An IoT intelligent monitoring system for port safety and health quarantine

Through the intelligent monitoring system of the Internet of Things, deep learning technology and sensors are used to collect data in real time, and detection and evaluation indexes are generated, which solves the problems of low efficiency and infection risk in traditional ports, and realizes automated and intelligent quarantine methods, improving port safety and hygiene. efficiency and safety.

CN118608032BActive Publication Date: 2024-11-12青岛国际旅行卫生保健中心
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411073766.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-12
Estimated Expiration
2044-08-07

AI Technical Summary

Technical Problem

Traditional port safety and health quarantine relies on manual operations, is inefficient and has the risk of infection, making it difficult to achieve real-time monitoring and rapid response, which may lead to the spread of disease and increase the risk of public health incidents and management costs.

Method used

Design an intelligent Internet of Things monitoring system for port safety and health quarantine, including data acquisition module, data preprocessing module, data analysis module, evaluation and early warning module and feedback module. Data is collected in real time through sensors and detection and evaluation model is established using deep learning technology. , generate the inspection and evaluation index of transported items, generate early warning strategies in a timely manner, conduct multiple matching verifications, and automatically adjust transportation conditions and notify relevant personnel.

Benefits of technology

It significantly improves the efficiency and safety of port quarantine, reduces the risk of infection, avoids the spread of disease epidemics, reduces management costs and complexity, and ensures port sanitation safety and operation efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118608032B_ABST
    Figure CN118608032B_ABST
Patent Text Reader

Abstract

The present invention discloses an Internet of Things intelligent monitoring system for port safety and health quarantine, which relates to the field of Internet of Things detection technology. When the system is in operation, the environment and status data of transported items are collected in real time through a sensor group. The detection and evaluation model established by deep learning technology can accurately identify potential risks in the transportation process, avoiding delays and errors that may be caused by manual operations. When the evaluation result reaches a preset threshold, an early warning strategy is generated in time and multiple matching verifications are performed, thereby avoiding the situation where an early warning is falsely triggered due to a one-time data fluctuation. Finally, through the response of a feedback module, the system can quickly adjust the transportation conditions and notify relevant personnel to intervene, and further accurately control abnormal areas through secondary evaluation, thereby significantly improving the efficiency and safety of port quarantine and reducing the infection risks of staff and surrounding personnel.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things detection, and in particular to an Internet of Things intelligent monitoring system for port safety and health quarantine. Background Art

[0002] In the traditional port safety and health quarantine process, the inspection of animals, plants and water bodies usually relies on manual operations. Workers need to personally check the health status of animals and plants and the quality of water bodies. This method has many disadvantages: first, manual inspection is inefficient and prone to omissions when faced with a large number of imported and exported items. Second, workers are at risk of contracting diseases during the inspection process, especially when they are not wearing protective equipment. In addition, even if protective equipment is worn, some diseases can be transmitted through the air and may still affect surrounding passengers and staff. Traditional quarantine methods are difficult to achieve real-time monitoring and rapid response, which may cause diseases to threaten public health before they are discovered.

[0003] The above-mentioned status quo and shortcomings are mainly due to the limitations of traditional quarantine methods. Manual operations cannot meet the efficiency and safety requirements of modern ports. When staff members directly contact high-risk animals, plants or water bodies without wearing protective equipment, the possibility of infection is greatly increased; and even with protective equipment, airborne diseases may still spread to surrounding personnel. Once the disease spreads, it will not only affect the health of relevant staff, but also pose a threat to passengers in the entire port area, increasing the risk of public health incidents. In addition, traditional quarantine methods have a delayed response. When abnormal situations are discovered, the disease may have spread, resulting in the need for large-scale emergency response and resource mobilization, which increases management costs and complexity. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an Internet of Things intelligent monitoring system for port safety and health quarantine, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an Internet of Things intelligent monitoring system for port safety and health quarantine, including a data acquisition module, a data preprocessing module, a data analysis module, an evaluation and early warning module and a feedback module;

[0006] The data acquisition module collects the detection information of the transported items in real time through the sensor group installed in the health and safety quarantine area, synchronously marks the timestamp and the unique mark of the transported items, and forms a transport collection data group;

[0007] The data preprocessing module preprocesses the transport collection data group, including data cleaning preprocessing, data normalization preprocessing and data storage, to form a processed transport data processing data group;

[0008] The data analysis module uses deep learning technology to establish a transport item detection and evaluation model for the transport processing data group, and obtains the transport item detection and evaluation index Jczs by training and fitting the transport item detection and evaluation model;

[0009] The evaluation and early warning module matches the preset transport item detection evaluation threshold P with the transport item detection evaluation index Jczs to obtain the transport item monitoring evaluation strategy plan;

[0010] The feedback module makes specific responses and notifications according to the contents of the transported items monitoring and evaluation strategy plan, including regulating the status of the transported items and notifying relevant security personnel, and simultaneously performing a secondary evaluation response to detect the abnormal control area, obtain the abnormal response control area plan, and notify and prompt the personnel in the area according to the contents of the abnormal response control area plan.

[0011] Preferably, the data acquisition module includes a sensor acquisition unit;

[0012] The sensor acquisition unit collects the detection information of the transported items in real time through the sensor group installed in the transport and inspection area of ​​animals, plants and water bodies, including the temperature, humidity, pH value, dissolved oxygen, harmful gas concentration, microbial concentration and bioelectric potential information of the transported items, and synchronously marks the timestamp, the unique mark of the transported items and the item type to form a transport collection data group;

[0013] Among them, the sensor group includes temperature sensors, humidity sensors, pH sensors, dissolved oxygen sensors, harmful gas sensors, microbial concentration sensors and biopotential sensors; the item types include animals and plants, water bodies, food and biological products.

[0014] Preferably, the data preprocessing module includes a data conversion unit and a data storage unit;

[0015] The data conversion unit preprocesses the transport collection data group, including data cleaning preprocessing and data normalization preprocessing, to form a processed transport data processing data group;

[0016] Among them, data cleaning preprocessing includes using smoothing methods to remove random noise in the data; using mean filling methods to fill missing values; using standard deviation methods to detect and correct outliers;

[0017] Data normalization processing includes minimum and maximum normalization and Z-score normalization methods to normalize the transportation collection data group after data cleaning and preprocessing;

[0018] The data storage unit stores data of the preprocessed transport data processing data group, wherein the data storage is performed by connecting to a database, and then obtaining a data table with the same transport item type as that in the transport data processing data group by writing a query SQL, and then writing an SQL insert statement to insert the transport data processing data group into the queried data table, and setting data access permissions at the same time.

[0019] Preferably, the data analysis module includes a modeling unit and a fitting unit;

[0020] The modeling unit analyzes and extracts the transport processing data group, obtains the temperature change rate TVR, the humidity fluctuation range HFR, the harmful gas concentration change HGCV and the microbial ratio change MBCV, and forms an input data set X={TVR, HFR, HGCV, MBCV}, and simultaneously inputs the input data set X as a training set, uses deep learning technology to establish a transport item detection and evaluation model, and trains the transport item detection and evaluation model to obtain an environmental anomaly factor EAF and a biological anomaly factor BAF;

[0021] The fitting unit obtains the transported goods detection evaluation index Jczs by fitting the environmental abnormality factor EAF and the biological abnormality factor BAF;

[0022] The transported goods detection evaluation index Jczs is obtained by the following calculation formula:

[0023] ;

[0024] Wherein, j1 and j2 represent the preset weight values ​​of environmental abnormality factor EAF and biological abnormality factor BAF respectively, and K represents the correction constant.

[0025] Preferably, the temperature change rate TVR is obtained by the following calculation formula:

[0026] ;

[0027] Where, T i represents the temperature value at the i-th time point, n represents the total number of acquisition time points, Indicates the time interval of the acquisition time points;

[0028] The humidity fluctuation range HFR is obtained by the following calculation formula:

[0029] ;

[0030] In the formula, represents the peak humidity value among the total number of acquisition time points n, It represents the humidity valley value among the total number of acquisition time points n;

[0031] The harmful gas concentration change HGCV is obtained by the following calculation formula:

[0032] ;

[0033] In the formula, Gi represents the concentration of harmful gases at the i-th time point, including carbon dioxide CO2, carbon monoxide CO, ammonia NH3, hydrogen sulfide H2S and volatile organic compounds VOCs;

[0034] The microbial ratio change MBCV is obtained by the following calculation formula:

[0035] ;

[0036] In the formula, Represents the proportion of microorganisms at the i-th time point, including fungi, parasites and bacteria, which is obtained by using the ATP bioluminescence method through the microbial concentration sensor. represents the mean value of the microbial proportion, represents the standard deviation of microbial concentration.

[0037] Preferably, the environmental anomaly factor EAF is obtained by the following calculation formula:

[0038] ;

[0039] In the formula, TVR represents the temperature change rate, HFR represents the humidity fluctuation range, and HGCV represents the change in harmful gas concentration. , and It represents the average of the temperature change rate TVR, humidity fluctuation range HFR, and harmful gas concentration change HGCV, and is obtained by filtering out the qualified transport item records from the data table queried by the transport item type.

[0040] Preferably, the biological abnormality factor BAF is obtained by the following calculation formula:

[0041] ;

[0042] In the formula, MBCV represents the change in microbial proportion, represents the mean value of the change in microbial proportion, represents the standard deviation of the variation in microbial proportions, Represents the standard deviation of the variation in microbial proportions.

[0043] Preferably, the evaluation and early warning module includes a matching unit and a strategy generation unit;

[0044] The matching unit matches the preset relevant information with the required comparison value, including matching the preset transported item detection evaluation threshold P with the transported item detection evaluation index Jczs to obtain a matching result;

[0045] The matching results are obtained through the following matching methods:

[0046] When the transported item detection evaluation index Jczs is less than the transported item detection evaluation threshold P, the detection result of the transported item is obtained as a qualified result;

[0047] When the transported item detection evaluation index Jczs ≥ the transported item detection evaluation threshold P, the detection result of the transported item is obtained as a warning result;

[0048] The strategy generation unit generates a transported item monitoring and evaluation strategy scheme according to a matching result obtained by matching a preset transported item detection and evaluation threshold value P with a transported item detection and evaluation index Jczs;

[0049] The transported goods monitoring and evaluation strategy is obtained by the following generation method:

[0050] When the matching result is a warning result, an item warning monitoring plan is generated, including stopping the transportation of items, closing the input and output ports of the conveyor belt, isolating and sealing the transported items, and disinfecting the transported items. A preset evacuation reminder is sent to personnel in the area transporting items, and the item abnormality monitoring plan is sent to the relevant inspection personnel's pending tasks and pinned to the top.

[0051] Preferably, the feedback module includes a control unit and a response detection unit;

[0052] The control unit makes specific responses and notifications according to the content of the transported item monitoring and evaluation strategy plan, including control of the transported item status and notification of relevant security personnel. The control includes marking the current transported item status abnormality on the interactive page and the conveyor belt monitoring screen. The notification includes preset prompt voice, internal communication software prompt and SMS notification;

[0053] When the content of the transported goods monitoring and evaluation strategy plan includes an early warning result, the response detection unit triggers a secondary evaluation response to detect the abnormal control area, obtains the abnormal response control area plan, and notifies and prompts the personnel in the area according to the content of the abnormal response control area plan;

[0054] The secondary evaluation response is obtained by the following formula:

[0055] ;

[0056] In the formula, represents the secondary assessment response index, represents the transport item detection evaluation index obtained by the rth evaluation, P represents the transport item detection evaluation threshold, represents an exponential function, when the condition is met, I=1, otherwise I=0, W represents the number of secondary evaluations performed within a fixed period, and K represents the number of times the detection result of the transported items that triggers the secondary evaluation is a warning result.

[0057] Preferably, the abnormal response control area plan is obtained in the following manner:

[0058] When the secondary evaluation response index ≥ Secondary response threshold E, obtain the control of the transport area range adjustment and the control of personnel entry prohibition in the transport area;

[0059] When the secondary evaluation response index <Secondary response threshold E, obtain the control of the transport items area and the isolation control of the personnel in the transport items area.

[0060] The present invention provides an Internet of Things intelligent monitoring system for port safety and health quarantine, which has the following beneficial effects:

[0061] (1) When the system is running, the sensor group collects the environmental and status data of the transported items in real time and performs standardized processing, providing a data basis for subsequent analysis. Secondly, the detection and evaluation model established using deep learning technology can accurately identify potential risks in the transportation process, avoiding delays and errors that may be caused by manual operations. When the evaluation result reaches the preset threshold, an early warning strategy is generated in a timely manner and multiple matching verifications are performed, thereby avoiding the false triggering of early warnings due to one-time data fluctuations. Finally, through the response of the feedback module, the system can quickly adjust the transportation conditions and notify relevant personnel to intervene. Further, through secondary evaluation, the abnormal areas are accurately controlled, which significantly improves the efficiency and safety of port quarantine, reduces the risk of infection for staff and surrounding personnel, and avoids the possible spread of diseases, thereby reducing the probability of quarantine anomalies in port safety and health. The automated and intelligent quarantine method can not only respond to emergencies in a timely manner, but also effectively reduce management costs and complexity, ensuring the health safety and operation efficiency of the port.

[0062] (2) Through the modeling unit, the key environmental and biological characteristics of temperature change rate TVR, humidity fluctuation range HFR, harmful gas concentration change HGCV and microbial ratio change MBCV are extracted to form an input data set, and the model is trained using deep learning technology to generate environmental anomaly factors EAF and biological anomaly factors BAF. After fitting these factors, the transport item detection evaluation index Jczs is calculated to effectively measure the overall status of the transported items. Through high integration and accuracy, it can comprehensively consider multiple environmental and biological parameters, and through rigorous calculation formulas and models, it can quickly identify potential abnormal conditions, thereby providing early warnings.

[0063] (3) By matching the transport item detection and evaluation threshold P with the transport item detection and evaluation index Jczs, the item status can be accurately judged and the corresponding monitoring and evaluation strategy can be generated. When the detection result triggers an early warning, the system immediately generates an abnormal monitoring plan for the item or an early warning monitoring plan, and performs multi-level regulation and notification through the feedback module to ensure that potential risks are handled in a timely manner. In particular, when multiple matching results are early warnings, the system will automatically start a secondary evaluation to obtain a more sophisticated abnormal control plan to avoid false triggering of early warnings due to single data fluctuations. Through multiple evaluations and automated regulation, the spread of safety hazards is effectively prevented, the health and safety of the port area is guaranteed, and the accuracy and timeliness of emergency response are significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 The present invention is a schematic diagram of a block diagram of an Internet of Things intelligent monitoring system for port safety and health quarantine. DETAILED DESCRIPTION

[0065] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0066] Example 1

[0067] The present invention provides an Internet of Things intelligent monitoring system for port safety and health quarantine. Figure 1 , including data acquisition module, data preprocessing module, data analysis module, evaluation and early warning module and feedback module;

[0068] The data acquisition module collects the detection information of the transported items in real time through the sensor group installed in the health and safety quarantine area, synchronously marks the timestamp and the unique mark of the transported items, and forms a transport collection data group;

[0069] The data preprocessing module preprocesses the transport collection data group, including data cleaning preprocessing, data normalization preprocessing and data storage, to form a processed transport data processing data group;

[0070] The data analysis module uses deep learning technology to establish a transport item detection and evaluation model for the transport processing data group, and obtains the transport item detection and evaluation index Jczs by training and fitting the transport item detection and evaluation model;

[0071] The evaluation and early warning module matches the preset transport item detection evaluation threshold P with the transport item detection evaluation index Jczs to obtain the transport item monitoring evaluation strategy plan;

[0072] The feedback module makes specific responses and notifications according to the contents of the transported items monitoring and evaluation strategy plan, including regulating the status of the transported items and notifying relevant security personnel, and simultaneously performing a secondary evaluation response to detect the abnormal control area, obtain the abnormal response control area plan, and notify and prompt the personnel in the area according to the contents of the abnormal response control area plan.

[0073] In this embodiment, the environmental and status data of the transported items are collected in real time through the sensor group and standardized, providing a data basis for subsequent analysis. Secondly, the detection and evaluation model established using deep learning technology can accurately identify potential risks in the transportation process, avoiding delays and errors that may be caused by manual operations. When the evaluation result reaches the preset threshold, an early warning strategy is generated in time and multiple matching verifications are performed, thereby avoiding the false triggering of early warnings due to one-time data fluctuations. Finally, through the response of the feedback module, the system can quickly adjust the transportation conditions and notify relevant personnel to intervene. Further, through secondary evaluation, the abnormal area is accurately controlled, which significantly improves the efficiency and safety of port quarantine, reduces the risk of infection for staff and surrounding personnel, and avoids the possible spread of diseases, thereby reducing the probability of quarantine anomalies in port safety and hygiene. The automated and intelligent quarantine method can not only respond to emergencies in a timely manner, but also effectively reduce management costs and complexity, ensuring the health safety and operation efficiency of the port.

[0074] Example 2

[0075] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes a sensor acquisition unit;

[0076] The sensor acquisition unit collects the detection information of the transported items in real time through the sensor group installed in the transport and inspection area of ​​animals, plants and water bodies, including the temperature, humidity, pH value, dissolved oxygen, harmful gas concentration, microbial concentration and bioelectric potential information of the transported items, and synchronously marks the timestamp, the unique mark of the transported items and the item type to form a transport collection data group;

[0077] Among them, the sensor group includes temperature sensors, humidity sensors, pH sensors, dissolved oxygen sensors, harmful gas sensors, microbial concentration sensors and biopotential sensors; the item types include animals and plants, water bodies, food and biological products.

[0078] The data preprocessing module includes a data conversion unit and a data storage unit;

[0079] The data conversion unit preprocesses the transport collection data group, including data cleaning preprocessing and data normalization preprocessing, to form a processed transport data processing data group;

[0080] Among them, data cleaning preprocessing includes using smoothing methods to remove random noise in the data; using mean filling methods to fill missing values; using standard deviation methods to detect and correct outliers;

[0081] Data normalization processing includes minimum and maximum normalization and Z-score normalization methods to normalize the transportation collection data group after data cleaning and preprocessing;

[0082] The data storage unit stores data of the preprocessed transport data processing data group, wherein the data storage is performed by connecting to a database, and then obtaining a data table with the same transport item type as that in the transport data processing data group by writing a query SQL, and then writing an SQL insert statement to insert the transport data processing data group into the queried data table, and setting data access permissions at the same time.

[0083] Example 3

[0084] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the data analysis module includes a modeling unit and a fitting unit;

[0085] The modeling unit analyzes and extracts the transport processing data group, obtains the temperature change rate TVR, the humidity fluctuation range HFR, the harmful gas concentration change HGCV and the microbial ratio change MBCV, and forms an input data set X={TVR, HFR, HGCV, MBCV}, and simultaneously inputs the input data set X as a training set, uses deep learning technology to establish a transport item detection and evaluation model, and trains the transport item detection and evaluation model to obtain an environmental anomaly factor EAF and a biological anomaly factor BAF;

[0086] The fitting unit obtains the transported goods detection evaluation index Jczs by fitting the environmental abnormality factor EAF and the biological abnormality factor BAF;

[0087] The transported goods detection evaluation index Jczs is obtained by the following calculation formula:

[0088] ;

[0089] Wherein, j1 and j2 represent the preset weight values ​​of environmental abnormality factor EAF and biological abnormality factor BAF respectively, and K represents the correction constant.

[0090] Among them, the temperature change rate TVR is obtained by the following calculation formula:

[0091] ;

[0092] Where, T i represents the temperature value at the i-th time point, n represents the total number of acquisition time points, Indicates the time interval of the acquisition time points;

[0093] The humidity fluctuation range HFR is obtained by the following calculation formula:

[0094] ;

[0095] In the formula, represents the peak humidity value among the total number of acquisition time points n, It represents the humidity valley value among the total number of acquisition time points n;

[0096] The harmful gas concentration change HGCV is obtained by the following calculation formula:

[0097] ;

[0098] In the formula, Gi represents the concentration of harmful gases at the i-th time point, including carbon dioxide CO2, carbon monoxide CO, ammonia NH3, hydrogen sulfide H2S and volatile organic compounds VOCs;

[0099] The microbial ratio change MBCV is obtained by the following calculation formula:

[0100] ;

[0101] In the formula, Represents the proportion of microorganisms at the i-th time point, including fungi, parasites and bacteria, which is obtained by using the ATP bioluminescence method through the microbial concentration sensor. represents the mean value of the microbial proportion, represents the standard deviation of microbial concentration.

[0102] The environmental anomaly factor EAF is obtained by the following calculation formula:

[0103] ;

[0104] In the formula, TVR represents the temperature change rate, HFR represents the humidity fluctuation range, and HGCV represents the change in harmful gas concentration. , and It represents the average of the temperature change rate TVR, humidity fluctuation range HFR, and harmful gas concentration change HGCV, and is obtained by filtering out the qualified transport item records from the data table queried by the transport item type.

[0105] The biological abnormality factor BAF is obtained by the following calculation formula:

[0106] ;

[0107] In the formula, MBCV represents the change in microbial proportion, represents the mean value of the change in microbial proportion, represents the standard deviation of the variation in microbial proportions, Represents the standard deviation of the variation in microbial proportions.

[0108] In this embodiment, the key environmental and biological characteristics of temperature change rate TVR, humidity fluctuation range HFR, harmful gas concentration change HGCV and microbial ratio change MBCV are extracted through the modeling unit to form an input data set, and the model is trained using deep learning technology to generate environmental anomaly factors EAF and biological anomaly factors BAF. After fitting these factors, the transported goods detection evaluation index Jczs is calculated to effectively measure the overall status of the transported goods. Through high integration and accuracy, it can comprehensively consider multiple environmental and biological parameters, and quickly identify potential abnormal conditions through rigorous calculation formulas and models, thereby providing early warnings.

[0109] Example 4

[0110] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the evaluation and early warning module includes a matching unit and a strategy generation unit;

[0111] The matching unit matches the preset relevant information with the required comparison value, including matching the preset transported item detection evaluation threshold P with the transported item detection evaluation index Jczs to obtain a matching result;

[0112] The matching results are obtained through the following matching methods:

[0113] When the transported item detection evaluation index Jczs is less than the transported item detection evaluation threshold P, the detection result of the transported item is obtained as a qualified result;

[0114] When the transported item detection evaluation index Jczs ≥ the transported item detection evaluation threshold P, the detection result of the transported item is obtained as a warning result;

[0115] The strategy generation unit generates a transported item monitoring and evaluation strategy scheme according to a matching result obtained by matching a preset transported item detection and evaluation threshold value P with a transported item detection and evaluation index Jczs;

[0116] The transported goods monitoring and evaluation strategy is obtained by the following generation method:

[0117] When the matching result is a warning result, an item warning monitoring plan is generated, including stopping the transportation of items, closing the input and output ports of the conveyor belt, isolating and sealing the transported items, and disinfecting the transported items. A preset evacuation reminder is sent to personnel in the area transporting items, and the item abnormality monitoring plan is sent to the relevant inspection personnel's pending tasks and pinned to the top.

[0118] The feedback module includes a control unit and a response detection unit;

[0119] The control unit makes specific responses and notifications according to the content of the transported item monitoring and evaluation strategy plan, including control of the transported item status and notification of relevant security personnel. The control includes marking the current transported item status abnormality on the interactive page and the conveyor belt monitoring screen. The notification includes preset prompt voice, internal communication software prompt and SMS notification;

[0120] When the content of the transported goods monitoring and evaluation strategy plan includes an early warning result, the response detection unit triggers a secondary evaluation response to detect the abnormal control area, obtains the abnormal response control area plan, and notifies and prompts the personnel in the area according to the content of the abnormal response control area plan;

[0121] The secondary evaluation response is obtained by the following formula:

[0122] ;

[0123] In the formula, represents the secondary assessment response index, represents the transport item detection evaluation index obtained by the rth evaluation, P represents the transport item detection evaluation threshold, represents an exponential function, when the condition is met, I=1, otherwise I=0, W represents the number of secondary evaluations performed within a fixed period, and K represents the number of times the detection result of the transported items that triggers the secondary evaluation is a warning result.

[0124] The abnormal response control area plan is obtained in the following ways:

[0125] When the secondary evaluation response index ≥ Secondary response threshold E, obtain the control of the transport area range adjustment and the control of personnel entry prohibition in the transport area;

[0126] When the secondary evaluation response index <Secondary response threshold E, obtain the control of the transport items area and the isolation control of the personnel in the transport items area.

[0127] In this embodiment, by matching the transport item detection and evaluation threshold P with the transport item detection and evaluation index Jczs, the item status is accurately judged and a corresponding monitoring and evaluation strategy is generated. When the detection result triggers an early warning, the system immediately generates an abnormal item monitoring plan or an early warning monitoring plan, and performs multi-level regulation and notification through the feedback module to ensure that potential risks are handled in a timely manner. In particular, when multiple matching results are early warnings, the system will automatically start a secondary evaluation to obtain a more sophisticated abnormal control plan to avoid false triggering of early warnings due to single data fluctuations. Through multiple evaluations and automated regulation, the spread of safety hazards is effectively prevented, the health and safety of the port area is guaranteed, and the accuracy and timeliness of emergency response are significantly improved.

[0128] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An IoT intelligent monitoring system for port safety and health quarantine, characterized by: It includes data acquisition module, data preprocessing module, data analysis module, evaluation and early warning module and feedback module; The data acquisition module collects the detection information of the transported items in real time through the sensor group installed in the health and safety quarantine area, synchronously marks the timestamp and the unique mark of the transported items, and forms a transport collection data group; The data preprocessing module preprocesses the transport collection data group, including data cleaning preprocessing, data normalization preprocessing and data storage, to form a processed transport data processing data group; The data analysis module uses deep learning technology to establish a transport item detection and evaluation model for the transport processing data group, and obtains the transport item detection and evaluation index Jczs by training and fitting the transport item detection and evaluation model; The data analysis module includes a modeling unit and a fitting unit; The modeling unit analyzes and extracts the transport processing data group, obtains the temperature change rate TVR, the humidity fluctuation range HFR, the harmful gas concentration change HGCV and the microbial ratio change MBCV, and forms an input data set X={TVR, HFR, HGCV, MBCV}, and simultaneously inputs the input data set X as a training set, uses deep learning technology to establish a transport item detection and evaluation model, and trains the transport item detection and evaluation model to obtain an environmental anomaly factor EAF and a biological anomaly factor BAF; The fitting unit obtains the transported goods detection evaluation index Jczs by fitting the environmental abnormality factor EAF and the biological abnormality factor BAF; The transported goods detection evaluation index Jczs is obtained by the following calculation formula: ; In the formula, j1 and j2 represent the preset weight values ​​of environmental abnormality factor EAF and biological abnormality factor BAF respectively, and K represents the correction constant; Among them, the temperature change rate TVR is obtained by the following calculation formula: ; Where, T i represents the temperature value at the i-th time point, n represents the total number of acquisition time points, Indicates the time interval of the acquisition time points; The humidity fluctuation range HFR is obtained by the following calculation formula: ; In the formula, represents the peak humidity value among the total number of acquisition time points n, It represents the humidity valley value among the total number of acquisition time points n; The harmful gas concentration change HGCV is obtained by the following calculation formula: ; In the formula, Gi represents the concentration of harmful gases at the i-th time point, including carbon dioxide , carbon monoxide CO, ammonia , Hydrogen sulfide and volatile organic compounds (VOCs); The microbial ratio change MBCV is obtained by the following calculation formula: ; In the formula, Represents the proportion of microorganisms at the i-th time point, including fungi, parasites and bacteria, which is obtained by using the ATP bioluminescence method through the microbial concentration sensor. represents the mean value of the microbial proportion, represents the standard deviation of microbial concentration; The environmental anomaly factor EAF is obtained by the following calculation formula: ; In the formula, TVR represents the temperature change rate, HFR represents the humidity fluctuation range, and HGCV represents the change in harmful gas concentration. , and It indicates the average value of temperature change rate TVR, humidity fluctuation range HFR, and harmful gas concentration change HGCV, and is obtained by filtering out the qualified transport item records from the data table queried by transport item type; The biological abnormality factor BAF is obtained by the following calculation formula: ; In the formula, MBCV represents the change in microbial proportion, represents the mean value of the change in microbial proportion, represents the standard deviation of the variation in microbial proportions; The evaluation and early warning module matches the preset transport item detection evaluation threshold P with the transport item detection evaluation index Jczs to obtain the transport item monitoring evaluation strategy plan; The feedback module makes specific responses and notifications according to the contents of the transported items monitoring and evaluation strategy plan, including regulating the status of the transported items and notifying relevant security personnel, and simultaneously performing a secondary evaluation response to detect the abnormal control area, obtain the abnormal response control area plan, and notify and prompt the personnel in the area according to the contents of the abnormal response control area plan.

2. The IoT intelligent monitoring system for port safety and health quarantine according to claim 1 is characterized by: The data acquisition module includes a sensor acquisition unit; The sensor acquisition unit collects the detection information of the transported items in real time through the sensor group installed in the transport and inspection area of ​​animals, plants and water bodies, including the temperature, humidity, pH value, dissolved oxygen, harmful gas concentration, microbial concentration and bioelectric potential information of the transported items, and synchronously marks the timestamp, the unique mark of the transported items and the item type to form a transport collection data group; Among them, the sensor group includes temperature sensors, humidity sensors, pH sensors, dissolved oxygen sensors, harmful gas sensors, microbial concentration sensors and biopotential sensors; the item types include animals and plants, water bodies, food and biological products.

3. The IoT intelligent monitoring system for port safety and health quarantine according to claim 1 is characterized by: The data preprocessing module includes a data conversion unit and a data storage unit; The data conversion unit preprocesses the transport collection data group, including data cleaning preprocessing and data normalization preprocessing, to form a processed transport data processing data group; Among them, data cleaning preprocessing includes using smoothing methods to remove random noise in the data; using mean filling methods to fill missing values; using standard deviation methods to detect and correct outliers; Data normalization processing includes minimum and maximum normalization and Z-score normalization methods to normalize the transportation collection data group after data cleaning and preprocessing; The data storage unit stores data of the preprocessed transport data processing data group, wherein the data storage is performed by connecting to a database, and then obtaining a data table with the same transport item type as that in the transport data processing data group by writing a query SQL, and then writing an SQL insert statement to insert the transport data processing data group into the queried data table, and setting data access permissions at the same time.

4. The IoT intelligent monitoring system for port safety and health quarantine according to claim 1 is characterized by: The evaluation and early warning module includes a matching unit and a strategy generation unit; The matching unit matches the preset relevant information with the required comparison value, including matching the preset transported item detection evaluation threshold P with the transported item detection evaluation index Jczs to obtain a matching result; The matching results are obtained through the following matching methods: When the transported item detection evaluation index Jczs is less than the transported item detection evaluation threshold P, the detection result of the transported item is obtained as a qualified result; When the transported item detection evaluation index Jczs ≥ the transported item detection evaluation threshold P, the detection result of the transported item is obtained as a warning result; The strategy generation unit generates a transported item monitoring and evaluation strategy scheme according to a matching result obtained by matching a preset transported item detection and evaluation threshold value P with a transported item detection and evaluation index Jczs; The transported goods monitoring and evaluation strategy is obtained by the following generation method: When the matching result is a warning result, an item warning monitoring plan is generated, including stopping the transportation of items, closing the input and output ports of the conveyor belt, isolating and sealing the transported items, and disinfecting the transported items. A preset evacuation reminder is sent to personnel in the area transporting items, and the item abnormality monitoring plan is sent to the relevant inspection personnel's pending tasks and pinned to the top.

5. The IoT intelligent monitoring system for port safety and health quarantine according to claim 4 is characterized by: The feedback module includes a control unit and a response detection unit; The control unit makes specific responses and notifications according to the content of the transported item monitoring and evaluation strategy plan, including control of the transported item status and notification of relevant security personnel. The control includes marking the current transported item status abnormality on the interactive page and the conveyor belt monitoring screen. The notification includes preset prompt voice, internal communication software prompt and SMS notification; When the content of the transported goods monitoring and evaluation strategy plan includes an early warning result, the response detection unit triggers a secondary evaluation response to detect the abnormal control area, obtains the abnormal response control area plan, and notifies and prompts the personnel in the area according to the content of the abnormal response control area plan; The secondary evaluation response is obtained by the following formula: ; In the formula, represents the secondary assessment response index, represents the transport item detection evaluation index obtained by the rth evaluation, P represents the transport item detection evaluation threshold, represents an exponential function, when the condition is met, I=1, otherwise I=0, W represents the number of secondary evaluations performed within a fixed period, and K represents the number of times the detection result of the transported items that triggers the secondary evaluation is a warning result.

6. The IoT intelligent monitoring system for port safety and health quarantine according to claim 5 is characterized by: The abnormal response control area plan is obtained in the following ways: When the secondary evaluation response index ≥ Secondary response threshold E, obtain the control of the transport area range adjustment and the control of personnel entry prohibition in the transport area; When the secondary evaluation response index <Secondary response threshold E, obtain the control of the transport items area and the isolation control of the personnel in the transport items area.