Health management physical examination big data platform

Abstract

The invention relates to the technical field of health management, in particular to a health management physical examination big data platform which comprises a fluctuation starting point positioning module, a rhythm structure adjusting module, a trend triggering recognition module, a physical sign linkage extraction module and an intervention task sorting module. According to the method, the fluctuation starting point is positioned through the combination of the resistance change direction and the offset mutation, the sampling interval is dynamically adjusted, the fluctuation sequence is rearranged, the trend continuation path is recognized through the boundary deviation state, the continuity and the stability of trend recognition are enhanced, and the response starting point and the continuation area are extracted in combination with the direction consistency item in the respiratory signs; the integrity of time domain response coverage is ensured, a priority calling sequence is further constructed according to the distribution density, the occurrence frequency and the duration of the signs on the time axis, and accurate identification of a trend starting point, orderly adjustment of a rhythm structure and optimization of an intervention task time sequence in the multi-sign dynamic linkage process are achieved; and the response efficiency and the control precision in the health state evolution process are improved.

Description

Technical Field

[0001] The present invention relates to the field of health management technology, and in particular to a health management and physical examination big data platform. Background Art

[0002] The field of health management technology involves a comprehensive service system that uses information technology to dynamically monitor, assess, and intervene in the health status of individuals or groups. Core issues include health data collection, vital sign analysis, risk prediction and assessment, health intervention plan development, and health behavior management. This field, based on medical informatization, integrates cutting-edge technologies such as big data, artificial intelligence, and wearable devices to achieve systematic management of a population's health throughout its lifecycle. The development of this technology stems from public health pressures brought about by limited medical resources and the high prevalence of chronic diseases, necessitating the establishment of data-driven proactive health management mechanisms to improve disease prevention efficiency and provide personalized services. Traditional health management physical examination data platforms are information systems that collect individual physical examination data to record and categorize health status. These platforms primarily address the complex and inconsistent data sources and the fragmented basis for health management decision-making. Traditional patent applications typically address this issue by storing physical examination data in tabular form and manually categorizing and aggregating it. Data structures rely on database field rules, and analysis is typically performed through manual classification and comparison based on preset query conditions. Individual health status assessments are based on static standard models or the empirical judgment of health managers.

[0003] Traditional physical examination data platforms have the problem of delayed identification of the starting state when dealing with rapidly evolving dynamic signal sequences. The preset field framework limits the flexible expression of continuously changing parameters. Manual classification methods are difficult to reflect the continuity and directionality of vital sign trends on the time axis. When there are multiple fluctuation stages in the sampling sequence, the platform is difficult to clarify their time sequence and trend continuity, resulting in deviations in the judgment of signal change paths. The lack of trend matching basis in linkage judgment of vital signs such as respiration can easily lead to ambiguous identification of response segments. In terms of intervention triggering, there are problems of chaotic response sequence and delayed call timing, which reduces the matching degree and execution efficiency in the vital sign intervention process. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a health management and physical examination big data platform.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A health management and physical examination big data platform, including: The fluctuation starting point positioning module obtains the tissue resistance record of the time period in the arterial resistance map detection scenario, determines the direction of adjacent resistance changes, compares the difference between the interface change position and the radio wave offset, selects the deviation time point, and shifts it backward as the new sampling starting point to obtain the starting time of the fluctuation delay; The rhythm structure adjustment module sets a starting point based on the fluctuation delay starting time point, compares the current and previous fluctuation directions, and adjusts the segment length if they are consistent, rearranges the order of the fluctuation points, and obtains the rhythm adjustment interval; A trend trigger identification module calibrates the blood pressure boundary position based on the rhythm adjustment interval, determines whether the measurement points continuously fall outside the boundary, and performs continuity judgment on the change path and interval to obtain an arterial pressure change trend identification result; The vital sign linkage extraction module selects the consistent items of exhalation time, inhalation hold time and lung expansion volume change based on the trend direction in the arterial pressure change trend identification result, compares the starting response position with the continuous segment coverage, and obtains the associated vital sign response trajectory.

[0006] As a further solution of the present invention, the fluctuation delay starting point includes reference time positioning, offset distance quantification, and updated sampling starting point; the rhythm adjustment interval includes time range adjustment, fluctuation sequence rearrangement, and change trend matching; the arterial pressure change trend identification result includes exceeding the measurement point boundary, continuous deviation paragraph, and trend path structure; the associated vital sign response trajectory includes consistency change starting point, response continuation interval, and fluctuation period coverage.

[0007] As a further solution of the present invention, the fluctuation starting point positioning module includes: The resistance trend difference detection submodule obtains continuous time period tissue resistance records in the arterial resistance map detection scenario, extracts the resistance change trend of each time period in the same time series, compares the direction marks of the time period resistance change in any two adjacent time periods, identifies the time period positions with inconsistent directions, and obtains the resistance direction inconsistent intervals; The junction offset anomaly detection submodule extracts the corresponding junction position state and radio wave offset state sequence based on the inconsistent resistance direction interval, compares the junction state change amplitude with the set junction change recognition threshold, screens the time period position of the offset state anomaly, and generates a junction offset mutation position set; The fluctuation starting point positioning submodule locates the time point sequence in the resistance record according to the position index of the time period where the interface offset mutation position is concentrated, identifies the position where the offset state changes, adjusts the time point backward by a specified time amount as the new sampling starting point, and obtains the starting time point of the fluctuation delay.

[0008] As a further solution of the present invention, the rhythm structure adjustment module includes: The directional consistency identification submodule extracts the sampling sequence within the current fluctuation segment based on the starting position of the fluctuation delay starting time point, records the fluctuation range change direction corresponding to the time point, extracts the change direction mark within the previous segment, compares the consistency of the current segment with the previous segment in the corresponding time direction, and screens out continuous time periods with consistent direction to obtain the directional consistency interval; The segment boundary revision submodule identifies the degree of overlap between the start and end time points of the current fluctuation segment and the coverage interval based on the time boundaries of the directional coherence interval, and determines whether the extension and compression conditions are met. If so, the start and end time boundaries of the current fluctuation segment are revised to generate the adjusted segment range; The rhythm reordering submodule calls the revised time range in the adjusted segment range, reorders the fluctuation points contained therein according to the original order of the fluctuation direction, and arranges the sorted fluctuation point position sequence as the segment reference to obtain the rhythm adjustment interval.

[0009] As a further solution of the present invention, the trend trigger identification module includes: The boundary extraction and calibration submodule extracts the upper and lower blood pressure boundaries of three adjacent detection segments based on the signal sequence within the rhythm adjustment interval, calibrates the time nodes where the boundary values in each segment are located, records the index sequence of the boundary time points in the segment, and generates a boundary position index set; The out-of-bounds interval screening submodule calls the corresponding positions of the upper and lower boundaries in the boundary position index set, extracts the position values of the measurement points in the same section, compares the position relationship between each measurement point and the corresponding boundary value, and screens the time period positions where consecutive measurement points exceed the upper and lower boundaries to obtain the continuous out-of-bounds point interval; The trend consistency determination submodule extracts the change path direction marks between the measuring points and the time interval sequence between adjacent measuring points based on the position information of the measuring points in the continuous cross-border point interval, determines whether the change direction remains consistent and the interval does not exceed the trend continuity threshold, and obtains the arterial pressure change trend identification result.

[0010] As a further solution of the present invention, the vital sign linkage extraction module includes: A direction matching and screening submodule extracts the change direction mark of the sign sequence in the respiratory-related signs based on the trend information in the arterial pressure change trend identification result, matches and screens the change direction of each sign with the trend direction, retains the sign data sequence with the consistent direction, and obtains the direction-matched signs; The morphological response segment extraction submodule calls the direction matching vital signs, identifies the position index where the direction change occurs, records the position number of the vital sign starting change point in the original sampling sequence, determines whether there is a change trajectory in which the morphological fluctuation amplitude exceeds the morphological recognition reference value in the continuous time period after the number, and obtains the morphological response segment; The response trajectory generation submodule extracts the covered time interval according to the start and end time indexes of the morphological response segment, calculates the fluctuation frequency value within the response segment, marks the distribution structure of the fluctuation interval within the time period, and obtains the associated vital sign response trajectory.

[0011] As a further solution of the present invention, the calculation formula of the fluctuation frequency value in the response section is specifically: ; in, Representative The fluctuation frequency value within the response segment, Representative The number of time index points in the response segment, Representative In the response section The difference between the physical sign value at a time point and the physical sign value at the previous time point, that is, , Representative The standard deviation of the sign values within the response segment, Representative The average value of the physical sign value in the response segment, Representative The maximum value of the sign value in the response segment, Representative The minimum value of the sign value in the response segment, Representative In the response section Sign values at each time point.

[0012] As a further solution of the present invention, an intervention task sorting module is also included: The intervention task sequencing module identifies changes, durations, and repetitions based on the starting point, duration, and frequency of the signs in the associated sign response trajectory, combines the intervention sequence, and obtains a sign intervention execution sequence list; The physical sign intervention execution sequence list includes the order of physical sign appearance, change maintenance time, and change frequency statistics.

[0013] As a further solution of the present invention, the intervention task sorting module includes: The first-place ranking submodule of the physical sign extracts the first response position of the physical sign on the sampling time axis based on all the responded physical sign items in the associated physical sign response trajectory, numbers and sorts the first response points of the differentiated physical signs in chronological order, records the time index arrangement structure of each physical sign, and generates the physical sign time series ranking value; The submodule for calculating the duration of a vital sign is used to call the time index of the vital sign in the sequence value of the vital sign time series, extract the start and end boundaries of the vital sign that continuously maintains the change in the sampling sequence, calculate the duration value of the change, and mark the complete segment index during the change period to obtain the duration interval of the vital sign change; The comprehensive sorting and list generation submodule counts the frequency of each sign change in the entire sequence based on the sign change segment index in the sign change duration interval, uses the time sequence, duration, and frequency of occurrence as the sorting basis, establishes a multi-factor combination judgment logic, and obtains a sign intervention execution order list.

[0014] As a further solution of the present invention, the calculation formula of the change duration value is specifically: ; in, Representative number is Signs The duration value of a change in a continuous change process, Indicates signs No. The end time point index of each change segment, Indicates signs No. The starting time point index of each change segment, Indicates signs In the Within the change segment The difference in the vital sign value between a sampling point and its previous sampling point, Indicates signs In the Within the change segment The time difference between a sampling point and its previous sampling point, Indicates signs In the The average change speed value of all sampling point pairs in a change segment, Indicates signs In the The number of sampling point pairs within a change segment, The difference sequence index.

[0015] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the fluctuation starting point is located jointly by the direction of resistance change and offset mutation, the sampling interval is dynamically adjusted and the order of the fluctuation sequence is rearranged, the boundary deviation state is used to identify the trend continuation path, and the consistency and stability of trend identification are enhanced. The response starting point and continuation area are extracted in combination with the direction-consistent items in the respiratory signs to ensure the integrity of the time domain response coverage, and the priority calling order is further constructed according to the distribution density, occurrence frequency and duration of the signs on the time axis, so as to realize the accurate identification of the trend starting point, orderly adjustment of the rhythm structure and optimization of the intervention task timing in the process of dynamic linkage of multiple signs, and improve the response efficiency and control accuracy in the process of health status evolution. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a system flow chart of the present invention.

[0018] Figure 2 This is a system block diagram of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0020] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0021] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0022] See also Figure 1 and Figure 2 , a health management and physical examination big data platform includes: The fluctuation starting point positioning module obtains tissue resistance records for three consecutive time periods in the arterial resistance map detection scenario, determines whether the direction of resistance change in any two adjacent time periods is consistent, compares the position of the interface change with the position deviation of the radio wave offset state, and screens out the reference time position corresponding to the significant change item. This time position is shifted back as the new sampling starting point to obtain the starting point of the fluctuation delay; The rhythm structure adjustment module determines whether the change trend of the sampling sequence in the current fluctuation range is consistent with the direction of the previous segment based on the starting position of the fluctuation delay starting point. If the change direction remains the same, the current time range is extended or compressed accordingly, and the position order of the fluctuation points is rearranged to obtain the rhythm adjustment interval; The trend trigger identification module, based on the signal sequence within the rhythm adjustment interval, calibrates the upper and lower blood pressure boundaries of each of the three adjacent detection segments. It then compares the deviation between the measurement points in the current sequence and the boundaries, determining whether there are consecutive measurement points that are all outside the boundaries. It then performs trend continuity judgment on the change path and interval time between these measurement points to obtain the arterial pressure change trend identification result. The vital signs linkage extraction module selects respiratory-related vital signs whose change direction is consistent with the trend based on the results of the arterial pressure change trend identification. It then identifies the location of the starting change point in the sampling sequence, determines whether the subsequent segment has a response pattern, and records the coverage of its fluctuation distribution within the time period to obtain the associated vital signs response trajectory. The intervention task sorting module, based on all the responded sign items in the associated sign response trajectory, records their position order on the sampling time axis, the time range for maintaining changes, and the frequency of repeated changes. It extracts the changers, change time, and frequent occurrences, and generates a sign priority call sorting structure based on this, and obtains a sign intervention execution order list.

[0023] The starting point of the fluctuation delay includes reference time positioning, offset distance quantification, and updated sampling starting point. The rhythm adjustment interval includes time range adjustment, fluctuation sequence rearrangement, and change trend matching. The arterial pressure change trend identification results include exceeding the measurement point boundary, continuous deviation segments, and trend path structure. The associated vital sign response trajectory includes consistent change starting point, response continuation interval, and fluctuation period coverage. The vital sign intervention execution sequence list includes the order of sign appearance, change maintenance time, and change frequency statistics.

[0024] See also Figure 1 and Figure 2 , the wave starting point positioning module includes: The resistance trend difference detection submodule obtains continuous time period tissue resistance records in the arterial resistance map detection scenario, extracts the resistance change trend of each time period in the same time series, compares the direction marks of the time period resistance change in any two adjacent time periods, identifies the time period positions with inconsistent directions, and obtains the resistance direction inconsistent intervals; In the context of arterial resistance mapping, to obtain tissue resistance records over a continuous period of time, the entire detection time must first be divided into multiple continuous time segments. The length of each segment can be set to 1 second or 0.5 seconds based on the refresh rate of the detection equipment and the signal change characteristics. For example, if each segment is set to 1 second, the number of data points corresponding to each segment is related to the sampling rate. If the sampling rate is 100Hz, each segment contains 100 resistance data points. Next, for each time segment, it is extracted from a unified time series to form a resistance value sequence at the corresponding time point. Based on this, the resistance value difference between two adjacent time points within each time segment is calculated. The direction of resistance change is determined by comparing the magnitude of adjacent resistance values. If the resistance at the latter moment is greater than the previous moment, it is marked as rising, otherwise it is marked as falling, forming a complete direction mark sequence for the time segment. After completing the direction marking for all time periods, any two adjacent time periods are compared one by one. If the direction marking at the same time point shows an upward trend in the previous period and a downward trend in the next period, or vice versa, it is determined to be a direction inconsistency. The position of this time point in the original time series is recorded. This allows the locations where the resistance change direction conflicts across multiple time periods to be gradually identified. If this inconsistency occurs at multiple consecutive time points, these time points are juxtaposed to form a resistance direction inconsistency interval. For example, if five consecutive time points have opposite directions and each point is separated by 0.1 seconds, the length of this interval is 0.5 seconds. This process can effectively demarcate the key time periods with reverse fluctuations in the signal change trend.

[0025] The junction offset anomaly detection submodule extracts the corresponding junction position state and radio wave offset state sequence based on the inconsistent resistance direction interval, compares the junction state change amplitude with the set junction change recognition threshold, screens the time period and position of the offset state anomaly, and generates a junction offset mutation position set; After identifying the intervals of inconsistent resistance direction, the time points within these intervals are expanded and processed to extract the records of the interface position state and the radio wave offset state corresponding to these time points in the original data. The interface position state can be obtained through the position sensor data provided by the detection system, while the radio wave offset state is obtained based on the time delay information conversion of the high-frequency detection signal in the medium propagation. The two constitute two types of state sequences corresponding to the time points. When processing the interface position state, it is necessary to calculate the absolute value of the position change between adjacent time points to obtain the amplitude of the change between each pair of time points. The interface change recognition threshold set here is generally set according to the tissue surface movement or detection resolution. For example, if the minimum detection displacement of the device is 0.1 mm, the threshold can be set to 0.3 mm, that is, when the interface position change is greater than or equal to 0.3 mm, it is considered that a significant displacement has occurred. The position change amplitude at each time point is compared with the threshold. If the change amplitude of any pair of adjacent time points reaches or exceeds this value, the point is determined to be a sudden change in the joint state. Based on this, the radio wave offset state in the short period before and after this time point is further checked to see if there is also a change. The criterion for determining an abnormal offset state is whether the offset time change within a short period of time (for example, 0.5 seconds) exceeds a certain threshold. This threshold is determined based on the timing resolution accuracy of the equipment. For example, if the resolution of high-frequency detection equipment is 0.05 milliseconds, the offset anomaly threshold can be set to 0.4 milliseconds. If the offset state corresponding to a certain time point changes by more than this value within the set time window, the radio wave offset state is considered abnormal. Time points with both sudden joint changes and offset anomalies are screened out, ultimately forming a set of joint offset mutation positions for subsequent analysis.

[0026] The fluctuation starting point positioning submodule locates the time point sequence in the resistance record based on the position index of the time period where the junction offset mutation is concentrated, identifies the position where the offset state changes, and adjusts the time point backward by a specified amount of time as the new sampling starting point to obtain the starting time point of the fluctuation delay; After obtaining all eligible time period indices from the joint offset mutation location set, these time points need to be mapped back to the time series of the original resistance data to precisely locate the original time point of each offset mutation event. After obtaining the original time point sequence, each time point is shifted backward by a set amount of time to serve as a new sampling starting point. This time delay is determined based on the typical delay characteristics of the tissue response and the system signal processing cycle. It can generally be set between 1.0 and 2.0 seconds. For example, based on observations of multiple samples, the signal perturbation response delay is generally around 1.2 seconds. Therefore, a 1.2-second delay can be used to ensure that subsequent sampling covers the entire perturbation response process. For each mutation time point, the sampling starting point is recalibrated by 1.2 seconds to form a new set of fluctuation starting time points. This new set of time points will serve as a key entry point in the subsequent resistance signal feature analysis to extract the fluctuation response trend after the perturbation, assisting in further state identification and structural stability assessment.

[0027] See also Figure 1 and Figure 2 , the rhythm structure adjustment module includes: The directional coherence identification submodule extracts the sampling sequence within the current fluctuation segment based on the starting position of the fluctuation delay starting point, records the fluctuation range change direction corresponding to the time point, extracts the change direction mark within the previous segment, compares the consistency of the current segment with the previous segment in the corresponding time direction, and screens out continuous time periods with consistent direction to obtain the directional coherence interval; Based on the starting position of the fluctuation delay starting time point, first, according to each calibrated starting time point, a certain length of continuous data is intercepted from the original resistance signal to form a sampling sequence in the current fluctuation segment. The length can be set to 2 seconds or 3 seconds. Combined with the actual sampling frequency, the corresponding number of data points is obtained. For example, if the sampling rate is 100Hz, the number of sampling points in each segment is 200 or 300. Then, the adjacent difference calculation is performed on each data point in the sampling sequence to determine the size relationship between each pair of adjacent data points. If the value of the latter data point is greater than the previous data point, it is recorded as "rising", otherwise it is recorded as "falling", forming a complete fluctuation direction sequence. Then, the fluctuation direction of all data points in the current fluctuation segment is summarized in order. Construct a list of change directions for the current segment, and at the same time retrieve the previous segment adjacent to the current segment, extract the change direction mark in the segment, and compare whether the direction values of each corresponding position of the two segments on the time axis are the same. If the direction of a point in the current segment is consistent with the direction of the same position in the previous segment, then this point is regarded as a point with consistent direction, and it is extended forward and backward point by point to find the largest continuous and consistent area. For example, if the direction marks of the 10th to 30th data points in the current segment are exactly the same as those of the 10th to 30th points in the previous segment, then it is considered a direction-consistent interval with a length of 21 data points. This operation will completely screen out the continuous time period with consistent direction in the fluctuation segment and record its time range, that is, the direction-consistent interval is obtained.

[0028] The segment boundary revision submodule identifies the degree of overlap between the start and end time points of the current fluctuation segment and the coverage interval based on the time boundaries of the directionally coherent interval, and determines whether the extension and compression conditions are met. If so, the start and end time boundaries of the current fluctuation segment are revised to generate the adjusted segment range. Based on the time boundaries of the directional coherence interval obtained above, first record its start time and end time respectively, and compare them with the overall time range of the current fluctuation segment, that is, the time interval formed by the original start point and end point. Calculate the time overlap range and overlap ratio between the start and end times of the directional coherence interval and the start and end times of the original segment. If the start time of the coherence interval is earlier than the original start time by more than the set extension threshold, or the end time is later than the original end time by more than the set compression threshold, then the boundaries are revised. The extension threshold and compression threshold are set according to the stability statistics of the historical fluctuation segments. For example, the extension threshold is set to 0.8 seconds and the compression threshold is set to 0.6 seconds. If the start time of the directional coherence interval is 1.0 seconds earlier than the original start time, the extension condition is met and the start time point is revised forward. If the end time is 0.7 seconds later than the original end time, the compression condition is met and the end time point is revised backward. The start and end boundaries are redefined to obtain the new time segment range as the adjusted segment range of the current fluctuation segment.

[0029] The rhythm reordering submodule calls the revised time range in the adjusted segment range, reorders the fluctuation points contained therein according to the original order of the fluctuation direction, and uses the sorted fluctuation point position sequence as the segment base arrangement to obtain the rhythm adjustment interval; Call the revised time range in the adjusted fluctuation segment range, re-extract the position indexes of all fluctuation points in the time period and the corresponding fluctuation direction marks, and perform preliminary sorting according to the direction marks. First, extract all points marked as "rising" and arrange them in chronological order, and then extract all points marked as "falling" and arrange them in chronological order to form a fluctuation point sequence with direction consistency priority. For example, if a segment contains 80 data points after adjustment, of which 45 are "rising" direction points and 35 are "falling" direction points, then the two subsets are sorted by time and spliced to form a new sorted sequence. The segment benchmark is reconstructed for this sequence as the interval result after rhythm adjustment. The benchmark arrangement refers to the changing trend of the original fluctuation direction to ensure that the sorted sequence can reflect the main trend characteristics of the fluctuation rhythm, and finally generate the rhythm adjustment interval.

[0030] See also Figure 1 and Figure 2 , the trend trigger identification module includes: The boundary extraction and calibration submodule extracts the upper and lower blood pressure boundaries of three adjacent detection segments based on the signal sequence within the rhythm adjustment interval, calibrates the time nodes where the boundary values are located in each segment, records the index sequence of the boundary time points in the segment, and generates a boundary position index set; Based on the signal sequence within the rhythm adjustment interval, the signal sequence is first segmented according to the adjusted time boundary, and three consecutive detection segments are extracted. The blood pressure values of all sampling points in each segment are calibrated respectively, and the maximum value in each segment is identified as the upper blood pressure boundary of the segment, and the minimum value is identified as the lower blood pressure boundary. The actual occurrence position of each boundary value in the time series is further located, and its sampling index number in the segment is recorded. For example, the sampling starting point of the first segment is 0. If the upper boundary value appears at the 42nd sampling point, its index is 4. 2. Store the upper and lower boundary position indexes in all segments one by one to form a complete set of boundary position indexes. If the sampling frequency is 100 Hz and each segment is 2 seconds, then each segment contains 200 data points. Suppose the upper and lower boundary indexes of the three segments are 45 for the upper boundary and 10 for the lower boundary of the first segment, 49 for the upper boundary and 8 for the lower boundary of the second segment, and 51 for the upper boundary and 12 for the lower boundary of the third segment. Then the boundary index set is {(45, 10), (49, 8), (51, 12)}. This index set will serve as the benchmark for subsequent cross-boundary judgment and trend tracking.

[0031] The out-of-bounds interval screening submodule calls the corresponding positions of the upper and lower boundaries in the boundary position index set, extracts the position values of the measurement points in the same section, compares the position relationship between each measurement point and the corresponding boundary value, and screens the time period positions where consecutive measurement points exceed the upper and lower boundaries to obtain the continuous out-of-bounds point interval; Each set of upper and lower boundary positions stored in the boundary position index set is called, and the corresponding blood pressure values are extracted as judgment criteria. Then, the position values of all sampling points in the same segment are traversed, and the value is determined point by point to see whether it exceeds the upper boundary or falls below the lower boundary. If the value of a measurement point is greater than the upper boundary value of the corresponding segment, or less than the lower boundary value, the point is marked as an out-of-bounds point. The positions of all consecutive out-of-bounds points are recorded to form an out-of-bounds point time index sequence. Further analysis is performed to see whether the time points between the out-of-bounds points are continuous. For example, if the blood pressure value of each point from the 45th to the 60th sampling point exceeds the upper boundary of the segment by 150 mmHg, then these 16 sampling points constitute a continuous out-of-bounds interval. Alternatively, if the blood pressure values of all points from the 5th to the 20th sampling point are less than the lower boundary by 90 mmHg, then this also constitutes a continuous out-of-bounds interval. All out-of-bounds point time periods that meet the "continuity" condition are screened out, where the "continuity" condition is that the index difference between two adjacent out-of-bounds points is 1. If there is a gap, it is not counted as a continuous interval. Finally, all segments that meet this criterion are retained as continuous out-of-bounds point intervals.

[0032] The trend consistency determination submodule extracts the change path direction marks between the measurement points and the time interval sequence between adjacent measurement points based on the position information of the measurement points in the continuous cross-border point interval, determines whether the change direction remains consistent and the interval does not exceed the trend continuity threshold, and obtains the arterial pressure change trend identification result; According to the position information of all measuring points in the continuous cross-border point interval, the direction of blood pressure value change between each pair of adjacent measuring points is first extracted, that is, whether the value of the latter measuring point is higher or lower than the value of the previous point, and its direction is judged as "upward" or "downward", forming a corresponding change path direction sequence. At the same time, the sampling time interval of each pair of adjacent points is counted. If the sampling frequency is 100Hz, the interval between each sampling point is 0.01 seconds. The time interval of each pair of measuring points is compared with the set trend continuity threshold. The threshold is set to 0.02 seconds here, which comes from the minimum period statistics of the device's response to the continuation of fluctuations. For example, by counting 10 The trend duration of 0 samples was counted and it was found that when the time between measuring points was less than 0.02 seconds and the direction was consistent, the trend was coherent. Therefore, this value was selected as the threshold benchmark. If the change direction of consecutive point pairs was consistent and the corresponding time interval was less than or equal to 0.02 seconds, the trend was considered to be continuous. If the change direction between a pair of points was inconsistent or the time interval was greater than the threshold, the trend was interrupted. The continuous measuring point segments that met the conditions were identified as the same trend block. After counting all trend blocks, it can be determined whether there is a significant upward or downward trend in the arterial pressure in the entire continuous cross-border interval, and finally the arterial pressure change trend identification result is obtained.

[0033] See also Figure 1 and Figure 2 , the vital sign linkage extraction module includes: The direction matching and screening submodule extracts the change direction mark of the sign sequence in the respiratory-related signs based on the trend information in the arterial pressure change trend recognition results, matches and screens the change direction of each sign with the trend direction, retains the sign data sequence with the consistent direction, and obtains the direction matching signs; Based on the trend information in the arterial pressure change trend recognition result, first read the direction mark clearly marked in the trend, for example, upward indicates that the arterial pressure continues to rise, downward indicates that it continues to fall, or remaining unchanged indicates a stable state, and then extract the respiratory-related vital sign data corresponding to the time period. Common vital sign sequences include respiratory rate, tidal volume, chest and abdominal movement amplitude, etc. Each vital sign is constructed in a chronological sequence based on the continuous sampling results. The difference between the two adjacent sampling points in each sequence is calculated to determine whether it is rising, falling or stable, thereby generating a complete change direction mark sequence for each vital sign, such as chest and abdominal movement amplitude The sequence is {2.1, 2.3, 2.5, 2.2}, and the direction sequence is {rising, rising, falling}. Then, the change direction sequence of each physical sign is compared one by one with the direction mark of the arterial pressure trend. If the continuous change direction of a physical sign is exactly the same as the arterial pressure trend direction, the physical sign data in this time period is marked as a direction matching physical sign. For example, if the arterial pressure is rising and the chest and abdominal movements are all in an rising direction from the 10th to the 40th sampling points, then this segment is retained. This process is repeated to match and screen all physical signs. Finally, the physical sign data sequence with the same direction is retained and summarized to form a direction matching physical sign.

[0034] The morphological response segment extraction submodule calls the direction matching sign, identifies the position index where the direction change occurs, records the position number of the sign starting change point in the original sampling sequence, and determines whether there is a change trajectory in the continuous time period after the number whose morphological fluctuation amplitude exceeds the morphological recognition benchmark value to obtain the morphological response segment; The direction-matching vital signs selected above are called, and the time point at which the first direction change occurs in each vital sign change sequence is detected. The position number of this change point in the original vital sign sampling sequence is recorded. For example, if the original sequence is {rise, rise, rise, fall, fall}, the first direction change occurs at the fourth sampling point. The vital sign values in the consecutive time periods after this number are interpolated to extract the fluctuation amplitude. It is determined whether the difference between each two adjacent sampling points exceeds the set morphological recognition benchmark value. This benchmark value is set based on the accuracy of the vital sign measurement equipment and the normal human fluctuation range, with a setting standard of 0.15 units. For example, the recognition benchmark for the chest and abdominal movement amplitude is set to 0.15 cm. If multiple differences in the measured continuous difference sequence are greater than or equal to 0.15 cm, it indicates that significant morphological fluctuation occurred within this time period. The segment that continuously meets this condition is identified as a morphological response segment, and its start and end time point indexes are recorded to ensure that the morphological response segment has substantial fluctuation characteristics and is capable of responding to trend changes.

[0035] The response trajectory generation submodule extracts the covered time interval according to the start and end time index of the morphological response segment, calculates the fluctuation frequency value within the response segment, marks the distribution structure of the fluctuation interval within the time period, and obtains the associated vital sign response trajectory; The calculation formula for the fluctuation frequency value within the response section is as follows: ; in, Representative The fluctuation frequency value within the response segment, Representative The number of time index points in the response segment, Representative In the response section The difference between the physical sign value at a time point and the physical sign value at the previous time point, that is, , Representative The standard deviation of the sign values within the response segment, Representative The average value of the physical sign value in the response segment, Representative The maximum value of the sign value in the response segment, Representative The minimum value of the sign value in the response segment, Representative In the response section Physical sign values at each time point; The formula uses a variety of mathematical operations such as summation (∑), subtraction (-), division ( / ), and absolute value (||): the summation symbol represents the calculation process repeated at multiple time points in the entire segment, starting from the second point because it needs to calculate the difference based on the previous moment; the absolute value operation is used to ensure that the direction of change does not affect the intensity of the fluctuation; the difference term is such as Measures the smoothness or continuity of fluctuations; standard deviation normalization and maximum and minimum value normalization improve dimensional consistency.

[0036] Parameter calculation and numerical example explanation: Time period selection instructions: Set The response segment is arrive , the recording frequency is once per second, a total of data points.

[0037] Sign values (Unit: mmHg): Obtained by continuous blood pressure monitoring, for example: , , , , , .

[0038] Change value ; For example: ; ; ; ; .

[0039] mean and standard deviation : The mean calculation formula is: ; Assumptions There are 61 values in total, and we get mmHg; The formula for calculating standard deviation is: ; have to mmHg.

[0040] Maximum With minimum value : Maximum vital sign value in the monitoring segment mmHg, minimum mmHg.

[0041] The calculation example using the formula (taking the first five groups of data points for calculation) is shown in Table 1 below: Table 1: Vital sign response segment monitoring parameters

[0042] As shown in Table 1, the parameters required for the calculation have been quantified and listed.

[0043] Normalized fluctuation frequency value calculation (Top 5): ; Right now ; ; The results show that: the fluctuation frequency value within the response section , which is significantly higher than the benchmark value of 20 (the benchmark value is set by calculating the average value of all static measurements of physical signs and the normal variation range), indicating that the physical signs fluctuated frequently and violently during this time period and require special attention.

[0044] Advantages of the formula: By introducing the absolute change term of the difference of physical signs, the rate of change of the difference and the standard deviation term, the fluctuation intensity, frequency and outlier characteristics of the physical signs in the time series are comprehensively reflected, so that the results At the same time, it has amplitude sensitivity, trend recognition ability and abnormal response capture ability, which enhances the reliability of judging the vital sign response trajectory and the accuracy of time positioning.

[0045] Description of the normalization method of each parameter dimension: ; Purpose: To convert the variation of physical signs between adjacent time points into relative standard deviation units to eliminate the influence of the absolute numerical scale of the physical signs themselves; Method: Divide the change value (unit: such as mmHg) by the standard deviation of the corresponding segment (unit is also mmHg). The result is a dimensionless value. Normalization logic: By standardizing the instantaneous changes in physical signs by standard deviation, we can measure whether the changes are significant.

[0046] ; Purpose: To reflect the degree of mutation in the rate of change of physical signs; Method: This item is the difference between two adjacent changes, the unit remains unchanged (such as mmHg), and does not participate in normalization; Normalization: This term is no longer normalized in the formula, retaining its original numerical difference to enhance the ability to respond to drastic changes.

[0047] ; Purpose: To measure the relative deviation of the current value of a sign from its segment mean and remove the absolute dimension effect of the upper and lower limits of the segment; Method: Divide the deviation of each point's sign value from the mean by the range of the segment (maximum value minus minimum value), the unit is mmHg, and the result is dimensionless; Normalization logic: The larger the ratio value is, the more the current point sign deviates from the normal fluctuation range.

[0048] Definition of the fluctuation frequency value within the response range: Fluctuation frequency value It refers to the cumulative intensity of the amplitude and rate fluctuations of the vital sign values over time within a specific response segment. It not only reflects the instantaneous change of the single-point vital sign value, but also comprehensively considers the continuity and trend of the change.

[0049] The fluctuation frequency value is different from a simple count of the number of changes. Instead, it combines the amplitude of each change (normalized), the continuity of the fluctuation (through the difference of the difference) and the degree of deviation from the central trend (normalized deviation) in a weighted form, and sums them over the entire segment to obtain a dimensionless intensity index.

[0050] Operation principle description: Starting condition: From the second time point in the segment, for each time point Perform fluctuation calculations; Item 1 : It is used to capture whether the amplitude of the change in the physical sign at that moment is statistically abnormal. A value greater than 1 usually indicates that the change at that point exceeds one standard deviation; Item 2 : Reflects the continuity and stability of the process of physical sign changes. The larger the value, the more unstable the change process. Item 3 : Measure the relative position of the vital sign value at that moment in the overall segment. If it deviates far from the median, it means that there is a significant abnormality at that point; Finally, by accumulating the sum of the above three items at all time points in the entire segment, we get , which is used to quantitatively characterize the frequency and total intensity of physical sign fluctuations within this time period.

[0051] This value can be used as a basic indicator for subsequent tasks such as determining abnormal response areas, feature clustering, and annotation of vital sign trends. The larger the value, the more frequent and drastic the fluctuations in the vital signs within the response segment.

[0052] See also Figure 1 and Figure 2 ,The intervention task sequencing module includes: The first-place ranking submodule of the physical sign extracts the first response position of the physical sign on the sampling time axis based on all the responded physical sign items in the associated physical sign response trajectory, numbers and sorts the first response points of the differentiated physical signs in chronological order, records the time index arrangement structure of each physical sign, and generates the physical sign time series ranking value; Based on all the responded sign items in the associated sign response trajectory, first extract the earliest response point in the response trajectory of each sign, read the starting response time index of each sign on the sampling time axis in turn, and record the time index as the first response point of the sign. For example, if the fluctuation amplitude of sign A first exceeds the threshold at the 102nd sampling point, sign B first responds at the 89th sampling point, and sign C first responds at the 95th sampling point, the corresponding time indexes are 102, 89, and 95, respectively. Sorting all the first response points of the signs from small to large according to the time index results in a sequence of: sign B, sign C, sign A, and assigning them sequence numbers 1, 2, and 3, respectively. Record the correspondence between the sorted sign names and their time indexes to form a sign time series sequence value table. This table fully records the order information of the sign responses on the time axis and constitutes the key basis for subsequent intervention sequencing.

[0053] The submodule for calculating the duration of the physical sign calls the time index of the physical sign in the sequence value of the physical sign time series, extracts the start and end boundaries of the physical sign that continuously maintains the change in the sampling sequence, calculates the duration value of the change, and marks the complete segment index during the change period to obtain the duration interval of the physical sign change; The specific calculation formula for the change duration value is: ; in, Representative number is Signs The duration value of a change in a continuous change process, Indicates signs No. The end time point index of each change segment, Indicates signs No. The starting time point index of each change segment, Indicates signs In the Within the change segment The difference in the vital sign value between a sampling point and its previous sampling point, Indicates signs In the Within the change segment The time difference between a sampling point and its previous sampling point, Indicates signs In the The average change speed value of all sampling point pairs in a change segment, Indicates signs In the The number of sampling point pairs within a change segment, is the difference sequence index; Parameter acquisition and actual calculation examples: Calculate the average rate of change: ; Compute the term for each pair of sampling points: Pair 1: ; Pair 2: ; Pair 3: ; Pair 4: ; Find the average: ; Calculate the final change duration: ; Result analysis: The results showed that the change duration of the sign α\alphaα in the change segment from the 10th minute to the 14th minute was 4.846 minutes. The advantages of the formula are: By introducing the square root of the product of the difference in vital sign values and the time difference, the amplitude and speed of the vital sign changes can be captured more sensitively; and by subtracting the term of the difference in vital sign values divided by the average change speed, the deviation caused by abnormal fluctuations can be adjusted, thereby more accurately reflecting the actual duration of the vital sign changes.

[0054] Description of the dimension normalization method of each parameter in the formula: To ensure comparability, integration, and calculation stability between data of different dimensions, all parameters involved in the formula need to be dimensionally normalized using a combination of standard normalization (Z-score normalization) and maximum and minimum normalization (Min-Max normalization). The normalization methods for each parameter are as follows: Time index class parameters ( 、 、 ); Used to ensure that time values are distributed between 0 and 1, improving the alignment between multiple time periods.

[0055] Sign difference parameter ( ); in is the mean of the sample sign differences, is its standard deviation; this method is used to eliminate the influence between different sign scales.

[0056] Average change rate parameter ( ); in 、 It is the minimum and maximum value of the change rate of the vital sign in the historical data.

[0057] When square roots, products, and ratios appear in mixed expressions, they must be normalized based on their result type (e.g., setting the maximum absolute value of all physical sign changes as a benchmark), and the unified standard interval must be mapped to Or centered to 0.

[0058] Definition of the change duration value: The duration of change value refers to the actual duration of a specific sign's change within a continuous interval of significant change in its trend or value within a monitored vital sign time series. This duration not only considers the start and end times of the change interval, but also factors such as the intensity, speed, and amplitude of the change, thereby comprehensively quantifying the nature of the "sustained change."

[0059] This value is an important indicator reflecting the stability of changes in vital signs and the continuity of trends. It is suitable for multiple scenarios such as medical monitoring (such as blood pressure and heart rate) and industrial process control (such as temperature changes).

[0060] Operation principle description (text explanation): The calculation of the change duration value is based on two core parts: Measurement of basic duration: The basic duration of the change is obtained by taking the difference between the end and start time points of the physical sign change segment. This part directly quantifies the absolute duration of the change period and is the basic dimension for analyzing the persistence of change.

[0061] Weighted adjustment of dynamic factors of physical sign changes: For each pair of sampling points, calculate the absolute value of the product of the difference in physical sign and the difference in time, and take the square root to measure the intensity of the instantaneous change; At the same time, the ratio of the difference in vital signs between each pair of sampling points and the average change rate of the segment is calculated as a correction term to suppress severe abnormal fluctuations; The difference between the two reflects the "real change effect" of the current sampling point pair, and then all sampling point pairs are summed and averaged to obtain the dynamic correction term; Add this modifier to the base duration and take the absolute value of the entire result to avoid negative values caused by reversing the start and end order.

[0062] The resulting change duration value is an integrated expression of the three-dimensional characteristics of change range, intensity, and speed. Its composition reflects the following logical structure: "Time span + average adjustment of change amplitude" uses multiple mathematical operations such as multiplication, square root, ratio and absolute value to achieve compound calculations, and has the ability to identify changes and estimate duration under data-driven conditions.

[0063] The comprehensive sorting and list generation submodule counts the frequency of each sign change in the entire sequence based on the change segment index of the sign in the sign change duration interval. It uses the time sequence, duration, and frequency of occurrence as the sorting basis, establishes a multi-factor combination judgment logic, and obtains a list of the order in which the sign intervention is to be executed; According to the index information of each segment recorded in the duration interval of the physical sign change, the number of changes of each physical sign in the entire sampling sequence is counted, that is, the number of response segments of the same physical sign. For example, physical sign A has a total of 3 response change segments in the entire signal segment, physical sign B appears 5 times, and physical sign C appears 2 times. Their occurrence frequencies are recorded as 3, 5, and 2, respectively. The time sequence number, cumulative duration, and occurrence frequency of each physical sign are extracted as comprehensive evaluation factors. The judgment logic is constructed to sort them in sequence. The priority weights in the judgment logic are set as time sequence factor 0.5, duration factor 0.3, and frequency factor 0.2. The ranking value of each physical sign is calculated according to the weight of each factor. For example, if the time sequence of sign B is 1 (value 1), the total duration is 2.5 seconds, and the frequency is 5 times, and the time sequence of sign C is 2 (value 2), the total duration is 1.2 seconds, and the frequency is 2 times, then the ranking values are calculated and compared according to the rules. Finally, the ranking values are arranged from small to large to generate a list of physical sign intervention execution sequences.

[0064] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A health management and physical examination big data platform, characterized by: include: The fluctuation starting point positioning module obtains the tissue resistance record of the time period in the arterial resistance map detection scenario, determines the direction of adjacent resistance changes, compares the difference between the interface change position and the radio wave offset, selects the deviation time point, and shifts it backward as the new sampling starting point to obtain the starting time of the fluctuation delay; The rhythm structure adjustment module sets a starting point based on the fluctuation delay starting time point, compares the current and previous fluctuation directions, and adjusts the segment length if they are consistent, rearranges the order of the fluctuation points, and obtains the rhythm adjustment interval; A trend trigger identification module calibrates the blood pressure boundary position based on the rhythm adjustment interval, determines whether the measurement points continuously fall outside the boundary, and performs continuity judgment on the change path and interval to obtain an arterial pressure change trend identification result; The vital sign linkage extraction module selects the consistent items of exhalation time, inhalation hold time and lung expansion volume change based on the trend direction in the arterial pressure change trend identification result, compares the starting response position with the continuous segment coverage, and obtains the associated vital sign response trajectory.

2. The health management and physical examination big data platform according to claim 1 is characterized by: The fluctuation delay starting point includes reference time positioning, offset distance quantification, and updated sampling starting point; the rhythm adjustment interval includes time range adjustment, fluctuation sequence rearrangement, and change trend matching; the arterial pressure change trend identification result includes exceeding the measurement point boundary, continuous deviation paragraph, and trend path structure; the associated vital sign response trajectory includes consistency change starting point, response continuation interval, and fluctuation period coverage.

3. The health management and physical examination big data platform according to claim 1 is characterized in that: The fluctuation starting point positioning module includes: The resistance trend difference detection submodule obtains continuous time period tissue resistance records in the arterial resistance map detection scenario, extracts the resistance change trend of each time period in the same time series, compares the direction marks of the time period resistance change in any two adjacent time periods, identifies the time period positions with inconsistent directions, and obtains the resistance direction inconsistent intervals; The junction offset anomaly detection submodule extracts the corresponding junction position state and radio wave offset state sequence based on the inconsistent resistance direction interval, compares the junction state change amplitude with the set junction change recognition threshold, screens the time period position of the offset state anomaly, and generates a junction offset mutation position set; The fluctuation starting point positioning submodule locates the time point sequence in the resistance record according to the position index of the time period where the interface offset mutation position is concentrated, identifies the position where the offset state changes, adjusts the time point backward by a specified time amount as the new sampling starting point, and obtains the starting time point of the fluctuation delay.

4. The health management and physical examination big data platform according to claim 1 is characterized in that: The rhythm structure adjustment module includes: The directional consistency identification submodule extracts the sampling sequence within the current fluctuation segment based on the starting position of the fluctuation delay starting time point, records the fluctuation range change direction corresponding to the time point, extracts the change direction mark within the previous segment, compares the consistency of the current segment with the previous segment in the corresponding time direction, and screens out continuous time periods with consistent direction to obtain the directional consistency interval; The segment boundary revision submodule identifies the degree of overlap between the start and end time points of the current fluctuation segment and the coverage interval based on the time boundaries of the directional coherence interval, and determines whether the extension and compression conditions are met. If so, the start and end time boundaries of the current fluctuation segment are revised to generate the adjusted segment range; The rhythm reordering submodule calls the revised time range in the adjusted segment range, reorders the fluctuation points contained therein according to the original order of the fluctuation direction, and arranges the sorted fluctuation point position sequence as the segment reference to obtain the rhythm adjustment interval.

5. The health management and physical examination big data platform according to claim 1 is characterized in that: The trend trigger identification module includes: The boundary extraction and calibration submodule extracts the upper and lower blood pressure boundaries of three adjacent detection segments based on the signal sequence within the rhythm adjustment interval, calibrates the time nodes where the boundary values in each segment are located, records the index sequence of the boundary time points in the segment, and generates a boundary position index set; The out-of-bounds interval screening submodule calls the corresponding positions of the upper and lower boundaries in the boundary position index set, extracts the position values of the measurement points in the same section, compares the position relationship between each measurement point and the corresponding boundary value, and screens the time period positions where consecutive measurement points exceed the upper and lower boundaries to obtain the continuous out-of-bounds point interval; The trend consistency determination submodule extracts the change path direction marks between the measuring points and the time interval sequence between adjacent measuring points based on the position information of the measuring points in the continuous cross-border point interval, determines whether the change direction remains consistent and the interval does not exceed the trend continuity threshold, and obtains the arterial pressure change trend identification result.

6. The health management and physical examination big data platform according to claim 1 is characterized in that: The vital signs linkage extraction module includes: A direction matching and screening submodule extracts the change direction mark of the sign sequence in the respiratory-related signs based on the trend information in the arterial pressure change trend identification result, matches and screens the change direction of each sign with the trend direction, retains the sign data sequence with the consistent direction, and obtains the direction-matched signs; The morphological response segment extraction submodule calls the direction matching vital signs, identifies the position index where the direction change occurs, records the position number of the vital sign starting change point in the original sampling sequence, determines whether there is a change trajectory in which the morphological fluctuation amplitude exceeds the morphological recognition reference value in the continuous time period after the number, and obtains the morphological response segment; The response trajectory generation submodule extracts the covered time interval according to the start and end time indexes of the morphological response segment, calculates the fluctuation frequency value within the response segment, marks the distribution structure of the fluctuation interval within the time period, and obtains the associated vital sign response trajectory.

7. The health management and physical examination big data platform according to claim 6 is characterized in that: The specific calculation formula for the fluctuation frequency value within the response section is: ； in, Representative The fluctuation frequency value within the response segment, Representative The number of time index points in the response segment, Representative In the response section The difference between the physical sign value at a time point and the physical sign value at the previous time point, that is, , Representative The standard deviation of the sign values within the response segment, Representative The average value of the physical sign value in the response segment, Representative The maximum value of the sign value in the response segment, Representative The minimum value of the sign value in the response segment, Representative In the response section Sign values at each time point.

8. The health management and physical examination big data platform according to claim 1 is characterized in that: Also includes intervention task sequencing modules: The intervention task sequencing module identifies changes, durations, and repetitions based on the starting point, duration, and frequency of the signs in the associated sign response trajectory, combines the intervention sequence, and obtains a sign intervention execution sequence list; The physical sign intervention execution sequence list includes the order of physical sign appearance, change maintenance time, and change frequency statistics.

9. The health management and physical examination big data platform according to claim 8, characterized in that: The intervention task sequencing module includes: The first-place ranking submodule of the physical sign extracts the first response position of the physical sign on the sampling time axis based on all the responded physical sign items in the associated physical sign response trajectory, numbers and sorts the first response points of the differentiated physical signs in chronological order, records the time index arrangement structure of each physical sign, and generates the physical sign time series ranking value; The submodule for calculating the duration of a physical sign calls the time index of the physical sign in the sequence value of the physical sign time series, extracts the start and end boundaries of the physical sign that continuously maintains the change in the sampling sequence, calculates the duration value of the change, and marks the complete segment index during the change period to obtain the duration interval of the physical sign change; The comprehensive sorting and list generation submodule counts the frequency of each sign change in the entire sequence based on the sign change segment index in the sign change duration interval, uses the time sequence, duration, and frequency of occurrence as the sorting basis, establishes a multi-factor combination judgment logic, and obtains a sign intervention execution order list.

10. The health management and physical examination big data platform according to claim 9, characterized in that: The calculation formula for the change duration value is specifically: ； in, Representative number is Signs The duration value of a change in a continuous change process, Indicates signs No. The end time point index of each change segment, Indicates signs No. The starting time point index of each change segment, Indicates signs In the Within the change segment The difference in the vital sign value between a sampling point and its previous sampling point, Indicates signs In the Within the change segment The time difference between a sampling point and its previous sampling point, Indicates signs In the The average change speed value of all sampling point pairs in a change segment, Indicates signs In the The number of sampling point pairs within a change segment, The difference sequence index.

Images