Internal medicine emergency treatment data processing method and system based on cloud computing

Abstract

The invention relates to the technical field of medical data processing, in particular to an internal medicine emergency treatment data processing method and system based on cloud computing, and the method comprises the following steps: monitoring the data of an emergency treatment patient, carrying out the dynamic interval correction of the systolic pressure, diastolic pressure and blood oxygen critical values of the patient through the analysis of the age, gender and weight, and generating an index threshold interval. According to the method, the abnormal physiological parameter detection threshold value is adjusted, the actual health condition of the patient is accurately reflected, the correlation and fluctuation trend of multiple physiological data are analyzed, the emergency degree of the emergency patient is effectively evaluated, the data transmission priority is optimized, key information is ensured to be transmitted in time, and encryption in the data transmission process is combined; according to the method, the integrity and the reliability of data are guaranteed, the storage position and the access priority are dynamically adjusted according to the access frequency and the activeness of the data, the data retrieval efficiency is improved, the utilization of storage resources is optimized, the response speed and the processing capacity are improved, and reliable real-time support is provided for medical staff.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a method and system for processing medical emergency data based on cloud computing. Background Art

[0002] The field of medical data processing technology includes a variety of technical means for the collection, storage, analysis and processing of medical data. With the continuous growth of the demand for medical and health management, medical data processing technology plays an important role in improving the quality and efficiency of medical services. It involves medical imaging data processing, electronic processing of clinical data, and intelligent diagnosis support based on patient medical records. It aims to effectively manage and analyze large amounts of complex medical data, and provide scientific and accurate medical decision-making support through data analysis. It combines cloud computing, big data, and artificial intelligence to improve the intelligence and precision of medical services.

[0003] Among them, the cloud computing-based internal medicine emergency data processing method refers to the processing and analysis of internal medicine emergency data through the application of cloud computing technology, covering the collection, storage and processing of emergency medical data, including the use of cloud computing platforms to centrally store and analyze patients' vital signs, medical records, and treatment process data. Through the cloud computing platform, remote sharing and rapid processing of data can be achieved, providing real-time medical data support, combined with data processing and optimization, so that medical staff can quickly obtain and analyze patient data in emergency scenarios and make accurate diagnosis and treatment decisions.

[0004] Traditional internal medicine emergency data processing methods rely on fixed indicator thresholds when processing emergency data, lack the ability to dynamically adjust to individual differences among patients, and cannot accurately reflect the patient's real-time health status. The data transmission priority is based on simple rules and fails to fully consider the correlation and fluctuation trend between multiple physiological data, resulting in delays in the transmission of key information and affecting the timeliness of emergency decision-making. In terms of data transmission security, a basic verification mechanism is adopted, and there is a lack of in-depth detection of transmission path nodes and key matching, resulting in the risk of data leakage or tampering. The storage strategy cannot be dynamically adjusted according to the access frequency and activity of the data, resulting in uneven utilization of storage resources and inefficient data retrieval, which affects the response speed of the overall system and leads to inefficient data processing in emergency scenarios. The accuracy and timeliness of medical decisions are limited, affecting the treatment of patients. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a cloud computing-based internal medicine emergency data processing method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for processing medical emergency data based on cloud computing, comprising the following steps: S1: Monitor emergency patient data, analyze age, gender, and weight, and dynamically correct the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical values ​​to generate indicator threshold intervals; S2: Based on the threshold interval of the indicator, by analyzing the fluctuation amplitude of the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data, adjusting the time window length, calculating and accumulating the difference between the physiological data and the threshold in multiple time windows, and generating a risk quantification score; S3: Analyze the correlation between multiple physiological data according to the risk quantification score, calculate the urgency score of each physiological data in combination with the fluctuation amplitude and change trend, adjust the transmission priority of the data packet, and generate a transmission queue identifier; S4: calling the transmission queue identifier, extracting multiple pieces of information of the data packet and matching the key, verifying the matching degree between the key and the path node, detecting abnormal transmission events and storing the verified data in the database, and generating a data storage record; S5: Based on the data storage records, extract various patient data from the database, evaluate access activity by access frequency of each data item, adjust storage location and access priority, and generate a storage index table.

[0007] As a further solution of the present invention, the indicator threshold interval is specifically a systolic pressure threshold, a diastolic pressure threshold, and a blood oxygen saturation threshold; the risk quantification score is specifically a heart rate risk score, a respiratory rate risk score, and a blood oxygen saturation risk score; the transmission queue identifier is specifically a transmission priority, a data packet number, and a transmission timestamp; the data storage record is specifically a key matching degree, a path node matching degree, and an abnormal transmission event mark; and the storage index table is specifically a data storage level, a data access frequency, and a data priority.

[0008] As a further solution of the present invention, the step of obtaining the indicator threshold interval is specifically: S111: Based on the emergency patient data, multiple basic information of the emergency patient is obtained, including age, gender, and weight, and the systolic blood pressure, diastolic blood pressure, and blood oxygen data of the patient are detected to obtain the patient data set; S112: Based on the patient data set, the formula is used: ; Analyze the impact of the patient's age, gender, and weight on the patient's physiological data and generate an impact coefficient; in, Representative The influence coefficient of each physiological parameter, Representative The physiological parameters are The actual measured value of a patient under the characteristics, Representative The physiological parameters are The average value of the patient's historical data under the characteristics, For the The physiological parameters are The standard deviation of the features, For the The physiological parameters are The weight coefficient under a feature indicates the relative weight of the feature’s influence on the physiological data. is the number of features, and each feature is summed. Represents different characteristics, It is an index variable that distinguishes each physiological parameter; S113: Calculate the threshold ranges of the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical value according to the influence coefficients, and generate indicator threshold ranges.

[0009] As a further solution of the present invention, the step of obtaining the risk quantification score is specifically as follows: S211: Based on the indicator threshold range, the fluctuation amplitude of each data item is calculated through the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data, the time length of the data window is adjusted, and the window adjustment amplitude parameter is obtained; S212: Based on the window adjustment amplitude parameter, the formula is adopted: ; Calculate the differences between multiple physiological parameters and the set indicator threshold intervals in real time, and accumulate the differences to obtain the cumulative risk offset; in, represents the cumulative risk offset, Representative The actual measured values ​​of the physiological indicators, Representative Setting thresholds for indicators, Representative The weight coefficient of the window adjustment amplitude parameter. Representative The absolute value of the fluctuation offset of the term, Represents the number of physiological indicator data, Represents the number of window adjustment parameters, Represents the data index number of the physiological indicator, The index number representing the window adjustment parameter; S213: calling the accumulated risk offset, combining the dynamic time window length, calculating the risk quantification score of the data and the threshold, and generating a risk quantification score.

[0010] As a further solution of the present invention, the step of obtaining the transmission queue identifier is specifically: S311: Based on the risk quantification score, calculate the correlation between the various physiological data, analyze the mutual influence between the various physiological data, and obtain a physiological data correlation coefficient matrix; S312: Call the physiological data correlation coefficient matrix, using the formula: ; Calculate the urgency score of obtaining physiological data; in, Represents the physiological data urgency score, Representative The current measured value of the physiological data, Representative Set baseline values ​​for physiological data. Representative The weight parameters of the physiological data, Representative The changing trend value of the physiological data, Representative Correlation correction coefficient of each physiological data item, Represents the amount of physiological data, The number of data items representing the trend analysis, Represents the index of physiological data, An index representing the changing trend data; S313: calling the physiological data urgency score, sorting the transmission priorities of the data packets according to the score value, and generating a transmission queue identifier.

[0011] As a further solution of the present invention, the step of obtaining the data storage record is specifically as follows: S411: calling the transmission queue identifier, extracting the MAC address and patient identity code from the data packet, using the path node sequence, extracting the serial number and corresponding hash value of each node, matching the key for each data packet, and obtaining identity and path matching data; S412: Call the identity and path matching data, using the formula: ; Calculate the key matching degree and obtain the key matching degree score; in, represents the key matching score, Representative The hash value of the key to be transferred. Representative The hash value of the item path node, Representative Correction parameters for item path nodes, Represents the number of key check items, Represents the number of path nodes, Represents the index number of the key verification item, Represents the index number of the path node; S413: Call the key matching score to detect and identify abnormal events in the transmission process, store the verified data in the database, and generate a data storage record.

[0012] As a further solution of the present invention, the step of acquiring the storage index table is specifically as follows: S511: extracting a variety of patient data from a database based on the data storage records, obtaining data access records, analyzing the access frequency of each data item, classifying access patterns of multiple categories of data, and obtaining access frequency distribution information; S512: Call the access frequency distribution information, using the formula: ; Calculate the access activity index, where: Represents the data access activity index, Representative The number of times the data item is accessed, Represents the weight coefficient of the data, Represents the total number of data, Representative How long the data item is stored, Represents the total amount of stored data. is the index of the data item, is the index of the storage item; S513: calling the data access activity index, adjusting the storage location and access priority of the data according to the access activity, and establishing a storage index table.

[0013] A medical emergency data processing system based on cloud computing, wherein the medical emergency data processing system based on cloud computing is used to execute the above-mentioned medical emergency data processing method based on cloud computing, and the system comprises: The threshold adjustment module is based on emergency patient data. By analyzing age, gender, and weight, the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical values ​​are dynamically corrected to generate indicator threshold intervals. The patient risk assessment module extracts the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data based on the indicator threshold interval, performs data fluctuation amplitude analysis, adjusts the time window length, calculates the cumulative deviation between the actual physiological data and the threshold interval, and obtains a risk quantitative score; The data priority adjustment module calculates the patient's physiological data urgency score based on the risk quantification score, evaluates the correlation between multiple physiological data, analyzes the transmission priority of multiple data in combination with the data fluctuation range and change trend, and generates a transmission queue identifier; The transmission security verification module extracts the MAC address, patient identification code, transmission path node sequence, matches the key, verifies the matching degree between the key and the path node, analyzes abnormal transmission behavior, and stores the verified data in the database to generate a data storage record based on the transmission queue identifier; The hierarchical storage management module extracts a variety of patient data from the database based on the data storage records, calculates access activity using the access frequencies of multiple data, adjusts the storage location and access priority of the data, and generates a storage index table.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by analyzing multiple basic information of patients, adjusting the detection threshold of abnormal physiological parameters, and combining with real-time monitoring data, the actual health status of patients can be accurately reflected. By analyzing the correlation and fluctuation trend of multiple physiological data, the urgency of emergency patients can be effectively evaluated, the data transmission priority can be optimized, and the timely transmission of key information can be ensured. By verifying the matching degree of keys and transmission path nodes, the security of data transmission is enhanced, the occurrence of abnormal transmission events is reduced, and the integrity and reliability of data are guaranteed. According to the access frequency and activity of data, the storage location and access priority are dynamically adjusted to improve data retrieval efficiency, optimize the utilization of storage resources, and improve the response speed and processing capacity of the overall system. The data processing efficiency and the accuracy of medical decision-making in emergency scenarios are improved, and reliable real-time support is provided for medical staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 A flow chart for obtaining the indicator threshold interval of the present invention; Figure 3 Obtaining a flow chart for the risk quantification scoring of the present invention; Figure 4 A flow chart for obtaining a transmission queue identifier of the present invention; Figure 5 A flow chart for obtaining data storage records of the present invention; Figure 6 A flow chart for obtaining a storage index table of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] See also Figure 1 The present invention provides a technical solution, a method for processing medical emergency data based on cloud computing, comprising the following steps: S1: Monitor emergency patient data, analyze age, gender, and weight, and dynamically correct the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical values ​​to generate indicator threshold intervals; S2: Based on the indicator threshold range, by analyzing the fluctuation range of the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data, adjusting the time window length, calculating and accumulating the difference between physiological data and thresholds in multiple time windows, and generating a risk quantitative score; S3: Analyze the correlation between multiple physiological data according to the risk quantification score, calculate the urgency score of each physiological data based on the fluctuation amplitude and change trend, adjust the transmission priority of the data packet, and generate the transmission queue identifier; S4: Call the transmission queue identifier, extract multiple pieces of information of the data packet and match the key, verify the matching degree between the key and the path node, detect abnormal transmission events and store the verified data in the database, and generate data storage records; S5: Based on the data storage records, extract various patient data from the database, evaluate the access activity by the access frequency of each data, adjust the storage location and access priority, and generate a storage index table.

[0019] The indicator threshold intervals are specifically the systolic blood pressure threshold, diastolic blood pressure threshold, and blood oxygen saturation threshold. The risk quantification score is specifically the heart rate risk score, respiratory rate risk score, and blood oxygen saturation risk score. The transmission queue identifier is specifically the transmission priority, data packet number, and transmission timestamp. The data storage record is specifically the key matching degree, path node matching degree, and abnormal transmission event mark. The storage index table is specifically the data storage level, data access frequency, and data priority.

[0020] See also Figure 2 , the steps for obtaining the indicator threshold interval are as follows: S111: Based on the emergency patient data, multiple basic information of the emergency patient is obtained, including age, gender, and weight, and the systolic blood pressure, diastolic blood pressure, and blood oxygen data of the patient are detected to obtain the patient data set; First, basic information is obtained from the patient's medical records, including age, gender, weight, and medical history. This data is obtained through the hospital information system or medical records to ensure the accuracy and completeness of the data. Then, the patient's physiological data, including systolic blood pressure, diastolic blood pressure, and blood oxygen value, are collected through real-time monitoring equipment. Blood pressure monitors, oximeters and other equipment are used for real-time detection. These data are summarized as a patient data set for subsequent analysis. Suppose the data of an emergency patient is as follows: Age Age, gender (for female), weight kg, medical history (indicating a history of hypertension), systolic blood pressure mmHg, diastolic pressure mmHg, blood oxygen value Based on these data, the patient's data set is composed of the above items of data. The data set will serve as the basis for subsequent analysis and calculation to form a complete record of the patient's basic information.

[0021] S112: Based on the patient data set, the formula is used: ; Analyze the impact of the patient's age, gender, and weight on the patient's physiological data and generate an impact coefficient; in, Representative The influence coefficient of each physiological parameter, Representative The physiological parameters are The actual measured value of a patient under the characteristics, Representative The physiological parameters are The average value of the patient's historical data under the characteristics, For the The physiological parameters are The standard deviation of the features, For the The physiological parameters are The weight coefficient under a feature indicates the relative weight of the feature’s influence on the physiological data. is the number of features, and each feature is summed. Represents different characteristics, It is an index variable that distinguishes each physiological parameter; Suppose there is an emergency patient whose basic information is as follows: age is 65 years old, gender is male, and weight is 80 kg. Calculate the patient's systolic blood pressure influence coefficient. Suppose the patient's historical systolic blood pressure is 140 mmHg, the standard deviation is 15 mmHg, and the current systolic blood pressure is 155 mmHg. For the influence coefficient of each feature, set the following weights: the influence weight coefficient of age is 1.2, the influence weight coefficient of gender is 1.0, and the influence weight coefficient of weight is 0.8. When setting these values, the weight coefficient is determined based on the specific impact of factors such as the patient's age, gender, and weight on the physiological parameter. For example, age usually has a greater impact on blood pressure, especially as blood pressure may gradually increase with age, so a higher weight coefficient is given. The impact of weight is smaller, but there is still a certain relationship, especially when overweight, it usually leads to higher blood pressure, so the weight coefficient of weight is smaller. Gender differences have a relatively small impact on blood pressure, so the weight coefficient of gender is set to 1.0. According to the formula, calculate the patient's systolic blood pressure influence coefficient: ; The results showed that the patient's systolic blood pressure influence coefficient was 3.0, indicating that age, gender and weight had a comprehensive impact on the patient's systolic blood pressure, with an influence of 3.0. Through this calculation method, the threshold of each patient's physiological indicators is dynamically adjusted to ensure a more personalized and accurate health assessment.

[0022] S113: Calculate the threshold intervals of the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical value according to the influence coefficient, and generate the indicator threshold interval; The critical thresholds of the patient's systolic blood pressure, diastolic blood pressure and blood oxygen values ​​are adjusted, and the individualized critical value interval is calculated. The threshold is corrected based on the known normal range, and the influence of the patient's age, gender, weight and medical history on these physiological data is considered. The adjusted critical value can be corrected by the influence coefficient. It is assumed that the baseline value range of systolic blood pressure, diastolic blood pressure and blood oxygen is set as follows: normal systolic blood pressure: 120mmHg-130mmHg, normal diastolic blood pressure: 80mmHg-85mmHg, normal blood oxygen: 95%-100%. The systolic blood pressure, diastolic blood pressure and blood oxygen values ​​are dynamically adjusted according to the patient's age, gender, weight and medical history data, as well as the corresponding coefficients.

[0023] Using the formula: , and ; Calculate the adjusted values ​​of the patient's systolic blood pressure, diastolic blood pressure and blood oxygen, where: are adjusted systolic and diastolic blood pressures, is the blood oxygen value, is the basal systolic blood pressure, is the basal diastolic pressure, is the weight coefficient of blood pressure, is the weight coefficient of blood oxygen, is the patient's age, is the patient's weight, For the patient's medical history. Assume that the baseline systolic blood pressure , , , age, , , indicating a history of hypertension, , , substitute the patient's specific values ​​into the formula for calculation: Systolic blood pressure adjustment: ; Diastolic blood pressure adjustment: ; Blood oxygen adjustment: ; The results showed that the patient's systolic blood pressure was adjusted to 142.3 mmHg, diastolic blood pressure was 92.3 mmHg, and blood oxygen value was 98.46%. These adjusted values ​​formed the patient's personalized critical value interval for subsequent treatment decisions.

[0024] See also Figure 3 , the specific steps for obtaining risk quantitative scores are: S211: Based on the indicator threshold range, the fluctuation amplitude of each data item is calculated through the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data, the time length of the data window is adjusted, and the window adjustment amplitude parameter is obtained; The acquisition of the patient's heart rate change rate, respiratory rate standard deviation and blood oxygen saturation offset data mainly relies on real-time physiological monitoring equipment, such as piezoelectric film sensors, photoelectric blood oxygen sensors, etc. First, the heart rate and respiratory rate are measured by piezoelectric sensors, and the respiratory and heartbeat components are extracted through signal processing technology. For example, if the heart beats 75 times and the respiratory rate is 18 times in one minute, the heart rate is 75bpm and the respiratory rate is 18bpm. Then, the blood oxygen saturation ( ) is obtained by light reflectance measurement and is calculated using the absorption ratio of red light to infrared light. For example, if a patient's red light to infrared light ratio is 0.5, then About 98%. In order to quantify the data fluctuation, the deviation of each physiological indicator relative to its historical mean is calculated. The comprehensive fluctuation deviation is calculated as follows: ; in, is the comprehensive fluctuation offset, which represents the accumulation of all physiological index offsets. For the The current measured values ​​of the physiological indicators, For the The historical average of physiological indicators, is the total number of physiological indicators monitored. Assuming the historical average heart rate is 70bpm and the current measured value is 75bpm, the heart rate offset is 5bpm. Similarly, if the historical average respiratory rate is 16 times / minute and the current measured value is 18 times / minute, the offset is 2; the historical average blood oxygen saturation is 99%, the current measured value is 98%, and the offset is 1%; According to the calculation, we get: ; When the comprehensive fluctuation offset exceeds the set threshold (for example, 5), the data window time length is adjusted. For example, if the original window is 60 seconds, the window is adjusted to 30 seconds to improve monitoring accuracy. At this time, the window adjustment amplitude parameter is recorded as , whose value is 30s. The threshold is set based on the analysis of a large number of patients' physiological data. For example, in the monitoring data of 1,000 healthy individuals, 95% of them have a comprehensive fluctuation offset of less than 5, so this value is set as the trigger point.

[0025] S212: Based on the window adjustment amplitude parameter, the formula is: ; Calculate the differences between multiple physiological parameters and the set indicator threshold intervals in real time, and accumulate the differences to obtain the cumulative risk offset; in, represents the cumulative risk offset, Representative The actual measured values ​​of the physiological indicators, Representative Setting thresholds for indicators, Representative The weight coefficient of the window adjustment amplitude parameter. Representative The absolute value of the fluctuation offset of the term, Represents the number of physiological indicator data, Represents the number of window adjustment parameters, Represents the data index number of the physiological indicator, The index number representing the window adjustment parameter; Based on the comprehensive fluctuation offset, the difference between it and the set physiological indicator threshold is calculated and accumulated to obtain the cumulative risk offset.

[0026] The calculation formula is as follows: ; in, is the cumulative risk offset, For the The actual measured values ​​of the physiological indicators, For the Setting thresholds for indicators, For the The weight of the window adjustment amplitude parameter, For the Item fluctuation offset, The number of physiological indicators monitored, The amount by which to adjust the amplitude parameter for the window.

[0027] Assignment calculation example: Set physiological indicator threshold Weibo, heart rate: 60-100bpm, set threshold , respiratory rate 12–20 times / minute, set threshold , Blood oxygen saturation: 95%–100%, set threshold .

[0028] Assume that the window adjusts the weight , fluctuation offset ,but: ; The final cumulative risk offset is 13.16, and combined with the window adjustment amplitude parameter, the calculation window time length is adjusted to obtain the dynamic time window length .

[0029] S213: calling the accumulated risk offset, combining the dynamic time window length, calculating the risk quantification score of the data and the threshold, and generating the risk quantification score; Calling cumulative risk offset , combined with the dynamic time window length , calculate the risk quantification score, and generate the final risk score. The calculation of the risk score is based on the size of the cumulative risk offset and the preset maximum risk offset. For example, in a risk assessment system, the maximum risk offset is set ,like If the patient's physiological index deviates from the normal range to a lesser extent, the risk score is also relatively low; on the contrary, if A larger value indicates a higher degree of deviation in physiological indicators and an increase in risk score.

[0030] The calculation formula is as follows: ; in, Quantify the risk score. is the cumulative risk offset, is the preset maximum risk bias, and 100 is the standardized score scale. , , substitute into the calculation: ; The final risk quantification score is 0.2632, which indicates the risk level of the current physiological indicators. Based on this score, the patient's monitoring frequency can be further adjusted or appropriate medical intervention measures can be taken to ensure that the physiological parameters remain within a safe range.

[0031] See also Figure 4 , the specific steps for obtaining the transmission queue identifier are: S311: Based on the risk quantification score, calculate the correlation between multiple physiological data, analyze the mutual influence between the multiple physiological data, and obtain the physiological data correlation coefficient matrix; To obtain the risk quantification score, calculate the correlation between each physiological data, and use the correlation coefficient to measure the degree of mutual influence between different physiological data, first collect the historical records of each physiological data and calculate its mean and standard deviation. For example, suppose a patient's heart rate change rate is ±5bpm, the standard deviation of respiratory rate is 1.2, and the fluctuation range of blood oxygen saturation is ±2%. The correlation between heart rate and respiratory rate is calculated using the Pearson correlation coefficient calculation formula. The Pearson correlation coefficient calculation formula is: ; Suppose that the measured data of a patient's heart rate and respiratory rate are: heart rate 72, 74, 75, 71, respiratory rate 16, 18, 17, 15, the average of heart rate , the mean respiratory rate .

[0032] Substituting into the calculation, we get: ; ; ; Therefore, the correlation coefficient between heart rate and respiratory rate is , which indicates that there is a strong positive correlation. The process is repeated to calculate the correlations between other physiological data, and the physiological data correlation coefficient matrix is ​​obtained.

[0033] S312: Call the physiological data correlation coefficient matrix using the formula: ; Calculate the urgency score of obtaining physiological data; in, Represents the physiological data urgency score, Representative The current measured value of the physiological data, Representative Set baseline values ​​for physiological data. Representative The weight parameters of the physiological data, Representative The changing trend value of the physiological data, Representative Correlation correction coefficient of each physiological data item, Represents the amount of physiological data, The number of data items representing the trend analysis, Represents the index of physiological data, An index representing the changing trend data; First, quantify the fluctuation amplitude and calculate the degree of deviation of each physiological data from the baseline value. For example, assuming that a patient's baseline heart rate is 70bpm and the current measured value is 75bpm, the deviation is calculated as follows: ; Similarly, if the baseline value of the respiratory rate is 16 and the current measured value is 18, the deviation is: ; Then, analyze the change trend and determine the change rate of the physiological data. For example, within 5 minutes, the heart rate increases from 70bpm to 78bpm, and the change rate is calculated as follows: ; To calculate the urgency score, use the following formula: ; Assuming weight parameters , trend correction coefficient , then the calculation is as follows: ; Therefore, the physiological data urgency score is 6.73, indicating that the data has medium urgency.

[0034] S313: calling the physiological data urgency score, sorting the transmission priority of the data packet according to the score value, and generating a transmission queue identifier; Call the physiological data urgency score and sort the transmission priority of the data packet according to the score value. Set the score range to 0-10, where 0-3 is low priority, 3-7 is medium priority, and 7-10 is high priority. Assume the following is the urgency score of the data: The heart rate data score was 6.73, the respiratory rate data score was 4.2, and the blood oxygen saturation data score was 8.1.

[0035] According to the set score range, the priority of the data packet is classified to obtain the following transmission priorities: Table 1 Transmission priority allocation table: ; As shown in Table 1, the transmission order of the data packets is arranged, and the data packets with high priority are given priority transmission. Finally, a transmission queue identifier is generated, which determines the order of data packet transmission and ensures that the data packets with high priority can be transmitted first.

[0036] See also Figure 5 , the specific steps for obtaining data storage records are: S411: calling the transmission queue identifier, extracting the MAC address and patient identity code from the data packet, using the path node sequence, extracting the sequence number and corresponding hash value of each node, matching the key for each data packet, and obtaining the identity and path matching data; Before the transmission begins, the transmission queue identifier is called to extract the MAC address and patient identification code from the data packet, decode and verify them, and ensure that the identity information in the data packet matches that in the patient information database. Specifically, the MAC address is used as a unique identifier to confirm the identity of the device, and the patient identification code verifies the legitimacy of the data to ensure that the transmitted data corresponds to the correct patient. Next, based on the transmission path node sequence, the serial number and corresponding hash value of each node are extracted, and the path node is verified using a hash algorithm to confirm the validity of the path and ensure the integrity of the path node to prevent data tampering during transmission. Finally, the corresponding key is matched for each data packet, and it is ensured that the key matches each item of data in the path node. To calculate the integrity check value of the path node, the node hash matching degree is calculated using the following formula: ; in, represents the path integrity check score, Representative The path node hash value of the item storage, Representative The path node hash value of the item extraction, Represents the total number of path nodes. Assume that the path hash value stored in the system is , the extracted packet path hash value is , the path integrity check score is calculated as follows: ; The baseline value of the path integrity check score is set to 1.5. This value comes from the fact that in normal network communications, the hash value of the data packet path node usually fluctuates within the range of ±1.5. If it exceeds this value, there may be a path change or potential anomaly. This value will change with the stability of the network transmission environment. When the network delay increases or the interference intensifies, the threshold is appropriately increased to ensure that the path deviation will not be misjudged as an anomaly due to slight jitter. Finally, the identity and path matching data are obtained, including patient identity information, path integrity score, and key for packet matching.

[0037] S412: Call the identity and path matching data, using the formula: ; Calculate the key matching degree and obtain the key matching degree score; in, represents the key matching score, Representative The hash value of the key to be transferred. Representative The hash value of the item path node, Representative Correction parameters for item path nodes, Represents the number of key check items, Represents the number of path nodes, Represents the index number of the key verification item, Represents the index number of the path node; The identity and path matching data are called. During the data transmission process, key comparison is performed and the key matching degree is calculated using the following formula: ; This formula calculates the absolute difference between the key value and the hash value of the path node to obtain the key matching score, and then corrects it with the correction parameters of the path node to ensure the stability of the matching process. Assumption value setting: Transmission key hash value , path node hash value , correction parameters , calculate the key matching score as follows: ; ; ; After the calculation is completed, the key matching score is obtained = 1.25. Correction parameters The setting basis of: The correction parameter is used to adjust the influence of path node matching error. It is assigned based on the security level of different path nodes. It is usually in the range of [0.3, 0.8]. The higher the value, the greater the influence weight of the path node on the transmission. For example, if a path node has good historical stability and small error, it will be assigned a lower weight (such as ); If the path nodes often change or the historical matching degree is low, a higher weight is given (such as ), ensure that high-impact path nodes are more strictly processed during path matching calculation.

[0038] S413: calling the key matching score, detecting and identifying abnormal events in the transmission process, and storing the verified data in the database to generate a data storage record; The key matching score is called, combined with the abnormal detection results of the path nodes, to analyze whether an abnormal event occurs during the transmission of the data packet. If the key matching score is lower than the set threshold (such as 0.6), it is considered a transmission abnormality event. Detect abnormal transmission events and store the verified data in the database. Use the following formula to calculate the abnormality score: ; in, represents the abnormality score, represents the key matching score, Represents the path integrity check score. Example calculation: If the key matching score = 1.25, the path integrity check score , then the anomaly score is calculated as follows: ; Abnormal score threshold setting: If , then mark the data packet as abnormal transmission; if , then the data packet transmission is normal. The threshold value of 0.5 is set based on the fact that in normal data transmission, the key matching score is usually above 1.0, and the path integrity score is usually no more than 2.5. Therefore, under normal circumstances, Most of them are above 0.5. When the path integrity score is high, that is, the data transmission path changes greatly, it will automatically decrease. The value of ensures that even if the key matching score is low but the path is normal, it will not be misjudged as abnormal. When the path integrity score is low but the key matching is still low, Rapidly reduce, determine that the data packet transmission is abnormal, and improve the accuracy of anomaly detection. <0.5, the data packet is considered to be abnormal transmission and an abnormal log is generated. If the path node matching degree of multiple consecutive data packets is abnormal, the system will issue an alarm to indicate possible network attacks or data tampering. Finally, the verified data is stored and a data storage record is generated.

[0039] See also Figure 6 , the specific steps for obtaining the storage index table are: S511: extracting various patient data from the database based on the data storage records, obtaining data access records, analyzing the access frequency of each data item, classifying access patterns of multiple categories of data, and obtaining access frequency distribution information; Extract the stored medical record data and its access records from the database. Each data item has an associated access log that records the number of times and time the data item was accessed. In this process, the data first needs to be classified by category (such as case, diagnosis, treatment history, etc.). Then, through the data in the access log, the access frequency of each type of data is counted, that is, the number of times each data item is accessed in a given time period. For example, for a patient's diagnostic data, if the data is accessed 100 times in a certain month, the number of accesses to the data item is 100. Through these data, we can calculate the access frequency of each data item and classify it as high-frequency access data or low-frequency access data. The calculation formula for access frequency is: ; in, Representative The access frequency of the data item, Representative The number of times the data item is accessed, Represents the total number of data accesses within a time period. Assuming that a data item is accessed 100 times in a month and the total number of accesses is 1000 times, the access frequency of the data is: ; This means that the data accounted for 10% of the total number of accesses in this month. This result can help the system identify which data is frequently accessed and which data is infrequently accessed, so as to facilitate subsequent storage optimization and access priority adjustment.

[0040] S512: Call access frequency distribution information, using the formula: ; Calculate the access activity index, where: Represents the data access activity index, Representative The number of times the data item is accessed, Represents the weight coefficient of the data, Represents the total number of data, Representative How long the data item is stored, Represents the total amount of stored data. is the index of the data item, is the index of the storage item; Assume there are 5 data items, the number of accesses to the data items ( =50, =30, =20, =10, =5), weight coefficient ( =1.2, =1.0, =1.1, =0.8, =0.9), and storage duration ( =1000, =800, =600, =400, =200), the total amount of data is 4000. Substitute the above values ​​into the formula and calculate: ; ; Visit activity index , indicating that the access activity of the data item is low, so the data will be stored in the low-priority storage area. This step first calls the access frequency distribution information in the storage system, combines the access frequency and storage duration of each data, and calculates the activity index of each data item. For data items that are frequently accessed and have a short storage duration, their activity will be higher, and these data may need to be stored in an efficient storage area to ensure a quick response to user access needs. For example, some diagnostic information may be accessed repeatedly in a short period of time, while some historical cases may not be accessed for a long time. By calculating the activity index, the system can more reasonably evaluate the storage requirements of each data item and decide how to adjust the storage location. The activity index of each data item is comprehensively evaluated by weighting the number of accesses and storage duration, so as to achieve a more accurate storage optimization goal.

[0041] S513: calling the data access activity index, adjusting the storage location and access priority of the data according to the access activity, and establishing a storage index table; First, obtain the access activity index of all data, and adjust the storage priority of each data based on these activity indexes. Specifically, if the activity index of a certain data is high, it means that it is frequently accessed and requires a quick response. This data should be stored in a high-priority storage area, usually memory or an efficient cache area; while data with low activity indicates that it is less frequently accessed, and it can be considered to be stored on a slower storage device, such as a cold storage or archive storage area. This process is adjusted through the following calculation formula: ; in, represents the adjustment value, Represents the data access activity index, Represents the storage space factor (a measure of the availability of storage location resources). The value calculated by this formula determines the storage priority of the data. The higher the value, the higher the priority of storing data in the fast storage area. , and the storage space factor , then adjust the value Calculated as: ; This result means that the data should be stored in a medium-priority storage area. Through this adjustment, the system can effectively allocate storage resources according to the access activity of the data, improve the overall storage performance and optimize the data access speed.

[0042] The medical emergency data processing system based on cloud computing is used to execute the medical emergency data processing method based on cloud computing. The system includes: The threshold adjustment module is based on emergency patient data. By analyzing age, gender, and weight, the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical values ​​are dynamically corrected to generate indicator threshold intervals. The patient risk assessment module extracts the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data based on the indicator threshold interval, analyzes the data fluctuation amplitude, adjusts the time window length, calculates the cumulative deviation between the actual physiological data and the threshold interval, and obtains the risk quantitative score; The data priority adjustment module calculates the patient's physiological data urgency score based on the risk quantification score, evaluates the correlation between multiple physiological data, analyzes the transmission priority of multiple data based on the data fluctuation range and change trend, and generates a transmission queue identifier; The transmission security verification module is based on the transmission queue identifier, extracts the MAC address, patient identity code, transmission path node sequence, matches the key, verifies the matching degree between the key and the path node, analyzes abnormal transmission behavior, and stores the verified data in the database to generate data storage records; The hierarchical storage management module extracts various patient data from the database based on data storage records, calculates access activity using the access frequency of multiple data, adjusts the storage location and access priority of the data, and generates a storage index table.

[0043] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for processing medical emergency data based on cloud computing, characterized in that: The following steps are involved: S1: Monitor emergency patient data, analyze age, gender, and weight, and dynamically correct the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical values ​​to generate indicator threshold intervals; S2: Based on the threshold interval of the indicator, by analyzing the fluctuation amplitude of the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data, adjusting the time window length, calculating and accumulating the difference between the physiological data and the threshold in multiple time windows, and generating a risk quantification score; S3: Analyze the correlation between multiple physiological data according to the risk quantification score, calculate the urgency score of each physiological data in combination with the fluctuation amplitude and change trend, adjust the transmission priority of the data packet, and generate a transmission queue identifier; S4: calling the transmission queue identifier, extracting multiple pieces of information of the data packet and matching the key, verifying the matching degree between the key and the path node, detecting abnormal transmission events and storing the verified data in the database, and generating a data storage record; S5: Based on the data storage records, extract various patient data from the database, evaluate access activity by access frequency of each data item, adjust storage location and access priority, and generate a storage index table.

2. The method for processing medical emergency data based on cloud computing according to claim 1, characterized in that: The indicator threshold interval specifically includes the systolic pressure threshold, the diastolic pressure threshold, and the blood oxygen saturation threshold; the risk quantification score specifically includes the heart rate risk score, the respiratory rate risk score, and the blood oxygen saturation risk score; the transmission queue identifier specifically includes the transmission priority, the data packet number, and the transmission timestamp; the data storage record specifically includes the key matching degree, the path node matching degree, and the abnormal transmission event mark; the storage index table specifically includes the data storage level, the data access frequency, and the data priority.

3. The method for processing medical emergency data based on cloud computing according to claim 2, characterized in that: The steps for obtaining the indicator threshold interval are specifically as follows: S111: Based on the emergency patient data, multiple basic information of the emergency patient is obtained, including age, gender, and weight, and the systolic blood pressure, diastolic blood pressure, and blood oxygen data of the patient are detected to obtain the patient data set; S112: Based on the patient data set, the formula is used: ； Analyze the impact of the patient's age, gender, and weight on the patient's physiological data and generate an impact coefficient; in, Representative The influence coefficient of each physiological parameter, Representative The physiological parameters are The actual measured value of a patient under the characteristics, Representative The physiological parameters are The average value of the patient's historical data under the characteristics, For the The physiological parameters are The standard deviation of the features, For the The physiological parameters are The weight coefficient under a feature indicates the relative weight of the feature’s influence on the physiological data. is the number of features, and each feature is summed. Represents different characteristics, It is an index variable that distinguishes each physiological parameter; S113: Calculate the threshold ranges of the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical value according to the influence coefficient, and generate an indicator threshold range.

4. The method for processing medical emergency data based on cloud computing according to claim 3, characterized in that: The steps for obtaining the risk quantification score are specifically as follows: S211: Based on the indicator threshold range, the fluctuation amplitude of each data item is calculated through the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data, the time length of the data window is adjusted, and the window adjustment amplitude parameter is obtained; S212: Based on the window adjustment amplitude parameter, the formula is adopted: ； Calculate the differences between multiple physiological parameters and the set indicator threshold intervals in real time, and accumulate the differences to obtain the cumulative risk offset; in, represents the cumulative risk offset, Representative The actual measured values ​​of the physiological indicators, Representative Setting thresholds for indicators, Representative The weight coefficient of the window adjustment amplitude parameter, Representative The absolute value of the fluctuation offset of the term, Represents the number of physiological indicator data, Represents the number of window adjustment parameters, Represents the data index number of the physiological indicator, The index number representing the window adjustment parameter; S213: calling the accumulated risk offset, combining the dynamic time window length, calculating the risk quantification score of the data and the threshold, and generating a risk quantification score.

5. The method for processing medical emergency data based on cloud computing according to claim 4, characterized in that: The steps for obtaining the transmission queue identifier are specifically as follows: S311: Based on the risk quantification score, calculate the correlation between the various physiological data, analyze the mutual influence between the various physiological data, and obtain a physiological data correlation coefficient matrix; S312: Call the physiological data correlation coefficient matrix, using the formula: ； Calculate the urgency score of obtaining physiological data; in, Represents the physiological data urgency score, Representative The current measured value of the physiological data, Representative Set baseline values ​​for physiological data. Representative The weight parameters of the physiological data, Representative The changing trend value of the physiological data, Representative Correlation correction coefficient of each physiological data item, Represents the amount of physiological data, The number of data items representing the trend analysis, Represents the index of physiological data, An index representing the changing trend data; S313: calling the physiological data urgency score, sorting the transmission priorities of the data packets according to the score values, and generating a transmission queue identifier.

6. The method for processing medical emergency data based on cloud computing according to claim 5, characterized in that: The steps for obtaining the data storage record are specifically as follows: S411: calling the transmission queue identifier, extracting the MAC address and patient identity code from the data packet, using the path node sequence, extracting the serial number and corresponding hash value of each node, matching the key for each data packet, and obtaining identity and path matching data; S412: Call the identity and path matching data, using the formula: ； Calculate the key matching degree and obtain the key matching degree score; in, represents the key matching score, Representative The hash value of the key to be transferred. Representative The hash value of the item path node, Representative Correction parameters for item path nodes, Represents the number of key check items, Represents the number of path nodes, Represents the index number of the key verification item, Represents the index number of the path node; S413: Call the key matching score to detect and identify abnormal events in the transmission process, store the verified data in the database, and generate a data storage record.

7. The method for processing medical emergency data based on cloud computing according to claim 6, characterized in that: The steps for obtaining the storage index table are specifically as follows: S511: extracting a variety of patient data from a database based on the data storage records, obtaining data access records, analyzing the access frequency of each data item, classifying access patterns of multiple categories of data, and obtaining access frequency distribution information; S512: Call the access frequency distribution information, using the formula: ； Calculate the access activity index, where: Represents the data access activity index, Representative The number of accesses to the data item. Represents the weight coefficient of the data, Represents the total number of data, Representative How long the data item is stored? Represents the total amount of stored data. is the index of the data item, is the index of the storage item; S513: calling the data access activity index, adjusting the storage location and access priority of the data according to the access activity, and establishing a storage index table.

8. The medical emergency data processing system based on cloud computing is characterized by: According to the cloud computing-based medical emergency data processing method according to any one of claims 1 to 7, the system comprises: The threshold adjustment module is based on emergency patient data. By analyzing age, gender, and weight, the patient's systolic blood pressure, diastolic blood pressure, and blood oxygen critical values ​​are dynamically corrected to generate indicator threshold intervals. The patient risk assessment module extracts the patient's heart rate change rate, respiratory rate standard deviation, and blood oxygen saturation offset data based on the indicator threshold interval, performs data fluctuation amplitude analysis, adjusts the time window length, calculates the cumulative deviation between the actual physiological data and the threshold interval, and obtains a risk quantitative score; The data priority adjustment module calculates the patient's physiological data urgency score based on the risk quantification score, evaluates the correlation between multiple physiological data, analyzes the transmission priority of multiple data in combination with the data fluctuation range and change trend, and generates a transmission queue identifier; The transmission security verification module extracts the MAC address, patient identification code, transmission path node sequence, matches the key, verifies the matching degree between the key and the path node, analyzes abnormal transmission behavior, and stores the verified data in the database to generate a data storage record based on the transmission queue identifier; The hierarchical storage management module extracts a variety of patient data from the database based on the data storage records, calculates access activity using the access frequencies of multiple data, adjusts the storage location and access priority of the data, and generates a storage index table.

Images