Equipment performance test system and method applied to vital sign cabin

Abstract

The invention discloses an equipment performance test system and method applied to a vital sign cabin, and relates to the technical field of equipment performance test.State data and monitoring features of the vital sign cabin are collected, a historical database of the vital sign cabin is established, effective monitoring features are analyzed, and state features corresponding to the effective monitoring features are obtained; establishing a monitoring feature analysis database, establishing limit intervals, integrating the limit intervals, establishing a limit interval database, calling the limit interval database, performing first monitoring feature judgment, selecting a first monitoring feature from to-be-monitored features, completing selection of all the to-be-monitored features, and recording the total number of times of selection; according to the method, the limit interval is constructed through the correlation analysis of the state features and the monitoring features, so that the test basis is more suitable for the actual operation rule of the equipment, the solid support is provided for the performance evaluation of the equipment, and the misjudgment risk is reduced.

Description

Technical Field

[0001] This invention relates to the field of equipment performance testing technology, specifically to an equipment performance testing system and method applied to a vital signs cabin. Background Technology

[0002] In current performance testing of vital signs chambers, the data acquisition process lacks unified standards, and the integration of status information and monitoring data is fragmented, making it difficult to effectively eliminate invalid and interfering information. The selection of monitoring features lacks clear validity criteria, the extraction of core features is not precise enough, and the intrinsic relationship between status features and monitoring features is not fully considered. Testing methods often deviate from the actual operating patterns of the equipment, relying solely on single-dimensional data for judgment. This is prone to bias due to fragmented data, making it difficult for test results to accurately reflect the actual operating status of the equipment, causing difficulties in equipment performance evaluation, and increasing the risk of misjudgment. Traditional testing methods often employ fixed feature selection patterns, failing to dynamically adjust feature combinations based on real-time device performance, frequently resulting in resource waste. Furthermore, the lack of effective advance notice of waiting times during testing prevents users from knowing the testing cycle in advance, easily causing unnecessary anxiety. Simultaneously, some screening processes require manual user intervention, leading to cumbersome procedures and a high barrier to entry, which not only reduces testing efficiency but also negatively impacts the user experience, failing to meet the demand for convenient and efficient testing. Existing testing methods are typically highly specific, adaptable only to particular types of vital signs chambers, lacking versatility. Changing the test object often requires readjusting the testing logic, increasing costs. Furthermore, the lack of systematic accumulation and integration of test-related data hinders the formation of an iteratively optimized database, preventing continuous improvement in the accuracy of testing methods and limiting long-term upgrade potential. Simultaneously, the application scenarios for test data are relatively limited, failing to provide effective support for equipment design optimization, maintenance, and other lifecycle management, thus restricting the practical application value of the testing methods. Summary of the Invention

[0003] The purpose of this invention is to provide a device performance testing system and method for use in vital signs cabins, in order to solve the problems mentioned in the background art.

[0004] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for testing the performance of equipment applied to a vital signs cabin, comprising the following steps: S1. Collect the status data and monitoring characteristics of the life characteristic chamber, preprocess and normalize them to obtain the status characteristics and monitoring characteristics of the life characteristic chamber, and establish a historical database of the life characteristic chamber. S2. Analyze effective monitoring features, obtain the state features corresponding to the effective monitoring features, establish a monitoring feature analysis database, and establish restriction intervals for the monitoring features; S3. Integrate restricted intervals and establish a restricted interval database; S4. After the user confirms the feature to be monitored, call the restriction interval database to perform the first monitoring feature judgment and select the first monitoring feature from the features to be monitored. S5. Further select the remaining features to be monitored until all features to be monitored have been selected, and record the total number of selections. S6. Based on the total number of selections and the reference selection time, provide users with a waiting time forecast.

[0005] Furthermore, in step S1, after authorization, for any type of vital signs chamber, status data of the vital signs chamber is collected. The status data is preprocessed and normalized to obtain the status features of the vital signs chamber, with N status features. After authorization, monitoring data from the vital signs chamber is acquired, preprocessed and normalized to obtain M monitoring features, where M is a preset number of monitoring features. A historical database of vital signs chambers is then established. This historical database includes: a group of status features of the vital signs chamber and the monitoring results of M monitoring features when vital signs monitoring is performed in the vital signs chamber. The monitoring result of the m-th monitoring feature indicates whether the m-th monitoring feature is effective or ineffective, where m = 1, 2, ..., M. The characteristics collected include: the ratio of the current battery level to the total battery level of the vital signs chamber, the ratio of the current service life of the vital signs chamber to the preset maximum service life, the ratio of the current equipment temperature of the vital signs chamber to the preset maximum equipment temperature, and the ratio of the current equipment humidity of the vital signs chamber to the preset maximum equipment humidity. Monitoring characteristics include: the ratio of the user's heart rate to the preset maximum heart rate threshold, the ratio of the user's blood pressure to the preset maximum blood pressure threshold, the ratio of the user's blood glucose to the preset maximum blood glucose threshold, and the ratio of the user's platelet count to the preset maximum platelet count threshold. After authorization, the status and monitoring data of various vital signs chambers are collected in a standardized manner. Through preprocessing and normalization, data standards are effectively unified, interfering information is eliminated, and core characteristics reflecting the equipment's operating status and monitoring status are accurately extracted. The constructed historical database system integrates the validity results of the equipment status characteristic groups and various monitoring characteristics, achieving orderly data storage and associated management. This process not only ensures the compliance and accuracy of data collection but also provides complete and high-quality data support for subsequent monitoring characteristic validity analysis and limit interval construction, laying a scientific and reliable foundation for the entire testing method.

[0006] Furthermore, in step S2, for the m-th monitoring feature, after monitoring life characteristics in the life characteristic chamber, the value of the m-th monitoring feature is obtained as A. If (A-A0) / A0>a, it is determined that the monitoring result of the m-th monitoring feature is invalid; otherwise, it is determined that the monitoring result of the m-th monitoring feature is valid. A0 is the preset standard value of the m-th monitoring feature, and a is the preset deviation threshold of the m-th monitoring feature. When the m-th monitoring feature is valid, the status feature of the life characteristic monitoring in the life characteristic chamber is stored in the m-th monitoring feature analysis database; when the m-th monitoring feature is invalid, the status feature of the life characteristic monitoring in the life characteristic chamber is ignored, and each value is substituted into m=1,2,…,M to establish an M-item monitoring feature analysis database. The database for analyzing the m-th monitoring feature is invoked. This database includes D groups of state features. The analysis focuses on the n-th state feature, where n = 1, 2, ..., N. The n-th state feature of the D group of state features is {E}. 1_n_m E 2_n_m ,…,E d_n_m ,…,E D_n_m}, where E d_n_m Let n be the nth state feature of the dth state feature, and then calculate the influence coefficient F of the nth state feature on the mth monitoring feature. n_m : ; Where E0 is the maximum value of the nth state feature of group D, when F n_m If F0 > 0, it is determined that the change of the nth state feature has an impact on the mth monitoring feature; otherwise, it is determined that the change of the nth state feature has no impact on the mth monitoring feature, where F0 is a preset threshold for the influence coefficient of the nth state feature on the mth monitoring feature, and thus the restriction interval G of the mth monitoring feature on the nth state feature is obtained. m_n When it is determined that the change of the nth state feature has an impact on the mth monitoring feature, the Z_score method is used to evaluate the nth state feature {E} of the D group of state features. 1_n_m E 2_n_m ,…,E d_n_m ,…,E D_n_m Anomaly elimination is performed to obtain the nth decontamination state feature set. The minimum value of the nth decontamination state feature set is selected as the constraint interval G. m_n The lower bound is determined by selecting the maximum value of the nth decontamination state feature set as the constraint interval G. m_n The upper limit; when it is determined that the change of the nth state feature has no impact on the mth monitoring feature, the limit interval G is set. m_nThe set of real numbers is used, and the restriction interval is set to a real number set, indicating that there are no restrictions on the state features. By clearly defining criteria to judge the effectiveness of monitoring features, valuable monitoring data is accurately screened, and the corresponding state features are categorized and stored in a dedicated analysis database. Invalid data interference is eliminated to ensure the quality of the database. By analyzing the degree of influence of state features on monitoring features, the inherent relationship between the two is clarified, and targeted restriction intervals are constructed. Outliers are excluded for influential state features to make the restriction intervals more closely reflect actual correlation patterns, while the interval range is flexibly set for ineffective state features. This process not only achieves accurate data purification and correlation analysis but also provides a scientific basis for subsequent restriction interval integration and monitoring feature selection, improving the logic and reliability of the entire testing method.

[0007] In step S3, each of the m=1,2,…,M terms is substituted to obtain the constraint interval {G} of the M monitoring features on the nth state feature. 1_n G 2_n ,…,G m_n ,…,G M_n}, and then obtain the restriction interval of M monitoring features on any state feature. Substitute them one by one into n=1,2,…,N to obtain the restriction interval {g} of the m-th monitoring feature on N state features. m_1 ,g m_2 ,…,g m_n ,…,g m_N}, thereby obtaining the restriction interval of any monitoring feature on N state features, and then establishing a restriction interval database.

[0008] Furthermore, in step S4, the restriction interval database is invoked. When the user selects X monitoring features for vital sign chamber monitoring, the user-selected monitoring features are categorized as features to be monitored, and the features to be monitored are {H1, H2, ..., H...}. x ,…,H X}, where H x For the x-th feature to be monitored, the feature H1 to be monitored is analyzed. The restriction interval of the feature H1 to be monitored on the n-th state feature is selected as the effective restriction interval of the n-th state feature. Then, the effective restriction intervals of N state features are obtained, and the monitoring feature H1 is classified as the first monitoring feature. Analyze the feature H2 to be monitored. If the restriction intervals of the feature H2 for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment is adequate. Calculate the intersection of the restriction interval of the feature H2 for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature H2 to be monitored as the first monitoring feature. Otherwise, it is determined that the life signs cabin equipment is inadequate. Keep the effective restriction intervals of the N state features unchanged and keep the feature H2 as a monitoring feature. Analyze the feature H3 to be monitored. If the restriction intervals of the feature H3 for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment is adequate. Calculate the intersection of the restriction interval of the feature H3 for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature H3 to be monitored as the first monitoring feature. Otherwise, it is determined that the life signs cabin equipment is inadequate. Keep the effective restriction intervals of the N state features unchanged and keep the feature H3 as a monitoring feature. To monitor the feature {H1,H2,…,H} x ,…,H X The analysis yields the first monitoring feature and the remaining features to be monitored, completing the selection of the first monitoring feature. The restriction interval database provides robust data support for feature selection, categorizing user-selected features into those to be monitored and conducting analysis and screening sequentially. By assessing the intersection of the features to be monitored with the current effective restriction intervals, the performance compatibility of the vital signs cabin equipment is accurately evaluated, ensuring that the selected initial monitoring features match the equipment's carrying capacity. When performance is sufficient, the effective restriction intervals are updated promptly to optimize subsequent screening criteria; when performance is insufficient, the features to be monitored are retained to avoid resource waste due to unreasonable selection. The entire process is logically clear and orderly, ensuring the scientific and rational selection of the initial monitoring features and laying a solid foundation for subsequent iterative screening, thus improving the overall efficiency of the testing process.

[0009] Furthermore, in step S5, after completing the selection of the first monitoring feature, the second monitoring feature is selected, and the monitoring features are renumbered as {J1, J2, ..., J...} y ,…,J Y}, where Y is the number of features to be monitored after the first selection of monitoring features, and J yTo complete the selection of the y-th monitoring feature after the first monitoring feature selection, the monitoring feature J1 is analyzed. The restriction interval of the monitoring feature J1 on the n-th state feature is selected as the effective restriction interval of the n-th state feature, and then the effective restriction intervals of N state features are obtained. The monitoring feature J1 is classified as the second monitoring feature. Analyze the feature J2 to be monitored. If the restriction intervals of the feature J2 to be monitored for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment performance is sufficient. Calculate the intersection of the restriction interval of the feature J2 to be monitored for the nth state feature with the effective restriction interval of the nth state feature, and replace the effective restriction interval of the nth state feature with the intersection. Substitute each of n=1,2,…,N into the system to update the effective restriction intervals of the N state features. At the same time, classify the feature J2 to be monitored as the second monitoring feature. Otherwise, it is determined that the life signs cabin equipment performance is insufficient. Keep the effective restriction intervals of the N state features unchanged and keep the feature J2 to be monitored as a feature to be monitored. Analyze the feature J3 to be monitored. If the restriction intervals of the feature J3 to be monitored for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment performance is sufficient. Calculate the intersection of the restriction interval of the feature J3 to be monitored for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature J3 to be monitored as the second monitoring feature. Otherwise, it is determined that the life signs cabin equipment performance is insufficient. Keep the effective restriction intervals of the N state features unchanged and keep the feature J3 to be monitored as a feature to be monitored. To monitor the feature {J1,J2,…,J y ,…,J YThe analysis yields the second set of monitoring features and the remaining features to be monitored. The selection of the second set of monitoring features is then completed, followed by the selection of the next set of monitoring features, until all features to be monitored are selected. The number of times a monitoring feature is selected is recorded as Z. Continuing this scientific iterative screening logic, the remaining features to be monitored are renumbered to ensure the orderly progress of the screening process. The compatibility of each feature to be monitored with the current effective limit range is analyzed sequentially to accurately determine whether the life signs cabin equipment performance is sufficient. If performance meets the standard, the effective limit range is updated promptly to optimize the judgment criteria for subsequent screening; if performance is insufficient, the features to be monitored are retained to avoid resource waste caused by unreasonable selection. Through multiple rounds of progressive screening, it is ensured that the monitoring features selected in each round are precisely matched with the equipment's carrying capacity, until all features to be monitored are screened, and the number of screenings is fully recorded. This process ensures both the comprehensiveness and rationality of feature selection and provides crucial data support for subsequent waiting time predictions, further improving the coherence and reliability of the overall testing process.

[0010] Furthermore, in step S6, the time taken for selecting a monitoring feature with the current time point as the endpoint is recorded as the selection reference time W. When the user selects a monitoring feature for vital signs cabin monitoring, the total time taken is prompted to the user considering the equipment performance. The total time taken is prompted to the user as Z*W, and the waiting time is predicted for the next user.

[0011] A device performance testing system for a vital signs cabin, comprising: a data acquisition and historical database construction module, a monitoring feature analysis and delimitation module, a limit interval integration and database entry module, a confirmation feature initial selection module, a remaining feature successive selection module, and a number of times time prediction module; The data acquisition and historical database construction module is used to collect the status data and monitoring characteristics of the life characteristic cabin, and after preprocessing and normalization, obtain the status characteristics and monitoring characteristics of the life characteristic cabin, and establish a historical database of the life characteristic cabin. The monitoring feature analysis and delimitation module is used to analyze effective monitoring features, obtain state features corresponding to the effective monitoring features, establish a monitoring feature analysis database, and establish restriction intervals for monitoring features. The restricted interval integration and database entry module is used to integrate restricted intervals and establish a restricted interval database. The confirmation feature initial selection module is used to call the restriction interval database after the user confirms the feature to be monitored, perform the initial monitoring feature judgment, and select the first monitoring feature from the features to be monitored; The remaining feature successive selection module is used to further select the remaining features to be monitored until all features to be monitored are selected, and the total number of selections is recorded. The "Waiting Time Prediction Module" is used to provide users with a waiting time prediction based on the selected total number of attempts and the selected reference waiting time.

[0012] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: On the one hand, through a standardized feature data acquisition and preprocessing process, the system integrates the status information and monitoring data of the life support cabin, effectively eliminating invalid interference information. Based on the criteria for judging the validity of monitoring features, core features with practical reference value are selected, and then a constraint range is constructed by combining the correlation analysis of status features and monitoring features, making the test basis more closely aligned with the actual operating rules of the equipment. This scientific data analysis logic avoids judgment bias caused by scattered data, ensuring that the equipment performance test results can truly reflect the operating status of the life support cabin, providing solid support for equipment performance evaluation, and reducing the risk of misjudgment.

[0013] On the one hand, the feature selection mode, which adopts a batch-based iterative selection approach, dynamically adjusts the combination of monitoring features based on equipment performance. This ensures the rationality of the selection process while avoiding resource waste. The waiting time prediction function allows users to know the testing cycle in advance, rationally plan their usage, and reduce unnecessary waiting anxiety. Simultaneously, this selection method eliminates the need for manual user intervention in the feature selection process. It is entirely automated, relying on preset rules and a database, simplifying the operation process, lowering the barrier to entry, and enabling convenient and efficient equipment performance testing, significantly improving ease of use and user satisfaction.

[0014] On the other hand, the construction of a multi-dimensional database enables compatibility and adaptation with different types of vital signs chambers, eliminating the need to adjust test logic for specific devices and significantly improving the method's versatility. As data accumulates during use, the database can be continuously enriched and improved, and the accuracy of the limiting ranges will be gradually optimized, giving the testing method the potential for long-term iterative upgrades. Furthermore, the device performance data recorded during testing can provide important references for the design optimization and maintenance of vital signs chambers, contributing to continuous improvement in device performance and expanding the application value of this testing method in the entire lifecycle management of equipment. Attached Figure Description

[0015] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a structural diagram of a device performance testing system applied to a vital signs cabin according to the present invention; Figure 2 This is a flowchart of a device performance testing method applied to a vital signs cabin according to the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 and Figure 2 The present invention provides a technical solution: a method for testing the performance of equipment applied to a vital signs cabin, comprising the following steps: S1. Collect the status data and monitoring characteristics of the life characteristic chamber, preprocess and normalize them to obtain the status characteristics and monitoring characteristics of the life characteristic chamber, and establish a historical database of the life characteristic chamber. S2. Analyze effective monitoring features, obtain the state features corresponding to the effective monitoring features, establish a monitoring feature analysis database, and establish restriction intervals for the monitoring features; S3. Integrate restricted intervals and establish a restricted interval database; S4. After the user confirms the feature to be monitored, call the restriction interval database to perform the first monitoring feature judgment and select the first monitoring feature from the features to be monitored. S5. Further select the remaining features to be monitored until all features to be monitored have been selected, and record the total number of selections. S6. Based on the total number of selections and the reference selection time, provide users with a waiting time forecast.

[0018] In step S1, after authorization, for any type of vital signs chamber, status data of the vital signs chamber is collected. The status data is preprocessed and normalized to obtain the status features of the vital signs chamber, with N status features. After authorization, monitoring data from the vital signs chamber is acquired, preprocessed and normalized to obtain M monitoring features, where M is a preset number of monitoring features. A historical database of vital signs chambers is then established. This historical database includes: the status feature group of the vital signs chamber and the monitoring results of the M monitoring features when vital signs monitoring is performed in the vital signs chamber. The monitoring result of the m-th monitoring feature indicates whether the m-th monitoring feature is effective or ineffective, where m = 1, 2, ..., M. The status features include... The data collected includes: the ratio of the current battery level to the total battery level of the vital signs chamber; the ratio of the current service life of the vital signs chamber to the preset maximum service life; the ratio of the current equipment temperature of the vital signs chamber to the preset maximum equipment temperature; and the ratio of the current equipment humidity of the vital signs chamber to the preset maximum equipment humidity. Monitoring features include: the ratio of the user's heart rate to the preset maximum heart rate threshold; the ratio of the user's blood pressure to the preset maximum blood pressure threshold; the ratio of the user's blood glucose to the preset maximum blood glucose threshold; and the ratio of the user's platelet count to the preset maximum platelet count threshold. After authorization, the status and monitoring data of various vital signs chambers are collected in a standardized manner. Through preprocessing and normalization, data standards are effectively unified, interfering information is eliminated, and core features reflecting the equipment's operating status and monitoring status are accurately extracted. The constructed historical database system integrates the validity results of the equipment status feature groups and various monitoring features, achieving orderly data storage and associated management. This process ensures the compliance and accuracy of data collection and provides complete and high-quality data support for subsequent monitoring feature validity analysis and limit interval construction, laying a scientific and reliable foundation for the entire testing method.

[0019] In step S2, for the m-th monitoring feature, after monitoring life characteristics in the life characteristic chamber, the value of the m-th monitoring feature is obtained as A. If (A-A0) / A0>a, the monitoring result of the m-th monitoring feature is determined to be invalid; otherwise, the monitoring result of the m-th monitoring feature is determined to be valid. A0 is the preset standard value of the m-th monitoring feature, and a is the preset deviation threshold of the m-th monitoring feature. When the m-th monitoring feature is valid, the status feature of the life characteristic monitoring in the life characteristic chamber is stored in the m-th monitoring feature analysis database; when the m-th monitoring feature is invalid, the status feature of the life characteristic monitoring in the life characteristic chamber is ignored, and each value is substituted into m=1,2,…,M to establish an M-item monitoring feature analysis database. The database for analyzing the m-th monitoring feature is invoked. This database includes D groups of state features. The analysis focuses on the n-th state feature, where n = 1, 2, ..., N. The n-th state feature of the D group of state features is {E}. 1_n_m E 2_n_m ,…,E d_n_m ,…,E D_n_m}, where E d_n_m Let n be the nth state feature of the dth state feature, and then calculate the influence coefficient F of the nth state feature on the mth monitoring feature. n_m : ; Where E0 is the maximum value of the nth state feature of group D, when F n_m If F0 > 0, it is determined that the change of the nth state feature has an impact on the mth monitoring feature; otherwise, it is determined that the change of the nth state feature has no impact on the mth monitoring feature, where F0 is a preset threshold for the influence coefficient of the nth state feature on the mth monitoring feature, and thus the restriction interval G of the mth monitoring feature on the nth state feature is obtained. m_n When it is determined that the change of the nth state feature has an impact on the mth monitoring feature, the Z_score method is used to evaluate the nth state feature {E} of the D group of state features. 1_n_m E 2_n_m ,…,E d_n_m ,…,E D_n_m Anomaly elimination is performed to obtain the nth decontamination state feature set. The minimum value of the nth decontamination state feature set is selected as the constraint interval G. m_n The lower bound is determined by selecting the maximum value of the nth decontamination state feature set as the constraint interval G. m_n The upper limit; when it is determined that the change of the nth state feature has no impact on the mth monitoring feature, the limit interval G is set. m_n The set of real numbers is used, and the restriction interval is set to a real number set, indicating that there are no restrictions on the state features. By clearly defining criteria to judge the effectiveness of monitoring features, valuable monitoring data is accurately screened, and the corresponding state features are categorized and stored in a dedicated analysis database. Invalid data interference is eliminated to ensure the quality of the database. By analyzing the degree of influence of state features on monitoring features, the inherent relationship between the two is clarified, and targeted restriction intervals are constructed. Outliers are excluded for influential state features to make the restriction intervals more closely reflect actual correlation patterns, while the interval range is flexibly set for ineffective state features. This process not only achieves accurate data purification and correlation analysis but also provides a scientific basis for subsequent restriction interval integration and monitoring feature selection, improving the logic and reliability of the entire testing method.

[0020] In step S3, each of the m=1,2,…,M terms is substituted to obtain the constraint interval {G} of the M monitoring features on the nth state feature. 1_n G 2_n ,…,G m_n ,…,G M_n}, and then obtain the restriction interval of M monitoring features on any state feature. Substitute them one by one into n=1,2,…,N to obtain the restriction interval {g} of the m-th monitoring feature on N state features. m_1 ,g m_2 ,…,g m_n ,…,g m_N}, thereby obtaining the restriction interval of any monitoring feature on N state features, and then establishing a restriction interval database.

[0021] In step S4, the restriction interval database is invoked. When the user selects X monitoring features for vital signs cabin monitoring, the user-selected monitoring features are categorized as features to be monitored, and the features to be monitored are {H1, H2, ..., H...}. x ,…,H X}, where H x For the x-th feature to be monitored, the feature H1 to be monitored is analyzed. The restriction interval of the feature H1 to be monitored on the n-th state feature is selected as the effective restriction interval of the n-th state feature. Then, the effective restriction intervals of N state features are obtained, and the monitoring feature H1 is classified as the first monitoring feature. Analyze the feature H2 to be monitored. If the restriction intervals of the feature H2 for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment is adequate. Calculate the intersection of the restriction interval of the feature H2 for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature H2 to be monitored as the first monitoring feature. Otherwise, it is determined that the life signs cabin equipment is inadequate. Keep the effective restriction intervals of the N state features unchanged and keep the feature H2 as a monitoring feature. Analyze the feature H3 to be monitored. If the restriction intervals of the feature H3 for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment is adequate. Calculate the intersection of the restriction interval of the feature H3 for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature H3 to be monitored as the first monitoring feature. Otherwise, it is determined that the life signs cabin equipment is inadequate. Keep the effective restriction intervals of the N state features unchanged and keep the feature H3 as a monitoring feature. To monitor the feature {H1,H2,…,H} x ,…,H X The analysis yields the first monitoring feature and the remaining features to be monitored, completing the selection of the first monitoring feature. The restriction interval database provides robust data support for feature selection, categorizing user-selected features into those to be monitored and conducting analysis and screening sequentially. By assessing the intersection of the features to be monitored with the current effective restriction intervals, the performance compatibility of the vital signs cabin equipment is accurately evaluated, ensuring that the selected initial monitoring features match the equipment's carrying capacity. When performance is sufficient, the effective restriction intervals are updated promptly to optimize subsequent screening criteria; when performance is insufficient, the features to be monitored are retained to avoid resource waste due to unreasonable selection. The entire process is logically clear and orderly, ensuring the scientific and rational selection of the initial monitoring features and laying a solid foundation for subsequent iterative screening, thus improving the overall efficiency of the testing process.

[0022] In step S5, after selecting the first monitoring feature, the second monitoring feature is selected, and the monitoring features are renumbered as {J1, J2, ..., J...}. y ,…,J Y}, where Y is the number of features to be monitored after the first selection of monitoring features, and J y To complete the selection of the y-th monitoring feature after the first monitoring feature selection, the monitoring feature J1 is analyzed. The restriction interval of the monitoring feature J1 on the n-th state feature is selected as the effective restriction interval of the n-th state feature, and then the effective restriction intervals of N state features are obtained. The monitoring feature J1 is classified as the second monitoring feature. Analyze the feature J2 to be monitored. If the restriction intervals of the feature J2 to be monitored for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment performance is sufficient. Calculate the intersection of the restriction interval of the feature J2 to be monitored for the nth state feature with the effective restriction interval of the nth state feature, and replace the effective restriction interval of the nth state feature with the intersection. Substitute each of n=1,2,…,N into the system to update the effective restriction intervals of the N state features. At the same time, classify the feature J2 to be monitored as the second monitoring feature. Otherwise, it is determined that the life signs cabin equipment performance is insufficient. Keep the effective restriction intervals of the N state features unchanged and keep the feature J2 to be monitored as a feature to be monitored. Analyze the feature J3 to be monitored. If the restriction intervals of the feature J3 to be monitored for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment performance is sufficient. Calculate the intersection of the restriction interval of the feature J3 to be monitored for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature J3 to be monitored as the second monitoring feature. Otherwise, it is determined that the life signs cabin equipment performance is insufficient. Keep the effective restriction intervals of the N state features unchanged and keep the feature J3 to be monitored as a feature to be monitored. To monitor the feature {J1,J2,…,J y ,…,J Y The analysis yields the second set of monitoring features and the remaining features to be monitored. The selection of the second set of monitoring features is then completed, followed by the selection of the next set of monitoring features, until all features to be monitored are selected. The number of times a monitoring feature is selected is recorded as Z. Continuing this scientific iterative screening logic, the remaining features to be monitored are renumbered to ensure the orderly progress of the screening process. The compatibility of each feature to be monitored with the current effective limit range is analyzed sequentially to accurately determine whether the life signs cabin equipment performance is sufficient. If performance meets the standard, the effective limit range is updated promptly to optimize the judgment criteria for subsequent screening; if performance is insufficient, the features to be monitored are retained to avoid resource waste caused by unreasonable selection. Through multiple rounds of progressive screening, it is ensured that the monitoring features selected in each round are precisely matched with the equipment's carrying capacity, until all features to be monitored are screened, and the number of screenings is fully recorded. This process ensures both the comprehensiveness and rationality of feature selection and provides crucial data support for subsequent waiting time predictions, further improving the coherence and reliability of the overall testing process.

[0023] In step S6, the time taken for a single monitoring feature selection with the current time point as the endpoint is recorded as the selection reference time W. When the user selects a monitoring feature for vital signs cabin monitoring, the total time taken is prompted to the user considering the equipment performance. The total time taken is prompted to the user as Z*W, and the waiting time is predicted for the next user.

[0024] A device performance testing system for a vital signs cabin, the system comprising: a data acquisition and historical database construction module, a monitoring feature analysis and delimitation module, a restriction interval integration and database entry module, a confirmation feature initial selection module, a remaining feature successive selection module, and a prediction duration of the number of selections; The data acquisition and historical database module is used to collect the status data and monitoring characteristics of the life characteristic chamber, and after preprocessing and normalization, the status characteristics and monitoring characteristics of the life characteristic chamber are obtained, and a historical database of the life characteristic chamber is established. The monitoring feature analysis and delimitation module is used to analyze effective monitoring features, obtain the state features corresponding to the effective monitoring features, establish a monitoring feature analysis database, and establish restriction intervals for monitoring features. The restricted interval integration and database entry module is used to integrate restricted intervals and establish a restricted interval database. The feature selection confirmation module is used to call the restriction interval database after the user confirms the feature to be monitored, to make the first monitoring feature judgment, and to select the first monitoring feature from the features to be monitored. The remaining feature successive selection module is used to further select the remaining features to be monitored until all features to be monitored have been selected, and the total number of selections is recorded. The "Waiting Time Prediction" module provides users with a prediction of the waiting time based on the selected total number of attempts and the selected reference waiting time.

[0025] Example 1: This example discloses a device performance testing method applied to a vital signs cabin. The specific implementation process is as follows: Step one: After obtaining relevant authorization, comprehensively collect status data during the operation of various vital sign chambers on the market, including the ratio of current battery level to total battery level, the ratio of current service life to preset maximum service life, the ratio of current equipment temperature to preset maximum equipment temperature, and the ratio of current equipment humidity to preset maximum equipment humidity. This status data undergoes preprocessing operations such as cleaning and noise reduction, and is normalized to unify data standards, extracting core status features that reflect the equipment's operating condition. Simultaneously, after authorization, acquire monitoring data generated during vital sign chamber monitoring, covering the ratio of user heart rate to preset maximum heart rate threshold, blood pressure to preset maximum blood pressure threshold, blood glucose to preset maximum blood glucose threshold, and platelet count to preset maximum platelet count threshold. This data is also preprocessed and normalized before extracting monitoring features. Based on the validity results of the above status feature groups and various monitoring features, construct a historical database of vital sign chambers to achieve orderly storage and associated management of both types of data.

[0026] Step two: For each monitoring feature, after a vital signs monitoring session is completed in the vital signs cabin, the actual value of the monitoring feature is obtained and compared with a preset standard value. The validity of the monitoring feature is determined based on the set deviation range. If the monitoring feature is valid, the corresponding equipment status feature is stored in its dedicated analysis database; if invalid, the corresponding status feature is ignored. Following this logic, a dedicated analysis database is established for each monitoring feature. Subsequently, the analysis databases for each monitoring feature are called to analyze the influence of each status feature on that monitoring feature, clarifying the intrinsic relationship between the two. For status features with significant influence, the relevant data is cleaned of outliers, and the extreme values ​​of the cleaned data are used as the upper and lower limits of the limit range for that status feature. For status features without influence, an unlimited range is set, thus completing the construction of the limit ranges for the status features corresponding to each monitoring feature.

[0027] Step three involves comprehensively integrating the restriction intervals of all monitoring features for various state features, systematically sorting out the interval correspondences between different monitoring features and state features, and avoiding the scattered distribution of interval data. Through standardized classification and organization, a well-structured and easily queried restriction interval database is constructed, achieving centralized storage and orderly management of all restriction intervals, providing stable data support for the subsequent monitoring feature selection process.

[0028] Step four: After the user selects the features to be monitored, the restriction interval database is invoked to categorize the selected features as features to be monitored, and analysis and filtering are carried out sequentially. First, the first feature to be monitored is selected, and its corresponding state feature restriction intervals are set as initial valid restriction intervals, thus classifying this feature as the first monitoring feature. Then, the remaining features to be monitored are analyzed sequentially, determining whether the restriction intervals for all state features corresponding to each feature intersect with the current valid restriction interval. If all intersect, it indicates sufficient device performance; the intersection is calculated, the valid restriction interval is updated, and the feature is classified as a first monitoring feature. If no intersection exists, it is determined that the device performance is currently insufficient to support the monitoring of this feature, and its monitoring status is retained. This logic completes the filtering of the first monitoring features, and the remaining features are still listed as features to be monitored.

[0029] Step 5: After completing the initial feature selection, reorder and number the remaining features to be monitored, and start the second round of screening. Following the same logic as the first screening, use the restriction interval corresponding to the new first feature to be monitored as the initial effective restriction interval. Sequentially assess the suitability of the remaining features with the current effective restriction interval, updating the interval or retaining the monitoring status, until the current round of feature screening is completed and the number of rounds is recorded. Repeat the above iterative screening process, updating the list of features to be monitored and the effective restriction interval after each round, gradually progressing until all features to be monitored have been screened, and record the total number of rounds of the entire screening process.

[0030] Step Six: After each round of feature selection, record the actual time taken from start to finish for that round of filtering. This will serve as a reference for subsequent time estimations. When a new user selects a feature, combine the previously recorded total number of filtering rounds with the reference time for each round, fully considering real-time performance differences of the device, accurately calculate the estimated total time for this test, and inform the current user to help them plan their time accordingly. Simultaneously, based on the estimated time and current test progress, provide a clear waiting time forecast for the next user waiting to use the service, improving service transparency and user experience.

[0031] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary sensing device embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for testing the performance of equipment applied to a vital signs cabin, characterized in that: The method includes the following steps: S1. Collect the status data and monitoring characteristics of the life characteristic chamber, preprocess and normalize them to obtain the status characteristics and monitoring characteristics of the life characteristic chamber, and establish a historical database of the life characteristic chamber. S2. Analyze effective monitoring features, obtain the state features corresponding to the effective monitoring features, establish a monitoring feature analysis database, and establish restriction intervals for the monitoring features; S3. Integrate restricted intervals and establish a restricted interval database; S4. After the user confirms the feature to be monitored, call the restriction interval database to perform the first monitoring feature judgment and select the first monitoring feature from the features to be monitored. S5. Further select the remaining features to be monitored until all features to be monitored have been selected, and record the total number of selections. S6. Provide users with a waiting time forecast based on the total number of selections and the reference selection time.

2. The device performance testing method applied to a vital signs cabin according to claim 1, characterized in that: In step S1, after authorization, for any type of life characteristic chamber, status data of the life characteristic chamber is collected. After preprocessing and normalization of the status data of the life characteristic chamber, the status characteristics of the life characteristic chamber are obtained. The number of status characteristics is N. After authorization, the monitoring data of the life characteristic chamber is obtained. After preprocessing and normalization, the monitoring data of the life characteristic chamber is obtained. M monitoring characteristics of the life characteristic chamber are obtained. M is the preset number of monitoring characteristics. Then, a historical database of life characteristic chambers is established. The historical database of life characteristic chambers includes: the status characteristic group of the life characteristic chamber and the monitoring results of M monitoring characteristics when life characteristic monitoring is carried out in the life characteristic chamber. The monitoring result of the m-th monitoring characteristic is either the m-th monitoring characteristic is effective or the m-th monitoring characteristic is ineffective. m=1,2,…,M.

3. The method for testing the performance of equipment applied to a vital signs cabin according to claim 2, characterized in that: In step S2, for the m-th monitoring feature, after monitoring the life features in the life feature chamber, the value of the m-th monitoring feature is obtained as A. If (A-A0) / A0>a, it is determined that the monitoring result of the m-th monitoring feature is invalid. Otherwise, the monitoring result of the m-th monitoring feature is determined to be valid. A0 is the preset standard value of the m-th monitoring feature, and a is the preset deviation threshold of the m-th monitoring feature. When the m-th monitoring feature is valid, the status feature of the life feature monitoring in this life feature cabin is stored in the m-th monitoring feature analysis database. When the m-th monitoring feature is invalid, the status feature of the life feature monitoring in this life feature cabin is ignored. Substitute m=1,2,…,M one by one to establish the M-th monitoring feature analysis database.

4. The device performance testing method applied to a vital signs cabin according to claim 3, characterized in that: The database for analyzing the m-th monitoring feature is invoked. This database includes D groups of state features. The analysis focuses on the n-th state feature, where n = 1, 2, ..., N. The n-th state feature of the D group of state features is {E}. 1_n_m E 2_n_m ,…,E d_n_m ,…,E D_n_m }, where E d_n_m Let n be the nth state feature of the dth state feature, and then calculate the influence coefficient F of the nth state feature on the mth monitoring feature. n_m : ； Where E0 is the maximum value of the nth state feature of group D, when F n_m If F0 > 0, it is determined that the change of the nth state feature has an impact on the mth monitoring feature; otherwise, it is determined that the change of the nth state feature has no impact on the mth monitoring feature, where F0 is a preset threshold for the influence coefficient of the nth state feature on the mth monitoring feature, and thus the restriction interval G of the mth monitoring feature on the nth state feature is obtained. m_n When it is determined that the change of the nth state feature has an impact on the mth monitoring feature, the Z_score method is used to evaluate the nth state feature {E} of the D group of state features. 1_n_m E 2_n_m ,…,E d_n_m ,…,E D_n_m Anomaly elimination is performed to obtain the nth decontamination state feature set. The minimum value of the nth decontamination state feature set is selected as the constraint interval G. m_n The lower bound is determined by selecting the maximum value of the nth decontamination state feature set as the constraint interval G. m_n The upper limit; when it is determined that the change of the nth state feature has no impact on the mth monitoring feature, the limit interval G is set. m_n It is the set of real numbers.

5. The device performance testing method applied to a vital signs cabin according to claim 4, characterized in that: In step S3, each of the m=1,2,…,M terms is substituted to obtain the constraint interval {G} of the M monitoring features on the nth state feature. 1_n G 2_n ,…,G m_n ,…,G M_n }, and then obtain the restriction interval of M monitoring features on any state feature. Substitute them one by one into n=1,2,…,N to obtain the restriction interval {g} of the m-th monitoring feature on N state features. m_1 ,g m_2 ,…,g m_n ,…,g m_N }, thereby obtaining the restriction interval of any monitoring feature on N state features, and then establishing a restriction interval database.

6. The method for testing the performance of equipment applied to a vital signs cabin according to claim 5, characterized in that: In step S4, the restriction interval database is invoked. When the user selects X monitoring features for vital signs cabin monitoring, the user-selected monitoring features are categorized as features to be monitored, and the features to be monitored are {H1, H2, ..., H...}. x ,…,H X }, where H x For the x-th feature to be monitored, the feature H1 to be monitored is analyzed. The restriction interval of the feature H1 to be monitored on the n-th state feature is selected as the effective restriction interval of the n-th state feature. Then, the effective restriction intervals of N state features are obtained, and the monitoring feature H1 is classified as the first monitoring feature. Analyze the feature H2 to be monitored. If the restriction intervals of the feature H2 for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment is adequate. Calculate the intersection of the restriction interval of the feature H2 for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature H2 to be monitored as the first monitoring feature. Otherwise, it is determined that the life signs cabin equipment is inadequate. Keep the effective restriction intervals of the N state features unchanged and keep the feature H2 as a monitoring feature. Analyze the feature H3 to be monitored. If the restriction intervals of the feature H3 for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment is adequate. Calculate the intersection of the restriction interval of the feature H3 for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature H3 to be monitored as the first monitoring feature. Otherwise, it is determined that the life signs cabin equipment is inadequate. Keep the effective restriction intervals of the N state features unchanged and keep the feature H3 as a monitoring feature. To monitor the feature {H1,H2,…,H} x ,…,H X The analysis yields the first monitoring feature and the remaining features to be monitored, thus completing the selection of the first monitoring feature.

7. The method for testing the performance of equipment applied to a vital signs cabin according to claim 6, characterized in that: In step S5, after selecting the first monitoring feature, the second monitoring feature is selected, and the monitoring features are renumbered as {J1, J2, ..., J...}. y ,…,J Y }, where Y is the number of features to be monitored after the first selection of monitoring features, and J y To complete the selection of the y-th monitoring feature after the first monitoring feature selection, the monitoring feature J1 is analyzed. The restriction interval of the monitoring feature J1 on the n-th state feature is selected as the effective restriction interval of the n-th state feature, and then the effective restriction intervals of N state features are obtained. The monitoring feature J1 is classified as the second monitoring feature. Analyze the feature J2 to be monitored. If the restriction intervals of the feature J2 to be monitored for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment performance is sufficient. Calculate the intersection of the restriction interval of the feature J2 to be monitored for the nth state feature with the effective restriction interval of the nth state feature, and replace the effective restriction interval of the nth state feature with the intersection. Substitute each of n=1,2,…,N into the system to update the effective restriction intervals of the N state features. At the same time, classify the feature J2 to be monitored as the second monitoring feature. Otherwise, it is determined that the life signs cabin equipment performance is insufficient. Keep the effective restriction intervals of the N state features unchanged and keep the feature J2 to be monitored as a feature to be monitored. Analyze the feature J3 to be monitored. If the restriction intervals of the feature J3 to be monitored for all N state features intersect with the effective restriction intervals of the N state features, it is determined that the life signs cabin equipment performance is sufficient. Calculate the intersection of the restriction interval of the feature J3 to be monitored for the nth state feature and the effective restriction interval of the nth state feature. Replace the effective restriction interval of the nth state feature with the intersection. Substitute each value into n=1,2,…,N to update the effective restriction intervals of the N state features. At the same time, classify the feature J3 to be monitored as the second monitoring feature. Otherwise, it is determined that the life signs cabin equipment performance is insufficient. Keep the effective restriction intervals of the N state features unchanged and keep the feature J3 to be monitored as a feature to be monitored. To monitor the feature {J1,J2,…,J y ,…,J Y The analysis is performed to obtain the second monitoring feature and the remaining features to be monitored. The selection of the second monitoring feature is completed, and then the selection of the next monitoring feature is carried out until all the features to be monitored are selected. The number of times the monitoring feature is selected is recorded as Z.

8. The method for testing the performance of equipment applied to a vital signs cabin according to claim 6, characterized in that: In step S6, the time taken for a single monitoring feature selection with the current time point as the endpoint is recorded as the selection reference time W. When the user selects a monitoring feature for vital signs cabin monitoring, the total time taken is prompted to the user considering the equipment performance. The total time taken is prompted to the user as Z*W, and the waiting time is predicted for the next user.

9. A device performance testing system applied to a vital signs cabin, wherein the system is applied to the device performance testing method for a vital signs cabin as described in any one of claims 1-8, characterized in that: The system includes: a data acquisition and historical database construction module, a monitoring feature analysis and delimitation module, a restriction interval integration and database entry module, a confirmation feature initial selection module, a remaining feature successive selection module, and a number of times consumption time prediction module. The data acquisition and historical database construction module is used to collect the status data and monitoring characteristics of the life characteristic cabin, and after preprocessing and normalization, obtain the status characteristics and monitoring characteristics of the life characteristic cabin, and establish a historical database of the life characteristic cabin. The monitoring feature analysis and delimitation module is used to analyze effective monitoring features, obtain state features corresponding to the effective monitoring features, establish a monitoring feature analysis database, and establish restriction intervals for monitoring features. The restricted interval integration and database entry module is used to integrate restricted intervals and establish a restricted interval database. The confirmation feature initial selection module is used to call the restriction interval database after the user confirms the feature to be monitored, perform the initial monitoring feature judgment, and select the first monitoring feature from the features to be monitored; The remaining feature successive selection module is used to further select the remaining features to be monitored until all features to be monitored are selected, and the total number of selections is recorded. The "Waiting Time Prediction Module" is used to provide users with a waiting time prediction based on the selected total number of attempts and the selected reference waiting time.

Images