WO2021253188A1 - Disease source information entropy-based method for preventing and treating altitude sickness of power grid construction personnel - Google Patents

Abstract

A disease source information entropy-based method for preventing and treating altitude sickness of power grid construction personnel: a feature database of altitude sickness is first established, then construction data of power grid construction personnel is collected, and the construction data is aggregated and then transmitted to a disease source information entropy modeling analysis platform; and the collected construction data of the power grid construction personnel is used by the disease source information entropy modeling analysis platform to establish the disease source independent information entropy of altitude sickness and the disease source combined information entropy of altitude sickness so as to determine whether the power grid construction personnel are at risk for altitude sickness. The method implements the rapid and real-time prevention, detection and treatment of altitude sickness for power grid construction personnel.

Description

A method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy Technical field

The invention belongs to the field of data collection and analysis, and specifically relates to a method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy.

Background technique

Altitude sickness usually refers to diseases caused by the high altitude low-oxygen environment at the time or within several days when the human body enters the plateau or enters the higher altitude area from the plateau. Altitude sickness refers to the acute hypoxic reaction or disease that occurs when entering the high altitude. According to its severity, it is divided into mild (or benign) and severe (or malignant). Mild reactive type or acute altitude sickness; severe acute mountain sickness (also known as high altitude coma or high altitude cerebral edema), pulmonary acute altitude sickness (also known as high altitude pulmonary edema), mixed type (that is, pulmonary and high altitude pulmonary edema) Comprehensive performance of brain type). Common clinical manifestations of altitude sickness include headache, dizziness, palpitation, shortness of breath, nausea, vomiting, fatigue, insomnia, vertigo, drowsiness, numbness of hands and feet, cyanosis of lips and fingers, and increased heart rhythm. Other symptoms and signs vary depending on the type. different.

At present, at home and abroad, the prevention and control of altitude sickness is mainly carried out by pre-physical examination of power grid construction personnel or sent to hospital for treatment after power grid construction personnel develop plateau sickness. Pre-physical examinations are carried out for personnel entering the Qinghai-Tibet area for construction work by means of ultrasound examination and electrocardiogram. Or use the method of establishing bone marrow nucleated red blood cell inspection and analysis software to conduct pre-analysis by construction workers in the Qinghai-Tibet area. The power grid infrastructure construction is often in remote areas. When the power grid constructor becomes ill, the power grid company will not only spend a lot of manpower and material resources to treat, but the life safety of the patient is also not guaranteed. The power grid constructor is sent to the hospital after the plateau sickness occurs. The prevention and treatment of altitude sickness often misses the prime time for altitude sickness prevention and treatment, causing permanent damage to the bodies of power grid construction personnel.

There is no effective real-time prediction and screening method for acute altitude sickness at home and abroad, and screening can only be carried out through pre-physical examination, and the screening effect of pre-physical examination is poor. The average altitude of the Qinghai-Tibet Plateau is above 4000 meters. Affected by factors such as high altitude, thin air, low atmospheric pressure, low partial pressure of oxygen, and strong ultraviolet rays in the area, acute altitude sickness has become a major threat to people entering Tibet's power grid. According to the severity of acute mountain sickness, there are two types: mild (reactive or acute altitude sickness) and severe (high altitude cerebral edema, high altitude pulmonary edema). Acute altitude sickness has a short onset time, which occurs within a few hours to a few days. If it is not treated in time, it will be life-threatening. The survey and research of the High Altitude Sickness Prevention Center of the State Grid Corporation of China shows that the construction personnel of the power grid who originally lived at a low altitude and went to the Qinghai-Tibet Plateau after physical examination before entering the Qinghai-Tibet Plateau are likely to induce acute altitude sickness. The incidence rate is 18.97%, of which the incidence rate of acute mild altitude sickness is 18.19%, and the incidence rate of severe altitude sickness is 0.78%. It can be seen that among those who have just entered the Qinghai-Tibet area for power grid operations, the incidence of acute altitude sickness is 18.19%. The high rate and harmfulness pose a serious threat to its health.

Summary of the invention

Aiming at the above-mentioned problems in the prior art, the present invention proposes a method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy. The source information is obtained by real-time collection of the vital characteristics data of the construction personnel and the cause traceability data of altitude sickness during construction. Entropy, through the analysis of the information entropy of the disease source, realizes the real-time prevention and treatment recommendations for the risk of altitude sickness for power grid construction workers.

The concrete realization content of the present invention is as follows:

The present invention proposes a method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy. Firstly, a plateau sickness feature database is established, and then construction data of power grid constructors is collected, and the construction data is gathered and transmitted to a disease source information entropy modeling analysis platform , The disease source information entropy modeling analysis platform uses the collected construction data of the power grid construction personnel to perform the disease source information entropy modeling analysis, and finally determines whether the power grid construction personnel are at risk of altitude sickness;

The construction data includes vital signs data and data on the origin of the incidence of altitude sickness; the vital signs include respiratory system vital signs, cardiovascular system vital signs, digestive system vital signs, and urinary system vital signs;

The specific operation for modeling and analysis of disease source information entropy is as follows: firstly calculate the independent information entropy H(z), respiratory system independent information entropy H(x), cardiovascular system independent information entropy H( y), the independent information entropy of the digestive system H(p), the independent information entropy of the urinary system H(q); then the independent information entropy H(z), the independent information entropy of the respiratory system H(x), cardiovascular System independent information entropy H(y), digestive system independent information entropy H(p), urinary system independent information entropy H(q) calculate the combined information entropy H(z,x,y,p,q) of the pathogenic source of altitude sickness.

In order to better implement the present invention, further, the traceability data of the incidence of altitude sickness includes: the altitude of the original residence, the time of the construction personnel entering the plateau area, the time of acclimatization in the middle altitude area, psychological factors, construction labor intensity, age, Respiratory tract infection; set the lower limit of the feature value range of the traceability data of altitude sickness to m and the upper limit to n; obtain the traceability feature value range table of the cause of altitude sickness:

The specific steps of calculating the independent information entropy H(z) of the origin of the incidence of altitude sickness are as follows: First define the information entropy of the origin of the incidence of altitude sickness as z, and the value range is {z _m ......z _n }; Set the altitude of the original residence as z _a , the value range is {z _am ......z _an }, the construction labor intensity is z _b , and the value range is {z _bm ......z _bn }, The acclimatization time in the medium-altitude area is z _c , and the value range is {z _cm ......z _cn }. The time when the construction personnel enter the plateau area is z _d , and the value range is {z _dm ..... .z _dn }, the psychological factor is z _e , the value range is {z _em ......z _en }, the respiratory tract infection is z _f , the value range is {z _fm ......z _fn } , The age is z _g , and the value range is {z _gm ......z _gn }; then calculate the disease source information entropy H(za), disease source information entropy H(zb), disease source information entropy H(zc), Disease source information entropy H(zd), disease source information entropy H(ze), disease source information entropy H(zf), disease source information entropy H(zg), conditional entropy H(z _a |z _b |z _c |z _d |z _e |z _f |z _g ); Finally, the disease source information entropy H(za), the disease source information entropy H(zb), the disease source information entropy H(zc), the disease source information entropy H(zd), the disease source information entropy H(ze), The disease source information entropy H(zf), the disease source information entropy H(zg), and the conditional entropy H(z _a |z _b |z _c |z _d |z _e |z _f |z _g ) are added together to obtain the independent origin of the incidence of altitude sickness. Information entropy H(z).

In order to better implement the present invention, further, the respiratory system vital signs data include BMI index, lung function-FVL, lung function-FEV1, lung function-FEE25, lung function-SaO2 decrease, number of breaths, and breathing pause time;

The vital characteristics data of the cardiovascular system include ST segment of electrocardiogram, blood pressure diastolic blood pressure, blood pressure systolic blood pressure, heart rate ≥100 times time, red blood cells, hemoglobin;

The vital characteristics data of the digestive system includes the number of abdominal muscle tension spasms;

The vital characteristics data of the urinary system include urine red blood cells and urine protein;

Set the information entropy of the respiratory system as x and the value range is {x _m ......x _n }, then set the BMI index to x _a , and the value range is {x _am ......x _an }, lung function-FVL is x _b , the value range is {x _bm ......x _bn }, lung function-FEV1 is x _c , the value range is {x _cm ......x _cn }, lung function-FEE25 is x _d , the value range is {x _dm ......x _dn }, lung function-SaO2 is reduced to x _e , the value range is {x _em ......x _en }, the number of breaths is x _f , the value range is {x _fm ......x _fn }, the breathing pause time is x _g , the value range is {x _gm ......x _gn }, Further calculate the disease source information entropy H(za), disease source information entropy H(zb), disease source information entropy H(zc), disease source information entropy H(zd), disease source information entropy H(ze), disease source information entropy H(zf) , Disease source information entropy H(zg), conditional entropy H(z _a |z _b |z _c |z _d |z _e |z _f |z _g ); finally, disease source information entropy H(za), disease source information entropy H( zb), disease source information entropy H(zc), disease source information entropy H(zd), disease source information entropy H(ze), disease source information entropy H(zf), disease source information entropy H(zg), conditional entropy H(z _a | z _b |z _c |z _d |z _e |z _f |z _g ) to obtain the independent information entropy of the respiratory system H(x);

In the same way, the independent information entropy of the cardiovascular system H(y), the independent information entropy of the digestive system H(p), and the independent information entropy of the urinary system H(q) are calculated.

In order to better implement the present invention, further, the specific calculation method of the combined information entropy H(z,x,y,p,q) of the altitude sickness disease source is as follows: first calculate the independent information entropy H( z), independent information entropy of the respiratory system H(x), independent information entropy of the cardiovascular system H(y), independent information entropy of the digestive system H(p), independent information entropy of the urinary system H(q), and then calculate the conditional entropy H (z|x|y|p|q), and finally calculate the joint information entropy H(z,x,y,p,q) of the altitude sickness source, the joint information entropy H(z,x,y, p,q) to trace the origin of altitude sickness independent information entropy H(z), respiratory system independent information entropy H(x), cardiovascular system independent information entropy H(y), digestive system independent information entropy H(p), urinary system The sum of system independent information entropy H(q) and conditional entropy H(z|x|y|p|q).

In order to better implement the present invention, further, the collection of construction data of power grid construction personnel is to adopt a multi-sensor data adaptive weighted fusion estimation algorithm for vital characteristic data collection, and the specific operation is: in each power grid that needs to be monitored The construction personnel are equipped with n sensors for measurement. The data collected by the sensors is the data recorded in the plateau sickness feature database, and according to the conditions of the construction personnel, several vital feature collection points are configured, and then through neural network, wavelet transformation, Kalman filtering technology performs multi-sensor data fusion, and calculates the self-adaptive weighted fusion estimate of multi-sensor data.

In order to better implement the present invention, further, the aggregation of construction data specifically uses the data-centric self-organizing algorithm SPIN to realize the aggregation of construction data of multiple power grid construction personnel.

In order to better implement the present invention, further, before carrying out the disease source information entropy modeling analysis, the vital characteristics data of the respiratory system, the vital characteristics of the cardiovascular system, the vital characteristics of the digestive system, and the urinary system of the power grid construction personnel in a static state System vitality data increased by 90%, used as the control target value of respiratory system vitality data, cardiovascular system vitality data, digestive system vitality data, and urinary system vitality data of power grid construction workers under exercise. At the same time, combined The experience database is used to revise the movement state data to obtain more accurate vital characteristics data of the power grid construction personnel in the movement state.

In order to better implement the present invention, further, after using the disease source information entropy modeling analysis platform to obtain the probability of occurrence of altitude sickness of the power grid construction personnel according to the pathogen information entropy modeling analysis of the altitude sickness, it is also combined with the evaluation of the expert diagnosis database of altitude sickness patients. According to the risk degree of altitude sickness for construction workers out of the power grid, an evaluation report and treatment opinions are generated according to the risk degree and sent to the medical staff on the construction site.

Compared with the prior art, the present invention has the following advantages and beneficial effects:

(1) Data can be collected in real time, and real-time monitoring and analysis can be carried out, which greatly reduces the discovery time of the disease and gains valuable time for patient treatment;

(2) Analyze the different causes of disease, and be targeted, which is helpful for the rapid treatment of the disease;

(3) When the patient is undergoing treatment, the vital characteristics data before the treatment can be quickly provided, which helps the doctor analyze the condition and is beneficial to the treatment.

Description of the drawings

Figure 1 is a schematic diagram of the overall flow of the present invention;

Figure 2 is a schematic diagram of data transmission through SPIN multi-person wireless networking in the present invention;

Figure 3 is a schematic diagram of the curve of the disease source information entropy function;

Figure 4 is a schematic diagram of the relationship between the source of altitude sickness and the associated information entropy H(z, x, y, p, q).

detailed description

In order to explain the technical solutions of the embodiments of the present invention more clearly, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present invention. It should be understood that the described embodiments are merely Part of the embodiments of the present invention, but not all of the embodiments, should not be regarded as a limitation of the scope of protection. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

Example 1:

The present invention proposes a method for preventing and controlling altitude sickness of power grid constructors based on disease source information entropy. As shown in Fig. 1, a method for preventing altitude sickness of power grid builders based on disease source information entropy is to first establish a plateau sickness feature database, and then to collect power grids. The construction data of the construction personnel is collected and transmitted to the disease source information entropy modeling analysis platform. The disease source information entropy modeling analysis platform uses the collected construction data of the power grid construction personnel to perform the disease source information entropy modeling analysis, and finally Judge whether there is a risk of altitude sickness for power grid construction personnel;

The construction data includes vital signs data and data on the origin of the incidence of altitude sickness; the vital signs include respiratory system vital signs, cardiovascular system vital signs, digestive system vital signs, and urinary system vital signs;

The specific operation for modeling and analysis of disease source information entropy is as follows: firstly calculate the independent information entropy H(z), respiratory system independent information entropy H(x), cardiovascular system independent information entropy H( y), the independent information entropy of the digestive system H(p), the independent information entropy of the urinary system H(q); then the independent information entropy H(z), the independent information entropy of the respiratory system H(x), cardiovascular System independent information entropy H(y), digestive system independent information entropy H(p), urinary system independent information entropy H(q) calculate the combined information entropy H(z,x,y,p,q) of the pathogenic source of altitude sickness.

How it works: In simple terms, disease source information entropy is how much information is measured by the amount of information, and the amount of information we receive is related to the specific event. The size of the information is related to the probability of the machine event. The smaller the probability that something happened, the greater the amount of information generated, such as an earthquake in a certain place; the greater the probability that the event occurred, the smaller the amount of information generated, such as the sun rising from the east. If we have two unrelated events x and y, then the information we obtain when the two observed events occur simultaneously should be equal to the sum of the information obtained when the observed events occur respectively, namely:

H(x,y)=H(x)+H(y);

Since x and y are two unrelated events, then p(x,y)=p(x)*p(y) is satisfied; according to the above derivation, we can easily see that H(x) must be the same as p(x) The logarithm of is related, because only the logarithmic form of the truth can be multiplied to correspond to the logarithmic addition form. Therefore, we have the following formula for the amount of information:

H(x)=-log2p(x);

The amount of information measures the information brought about by a specific event, and the entropy is the expectation of the amount of information that may be generated before the result comes out-considering all possible values of the random variable, that is, all possible events. Expectations of the amount of information brought, namely:

H(x)=-sum(p(x)log ₂ p(x));

The information entropy of the disease source can also be used as a measure of the complexity of altitude sickness. If altitude sickness is more complicated and there are more types of different situations, then its information entropy is relatively large. If a kind of altitude sickness is simpler, there are few kinds of situations, and the extreme case is one situation, then the corresponding probability is 1, then the corresponding disease source information entropy is 0, and the disease source information entropy is smaller at this time.

Example 2:

On the basis of the above-mentioned embodiment 1, the present invention first establishes a plateau sickness feature database, and the specific operation is as follows: according to the survey of altitude sickness of the grid construction personnel of the People’s Hospital of Suzhou High-tech Zone based on the plateau sickness prevention center of the State Grid Corporation of China, The construction personnel of the sick power grid conducted an analysis of the causes and characteristics of the illness, analyzed 452 patients, and summarized the causes of 7 types of altitude sickness and 4 types of 16 sub-types of illness characteristics; in terms of the causes of altitude sickness, It is mainly composed of 7 aspects: the altitude of the constructor’s original residence, the time when the constructor enters the plateau area, the time to acclimate in the medium altitude area, psychological factors, construction labor intensity, age and respiratory infection. After a constructor becomes ill, the source can be traced at most The analysis results are shown in Table 1:

Table 1 Analysis of the causes of altitude sickness among construction workers:

It can be seen from Table 1 that, from high to low, the causes of high-altitude disease for power grid construction workers are construction labor intensity, original home altitude, medium-altitude area acclimatization time, construction personnel entering plateau area, psychological factors, respiratory tract infection, and age. . Based on this, in the initial stage of power grid construction personnel entering the plateau, the cause of the construction personnel's illness is included in the category of disease source information entropy analysis, focusing on the observation of the original home altitude, the time of acclimatization in the medium-altitude area, and the construction labor intensity exceeding the threshold.

Table 2 shows the characteristic data of 16 types of illnesses of power grid constructors after suffering from altitude sickness:

Table 2 Data table of characteristics of high altitude sickness of construction workers

It can be seen from Table 2 that after the power grid constructors suffer from altitude sickness, their physical characteristics are mainly composed of four major categories of respiratory, cardiovascular, digestive, and urinary systems, and 16 sub-categories of abnormalities, which need to be combined with the cause of altitude sickness and the characteristic data of altitude sickness. Carry out joint disease source information entropy modeling. When power grid construction personnel have abnormal physical characteristics, effective treatment and rescue are carried out to prevent such personnel from developing into altitude sickness.

The other parts of this embodiment are the same as the above-mentioned embodiment 1, so they will not be described again.

Example 3:

On the basis of any one of the above embodiments 1-2, the present invention collects the construction data of power grid construction personnel after the plateau disease feature database is established. The construction data mainly includes the life characteristics data of the construction personnel and the plateau during construction. Traceability data on the cause of the disease;

The vital sign data of power grid construction personnel are collected through wearable vital sign sensors. The sensors are mainly divided into heartbeat, cardiogram, blood pressure, blood oxygen, body temperature, respiration rate and altitude, etc., and a number of vital signs are collected according to the condition of the construction personnel. Point, through neural network, wavelet transform, Kalman filter technology for multi-sensor data fusion to obtain accurate measurement signals;

The present invention adopts multi-sensor data self-adaptive weighted fusion estimation algorithm to collect vital characteristic data:

There are n sensors to measure a certain power grid construction personnel, and the variances of the sensors are respectively

The number of measurements is z, and the estimated true value of the sensor measurement is x, then the measured value of each sensor is x ₁ , x ₂ ......x _n , and the weighting factor of each sensor is y ₁ , y ₂ .. ...y _n , after multi-sensor fusion, the sensor fusion measurement value x _t after calculating the sensor weighting factor is:

Suppose that the second group of measurements is performed h times, and the average variance of the sensor is obtained as:

It can be seen from Equation 2 that the average variance of the sensor

Is the multivariate quadratic function of each weighting factor, so

There is a minimum. According to the extreme value theory of the multivariate function theory, the weighting factor corresponding to the minimum total mean square error can be obtained:

At this time, the minimum variance corresponding to the multi-sensor is:

From equations (3) and (4), the multi-sensor data adaptive weighted fusion estimated value x _g can be calculated, and the specific calculation formula is:

It can be seen from equation (5) that through the data fusion of wearable vital signs multi-sensor data, accurate heartbeat, cardiogram, blood pressure, blood oxygen, body temperature and other types of vital signs data for power grid construction workers can be obtained.

The other parts of this embodiment are the same as any one of the foregoing embodiments 1-2, so they will not be described in detail.

Example 4:

The present invention is based on any one of the foregoing embodiments 1-3, as shown in Fig. 2, at the power grid construction site on the Qinghai-Tibet Plateau, there are often several people participating in the power grid construction operation. If each construction worker occupies a 5G transmission channel, It will cause waste of resources and increase transmission costs. Therefore, the data-centric self-organizing algorithm SPIN can be used to realize the local aggregation of vital characteristics data of multiple construction workers.

In the SPIN multi-person wireless networking for power grid construction personnel, the geographical location of the construction personnel is randomly arranged. Each vital sign monitoring sensor node will first send a command to the neighboring base point sensor to request the allocation level. If the neighboring base point sensor is the convergence point , The vital sign monitoring sensor node will receive the level assigned by the convergence point, and the sensor node will send the vital sign information datagram to the convergence point. If the adjacent base point sensor is another transit vital sign monitoring sensor, the sensor node will send vital sign information data to the transit sensor. Through the SPIN routing algorithm networking, each sensor node hopes to become a transit node, and instructs whether its transmission path is on the path of the sink node. In order to reduce the loss of node transmission, the vitality sensor node of each construction worker is directly transmitted during transmission. Negotiations to achieve the best transmission efficiency, as shown in Figure 2. When the vital characteristics data of the power grid construction personnel arrive at the convergence point, the 5G network is adopted and the data is transmitted to the plateau disease prevention platform of the power grid construction personnel through the multi-level security architecture of the ubiquitous power Internet of Things.

The other parts of this embodiment are the same as any one of the foregoing embodiments 1-3, so they will not be described in detail.

Example 5:

The present invention is based on any one of the above-mentioned embodiments 1-4, the source information entropy of altitude sickness mainly involves the traceability analysis of the cause of the power grid construction personnel, the respiratory system, the cardiovascular system, the digestive system, and the urinary system. Analyze and analyze the characteristics of altitude sickness of power grid construction personnel, and carry out two-layer disease source information entropy modeling of independent information entropy of disease source and combined information entropy of altitude sickness. The specific source-independent information entropy modeling calculation method is as follows:

1) Modeling the origin of the incidence of altitude sickness

The traceability of the cause of altitude sickness mainly includes 7 aspects. Let m be the lower limit of the traceability feature value range of the cause of altitude sickness, and n is the upper limit of the value range. The upper and lower limits of the traceability feature value of the cause of various altitude sickness are shown in Table 3. Show:

Table 3 The value range of the traceability characteristics of the cause of altitude sickness

Suppose the traceability information entropy of the cause of altitude sickness is z, the value range is {z _m ......z _n }, the altitude of the original residence is z _a , and the value range is {z _am ......z _an }, the construction labor intensity is z _b , the value range is {z _bm ......z _bn }, the acclimatization time in the middle altitude area is z _c , and the value range is {z _cm ...... z _cn }, the time for the construction personnel to enter the plateau area is z _d , the value range is {z _dm ......z _dn }, the psychological factor is z _e , and the value range is {z _em ..... .z _en }, respiratory infection is z _f , the value range is {z _fm ......z _fn }, age is z _g , the value range is {z _gm ......z _gn }, The source entropy of the origin of altitude sickness is:

2) Respiratory system modeling

There are 7 main aspects of respiratory system modeling. According to the breathing data monitored by the vital sign sensor, it is detected that the person's breathing is accelerated, and after 3 or 4 breaths in rapid succession, a pause of more than 10 seconds and other monitoring data are generated to determine the onset of altitude sickness. risk. Set m as the lower limit of the respiratory system characteristic value range, n as the upper limit of the respiratory system characteristic value range. The upper and lower limits of the respiratory system characteristic value are shown in Table 4:

Table 4 Respiratory system characteristic value range table

Suppose the information entropy of the respiratory system is x, the value range is {x _m ......x _n }, the BMI index is x _a , the value range is {x _am ......x _an }, and the lung function -FVL is x _b , the value range is {x _bm ......x _bn }, lung function -FEV1 is x _c , the value range is {x _cm ......x _cn }, lung function -FEE25 is x _d , the value range is {x _dm ......x _dn }, lung function -SaO2 is reduced to x _e , the value range is {x _em ......x _en }, breathing The number of times is x _f , the value range is {x _fm ......x _fn }, the breathing pause time is x _g , the value range is {x _gm ......x _gn }, the respiratory system disease source entropy for:

3) Cardiovascular system modeling

According to the heartbeat data, dynamic electrocardiogram data, and blood pressure data monitored by the vital sign sensor, detect whether the heart rate, blood pressure increase, whether the red blood cells, hemoglobin increase, whether there are clinical symptoms such as ectopic arrhythmia, so as to judge the risk of altitude sickness; set m Is the lower limit of the characteristic value range of the cardiovascular system, n is the upper limit of the characteristic value range of the cardiovascular system, the upper and lower limits of the characteristic value of the cardiovascular system are shown in Table 5:

Table 5 Value range of cardiovascular system characteristics

Suppose the information entropy of the cardiovascular system is y, the value range is {y _m ......y _n }, the ST segment of the electrocardiogram is y _a , and the value range is {y _am ......y _an }, The diastolic blood pressure is y _b , the value range is {y _bm ......y _bn }, the systolic blood pressure is y _c , the value range is {y _cm ......y _cn }, and the heart rate ≥ The 100 times time is y _d , the value range is {y _dm ......y _dn }, the red blood cell is y _e , the value range is {y _em ......y _en }, and the hemoglobin is y _f , the value range is {y _fm ......y _fn }, the source entropy of the cardiovascular system is:

It should be noted that the detection of hemoglobin and red blood cells is not performed by sensors, but is periodically detected by collecting blood samples. Here, the data of hemoglobin and red blood cells are updated based on regular detection.

4) Modeling the digestive system

According to the intestinal peristalsis data monitored by the vital sign sensor, detect whether the intestinal peristalsis is weak, the strength of the intestinal tension and other clinical symptoms, so as to judge the risk of altitude sickness; set m as the lower limit of the value range of digestive system characteristics, and n as The upper limit of the digestive system characteristic value range, the upper and lower limits of the digestive system characteristic value are 0 times/h and 60 times/h respectively.

Suppose the digestive system information entropy is p, the value range is {p _m ......p _n }; the abdominal muscle tension (the number of spasms/h) is P _a , and the value range is {p _am ..... .p _an }The source entropy of the digestive system is:

H(p)=H(p _a ) (9)

5) Urinary system modeling

According to the blood data monitored by the vital sign sensor, detect whether there are clinical symptoms such as hematuria and proteinuria to determine the risk of altitude sickness. Let m be the lower limit of the value range of urinary system characteristics, and n be the upper limit of the value range of urinary system characteristics. The upper and lower limits of urinary system characteristic values are shown in Table 5:

Table 6 Value range of urinary system characteristics

Suppose the information entropy of the urinary system is q, the value range is {q _m ......q _n }, the urine red blood cell is q _a , the value range is {q _am ......q _an }, and the urine protein Is q _b , the value range is {q _bm ......q _bn }, and the source entropy of the urinary system is:

H(q)=H(q _a )+H(q _b )+H(q _a |q _b ) (10);

It should be noted that the vital signs detection of the urinary system is not real-time detection, but also updates the data according to regular sampling detection.

Working principle: The source information entropy of altitude sickness mainly involves the modeling of the respiratory system, cardiovascular system, digestive system, and urinary system of power grid construction workers. Among them, in the aspect of respiratory system modeling, according to the respiratory data monitored by the vital sign sensor, it is detected that the person's breathing is accelerated, and after 3 or 4 breaths in rapid succession, clinical symptoms such as pauses of more than 10 seconds are generated to determine the onset of altitude sickness. Risk: In the modeling of the cardiovascular system, according to the heartbeat data, Holter chart data, and blood pressure data monitored by the vital sign sensor, it can detect whether the heart rate, blood pressure, red blood cells, hemoglobin are increased, and whether there are clinical symptoms such as ectopic arrhythmia. This judges the risk of altitude sickness; on the cover of the digestive system, according to the intestinal peristalsis data monitored by vital signs sensors, detect whether the intestinal peristalsis is weak, the strength of intestinal tension and other clinical symptoms, so as to judge the risk of altitude sickness; in urinary In terms of the system, according to the blood data monitored by the vital sign sensor, it detects whether there are clinical symptoms such as hematuria and proteinuria to determine the risk of altitude sickness.

The other parts of this embodiment are the same as any one of the foregoing embodiments 1-4, so they will not be described again.

Example 6:

The present invention is based on any one of the foregoing embodiments 1-5, as shown in FIG. 3, the specific calculation principle of the joint information entropy H(z, x, y, p, q) of the altitude sickness disease source is as follows:

In the modeling of the source information entropy of altitude sickness, the five variables of the origin of altitude sickness, the respiratory system, the cardiovascular system, the digestive system, and the urinary system are independent of each other, so the amount of information obtained by observing the five variables should be The amount of information is the same as when observing 5 variables at the same time. Set m as the lower limit of the value range of the joint information entropy feature of altitude sickness, and the upper limit of the value range of n respiration. Set the traceability information entropy of the cause of altitude sickness as z, and the value range is {z _m ......z _n }, suppose the information entropy of the respiratory system is x, the value range is {x _m ......x _n }; the information entropy of the cardiovascular system is y, the value The range is {y _m ......y _n }; the information entropy of the digestive system is p, the value range is {p _m ......p _n }; the information entropy of the urinary system is q, the value is The range is {q _m ......q _n }; suppose that the origin of altitude sickness, the independent information entropy of the respiratory system, the cardiovascular system, the digestive system, and the urinary system can be expressed as s _i = s{z = _{z i}, a i = a} {x = x i}, b i = b {y = y i}, c i = c {p = p i}, d i = d {q = q i}; can Calculated:

If the base of the logarithm in equations (11) to (15) is 2, then the origin of the origin of altitude sickness, the independent information entropy of the respiratory system, cardiovascular system, digestive system, and urinary system are expressed as H ₂ ( z), H ₂ (x), H ₂ (y), H ₂ (p), H ₂ (q), representing the entropy based on 2, the unit is bits, the curve of the entropy function is shown in Figure 3;

From Figure 3, the information volume functions corresponding to H(z), H(x), H(y), H(p), and H(q) can be obtained: I(p), I(q). At this time, I(z), I(x), I(y), I(p), I(q) can be regarded as the amount of information provided by z, x, y, p, q; and H(z) , H(x), H(y), H(p), H(q) can be the average value of I(z), I(x), I(y), I(p), I(q), respectively . Then obtain the joint information entropy H(z,x,y,p,q) of altitude sickness disease source.

The joint information entropy of the source of altitude sickness is defined as the uncertainty of the simultaneous occurrence of five factors including the origin of the cause of altitude sickness, the respiratory system, the cardiovascular system, the digestive system, and the urinary system. The joint information entropy of the source of altitude sickness is:

Formula (16) can be simplified as:

The conditional entropy H(z|x|y|p|q) can be regarded as the average amount of information lost due to interference and noise on the channel, and it can also be used as the only way to determine the channel noise or spread.

The source information of altitude sickness The joint information entropy relationship and mutual information of altitude sickness source are shown in Figure 4. The intersection of H(z), H(x), H(y), H(p), H(q) is plateau Conditional entropy H(z|x|y|p|q) of joint information entropy of sickness. If the value of joint information entropy of altitude sickness is greater, the difference between the five functions will be greater, which means that the probability of occurrence of altitude sickness is greater , To determine whether there is a risk of altitude sickness for power grid construction personnel.

How it works: In the modeling of the source information entropy of altitude sickness, the five variables of the respiratory system, cardiovascular system, digestive system, and urinary system are independent of each other, H(z), H(x), H(y) The intersection of, H(p), H(q) is the joint information entropy of altitude sickness H(x|y|p|q). If the value of joint information entropy of altitude sickness is greater, the difference between the four functions will be greater. This means that the higher the probability of occurrence of altitude sickness, the higher the risk of altitude sickness for power grid construction personnel.

The other parts of this embodiment are the same as any one of the foregoing embodiments 1-5, so they will not be described again.

Example 7:

The present invention is based on any one of the above embodiments 1-6, the power grid construction personnel's altitude sickness prevention platform analyzes the incidence of altitude sickness of the power grid builders based on the source information entropy modeling of the altitude sickness, and combines the expert diagnosis of the altitude sickness patients at the same time The database can accurately assess the risk of altitude sickness for power grid construction personnel, and generate altitude sickness risk assessment reports and disposal opinions according to the construction personnel. The assessment grades are divided into three types: minor, moderate, and critical risks. It can generate stop work and rest on site. Recommendations for taking glucose, breathing oxygen, and sending to the hospital urgently are shown in Table 7:

Table 7 High altitude sickness risk assessment grade and treatment opinion form

The plateau disease prevention and control platform of power grid construction personnel sends the assessment report and treatment opinions to the medical staff at the power grid construction site through the 5G network. The on-site hospital personnel perform on-site treatment or urgently send to nearby power grid operators who are assessed to be at risk of plateau disease according to the treatment opinions. Hospital for treatment.

The other parts of this embodiment are the same as any one of the foregoing embodiments 1-6, so they will not be described in detail.

The above are only preferred embodiments of the present invention, and do not limit the present invention in any form. Any simple modification or equivalent change made to the above embodiments based on the technical essence of the present invention shall fall into the scope of the present invention. Within the scope of protection.

Claims (8)

1. A method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy, which is characterized by first establishing a plateau sickness feature database, and then collecting construction data of power grid constructors, and transferring the construction data to the disease source information entropy modeling analysis platform. , The disease source information entropy modeling analysis platform uses the collected construction data of the power grid construction personnel to perform the disease source information entropy modeling analysis, and finally determines whether the power grid construction personnel are at risk of altitude sickness;

   The construction data includes vital signs data and data on the origin of the incidence of altitude sickness; the vital signs include respiratory system vital signs, cardiovascular system vital signs, digestive system vital signs, and urinary system vital signs;

   The specific operation for modeling and analysis of disease source information entropy is as follows: firstly calculate the independent information entropy H(z), respiratory system independent information entropy H(x), cardiovascular system independent information entropy H( y), the independent information entropy of the digestive system H(p), the independent information entropy of the urinary system H(q); then the independent information entropy H(z), the independent information entropy of the respiratory system H(x), cardiovascular System independent information entropy H(y), digestive system independent information entropy H(p), urinary system independent information entropy H(q) calculate the combined information entropy H(z,x,y,p,q) of the pathogenic source of altitude sickness.
2. The method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy according to claim 1, characterized in that the traceability data of the cause of altitude sickness includes: altitude of original residence, time of construction personnel entering the plateau area, medium Time of acclimatization in altitude area, psychological factors, construction labor intensity, age, respiratory tract infection; set the lower limit of the characteristic value range of the traceability data of the cause of altitude sickness as m and the upper limit as n;

   The specific steps of calculating the independent information entropy H(z) of the origin of the incidence of altitude sickness are as follows: First define the information entropy of the origin of the incidence of altitude sickness as z, and the value range is {z _m ......z _n }; Set the altitude of the original residence as z _a , the value range is {z _am ......z _an }, the construction labor intensity is z _b , and the value range is {z _bm ......z _bn }, The acclimatization time in the medium-altitude area is z _c , and the value range is {z _cm ......z _cn }. The time when the construction personnel enter the plateau area is z _d , and the value range is {z _dm ..... .z _dn }, the psychological factor is z _e , the value range is {z _em ......z _en }, the respiratory tract infection is z _f , the value range is {z _fm ......z _fn } , The age is z _g , and the value range is {z _gm ......z _gn }; then calculate the disease source information entropy H(za), disease source information entropy H(zb), disease source information entropy H(zc), Disease source information entropy H(zd), disease source information entropy H(ze), disease source information entropy H(zf), disease source information entropy H(zg), conditional entropy H(z _a |z _b |z _c |z _d |z _e |z _f |z _g ); Finally, the disease source information entropy H(za), the disease source information entropy H(zb), the disease source information entropy H(zc), the disease source information entropy H(zd), the disease source information entropy H(ze), The disease source information entropy H(zf), the disease source information entropy H(zg), and the conditional entropy H(z _a |z _b |z _c |z _d |z _e |z _f |z _g ) are added together to get the origin of the altitude sickness independent. Information entropy H(z).
3. The method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy according to claim 1, characterized in that:

   The vital characteristics data of the respiratory system include BMI index, lung function-FVL, lung function-FEV1, lung function-FEE25, lung function-SaO2 decrease, number of breaths, and breathing pause time;

   The vital characteristics data of the cardiovascular system include ST segment of electrocardiogram, blood pressure diastolic blood pressure, blood pressure systolic blood pressure, heart rate ≥ 100 times time, red blood cells, hemoglobin;

   The vital feature data of the digestive system includes the number of abdominal muscle tension spasms;

   The vital characteristics data of the urinary system include urine red blood cells and urine protein;

   Set the information entropy of the respiratory system as x and the value range is {x _m ......x _n }, then set the BMI index to x _a , and the value range is {x _am ......x _an }, lung function-FVL is x _b , the value range is {x _bm ......x _bn }, lung function-FEV1 is x _c , the value range is {x _cm ......x _cn }, lung function-FEE25 is x _d , the value range is {x _dm ......x _dn }, lung function-SaO2 is reduced to x _e , the value range is {x _em ......x _en }, the number of breaths is x _f , the value range is {x _fm ......x _fn }, the breathing pause time is x _g , the value range is {x _gm ......x _gn }, Further calculate the disease source information entropy H(za), disease source information entropy H(zb), disease source information entropy H(zc), disease source information entropy H(zd), disease source information entropy H(ze), disease source information entropy H(zf) , Disease source information entropy H(zg), conditional entropy H(z _a |z _b |z _c |z _d |z _e |z _f |z _g ); finally, disease source information entropy H(za), disease source information entropy H( zb), disease source information entropy H(zc), disease source information entropy H(zd), disease source information entropy H(ze), disease source information entropy H(zf), disease source information entropy H(zg), conditional entropy H(z _a | z _b |z _c |z _d |z _e |z _f |z _g ) to obtain the independent information entropy of the respiratory system H(x);

   In the same way, the independent information entropy of the cardiovascular system H(y), the independent information entropy of the digestive system H(p), and the independent information entropy of the urinary system H(q) are calculated.
4. The method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy according to any one of claims 1 to 3, characterized in that the joint information entropy of the altitude sickness source H(z, x, y, p, q The specific calculation method of) is: first calculate the independent information entropy H(z), independent information entropy of the respiratory system H(x), independent information entropy of the cardiovascular system H(y), and independent information entropy of the digestive system H(z). (p), the independent information entropy of the urinary system H(q), and then calculate the conditional entropy H(z|x|y|p|q), and finally calculate the combined information entropy H(z,x,y,p ,q), the combined information entropy H(z,x,y,p,q) of the origin of the altitude sickness is the independent information entropy H(z), the independent information entropy of the respiratory system H(x), the cardiovascular system The sum of system independent information entropy H(y), digestive system independent information entropy H(p), urinary system independent information entropy H(q), and conditional entropy H(z|x|y|p|q).
5. The method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy according to claim 1, characterized in that the collection of construction data of power grid construction personnel is the use of multi-sensor data adaptive weighted fusion estimation algorithm for vital characteristics data The specific operation is as follows: install n sensors on each power grid construction worker who needs to be monitored for measurement. The data collected by the sensors is the data recorded in the plateau sickness database and is based on the conditions of the construction personnel. Configure a number of vital feature collection points, and then perform multi-sensor data fusion through neural network, wavelet transform, and Kalman filter technology, and calculate the multi-sensor data adaptive weighted fusion estimate.
6. The method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy according to claim 5, characterized in that, the aggregation of construction data specifically uses the data-centric self-organizing algorithm SPIN to realize the monitoring of multiple power grid construction personnel. Convergence of construction data.
7. The method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy according to claim 1, characterized in that, before performing disease source information entropy modeling analysis, the vital characteristics data of the respiratory system of the power grid construction personnel in a static state are collected. , Cardiovascular system vitality data, digestive system vitality data, and urinary system vitality data increased by 90%, used as respiratory system vitality data, cardiovascular system vitality data, and digestive system vitality data for grid construction workers under exercise The control target value of data and vital characteristics of the urinary system, and at the same time, combined with the experience database, the exercise state data is revised to obtain more accurate vital characteristics data of the power grid construction personnel in the exercise state.
8. The method for preventing and controlling altitude sickness of power grid construction personnel based on disease source information entropy according to any one of claims 1-7, characterized in that, the disease source information entropy modeling analysis platform is used to model and analyze the altitude sickness information entropy. After obtaining the probability of altitude sickness for power grid construction workers, the expert diagnosis library of altitude sickness patients is used to evaluate the risk of altitude sickness for power grid construction workers, and the assessment report and treatment opinions are generated according to the risk level and sent to the medical staff on the construction site. .

Images