Limited space operation safety monitoring method and system based on multi-sign parameter intelligent judgment, computer equipment and storage medium

Abstract

The invention relates to a limited space operation safety monitoring method based on multi-sign parameter intelligent judgment, which comprises the following steps of: training a single-class support vector machine model by utilizing historical data, and establishing a normal physiological state multi-dimensional reference model under each operation content; the method comprises the following steps: acquiring current operation content in a limited space, determining a vital sign parameter set needing to be monitored, and collecting real-time vital sign data of an operator through a user terminal; calculating a comprehensive abnormal score AS of the real-time vital sign data, and when the comprehensive abnormal score AS exceeds a dynamic threshold value delta, marking the data as comprehensive abnormal data; marking the vital sign parameter with the maximum contribution degree absolute value in the abnormal parameters as a key vital sign; and sending alarm information to a monitoring terminal, wherein the alarm information comprises the identifier of the key vital sign. By comprehensively analyzing the real-time vital signs and comparing the real-time vital signs with the dynamic threshold value, the accuracy of abnormal person recognition is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer technology, in particular to a limited space operation safety monitoring method and system based on multi-signature parameter intelligent adjudication, a computer device and a storage medium. BACKGROUND

[0002] In the field of industrial production, limited space operation is always a high-risk link of safety accidents. There are a large number of limited spaces such as cabins, storage tanks, reaction kettles, underground pipelines and box girders in the industries of shipbuilding, port machinery manufacturing and petrochemical industry. When the operating personnel perform various types of operations such as welding, grinding, spraying, cleaning and electrical installation in these limited spaces, they face extremely complex and dangerous working environments. These limited spaces are usually poorly ventilated, and dangerous substances such as welding dust, organic solvent vapor and toxic and harmful gases are easily accumulated, and there are also harsh environmental conditions such as high temperature, high humidity and oxygen deficiency, which pose a serious threat to the safety of operating personnel.

[0003] In recent years, with the development of Internet of Things and wearable device technology, some schemes for safety monitoring of limited space personnel operation based on vital signs have emerged, but these schemes still have many limitations: 1. Single function defect: Many industrial safety monitoring devices only have single parameter monitoring function (such as only monitoring heart rate or blood oxygen), which cannot comprehensively and multi-dimensionally reflect the health status of operating personnel, and the risk of missing reports is high. For example, only heart rate abnormalities may not be able to distinguish between normal operation fatigue and pre-disease symptoms.

[0004] 2. Simple and rough alarm logic: The existing technology mostly adopts a fixed threshold alarm mechanism (such as alarm when heart rate exceeds 140 times / minute), which is a rigid logic that cannot adapt to different work intensities and individual differences (such as age and physical fitness). When the work intensity is high, the heart rate naturally increases, and simple threshold alarm will lead to frequent false alarms; and individual differences make the unified alarm threshold lack of scientificity and practicality.

[0005] 3. Existing schemes usually only upload monitoring data to the monitoring center, rely on manual judgment and decision-making, have slow response speed and are greatly affected by the state of the monitored personnel. There is a lack of automatic intelligent adjudication system based on multi-dimensional data fusion, which cannot realize early warning and rapid response.

[0006] 4. The alarm threshold is usually fixed and cannot be dynamically adjusted according to the specific operation content (such as high-intensity handling and low-intensity inspection), resulting in a significant reduction in monitoring accuracy and applicability. SUMMARY

[0007] The purpose of the present application is to provide a limited space operation safety monitoring method based on multi-signature parameter intelligent adjudication to solve the problems raised in the background.

[0008] The application provides a limited space operation safety monitoring method based on multi-sign parameter intelligent judgment, comprising: training a single-class support vector machine model with historical data to establish a normal physiological state multi-dimensional reference model under each operation content; acquiring the current operation content of the limited space, determining a set of vital sign parameters to be monitored according to the normal physiological state multi-dimensional reference model corresponding to the current operation content, and collecting real-time vital sign data of the operation personnel through a user terminal; calculating a comprehensive abnormal score AS of the real-time vital sign data, and marking the real-time vital sign data as comprehensive abnormal data when the comprehensive abnormal score AS exceeds a dynamic threshold δ; obtaining the contribution degree of each vital sign parameter of the comprehensive abnormal data through an explainable analysis model, and marking the vital sign parameter as an abnormal parameter if the contribution degree of the vital sign parameter is positive and the absolute value exceeds a preset reliability threshold η; marking the vital sign parameter with the largest contribution degree absolute value in each abnormal parameter as a key vital sign; sending an alarm information to a monitoring terminal, wherein the alarm information contains the identification of the key vital sign.

[0009] In a possible implementation, the dynamic threshold δ is obtained in the following manner: collecting a historical vital sign data set under a specific operation content; calculating the decision boundary offset of the single-class support vector machine model under the preset confidence level through cross-validation; taking the maximum offset as the dynamic threshold δ of the operation content.

[0010] In a possible implementation, the contribution degree of each vital sign parameter of the comprehensive abnormal data comprises: calculating the marginal influence of each vital sign parameter on the comprehensive abnormal score AS by using a SHAP value assignment rule; quantifying the marginal influence as a contribution degree value.

[0011] In a possible implementation, after sending the alarm information, the method further comprises: acquiring real-time location information of the abnormal operation personnel, and matching the limited space where the abnormal operation personnel is located; sending an audible and visual alarm instruction to the terminal of the limited space, synchronously lighting an alarm lamp and starting a voice warning.

[0012] In a possible implementation, the calculation of the comprehensive abnormal score AS of the real-time vital sign data comprises: mapping the real-time vital sign data to a high-dimensional feature space; calculating a spatial distance of the real-time data point from a decision boundary of the one-class support vector machine model; normalizing the spatial distance into an integrated abnormality score AS in a range of 0-100.

[0013] In a possible implementation, the training of the one-class support vector machine model using historical data comprises: performing segmented cleaning on the historical data to remove data during sensor interruption periods and transient interference data, updating the training set using a sliding window mechanism, inputting the updated training set into the one-class support vector machine model for training, verifying a model health coverage index, and deploying the model when the index is greater than an index threshold.

[0014] A second aspect of the present application provides a limited space operation safety monitoring system based on intelligent decision of multiple vital sign parameters, comprising: a user terminal: worn by an operator, integrated with a vital sign sensor and a communication module, and configured to collect and upload vital sign data in real time; a server end, comprising: a data analysis module: configured to train a one-class support vector machine model using historical data, and establish a normal physiological state multi-dimensional reference model under each operation content; acquire a current operation content of a limited space, determine a set of vital sign parameters to be monitored according to a normal physiological state multi-dimensional reference model corresponding to the current operation content, and collect real-time vital sign data of an operator through the user terminal; an intelligent decision module: configured to calculate an integrated abnormality score AS of real-time vital sign data, and mark the real-time vital sign data as integrated abnormality data when the integrated abnormality score AS exceeds a dynamic threshold δ; acquire a contribution degree of each vital sign parameter of the integrated abnormality data through an explainable analysis model, and mark a vital sign parameter as an abnormal parameter if the contribution degree of the vital sign parameter is positive and the absolute value of the contribution degree exceeds a preset reliability threshold η; and mark a vital sign parameter with the largest contribution degree absolute value among the abnormal parameters as a key vital sign; an alarm issuing module: configured to send alarm information to a monitoring terminal, the alarm information containing an identifier of the key vital sign; a monitoring terminal, comprising: an audible and visual alarm: deployed at an entrance of a limited space, and configured to start audible and visual warning in response to an alarm instruction; a management module: configured to receive alarm information and analysis results of the key vital sign.

[0015] In a possible implementation, the server end further comprises: a spatial positioning module: configured to determine a space where an abnormal person is located by comparing GPS coordinates of the user terminal with a limited space position database.

[0016] The third aspect of the present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to realize the method for monitoring safety of limited space operation based on intelligent decision of multi-sign parameters according to the first aspect of the present application.

[0017] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to realize the method for monitoring safety of limited space operation based on intelligent decision of multi-sign parameters according to the first aspect of the present application.

[0018] Compared with the prior art, the present application has the following beneficial effects: 1. By adopting comprehensive analysis of real-time vital signs and comparing with dynamic threshold, the accuracy of abnormal personnel identification is effectively improved; 2. By effectively processing historical data through a machine learning model, the vital sign conditions of personnel working in a limited space are more accurately evaluated. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 Fig. 1 is a flowchart of the method for monitoring safety of limited space operation based on intelligent decision of multi-sign parameters according to the present application; Figure 2 Fig. 2 is a schematic diagram of the system for monitoring safety of limited space operation based on intelligent decision of multi-sign parameters according to the present application; Figure 3 Fig. 3 is a schematic diagram of the computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be described clearly and completely below in combination with the drawings of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0021] It should be noted that the serial numbers of components in the embodiments of the present application, such as "first", "second", etc., are only used to distinguish the described objects, and do not have any sequence or technical meaning.

[0022] The following will be described in combination with Figure 1 A method for monitoring safety of limited space operation based on intelligent decision of multi-sign parameters according to the present application is described.

[0023] ​A limited space operation safety monitoring method based on multi-sign parameter intelligent decision, comprising: S1, training a single-class support vector machine model by using historical data to establish a normal physiological state multi-dimensional reference model under each operation content; In the present application, the historical vital sign data of a large number of operation personnel forms a multi-dimensional data set X = {x i | i=1, 2,..., N} wherein each data point x i = [HR i , SpO 2i , T i ] and HR i , SpO 2i , T i represent heart rate, blood oxygen and body temperature readings of a certain minute respectively. The core idea of the single-class support vector machine model is to find a smallest hypersphere that can surround all (or most) normal data points. In the high-dimensional feature space mapped by the kernel function (such as Gaussian RBF kernel), this hypersphere is actually a decision boundary When training the single-class support vector machine model by using historical data, first, segment cleaning is performed on the historical data to remove sensor interruption period data and transient interference data, then a sliding window mechanism is used to update the training set, such as retaining the data of the last 30 days, triggering incremental training of the model when the daily new data volume exceeds 100, inputting the updated training set into the single-class support vector machine model for training, verifying the model health coverage rate index, and finally deploying the model when the index is greater than the index threshold.

[0024] S2, obtaining the current operation content of the limited space, determining the vital sign parameter set to be monitored according to the normal physiological state multi-dimensional reference model corresponding to the current operation content, and collecting the real-time vital sign data of the operation personnel through the user terminal; Specifically, in the present application, the limited space mainly refers to the scene of shipbuilding, container welding and other operations in the cabin. In these scenes, there are multiple limited spaces that need to be operated, and each limited space can be numbered. For example, cabin No. 1, cabin No. 2, etc. Different limited spaces have different operations, such as welding in cabin No. 1 and spraying in cabin No. 2. The operation temperature of cabin No. 1 will be higher than that of cabin No. 2, and accordingly the breathing rate and other vital signs of the personnel working in cabin No. 1 will be higher than those of the personnel working in cabin No. 2. The operation content of different limited spaces is different.

[0025] The current operation content can be automatically imported from the enterprise production management system (MES), which includes: Job space number (e.g. "T-203 Tank"), job type code (e.g. "WELD" for welding, "CLEAN" for cleaning), estimated job duration (e.g. "4.5 hours"), etc.

[0026] For different job content, the corresponding normal physiological state multi-dimensional reference model has different vital sign parameters.

[0027] For example, the welding job model focuses on heart rate fluctuation range and blood oxygen saturation baseline, while the cleaning job model focuses on body temperature change gradient and respiratory rate pattern.

[0028] S3, calculate the comprehensive anomaly score AS of real-time vital sign data, and mark as comprehensive abnormal data when the comprehensive anomaly score AS exceeds the dynamic threshold δ; The comprehensive anomaly score AS can be calculated as follows: for a new real-time data point x_new = [HR_new, SpO2_new, T_new] (taking heart rate, blood oxygen, and body temperature as an example), the model calculates the distance from the decision boundary (in the feature space). This distance is converted into a comprehensive anomaly score AS. The formula is: AS(x_new) = ∮(Φ(x_new), center), where Φ is the kernel function mapping, center is the center of the hyper-sphere in the high-dimensional feature space, and ∮ is the distance function. The larger the AS value, the more the data point deviates from the normal reference model.

[0029] In this step, the dynamic threshold δ can be obtained as follows: collect the historical vital sign data set X = {x i i=1,2,...,N} under a certain job content, where x i is a multi-dimensional vector containing heart rate, blood oxygen, and body temperature; Calculate the decision boundary offset of the one-class support vector machine under the confidence level α through cross-validation, and take the maximum offset as the dynamic threshold δ, which satisfies the relationship: δ=max(distance(Φ(x i ), decision_boundary)), i=1,2,...,N where Φ(x i ) is the Gaussian RBF kernel function mapping.

[0030] When AS(x_new) > δ, it is determined that the current minute's comprehensive physiological state is "abnormal".

[0031] S4, obtaining the contribution degree of each vital sign parameter of the comprehensive abnormal data through the explainable analysis model, if there is a vital sign parameter with a positive contribution degree and an absolute value exceeding a preset reliability threshold η, marking the vital sign parameter as an abnormal parameter; Wherein, when the normal physiological state multi-dimensional reference model judges AS(x_new) > δ (i.e. abnormality occurs), the explainable analysis model such as SHAP (SHapley Additive exPlanations) is analyzed.

[0032] According to the SHAP value allocation rule, the marginal contribution of each vital sign parameter to the comprehensive abnormal score AS is obtained, and the marginal contribution is the contribution degree φ i . The SHAP value is based on game theory, which can fairly allocate the contribution degree of each input feature (heart rate, blood oxygen and body temperature) to this abnormal decision (i.e. high AS value). It calculates a SHAP value (φ_HR, φ_SpO2, φ_T) for each vital sign parameter.

[0033] In the formula, F is the full set of feature parameters, S is the feature subset, and f is the output function of the single-class support vector machine model.

[0034] S5, marking the vital sign parameter with the largest contribution degree absolute value in each abnormal parameter as the key vital sign.

[0035] Only when AS > δ and at least one of the contribution degrees of all positive contribution features exceeds its preset contribution degree threshold η, the final alarm is triggered. This avoids the alarm due to slight and meaningless abnormal fluctuations. At the same time of triggering the alarm, the vital sign parameter with the largest contribution degree absolute value is dynamically determined as the "key vital sign" of this abnormality.

[0036] S6, sending alarm information to the monitoring terminal, wherein the alarm information includes the identification of the key vital sign.

[0037] After sending the alarm information to the monitoring terminal, the method further comprises: acquiring the real-time limited space where the abnormal worker is located, and sending a lighting instruction of an alarm lamp to the terminal of the real-time limited space. An alarm lamp is installed on each limited space, which will light up and emit an alarm sound to attract the attention of monitoring personnel after receiving the lighting instruction. In the present application, the alarm lamp can be a 4G alarm lamp, which has three modes of sound, light and voice. When determining the real-time limited space where the abnormal worker is located, the following methods can be used: The system acquires the terminal location information of the worker experiencing the anomaly, compares this information with the spatial location information of each of the confined spaces, and determines the real-time confined space where the worker is located based on the comparison results. GPS, BeiDou, or other satellite positioning methods can be used for location comparison.

[0038] A second aspect of the present invention provides a confined space operation safety monitoring system based on intelligent adjudication of multiple vital signs parameters, such as... Figure 2 As shown, it includes: User Terminal 10: A smart bracelet or smartwatch worn by the worker, equipped with a built-in heart rate sensor, blood oxygen sensor, body temperature sensor, and 4G / 5G communication module. It is used to collect the worker's heart rate (HR), blood oxygen saturation (SpO2), and body surface temperature (T) data in real time, and upload the vital signs data to the server once per minute. Server 20 serves as a cloud-based data processing and decision-making center, comprising: Data Analysis Module 21: Used to train a single-class support vector machine model using historical data, establish a multi-dimensional benchmark model of normal physiological state under various work contents; obtain the current work contents in a limited space, determine the set of vital sign parameters to be monitored based on the multi-dimensional benchmark model of normal physiological state corresponding to the current work contents, and collect real-time vital sign data of workers through user terminals; Intelligent adjudication module 22: Calculates the comprehensive anomaly score AS of real-time vital sign data. When the comprehensive anomaly score AS exceeds the dynamic threshold δ, it is marked as comprehensive anomaly data. The contribution of each vital sign parameter of the comprehensive anomaly data is obtained through the interpretability analysis model. If there is a vital sign parameter with a positive contribution and an absolute value exceeding the preset reliability threshold η, the vital sign parameter is marked as an anomaly parameter. The vital sign parameter with the largest absolute value of contribution among the anomaly parameters is marked as a critical vital sign. Alarm publishing module 23: used to send alarm information to the monitoring terminal, wherein the alarm information includes the identifier of the key vital signs; Spatial positioning module 24: By comparing the user terminal's GPS coordinates with a limited spatial location database, it determines the space where the abnormal person is located.

[0039] Monitoring terminal 30, which includes: Audible and visual alarm 31: Deployed at the entrance of a confined space, it activates audible and visual warnings in response to alarm commands; Management module 32: Receives alarm information and analysis results of key vital signs.

[0040] In one embodiment, such as Figure 3As shown, a computer device 40 applied to a management end is provided, including a memory 42, a processor 41 and a computer program 43 stored in the memory 42 and executable on the processor 41, the processor 41 implements the steps in the data processing method of the above embodiment when executing the computer program 43, for the sake of brevity, details are not repeated here. Alternatively, the processor 41 implements the functions of each module in the above embodiment of the limited space operation safety monitoring device based on multi-signature parameter intelligent decision when executing the computer program 43, for the sake of brevity, details are not repeated here.

[0041] In one embodiment, a readable storage medium is provided, which stores a computer program 43, the computer program 43 is executed by the processor 41 to implement the steps in the data processing method of the above embodiment, for the sake of brevity, details are not repeated here. Alternatively, the processor 41 implements the functions of each module in the above embodiment of the data processing device when executing the computer program 43, for the sake of brevity, details are not repeated here.

[0042] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments of each method. Among them, any reference to memory, storage, database or other medium used in each embodiment of the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM) and the like.

[0043] ​Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit, module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional modules, sub-modules and units according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0044] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A limited space operation safety monitoring method based on multi-sign parameter intelligent decision, characterized in that, Comprise: Train a one-class support vector machine model using historical data to establish a multi-dimensional baseline model of normal physiological state under each work content; Obtain the current work content in a limited space, determine the set of vital sign parameters to be monitored according to the multi-dimensional baseline model of normal physiological state corresponding to the current work content, and collect real-time vital sign data of the worker through the user terminal; Calculate the comprehensive abnormal score AS of the real-time vital sign data, and mark it as comprehensive abnormal data when the comprehensive abnormal score AS exceeds the dynamic threshold δ; Obtain the contribution degree of each vital sign parameter of the comprehensive abnormal data through an interpretable analysis model, and mark the vital sign parameter as an abnormal parameter if there is a vital sign parameter with a positive contribution degree and an absolute value exceeding a preset reliability threshold η; Mark the vital sign parameter with the largest contribution degree absolute value in each abnormal parameter as the key vital sign; Send an alarm information to the monitoring terminal, and the alarm information contains the identification of the key vital sign.

2. The multi-signature parameter-based intelligent decision-making limited space operation safety monitoring method according to claim 1, characterized in that, The dynamic threshold δ is obtained in the following way: Collect a historical vital sign data set under a specific work content; Calculate the decision boundary offset of the one-class support vector machine model under the preset confidence level through cross-validation; Take the maximum offset as the dynamic threshold δ of the work content. 3.The method of claim 2, wherein, The contribution degree of each vital sign parameter of the comprehensive abnormal data includes: Calculate the marginal influence of each vital sign parameter on the comprehensive abnormal score AS using the SHAP value assignment rule; Quantify the marginal influence as a contribution degree value.

4. The multi-signature parameter-based intelligent decision-making limited space operation safety monitoring method according to claim 1, characterized in that, After sending the alarm information, it also includes: Obtain the real-time location information of the abnormal worker, match the limited space where he is located; Send a sound and light alarm instruction to the terminal of the limited space, synchronously light up the alarm lamp and start the voice warning.

5. The method for safety monitoring of limited space operation based on intelligent multi-sign parameter judgment according to claim 2, characterized in that, The calculation of the comprehensive abnormal score AS of the real-time vital sign data includes: Map the real-time vital sign data to a high-dimensional feature space; Calculate the spatial distance between the real-time data point and the decision boundary of the one-class support vector machine model; Normalize the spatial distance to a comprehensive abnormal score AS in the range of 0-100.

6. The multi-signature parameter-based intelligent decision-making limited space operation safety monitoring method according to claim 1, characterized in that, The one-class support vector machine model trained using historical data includes: Perform segmented cleaning on historical data, remove sensor interruption period data and transient interference data, update the training set using a sliding window mechanism, input the updated training set to the one-class support vector machine model for training, and verify the model health coverage rate index. When the index is greater than the index threshold, deploy the model.

7. A limited space work safety monitoring system based on multi-vital sign parameter intelligent decision, comprising: User terminal: worn on the worker, integrated with vital sign sensor and communication module, real-time collection and uploading of vital sign data; Server side, comprising: Data analysis module: for training a one-class support vector machine model using historical data to establish a multi-dimensional baseline model of normal physiological state under each work content; obtain the current work content in a limited space, determine the set of vital sign parameters to be monitored according to the multi-dimensional baseline model of normal physiological state corresponding to the current work content, and collect real-time vital sign data of the worker through the user terminal; The intelligent adjudication module calculates a comprehensive abnormal score AS of real-time vital sign data, and marks the comprehensive abnormal score AS as comprehensive abnormal data when the comprehensive abnormal score AS exceeds a dynamic threshold δ; obtains a contribution degree of each vital sign parameter of the comprehensive abnormal data through an explainable analysis model, and marks the vital sign parameter as an abnormal parameter if there is a vital sign parameter with a positive contribution degree and an absolute value exceeding a preset reliability threshold η; and marks a vital sign parameter with the largest contribution degree absolute value among each abnormal parameter as a key vital sign; The alarm issuing module is configured to send alarm information to the monitoring terminal, and the alarm information contains an identifier of the key vital sign; The monitoring terminal comprises: The audible and visual alarm is disposed at an entrance of the limited space, and starts audible and visual warning in response to an alarm instruction. The management module receives the alarm information and the analysis result of the key vital sign.

8. The multi-vital sign parameter intelligent adjudication-based limited space operation safety monitoring system according to claim 7, wherein the server end further comprises: The space positioning module determines the space where the abnormal personnel is located by comparing the GPS coordinates of the user terminal with a limited space position database.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the multi-vital sign parameter intelligent adjudication-based limited space operation safety monitoring method according to any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the multi-vital sign parameter intelligent adjudication-based limited space operation safety monitoring method according to any one of claims 1-6.

Images