Cross-border personnel isolation health monitoring system based on Internet of Things

Abstract

The invention relates to the technical field of electrical fault identification and response, in particular to a cross-border personnel isolation health monitoring system based on the Internet of Things, which comprises an isolation reference module, a data migration module, a scene adjustment module, a credible judgment module and a remote presentation module. According to the method, the personalized health interval is established, so that the health data of each cross-border person is based on the initial state of the cross-border person, and misjudgment caused by physiological difference is avoided. And dynamic adjustment and multi-parameter analysis of the health interval can timely identify health fluctuation and give risk early warning, so that the monitoring sensitivity and accuracy are improved. The display weight is dynamically adjusted, management personnel are helped to focus on key indexes, information redundancy is reduced, and efficiency is improved. Noise judgment and consistency analysis can effectively distinguish real change and interference data, and data reliability is enhanced. A monitoring interface is adjusted in real time according to data changes, it is ensured that information is consistent with an isolation management state, decision adaptability is improved, and the fine management capacity in an isolation scene is enhanced.

Description

Technical Field

[0001] This invention relates to the field of remote operation technology, and in particular to a cross-border personnel isolation health monitoring system based on the Internet of Things. Background Technology

[0002] The field of remote operation technology encompasses a comprehensive technological system for collecting, transmitting, and centrally managing personnel status and environmental information in off-site scenarios. This technology is based on communication networks, uses sensing terminals as information sources, and employs a remote management platform as the control and presentation carrier. Its core components include personnel identification binding, sensing data collection, data transmission link organization, remote status presentation, and management control. This field typically addresses the management needs of personnel located in different physical spaces. By deploying sensing devices with communication capabilities, relevant information about personnel scattered across different locations is aggregated to a unified node, enabling continuous monitoring and centralized processing of personnel status across regions. This technology is applicable to various scenarios such as public administration, medical supervision, and isolation management.

[0003] Among them, the IoT-based cross-border personnel isolation health monitoring system refers to a system structure that, in the context of cross-border personnel isolation management, utilizes network-enabled sensing units and communication nodes to uniformly associate and continuously collect the identity information, physiological parameters, and isolation environment status of isolated personnel. The technical aspects addressed by this system include the registration and binding of cross-border personnel information, the access methods for temperature collection devices, heart rate collection devices, and positioning identification modules worn or deployed by personnel within the isolation area, and the organization of transmitting the collected information to a designated management platform via cellular communication or local area networks. It also includes the network-based collection configuration of the isolation site's entrance and exit status and room environmental parameters, and the aggregation of personnel health-related data and isolation status data through IoT nodes for centralized viewing and management by a remote management terminal.

[0004] Existing monitoring technologies mainly rely on fixed health parameter thresholds, failing to establish health benchmarks based on individual differences. This leads to the use of uniform standards for assessment across different populations, which can easily result in misjudgments. Monitoring data is typically collected in a single instance, lacking cross-time correlation analysis and failing to reflect dynamic changes in individual health status in a timely manner. Managers are unable to effectively identify potential risks. Health parameter displays are not adapted, with all data displayed equally, making it difficult to highlight key indicators. Environmental interference, such as loose equipment or communication fluctuations, is not effectively handled, easily generating false alarms. The monitoring interface is not adjusted according to changes in health data or isolation status, causing managers to gradually lose sensitivity to abnormal signals and reducing the system's adaptability in complex isolation scenarios. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing an Internet of Things-based cross-border personnel isolation health monitoring system.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A cross-border personnel isolation health monitoring system based on the Internet of Things includes: The isolation baseline module acquires body temperature, resting heart rate, and blood oxygen data uploaded by the monitoring terminal worn by cross-border quarantine personnel through remote operation, statistically analyzes the health parameters collected initially, constructs a reliable interval, and stores it as the monitoring baseline for the initial stage of quarantine, thus forming the initial health monitoring interval. Based on the initial health monitoring interval, the data migration module continuously collects health data during the isolation period, statistically analyzes the data within the time window and compares it with the previous period's reliable interval, dynamically adjusts the health parameter interval, and generates a remote risk identifier when the monitoring results meet the risk judgment conditions. The scenario adjustment module calls the remote risk identifier, combines the isolation status and health status level to determine the current isolation management scenario, and adjusts the weight of the health parameters to determine the parameter display order; The credibility determination module analyzes the consistency of continuous health parameter collection results based on the parameter display order, and determines the credibility status of the health parameters by combining noise judgment conditions, and generates a credibility level. The remote presentation module dynamically adjusts the display method of health data according to the trust level and the display order of the parameters, and outputs a monitoring interface that matches the current isolation management status, so as to realize the health monitoring of cross-border personnel in isolation.

[0007] As a further aspect of the present invention, the initial health monitoring interval includes an individual health reference range, initial parameter distribution characteristics, and a normal reference range; the remote risk identifier specifically includes risk status identifier, abnormality type identifier, and risk level identifier information; the parameter display order includes a parameter display priority list, scenario-corresponding sorting results, and display level correspondence; the credibility level specifically includes a data credibility level identifier, stability status level, and data reliability identifier; and the monitoring interface includes an interface information display area, a health parameter display unit, and a status prompt display area.

[0008] As a further aspect of the present invention, the confidence interval is the body temperature, resting heart rate and blood oxygen data collected in the initial stage of isolation, which are analyzed by continuous collection and time correlation. The health parameter range is based on three types of data: body temperature, resting heart rate, and blood oxygen. The range of values ​​is updated over time during the isolation process.

[0009] As a further aspect of the present invention, the remote risk identification is a correlation analysis between the data and the current health parameter range performed by the system during the continuous reception of health data; The initial health monitoring range is a basic reference range formed based on the body temperature, resting heart rate, and blood oxygen data collected synchronously for the first time during the initial use of the system.

[0010] As a further aspect of the present invention, the isolation reference module includes: The remote acquisition submodule acquires body temperature, resting heart rate, and blood oxygen data uploaded by the monitoring terminal worn by cross-border quarantine personnel through remote operation, filters data within the same acquisition cycle, and obtains a synchronized health dataset. The initial sampling statistics submodule extracts the initial body temperature, resting heart rate and blood oxygen value based on the synchronous health dataset, calculates the mean of the three items and compares them with the number of samplings to obtain the initial health parameter set; The interval database construction submodule integrates body temperature, resting heart rate and blood oxygen value sequences based on the initial health parameter set, calculates the standard deviation and judges the abnormal deviation magnitude, obtains the deviation amount and synthesizes the interval expansion magnitude, and establishes the initial health monitoring interval.

[0011] As a further aspect of the present invention, the interval migration module includes: The continuous data collection submodule continuously collects health data during the isolation period based on the initial health monitoring interval, records timestamps, filters data with consecutive and complete timestamps, removes duplicate records, and obtains a window health dataset. The interval comparison submodule calls the window health dataset to count the mean of health parameters, compares the mean with the upper and lower limits of the initial health monitoring interval, counts the number of times the limit is exceeded, adjusts the upper and lower limits of the intervals for body temperature, resting heart rate, and blood oxygen, updates the cycle identifier, and establishes the migration health parameter interval. The risk identification submodule calculates the absolute value of the deviation of body temperature, resting heart rate and blood oxygen in the migration health parameter range and the window health dataset, compares it with the risk judgment threshold, obtains various risk quantities and synthesizes the risk intensity quantity, and generates a remote risk identification. The health data includes body temperature, resting heart rate, and blood oxygen saturation.

[0012] As a further aspect of the present invention, the scene weighting module includes: The remote identifier invocation submodule invokes the remote risk identifier, detects the consistency with the isolation status time identifier, removes missing identifier records, and performs matching and verification between the source of the remote risk identifier and the personnel identifier to obtain a valid risk identifier set; The scenario determination submodule, based on the effective risk identifier set, associates isolation status with health status level identifiers, compares isolation status with scenario mapping rules, determines the scenario type, performs cross-verification of health status and scenario type, eliminates conflicting combinations, and establishes the current management scenario identifier. The display order generation submodule associates health parameters with the display record sequence based on the current management scenario identifier, adjusts the weights of body temperature, resting heart rate, and blood oxygen, calculates the comprehensive ranking quantity, and generates a display sequence index to obtain the parameter display order.

[0013] As a further aspect of the present invention, the process of detecting the consistency of the isolation status time stamp is as follows: comparing the timestamp recorded in the remote risk identifier with the interval between the start time and end time corresponding to the isolation status; when the timestamp is outside the duration range of the isolation status, the corresponding remote risk identifier is determined to be an inconsistent record and is removed. The process of matching and verifying the source and personnel identifiers of the remote risk identifier is as follows: a one-to-one correspondence verification is performed between the source identifier field contained in the remote risk identifier and the device identifier field registered in the personnel identifier. When the source identifier field and the device identifier field are inconsistent, the corresponding record is excluded from the set of valid risk identifiers. The process of comparing the isolation state with the scene mapping rules is as follows: the state level identifier corresponding to the isolation state is matched with the pre-stored scene mapping rule table, and the scene type is confirmed only when the matching result is unique; The process of adjusting the weights of body temperature, resting heart rate, and blood oxygen is as follows: when the isolation status level corresponding to the current management scenario is enhanced isolation, the weight of body temperature is increased and the weight of resting heart rate is decreased; when the isolation status level corresponding to the current management scenario is regular isolation, the weight of blood oxygen is increased and the ratio between the weights of body temperature and resting heart rate remains unchanged, and the parameter display order is generated.

[0014] As a further aspect of the present invention, the trust determination module includes: The sequential association submodule displays the parameters in the order they are presented, associates the sequences of body temperature, resting heart rate and blood oxygen value, filters data with consistent time identifiers and removes missing fields, and obtains the sequence of collected parameters. The consistency analysis submodule extracts the difference components of body temperature, resting heart rate, and blood oxygen based on the parameter sequence collected in the order, summarizes the difference sequence, compares the difference sequence with the noise judgment threshold, filters out the difference items exceeding the threshold, calculates the consistency intensity quantity and generates a reliable judgment label to obtain a reliable state identifier. The level generation submodule verifies the consistency between the trust status identifier, health status level identifier, and isolation status identifier and the noise judgment condition, eliminates conflicting identifiers, and generates a trust level.

[0015] As a further aspect of the present invention, the remote presentation module includes: The level parsing submodule verifies the consistency between the trust level identifier and the personnel identifier based on the trust level and the parameter display order, removes missing items, compares the index sequence with the health parameter identifier and removes unmapped items, and obtains the presentation control identifier set. The style adjustment submodule extracts and associates the display weight with the current isolation management status based on the presentation control identifier set, compares the display weight with the trust level threshold to generate a style switching flag, obtains the style driving quantity and writes it into the style mapping identifier to obtain the display style configuration; Based on the display style configuration, the interface output submodule obtains the isolation management status identifier sequence, filters and verifies that the interface component identifier and the style mapping identifier are consistent, adjusts the component display order and writes the interface version identifier, and outputs the monitoring interface.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are as follows: This invention establishes personalized health zones, ensuring that the health data of each cross-border individual is based on their initial state, thus avoiding misjudgments caused by physiological differences. Dynamic adjustment and multi-parameter analysis of health zones can promptly identify health fluctuations and issue risk warnings, improving monitoring sensitivity and accuracy. Dynamically adjusting display weights helps managers focus on key indicators, reducing information redundancy and improving efficiency. Noise detection and consistency analysis effectively distinguish between real changes and interfering data, enhancing data reliability. The monitoring interface adjusts in real time according to data changes, ensuring information is consistent with the isolation management status, improving decision-making adaptability, and strengthening refined management capabilities in isolation scenarios. Attached Figure Description

[0017] Figure 1 This is a system flowchart of the present invention; Figure 2 This is a flowchart of the isolation reference module acquisition process of the present invention; Figure 3 This is a flowchart of the data migration module of the present invention. Figure 4 This is a flowchart of the scene adjustment module of the present invention. Figure 5 This is a flowchart of the credibility determination module of the present invention; Figure 6 This is a flowchart of the remote presentation module acquisition process of the present invention; Figure 7 This diagram shows a comparison between the prior art and the present invention. Figure 8 This is a diagram of the health monitoring terminal of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0019] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0020] Please see Figures 1-8 The IoT-based cross-border personnel quarantine health monitoring system includes: The isolation baseline module acquires body temperature, resting heart rate, and blood oxygen data uploaded by the monitoring terminal worn by cross-border quarantine personnel through remote operation, statistically analyzes the health parameters collected initially, constructs a reliable interval, and stores it as the monitoring baseline for the initial stage of quarantine, thus forming the initial health monitoring interval. The data migration module continuously collects health data during the isolation period based on the initial health monitoring interval, statistically analyzes the data within the time window and compares it with the previous period's reliable interval, dynamically adjusts the health parameter interval, and generates a remote risk label when the monitoring results meet the risk judgment conditions. The scenario adjustment module calls the remote risk identifier, combines the isolation status and health status level to determine the current isolation management scenario, and adjusts the weight of health parameters to determine the parameter display order; The credibility determination module analyzes the consistency of continuous health parameter collection results based on the parameter display order, and determines the credibility status of health parameters by combining noise judgment conditions, and generates a credibility level. The remote presentation module dynamically adjusts the way health data is displayed based on the trust level and the order of parameter display, and outputs a monitoring interface that matches the current isolation management status.

[0021] The initial health monitoring interval includes the individual health reference range, initial parameter distribution characteristics, and normal reference interval; Remote risk identification specifically includes risk status identification, anomaly type identification, and risk level identification information; The parameter display order includes a list of parameter display priority, the scene-corresponding sorting results, and the display hierarchy correspondence. The trust level specifically includes the data trust level identifier, the stability status level, and the data reliability identifier; The monitoring interface includes an information display area, a health parameter display unit, and a status prompt display area.

[0022] Please see Figure 2 The isolation baseline module includes: The remote acquisition submodule acquires body temperature, resting heart rate, and blood oxygen data uploaded by the monitoring terminal worn by cross-border quarantine personnel through remote operation, filters data within the same acquisition cycle, and obtains a synchronized health dataset. The monitoring terminal worn by cross-border quarantine personnel is accessed remotely, and body temperature values ​​are actively recorded at fixed time intervals. Heart rate at rest and blood oxygen saturation value Subsequently, a data reading action is initiated through the remote communication channel. The remote end receives multiple records within the same collection period sequentially according to the object number, sorts the received data according to the timestamp field, and selects data with timestamp differences less than the set collection period. Data is grouped into the same batch. For example, if the collection period is set to 5 minutes, then body temperatures of 36.6℃ and 36.7℃, heart rates of 68 beats / minute and 70 beats / minute, and blood oxygen levels of 97% and 98% between 08:00:00 and 08:05:00 are selected as data for the same period, and body temperature sets are created separately within this batch. Heart rate set Blood oxygen collection Then, the integrity of the sets is checked by comparing the number of elements in each of the three sets. If the number is inconsistent, a purge action is performed, retaining only records that exist in all three categories of indicators. This method forms time-aligned data rows, such as record rows. and Each row is assigned an object identifier and a period number, and the multidimensional records processed by time synchronization within the period are finally summarized into a structured dataset, which serves as the synchronized health dataset called for subsequent processing. The initial sampling statistics submodule extracts the initial body temperature, resting heart rate and blood oxygen value based on the synchronous health dataset, calculates the mean of the three items and compares them with the number of samplings to obtain the initial health parameter set; Based on the synchronized health dataset, the data was first sorted in ascending order by collection time. The first collection period after the system was activated for each isolated individual was selected as the statistical starting point, and the body temperature field was called within that period. Heart rate field Blood oxygen field Within the period Each record is added up sequentially. For example, if the body temperature records are 36.6℃, 36.7℃, and 36.5℃, the total is 109.8. Then, the sum is calculated based on the number of data collections. After performing division, the initial average body temperature was 36.6℃. The heart rate records were 68, 70, and 69 beats / minute, so the calculated result is 69 beats / minute. The blood oxygen records were 97, 98, and 97%, so the calculated result is 97.3%. The number of data collections was recorded simultaneously during the mean calculation. and will With preset minimum number of valid attempts Perform numerical comparisons, for example, set ,when When the mean is equal to 3, retain the mean result. If the value is less than 3, the object is marked as having incomplete initial data and subsequent processing is paused. Then, the mean body temperature, mean heart rate, mean blood oxygen saturation, and the corresponding number of data collections are combined into a parameter row. Repeat the above calculation steps for each object to finally form a parameter set containing only the initial statistical results. Each record in this set comes from explicit frequency statistics and item-by-item arithmetic operations to obtain the initial health parameter set. The interval database construction submodule integrates body temperature, resting heart rate and blood oxygen value sequences based on the initial health parameter set, calculates the standard deviation and judges the abnormal deviation magnitude, obtains the deviation amount and synthesizes the interval expansion magnitude, and establishes the initial health monitoring interval. After obtaining the initial parameter set, for each isolated individual, their body temperature, heart rate, and blood oxygen saturation data from subsequent collection periods are retrieved, and each indicator is constructed as a time series, for example, the body temperature series is... Heart rate sequence is The blood oxygen sequence is Then, using the initial mean as the reference center value, the difference between each sampling point and the center value is calculated item by item, such as body temperature deviation. They are respectively Then sum the squared deviations and divide by the sample size. Obtain the variance, then perform a square root operation on the variance to obtain the standard deviation. ,For example Calculate in the same way , After obtaining the standard deviation, the deviation judgment factor is pre-set based on medical monitoring experience. , The value is determined based on the sensitivity of the indicator to fluctuations, such as body temperature. Heart rate Blood oxygenation Then, the allowable deviation for each indicator was calculated separately. For example, the permissible deviation of body temperature is 0.3℃. This deviation is then added to the initial mean to form the interval boundary, for example, the body temperature interval is... Heart rate zone is Blood oxygenation range is Finally, the range offsets of the three indicators are numerically integrated to form a range expansion parameter that describes the overall fluctuation range. This parameter is then associated with and stored with the corresponding object identifier to establish the initial health monitoring range.

[0023] Please see Figure 3 The interval migration module includes: The continuous data collection submodule collects health data continuously during the isolation period based on the initial health monitoring interval, records timestamps, filters data with consecutive and complete timestamps, removes duplicate records, and obtains a window health dataset. Health data includes body temperature, resting heart rate, and blood oxygen saturation. Based on the established initial health monitoring interval, the quarantined individuals are treated as the subjects of continuous monitoring, and periodic data readings are initiated on the monitoring terminals they wear, with a fixed collection cycle during the quarantine period. Repeatedly obtain body temperature resting heart rate With blood oxygen The data is processed by writing a timestamp accurate to the second to the data each time it is read. Then, the data collected consecutively are sorted in ascending order by timestamp according to the object identifier. The difference between the timestamps of adjacent records is calculated one by one. For example, if the consecutive records are 10:00:00, 10:05:00, and 10:10:00, the time is considered continuous if the difference is equal to 5 minutes. If the difference is 0 or less... The record is marked as a duplicate and deleted when the difference is greater than 1. When a time breakpoint is identified, the selection of that data segment is terminated, retaining only those timestamps that are continuous and whose quantity meets the preset window length. For example, if the window length is set to 12, then 12 consecutive records are needed to form a 60-minute window, within which the body temperature sequence is extracted. Heart rate sequence Blood oxygen sequence The system checks whether the number of data entries for the three types of sequences within the window is consistent, retains only the data rows with completely matching numbers, and finally forms a window health dataset by combining the multi-indicator record set after time continuity verification, duplicate removal and integrity filtering. The interval comparison submodule calls the window health dataset to calculate the mean of health parameters, compares the deviation of the mean with the upper and lower limits of the initial health monitoring interval, counts the number of times the limit is exceeded, adjusts the upper and lower limits of the intervals for body temperature, resting heart rate, and blood oxygen, updates the cycle identifier, and establishes the migration health parameter interval. The system calls the window's health dataset to calculate the average values ​​of health parameters. First, it calculates the average values ​​for body temperature, resting heart rate, and blood oxygen saturation data within the window. Body temperature record to Summing each term and dividing by For example, if the body temperature records are 36.7, 36.9, 36.8, and 37.0, the execution result will be 36.85. Similarly, the average heart rate within the window is obtained as (70+72+74+71) / 4=71.75, and the average blood oxygen saturation within the window is obtained as (97+96.8+96.5+96.9) / 4≈96.8. Then, the initial health monitoring interval upper and lower limit parameters of the corresponding object are called, such as the body temperature interval. The window mean is compared with the upper and lower limits, and the offset of the mean exceeding the upper or lower limit is calculated. For example, if 36.85 is within the interval, the offset is 0. If the heart rate mean of 71.75 exceeds the upper limit of 72, the offset is calculated as 72 - 71.75, which is recorded as 0. If the blood oxygen mean of 96.8 is lower than the lower limit of 96.7, the absolute value of 96.7 - 96.8 is calculated to obtain 0.1. This comparison process is repeated over multiple consecutive window periods, and the number of times c occurs for each indicator where the mean exceeds the interval boundary is counted. For example, if blood oxygen is below the lower limit 3 times in 5 windows, then... ,when Reaching the preset adjustment threshold For example, at time 3, the interval update action is triggered. The upper and lower limits are shifted according to the direction of exceeding the limit. For example, the lower limit of blood oxygen is adjusted from 96.7 to 96.5, while the upper limit remains unchanged. At the same time, the new interval parameters and the corresponding cycle number are recorded, and finally a migration health parameter interval containing the updated body temperature, heart rate, upper and lower limits of blood oxygen and cycle identifier is formed. The risk identification submodule calculates the absolute value of the deviation of body temperature, resting heart rate and blood oxygen in the migration health parameter range and the window health dataset, compares it with the risk judgment threshold, obtains various risk quantities and synthesizes the risk intensity quantity, and generates a remote risk identification. After the health parameter range is generated, risk calculation is performed on each individual record in the window health dataset, calling the body temperature value at each moment within the window. Heart rate value With blood oxygen level The deviation is compared with the upper and lower limits corresponding to the migration interval. When a value is within the interval, the deviation is recorded as 0. When a value exceeds the upper limit or falls below the lower limit, the difference between the value and the nearest boundary is calculated and the absolute value is taken. For example, if the body temperature is 37.2°C and the upper limit of the interval is 36.9°C, the deviation is |37.2−36.9|=0.3; the heart rate is 78 bpm and the upper limit is 75 mmol / L, so the deviation is 3; the blood oxygen saturation is 95.8 mmol / L and the lower limit is 96.5 mmol / L, so the deviation is 0.7. Then, each deviation is compared with the corresponding risk assessment threshold, which is based on historical monitoring data. The fluctuation range is set, for example, the risk threshold for body temperature is 0.5℃, the risk threshold for heart rate is 5 beats / minute, and the risk threshold for blood oxygen is 1.0%. When the deviation is less than the threshold, it is recorded as a low risk; when the deviation is equal to or greater than the threshold, it is recorded as a high risk. The three risk values ​​are then combined according to their numerical values. For example, (0.3 / 0.5)+(3 / 5)+(0.7 / 1.0)=0.6+0.6+0.7=1.9 to obtain the risk intensity value. Finally, the risk intensity value is bound to the object identifier and timestamp to generate the corresponding remote risk identifier.

[0024] Please see Figure 4 The scene weighting module includes: The remote identifier invocation submodule invokes remote risk identifiers, checks the consistency with the isolation status time identifier, removes missing identifier records, and performs matching and verification between the source of the remote risk identifier and the personnel identifier to obtain a valid set of risk identifiers; The remote risk identifier is invoked, and its consistency with the isolation status timestamp is checked. First, the corresponding risk identifier record is retrieved one by one according to the unique personnel identifier of the isolated person, and the generation timestamp of each record is read. It also simultaneously reads the isolation status time stamp registered by the person in the isolation management system. The execution time consistency check action is performed by calculating... The numerical value determines whether they are within the same isolation period. For example, if the allowed time deviation threshold is set to 10 minutes, when... , If the time difference is less than 5 minutes, the record is retained; if the time difference is greater than the threshold, deletion is performed directly. Then, the retained records are checked for empty or missing risk identifier fields. If the risk intensity field is missing or empty, the record is removed. After completing time and integrity checks, the source terminal number and personnel binding number in the risk identifier are compared item by item. For example, the terminal number... Bound personnel When the risk label appears correspond Records that are determined to be mismatched are deleted, and only records whose terminal source and personnel identifier are completely consistent are retained. Finally, the risk identifiers that have passed the time consistency verification, missing data removal and source matching verification are summarized to form a valid risk identifier set. The scenario determination submodule, based on the effective risk identifier set, associates the isolation status with the health status level identifier, compares the isolation status with the scenario mapping rules, determines the scenario type, performs cross-verification of the health status and scenario type, eliminates conflicting combinations, and establishes the current management scenario identifier. After obtaining the set of valid risk indicators, the corresponding risk intensity value is read for each valid risk indicator, and the current isolation status level indicator of the person is retrieved simultaneously, for example, home isolation is recorded as Centralized quarantine is recorded as Medical observation is recorded as At the same time, retrieve the health status level range in which the risk intensity level falls, for example, by setting the risk intensity level. For a healthy state , for greater than 2 When a certain record has a risk intensity of 1.9, it is classified as Then, the isolation status identifier and the health status identifier are combined into a status pair. And compare each rule with the preset scene mapping rule table, for example, the rule defines Corresponding to conventional monitoring scenarios, Corresponding to enhanced monitoring scenarios, For key management scenarios, a corresponding scenario type identifier is generated when the status matches a rule; otherwise, the combination is directly removed. After the initial determination of the scenario type, a cross-validation action is performed, which reversely verifies the health status level against the scenario type. For example, in the enhanced monitoring scenario, only [certain rules are allowed]. or When it appears When combined with enhanced monitoring scenarios, they are directly deleted. Logically conflicting combinations are removed through item-by-item verification. In the end, only records whose status is consistent with the scenario logic are retained, and the corresponding scenario type identifier is stored as the current management scenario identifier. The display order generation submodule associates health parameters with the display record sequence based on the current management scenario identifier, adjusts the weights of body temperature, resting heart rate, and blood oxygen, calculates the comprehensive sorting quantity, and generates a display sequence index to obtain the parameter display order. Once the current management scenario identifier is determined, it is used as the basis for weight adjustment. First, the associated health parameter display record sequence under this scenario is retrieved, and each record is labeled with body temperature, resting heart rate, and blood oxygen parameters. Then, initial weight base values ​​are assigned to each parameter according to the scenario type. For example, in a routine monitoring scenario, the initial weight values ​​for body temperature, heart rate, and blood oxygen are all set to 1; in an intensive monitoring scenario, the weight base value for body temperature is set to 1.5, heart rate to 1.2, and blood oxygen to 1.3. The setting of these weight base values ​​is derived from the historical risk deviation frequency statistics results under this scenario. Then, the average deviation of each parameter in the effective risk identifier set is read, such as the average deviation of body temperature. The deviation is set to 0.2, heart rate to 2, and blood oxygen to 0.6. The deviation is multiplied by the weighted base value to obtain the weighted parameter values. For example, the weighted value of body temperature is 1.5 × 0.2 = 0.3, heart rate is 1.2 × 2 = 2.4, and blood oxygen is 1.3 × 0.6 = 0.78. The three weighted parameter values ​​are then sorted according to their numerical values, with larger values ​​having higher priority. This yields the sorting results for heart rate, blood oxygen, and body temperature. Subsequently, corresponding display sequence index numbers are generated, for example, heart rate is recorded as sequence number 1, blood oxygen as sequence number 2, and body temperature as sequence number 3. The index results are written into the display control record, ultimately forming a clear parameter display order.

[0025] Please see Figure 5 The trust determination module includes: The sequential association submodule associates the sequences of body temperature, resting heart rate and blood oxygen value based on the parameter display order, filters data with consistent time identifiers and removes missing fields to obtain the sequentially collected parameter sequence. Based on the displayed order of the obtained parameters, the sorting result is broken down into a display index. And bind body temperature sequences respectively Resting heart rate sequence Blood oxygen sequence ,according to The primary parameter pointed to first reads the record lines of its sequence and simultaneously reads the corresponding time markers. Then press and The parameter being pointed to is identified at the same time. The execution field is located and read, then executed. Consistency filtering is performed on each record. And With the collection cycle Perform an equality comparison, for example, take... Read in seconds sequence but Both 300-second intervals are considered consecutive. If 10:05:00 and 10:05:00 are read, then... If the time is 0 seconds, it is considered a duplicate and the next entry is deleted. If 10:05:00 and 10:12:00 are read, then... The 420-second mark was used as a breakpoint to stop the splicing of that segment. After completing the time filtering, a field integrity check was performed on each time point. The function checks whether the field value is empty or whether the string is missing a decimal place identifier. The field performs a check to determine whether it is a numeric character. The field is checked for a value between 0 and 100. If any field is missing, the entire row for that time point is deleted. For example, if a row contains... , Empty The entire row is then deleted, and the remaining rows are rearranged in the order they are displayed. The structure, for example, retaining three lines, yields... The data is written to the same buffer according to the object identifier, and the final output is a sequence of collected parameters that are aligned in the display order, have consistent time identifiers, and have complete fields. The consistency analysis submodule extracts the difference components of body temperature, resting heart rate, and blood oxygen based on the sequentially acquired parameter sequence and summarizes the difference sequence. It compares the difference sequence with the noise judgment threshold, filters out the difference items that exceed the threshold, calculates the consistency intensity, generates a reliable judgment label, and obtains a reliable state identifier. After obtaining the sequentially acquired parameter sequence, the adjacent sampling difference components of the three types of parameters are extracted one by one, and the body temperature difference is defined. The subscript ᵢ indicates the ᵢth time point record, defining the heart rate difference. Define blood oxygen difference Then, the three types of differences are summarized into a difference vector according to the time points. And form a difference sequence The noise threshold is set according to the reasonable range between the equipment and physiological parameters. The common range for normal oral body temperature measurement is 36.1℃ to 37.2℃. For clinical thermometers, a ±0.1℃ accuracy specification is given within the range of 35.5℃ to 39.0℃, which can be used as a reference for reading error. Therefore, The noise threshold was set to 0.4℃, and segmented into three zones: 0 to 0.2℃ was the low noise zone, 0.2 to 0.4℃ was the medium noise zone, and greater than 0.4℃ was the over-threshold zone. The common resting heart rate range for adults is 60 to 100 beats per minute. Combined with the finger clip reading, under correct wearing conditions, the common heart rate error can fall within a few beats per minute. Therefore, [the following is a continuation of the previous sentence, but the context is unclear]. The threshold is set to 8 pulses per minute and divided into segments: 0 to 3, 3 to 8, and greater than 8. Normal blood oxygenation typically ranges from 95% to 100%. Pulse oximeters are commonly used for accurate measurements. Measure and in the example when true When the accuracy is 94%, the device may read between 91% and 97%, therefore... The threshold is set to 4%, and the data is segmented into groups: 0 to 2, 2 to 4, and greater than 4. Then, the absolute value of the difference is compared with each threshold for each group, and the result is calculated. When any absolute difference falls into the threshold interval, that time point is marked as a noise difference and removed from the consistency calculation set. For example, the sequential acquisition parameters are... The difference is divided into but The second term, 0.6, exceeds 0.4; therefore, the difference at the third time point is deleted. The second item, which has more than 8 items, should be deleted. The third item, if 5 exceeds 4, is deleted. The number of valid difference terms remaining after deletion is determined. The number of difference terms compared to the original Perform ratio calculations As a measure of consistency strength, For example but If only the second difference vector is retained, then ,get Then With confidence threshold Compare, The allowable noise percentage within the window is set to 0.67, corresponding to at least 2 / 3 of the differential retention. Then the trustworthiness flag is set to 0, when The trust determination flag is set to 1, and the final output carries the trust status identifier carrying the consistency strength and the trust determination flag; The level generation submodule verifies the consistency between the trustworthiness judgment mark and the noise judgment condition based on the trustworthiness status mark, health status level mark and isolation status mark, eliminates conflict marks and generates a trustworthiness level.

[0026] Simultaneously read health status level identifiers based on trusted status identifiers. With isolation status identifier And combine them into triples First, a consistency check is performed between the confidence determination flag and the noise determination condition. The check is performed by checking the differential deletion ratio from the previous stage. and noise percentage threshold Comparison implementation, Depend on Converted ,Pick but ,like Then it is required ,like Then it is required For example, in paragraph 2 but satisfy Therefore, only allow If detected If a conflict is identified, the state record is deleted. After conflict removal, the trust level is discretized and generated, with the level boundary based on... and The combination rules are determined and the numerical range boundaries are given. First, the health status level is determined. Quantized to integers in Mapped to 1, Mapped to 2, Mapped to 3 and with isolation level Quantized to integers Home isolation is mapped to 1, centralized isolation to 2, and medical observation to 3. A reliability score is then constructed. And on Divide the interval into ranges, and divide the intervals according to the maximum value. Segmented by the minimum value 0, with 0 representing the level. Levels 1 to 3 Levels 4 to 6 Levels 7 to 9 For example, a certain object , but , but Substituting into Then write it as an equation. The confidence level is obtained when the value falls within the range of 4 to 6. Another object but Directly obtain Finally, the trust level, object identifier, and window time period identifier are written together into the level output record to generate the trust level.

[0027] Please see Figure 6 The remote presentation module includes: The level parsing submodule verifies the consistency between the trust level identifier and the personnel identifier based on the trust level and the parameter display order, removes missing items, compares the index sequence with the health parameter identifier and removes unmapped items, and obtains the presentation control identifier set. Based on the two input items, trust level and parameter display order, the fields are first decomposed, and the trust level record is split into personnel identifier. Window icon Trust Level Code Generate timestamp The parameter display order is split into an index sequence. Corresponding health parameter identifier sequence ,in Pointing to body temperature field , Pointing to the resting heart rate field , Pointing to the blood oxygen field Subsequently, during the consistency check of the personnel, the same In the same Internal Read and Fields and their relationship with the main personnel table The fields are compared for equality, with each character matched sequentially. If any character is not equal, the corresponding trust level record is deleted. A missing field check is then performed on the required trust level fields. Is it null? Read Is it null? Read If any value is empty, delete it. For example... In the records If the row is empty, delete it directly. After cleaning the trust level side, proceed to index mapping verification. Reading the sequence bit by bit And limit the set of values. When it appears If the index is not defined, the entire record for display order will be deleted. Reading the sequence bit by bit And limit the set of values. When it appears If an unmapped parameter is identified, it is deleted. Then, an index-parameter mapping verification is performed. The parameter identifier it points to should be the same as... No. 1 in the sequence The comparison is based on the rule of bit consistency, for example and Then the second position is The third one is The first one is The sorting parameter sequence is obtained. If a duplicate item appears in the calculated sorting parameter sequence, the record is deleted. After mapping is completed, a presentation control identifier field is generated. The construction uses concatenation operations. Example , but Simultaneously write to the parameter sequence field Write to the index sequence field , and then the same Perform deduplication on multiple records below, deduplication action read And perform hash set deduplication; if duplicates are found... Only keep Larger records were eventually obtained by The set of presentation control identifiers constituted; The style adjustment submodule extracts and associates the display weight with the current isolation management status based on the presentation control identifier set, compares the display weight with the trust level threshold to generate a style switching flag, obtains the style driving quantity and writes it into the style mapping identifier to obtain the display style configuration; Based on the presentation control identifier set, the association between display weight and isolation management status is first decomposed, and each item is then... corresponding Expanded into three parameter bits These are body temperature positions. Heart rate position Blood oxygen level One of them, for each, reads its weight term output by the scene weight module. And form a weight vector Simultaneously read the current isolation management status identifier. And quantize into integers Home isolation centralized quarantine Medical observation Then read the trust level code. And quantize into integers ,set up Mapping 0, Mapping 1, Mapping 2, Mapping 3, followed by the generation of a trust level threshold vector. The threshold value is determined with reference to the physiologically reasonable range and the equipment error level. The normal body temperature range can be considered to be 36.1℃ to 37.2℃. The body temperature style threshold is set to... The sensitive boundary used to drive style switching; a heart rate that is typically 60 to 100 beats per minute for adults at rest; set the heart rate style threshold to The pulse oximeter is used for drive switching, and blood oxygen levels are typically 95% to 100%. Commonly seen in the 2% to 3% range, the blood oxygen pattern threshold is set to... To drive the switching, the coupling between the threshold and the trust level uses linear scaling, defining a level scaling factor. ,when hour , to obtain the graded threshold Example but Then, style toggle tags are generated. Perform a comparison operation on each parameter bit and read the absolute value of the deviation of that parameter from the window data. And compare it with the corresponding level threshold, when Then the parameter bit flag ,when Then mark Deviation The acquisition is achieved by reading the mean of the effective difference absolute values ​​stored in the confidence determination module. For example, the effective difference absolute value sequence of body temperature is... ,but The heart rate effective difference absolute value sequence is but The sequence of absolute values ​​of effective difference in blood oxygen is as follows: but Substituting the values ​​into the equation, we get 0.1167 < 0.56, therefore... Then write the three-digit flags in the parameter order. Then calculate the style-driven quantity. The driving quantity is weighted and summed, and an isolation state quantization value is introduced. ,definition: , The summation symbol Indicates three bits Add digit by digit; 3 indicates adding up to the third digit. Indicates the current bit index; Assumption: and All zeros; Substituting into the formula, we get: ; If a window gets And the rest are 0; but Then Mapping to style mapping identifier The mapping uses interval determination, let... correspond , correspond , correspond, correspond Example Falling into 2 to 4 results in Finally, it is written into the display style configuration field set. And output the display style configuration; The interface output submodule obtains the isolation management status identifier sequence based on the display style configuration, filters and verifies that the interface component identifier and the style mapping identifier are consistent, adjusts the component display order and writes the interface version identifier, and outputs the monitoring interface. First, obtain the isolation management status identifier sequence based on the display style configuration. Sequence elements are read in ascending order of time. In recent Within a window The value is accompanied by the window start and end times, and then a consistency filter is performed between the UI component and style mapping, resulting in a set of UI component identifiers. Split into component identifiers With the supported set of style tags Read the configuration record for each display style. And on Perform equality comparisons on each component, and the comparison actions are performed on each component. and Each element in the list is compared for string equality. If any element matches, the component passes the filter; otherwise, the component is deleted from the list. The following are examples of components. Only supports and Then delete Components support Then retain it, and after filtering, proceed to consistency verification. For the same Same window Read the style binding fields of the retained component and Perform an equality comparison; if they are not equal, delete the component instance, and then adjust the component display order according to the parameter display order. Fields bound to the component's parameters Complete, each component's Convert to serial number The rules are equal The first one is , equal The second one , equal The third one If component For integrated components Set to 0, then press Sort the components from smallest to largest to get the component sequence, example. Then heart rate component Blood oxygenation components Body temperature component Integrated components First, sort them and write them into the component rendering queue. At the same time, write the interface version identifier. , Depend on and Generate the version increment number by concatenating and adding the version increment number. By reading the same history The last digit plus 1 gives the result, for example, history. The end is Then new Take 8, and you get Finally and Write the output record to the interface and... With the present Intersecting time periods The values ​​are written to the status bar field of the interface, and then the display parameters of each component are read from the window health dataset according to the timestamp and filled into the data slot of the corresponding component. After completion, the monitoring interface is output, thereby realizing isolated health monitoring.

[0028] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A cross-border personnel quarantine health monitoring system based on the Internet of Things, characterized in that, The system includes: The isolation baseline module acquires body temperature, resting heart rate, and blood oxygen data uploaded by the monitoring terminal worn by cross-border quarantine personnel through remote operation, statistically analyzes the health parameters collected initially, constructs a reliable interval, and stores it as the monitoring baseline for the initial stage of quarantine, thus forming the initial health monitoring interval. Based on the initial health monitoring interval, the data migration module continuously collects health data during the isolation period, statistically analyzes the data within the time window and compares it with the previous period's reliable interval, dynamically adjusts the health parameter interval, and generates a remote risk identifier when the monitoring results meet the risk judgment conditions. The scenario adjustment module calls the remote risk identifier, combines the isolation status and health status level to determine the current isolation management scenario, and adjusts the weight of the health parameters to determine the parameter display order; The credibility determination module analyzes the consistency of continuous health parameter collection results based on the parameter display order, and determines the credibility status of the health parameters by combining noise judgment conditions, and generates a credibility level. The remote presentation module dynamically adjusts the display method of health data according to the trust level and the display order of the parameters, and outputs a monitoring interface that matches the current isolation management status.

2. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 1, characterized in that, The initial health monitoring interval includes an individual health reference range, initial parameter distribution characteristics, and a normal reference range. The remote risk identifier specifically includes risk status identifier, abnormality type identifier, and risk level identifier information. The parameter display order includes a parameter display priority list, scenario-corresponding sorting results, and display level correspondence. The credibility level specifically includes a data credibility level identifier, stability status level, and data reliability identifier. The monitoring interface includes an interface information display area, a health parameter display unit, and a status prompt display area.

3. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 1, characterized in that, The confidence interval is the body temperature, resting heart rate and blood oxygen data collected from the initial stage of the quarantined personnel, which are analyzed by continuous collection and time correlation. The health parameter range is based on three types of data: body temperature, resting heart rate, and blood oxygen. The range of values ​​is updated over time during the isolation process.

4. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 1, characterized in that, The remote risk identification is a correlation analysis performed by the system on the data and the current health parameter range during the continuous reception of health data; The initial health monitoring range is a basic reference range formed based on the body temperature, resting heart rate, and blood oxygen data collected synchronously for the first time during the initial use of the system.

5. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 1, characterized in that, The isolation reference module includes: The remote acquisition submodule acquires body temperature, resting heart rate, and blood oxygen data uploaded by the monitoring terminal worn by cross-border quarantine personnel through remote operation, filters data within the same acquisition cycle, and obtains a synchronized health dataset. The initial sampling statistics submodule extracts the initial body temperature, resting heart rate and blood oxygen value based on the synchronous health dataset, calculates the mean of the three items and compares them with the number of samplings to obtain the initial health parameter set; The interval database construction submodule integrates body temperature, resting heart rate and blood oxygen value sequences based on the initial health parameter set, calculates the standard deviation and judges the abnormal deviation magnitude, obtains the deviation amount and synthesizes the interval expansion magnitude, and establishes the initial health monitoring interval.

6. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 1, characterized in that, The interval migration module includes: The continuous data collection submodule continuously collects health data during the isolation period based on the initial health monitoring interval, records timestamps, filters data with consecutive and complete timestamps, removes duplicate records, and obtains a window health dataset. The interval comparison submodule calls the window health dataset to count the mean of health parameters, compares the mean with the upper and lower limits of the initial health monitoring interval, counts the number of times the limit is exceeded, adjusts the upper and lower limits of the intervals for body temperature, resting heart rate, and blood oxygen, updates the cycle identifier, and establishes the migration health parameter interval. The risk identification submodule calculates the absolute value of the deviation of body temperature, resting heart rate and blood oxygen in the migration health parameter range and the window health dataset, compares it with the risk judgment threshold, obtains various risk quantities and synthesizes the risk intensity quantity, and generates a remote risk identification. The health data includes body temperature, resting heart rate, and blood oxygen saturation.

7. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 1, characterized in that, The scene weighting module includes: The remote identifier invocation submodule invokes the remote risk identifier, detects the consistency with the isolation status time identifier, removes missing identifier records, and performs matching and verification between the source of the remote risk identifier and the personnel identifier to obtain a valid risk identifier set; The scenario determination submodule, based on the effective risk identifier set, associates isolation status with health status level identifiers, compares isolation status with scenario mapping rules, determines the scenario type, performs cross-verification of health status and scenario type, eliminates conflicting combinations, and establishes the current management scenario identifier. The display order generation submodule associates health parameters with the display record sequence based on the current management scenario identifier, adjusts the weights of body temperature, resting heart rate, and blood oxygen, calculates the comprehensive ranking quantity, and generates a display sequence index to obtain the parameter display order.

8. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 7, characterized in that, The process of ensuring consistency between the detection and isolation status time stamps is as follows: compare the timestamp recorded in the remote risk identifier with the interval between the start and end times corresponding to the isolation status. When the timestamp is outside the duration of the isolation status, the corresponding remote risk identifier is determined to be an inconsistent record and is removed. The process of matching and verifying the source and personnel identifiers of the remote risk identifier is as follows: a one-to-one correspondence verification is performed between the source identifier field contained in the remote risk identifier and the device identifier field registered in the personnel identifier. When the source identifier field and the device identifier field are inconsistent, the corresponding record is excluded from the set of valid risk identifiers. The process of comparing the isolation state with the scene mapping rules is as follows: the state level identifier corresponding to the isolation state is matched with the pre-stored scene mapping rule table, and the scene type is confirmed only when the matching result is unique; The process of adjusting the weights of body temperature, resting heart rate, and blood oxygen is as follows: when the isolation status level corresponding to the current management scenario is enhanced isolation, the weight of body temperature is increased and the weight of resting heart rate is decreased; when the isolation status level corresponding to the current management scenario is regular isolation, the weight of blood oxygen is increased and the ratio between the weights of body temperature and resting heart rate remains unchanged, and the parameter display order is generated.

9. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 1, characterized in that, The credibility determination module includes: The sequential association submodule displays the parameters in the order they are presented, associates the sequences of body temperature, resting heart rate and blood oxygen value, filters data with consistent time identifiers and removes missing fields, and obtains the sequence of collected parameters. The consistency analysis submodule extracts the difference components of body temperature, resting heart rate, and blood oxygen based on the parameter sequence collected in the order, summarizes the difference sequence, compares the difference sequence with the noise judgment threshold, filters out the difference items exceeding the threshold, calculates the consistency intensity quantity and generates a reliable judgment label to obtain a reliable state identifier. The level generation submodule verifies the consistency between the trust status identifier, health status level identifier, and isolation status identifier and the noise judgment condition, eliminates conflicting identifiers, and generates a trust level.

10. The cross-border personnel isolation health monitoring system based on the Internet of Things according to claim 1, characterized in that, The remote presentation module includes: The level parsing submodule verifies the consistency between the trust level identifier and the personnel identifier based on the trust level and the parameter display order, removes missing items, compares the index sequence with the health parameter identifier and removes unmapped items, and obtains the presentation control identifier set. The style adjustment submodule extracts and associates the display weight with the current isolation management status based on the presentation control identifier set, compares the display weight with the trust level threshold to generate a style switching flag, obtains the style driving quantity and writes it into the style mapping identifier to obtain the display style configuration; Based on the display style configuration, the interface output submodule obtains the isolation management status identifier sequence, filters and verifies that the interface component identifier and the style mapping identifier are consistent, adjusts the component display order and writes the interface version identifier, and outputs the monitoring interface.

Images