used for triggering a preset alarm when the judgment result is abnormal, and giving a help-seeking prompt to the terminal device pre-bound by the intelligent device sensor;

a judgment result normal unit: and the data processing module is used for storing the state sign data to a preset storage database when the judgment result is normal.

The working principle and the beneficial effects of the technical scheme are as follows:

the real-time monitoring module comprises a state sign data unit, a variance fluctuation value unit, a judging result abnormal unit and a judging result normal unit, wherein the state sign data unit is used for acquiring a timing acquisition frequency, acquiring state sign data of an object to be detected according to the timing acquisition frequency, and determining the current body data of the object to be detected, and the variance fluctuation value unit: the system is used for acquiring historical sign data and calculating variance fluctuation values of the state sign data and the historical state data; the variance value is used for determining whether the body of the object to be detected has unstable and large difference, judging whether the health state of the object to be detected is abnormal or not according to the variance fluctuation value by the judging unit and generating a judging result, and is used for judging whether the body of the object to be detected is different from the body of the object to be detected in the past or not, and finally triggering a preset alarm and prompting the wearing device sensor to ask for help by the judging unit when the judging result is normal by the judging unit, and storing the state sign data to a preset storage database when the judging result is normal, so as to carry out characteristic statistics on the body of the object to be detected, and the technical scheme can also be based on the biological data of human body at the beginning by inputting the biological data of the body of the object to be detected in advance, when the wearing equipment sensor is not worn by the object to be detected, sudden cerebral apoplexy caused by the fact that body characteristic data of the object to be detected is not collected, so that the risk of the object to be detected is reduced, the object to be detected is protected by heavy safety guarantee, the sudden cerebral apoplexy of the object to be detected is avoided, and the loss of the body and property of people is reduced.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A stroke intelligent early warning method is characterized by comprising the following steps:

acquiring and processing an original pulse wave signal through a preset wearable device sensor, and determining a pulse characteristic point;

transmitting the pulse characteristic points to a preset big data analysis platform, carrying out analysis calculation, determining sign data, transmitting the sign data to a preset artificial intelligence algorithm for analysis processing, and determining an analysis result; wherein,

the analysis result is used for judging whether the object to be detected has a cerebral apoplexy aura;

based on a deep neural network learning algorithm, establishing a stroke premonitory pathology model by periodically collecting the analysis result and transmitting the analysis result to preset simulation equipment;

and judging whether the sign data of the object to be detected is abnormal in real time according to the stroke occurrence premonitory pathology model, and carrying out abnormity reminding when the sign data is abnormal.

2. The intelligent early warning method for cerebral apoplexy according to claim 1, wherein the obtaining and processing of the original pulse wave signal by the preset wearable device sensor to determine the pulse feature point comprises:

the method comprises the steps that pulse sign information of a to-be-detected object is detected regularly through a preset wearable device sensor, and an original pulse wave signal of the to-be-detected object is determined according to the pulse sign information;

denoising, baseline removing and wavelet decomposition are carried out on the original pulse wave signals, and preprocessed pulse wave signals are determined;

and acquiring and reconstructing pulse wave characteristic signal points according to the preprocessed pulse wave signals, and determining the pulse wave characteristic points.

3. The intelligent early warning system and method for cerebral apoplexy according to claim 1, wherein the steps of transmitting the pulse feature points to a preset big data analysis platform, performing analysis calculation, determining sign data, transmitting the sign data to a preset artificial intelligence algorithm for analysis processing, and determining an analysis result include:

acquiring pulse wave characteristic points, and transmitting the pulse wave characteristic points to a big data analysis platform;

analyzing the characteristics of the transmitted pulse wave signals based on the big data analysis platform, and analyzing and calculating to obtain sign data; wherein,

the physical sign data at least comprises heart rate data, blood pressure data and blood oxygen data;

and mining and screening the physical sign data of the user through a preset artificial intelligence algorithm, pushing out a corresponding treatment scheme, and determining an analysis result.

4. The intelligent early warning method for stroke according to claim 1, wherein the deep neural network learning algorithm is used for establishing a stroke premonitory pathology model by periodically collecting the analysis result and transmitting the analysis result to a preset simulation device, and the method comprises the following steps:

step 1: collecting and obtaining analysis results delta Re (delta t, hr, bp, spo, F (m)) periodically;

wherein Δ Re (Δ t, hr, bp, spo, f (m)) represents an analysis result which is periodically collected and acquired, hr represents heart rate data of a to-be-detected object, bp represents blood pressure data of the to-be-detected object, and spo represents blood oxygen data of the to-be-detected object; Δ t time period for the collection of the object to be detected, f (m) represents the analysis data for the object to be detected based on the pre-entered traditional Chinese medicine thinking treatment data and western medicine clinical archive data;

step 2: according to the analysis result, calculating a prediction analysis result in the simulation equipment, and determining a difference value between the analysis result and the prediction analysis result:

wherein,

represents the result of the i-th predictive analysis, Δ Re_iRepresenting the ith regularly acquired analysis result, n representing the total number of the acquired analysis results, i representing a natural number, i belongs to (1, n), MAE representing the average absolute error of the analysis results and the prediction analysis results, RMSE representing the root mean square error of the analysis results and the prediction analysis results, and MRE representing the average relative error of the analysis results and the prediction analysis results; w is a_iRepresenting the weight matrix corresponding to the ith analysis result, b_iRepresenting the bias vector corresponding to the analysis result;

and step 3: evaluating the difference to determine an evaluation result:

wherein H is an evaluation result;

and 4, step 4: when the average absolute error, the root mean square error and the average relative error simultaneously meet a preset threshold value, determining that the value of an evaluation result H is 1, and establishing a stroke premonitory pathology model based on a deep neural network learning algorithm;

and 5: and when the average absolute error, the root mean square error and the average relative error do not meet the preset threshold, determining that the value of the evaluation result H is 0, representing that the correlation degree of the historical analysis result and the real-time collected analysis result is too small, and performing exception prompting.

5. The intelligent early warning method for cerebral apoplexy according to claim 1, wherein the judging whether the sign data of the subject to be detected is abnormal in real time according to the model of premonitory pathology caused by cerebral apoplexy, and performing an abnormality prompt when the sign data is abnormal comprises:

acquiring a timing acquisition frequency, and acquiring state sign data of an object to be detected according to the timing acquisition frequency;

acquiring historical sign data, and calculating variance fluctuation values of state sign data and historical state data;

judging whether the body health state of the object to be detected is abnormal or not according to the variance fluctuation value based on the stroke premonitory pathology model, and generating a judgment result;

when the judgment result is abnormal, triggering a preset alarm, and carrying out distress prompt on the terminal equipment bound with the wearable equipment sensor in advance;

and when the judgment result is normal, storing the state sign data into a preset storage database.

6. The utility model provides a cerebral apoplexy intelligence early warning system which characterized in that includes:

a feature extraction module: the device comprises a sensor, a pulse wave processing module, a pulse processing module and a pulse characteristic point acquiring module, wherein the sensor is used for acquiring and processing an original pulse wave signal through a preset intelligent device sensor and determining the pulse characteristic point;

a data analysis module: the pulse characteristic points are transmitted to a preset big data analysis platform and are analyzed and calculated to determine sign data, and the sign data are transmitted to a preset artificial intelligence algorithm to be analyzed and processed to determine an analysis result; wherein,

the analysis result is used for judging whether the object to be detected has a cerebral apoplexy aura;

establishing a pathological model module: the system is used for establishing a stroke premonitory pathology model by periodically acquiring the analysis result and transmitting the analysis result to preset simulation equipment based on a deep neural network learning algorithm;

a real-time monitoring module: and the system is used for judging whether the sign data of the object to be detected is abnormal in real time according to the stroke occurrence premonitory pathology model and carrying out abnormity reminding when the sign data is abnormal.

7. The intelligent early warning system for stroke according to claim 6, wherein the feature extraction module comprises:

acquiring an original pulse wave signal unit: the device comprises a wearable device sensor, a pulse wave signal generator and a pulse wave signal generator, wherein the wearable device sensor is used for detecting pulse sign information of a to-be-detected object at regular time and determining an original pulse wave signal of the to-be-detected object according to the pulse sign information;

an original pulse wave signal processing unit: the system is used for denoising, baseline removing and wavelet decomposition of the original pulse wave signals and determining preprocessed pulse wave signals;

a pulse wave feature point reconstruction unit: and the pulse wave characteristic signal point acquisition and reconstruction unit is used for acquiring and reconstructing a pulse wave characteristic signal point according to the preprocessed pulse wave signal and determining the pulse wave characteristic point.

8. The intelligent early warning system for stroke according to claim 6, wherein the data analysis module comprises:

a transmission unit: the device comprises a big data analysis platform, a data acquisition module, a data analysis module and a data analysis module, wherein the big data analysis platform is used for acquiring pulse wave characteristic points and transmitting the pulse wave characteristic points to the big data analysis platform;

an analysis unit: the big data analysis platform is used for analyzing and calculating the characteristics of the transmitted pulse wave signals to obtain sign data; wherein,

the physical sign data at least comprises heart rate data, blood pressure data and blood oxygen data;

an analysis unit: and mining and screening the physical sign data of the user through a preset artificial intelligence algorithm, pushing out a corresponding treatment scheme, and determining an analysis result.

9. The intelligent stroke warning system of claim 6, wherein the pathology model establishing module comprises: a periodic acquisition unit: for collecting and obtaining analysis results Delta Re (Delta t, hr, bp, spo, F (m)) periodically,

wherein Δ Re (Δ t, hr, bp, spo, f (m)) represents an analysis result which is periodically collected and acquired, hr represents heart rate data of a to-be-detected object, bp represents blood pressure data of the to-be-detected object, and spo represents blood oxygen data of the to-be-detected object; Δ t time period for the collection of the object to be detected, f (m) represents the analysis data for the object to be detected based on the pre-entered traditional Chinese medicine thinking treatment data and western medicine clinical archive data;

a difference value calculation unit: the device is used for calculating a prediction analysis result in the simulation equipment according to the analysis result and determining a difference value between the analysis result and the prediction analysis result:

wherein,

represents the result of the i-th predictive analysis, Δ Re_iRepresenting the ith regularly acquired analysis result, n representing the total number of the acquired analysis results, i representing a natural number, i belongs to (1, n), MAE representing the average absolute error of the analysis results and the prediction analysis results, RMSE representing the root mean square error of the analysis results and the prediction analysis results, and MRE representing the average relative error of the analysis results and the prediction analysis results; w is a_iRepresenting the weight matrix corresponding to the ith analysis result, b_iRepresenting the bias vector corresponding to the analysis result;

an evaluation unit: the device is used for evaluating the difference value and determining an evaluation result:

wherein H is an evaluation result;

establishing a pathological model unit: the method comprises the steps of determining the value of an evaluation result H as 1 when an average absolute error, a root mean square error and an average relative error simultaneously meet a preset threshold, and establishing a stroke premonitory pathology model based on a deep neural network learning algorithm;

an abnormality presentation unit: and when the average absolute error, the root mean square error and the average relative error do not meet the preset threshold, determining that the value of the evaluation result H is 0, representing that the correlation degree of the historical analysis result and the real-time acquired analysis result is too small, and performing exception prompting.

10. The intelligent early warning system for stroke according to claim 6, wherein the real-time monitoring module comprises:

status sign data unit: the system comprises a timing acquisition frequency acquisition unit, a data acquisition unit and a data acquisition unit, wherein the timing acquisition frequency acquisition unit is used for acquiring timing acquisition frequency and acquiring state sign data of an object to be detected according to the timing acquisition frequency;

variance fluctuation value unit: the system is used for acquiring historical sign data and calculating variance fluctuation values of the state sign data and the historical state data;

a judging unit: the system is used for judging whether the body health state of a to-be-detected object is abnormal or not according to the variance fluctuation value based on the stroke occurrence premonitory pathology model and generating a judgment result;

a judgment result abnormality unit: the alarm device is used for triggering a preset alarm when the judgment result is abnormal, and giving a help-seeking prompt to the terminal device pre-bound by the intelligent device sensor;

a judgment result normal unit: and the data processing module is used for storing the state sign data to a preset storage database when the judgment result is normal.

Images