Internet of Things equipment closed-loop management and control cloud platform and method based on dynamic safety index

Abstract

The invention discloses an Internet of Things equipment closed-loop management and control cloud platform and method based on a dynamic safety index, and relates to the technical field of Internet of Things. Comprising a database server, an application server, a monitoring module used for collecting and synchronizing equipment operation state data in real time, an alarm module used for judging the working state of a sensor, and an early warning module used for carrying out early warning on a future time node. The processing module is used for calculating a dynamic security index of the cloud platform; the feedback module is used for bidirectional transmission; the monitoring module, the alarm module, the early warning module, the processing module and the feedback module are all deployed in an application server, and operation data, alarm information, early warning information and processing results generated by all the modules are all stored in the database server; through introduction of a dynamic safety index, real-time adjustment of dynamic changes of potential faults of equipment is realized, and response hysteresis is avoided. And through a complete closed-loop management and control mechanism, the processing efficiency is improved, and an effective equipment management and control system is formed.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and particularly to an Internet of Things device closed-loop control cloud platform and method based on a dynamic security index. Background Art

[0002] The Internet of Things technology forms a digital network with informatized production processes and intelligent remote control by seamlessly connecting elements such as sensors, controllers, and production equipment. Currently, the security protection of many Internet of Things devices mainly relies on static security policies, which are set during device deployment and are difficult to adjust in real time according to the dynamic changes of the device operating environment and potential threats, resulting in limited control effects. Internet of Things devices are usually produced by different manufacturers and lack a unified security management platform for centralized control, making it difficult for managers to comprehensively grasp the security status of devices, promptly discover and respond to security incidents. Existing Internet of Things security assessment methods are mostly based on static indicators, which are difficult to accurately reflect the actual security status of devices during operation. At the same time, there is a lack of an effective security warning mechanism, and potential threats cannot be discovered in time before anomalies occur, resulting in a lag in security incident response. Current security control solutions often focus on a single link and lack a complete closed-loop control mechanism, leading to low efficiency in handling security incidents and difficulty in forming an effective security control system.

[0003] Therefore, there is an urgent need for an Internet of Things device closed-loop control cloud platform and method based on a dynamic security index to break through the limitations of the existing technology. Summary of the Invention

[0004] The purpose of the present invention is to provide an Internet of Things device closed-loop control cloud platform and method based on a dynamic security index to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] An Internet of Things device closed-loop control cloud platform based on a dynamic security index includes a database server, an application server, and a monitoring module, an alarm module, a warning module, a processing module, and a feedback module deployed in the application server. The monitoring module, alarm module, warning module, processing module, and feedback module are respectively used to generate operation data, alarm records, warning information, and processing results, and the above information is stored in the database server.

[0007] The monitoring module is used to collect and synchronize device operation status data in real time.

[0008] The alarm module is used to judge the working state of the sensor and perform multi-channel alarms according to a preset push mechanism.

[0009] The warning module is used to give a warning about future time nodes and generate warning information;

[0010] The processing module is used to calculate the dynamic security index of the cloud platform;

[0011] The feedback module is used to transmit information between the user and the system bidirectionally and support multi-modal feedback input and instruction response.

[0012] As a preferred technical solution, the monitoring module includes a collection unit and a transmission unit:

[0013] The collection unit is used to collect the device operation status data of the Internet of Things devices in real time through a multi-source sensor network deployed on the Internet of Things terminals;

[0014] The transmission unit uses a secure encryption transmission protocol to synchronously transmit the collected device operation data and the monitoring data of the multi-source sensors to the database server for storage, and sends them to the alarm module in real time for working status analysis.

[0015] It should be noted that Internet of Things devices such as the headquarters special gas cabinet contain multiple components. Among them, the components are composed of multi-source sensors, and the multi-source sensors include leakage sensors, high-pressure pressure transmitters, temperature sensors, flame detectors, mass flow meters, etc.; the device operation data of Internet of Things devices includes multi-source sensor information, information on vulnerable parts that need to be replaced regularly for the device, gas information used by the device, panel diagram information of the device, as well as operation instruction information and working status of the device.

[0016] As a preferred technical solution, the alarm module includes a judgment unit, a level division unit and an alarm unit;

[0017] The judgment unit is used to judge the working status of the sensor according to a preset dynamic threshold judgment mechanism:

[0018] When the monitoring data of the sensor is within the alarm threshold interval, it is determined that the sensor is in a normal working state, where the alarm threshold interval includes an upper limit value and a lower limit value;

[0019] When the monitoring data of the sensor is not within the alarm threshold interval, it is determined that the sensor is in an abnormal working state;

[0020] The level division unit extracts the monitoring data of the sensors in the abnormal working state and divides the alarm level according to a preset sensor level division mechanism;

[0021] The alarm unit generates alarm information according to a preset push mechanism and conducts multi-channel alarms.

[0022] It should be noted that the warning threshold interval is set by the administrator for the sensors that need to give warnings. The setting process includes: querying the security index information, selecting the sensors that need to give warnings to modify the warning thresholds. During operation, when the operation data of the sensors that need to give warnings is higher than the upper limit value or lower than the lower limit value, a warning will be triggered, and it is determined that the sensors that need to give warnings are in an abnormal working state; the preset sensor level division mechanism is set by the administrator. The warning levels are divided into three levels, from the lowest level 1 to the highest level 3, and different levels correspond to different warning contacts; the preset push mechanism is set by the administrator, including warning contact information, push methods and notification methods. The warning contact information includes warning staff numbers, warning person names, warning levels, mobile phone numbers, apps and email addresses; the push methods include only the first push and multiple pushes. Among them, multiple pushes include a push interval, and the notification methods include a short message notification method (when a warning occurs, send a short message to the contact's mobile phone), an email notification method (when a warning occurs, send an email to the contact's email), an APP notification method and a voice notification method.

[0023] As a preferred technical solution, the warning module includes an extraction unit and a prediction unit:

[0024] The extraction unit is used to extract the work logs and real-time monitoring data of multi-source sensors from the database server. The work logs include the historical monitoring data and warning types of the multi-source sensors. The warning types include normal, high-threshold warning and fault warning;

[0025] The prediction unit establishes a feature data set according to the historical monitoring data, constructs a prediction model based on the LSTM neural network, inputs the time series feature data, and then outputs the warning probabilities of different warning types within the future time nodes. According to the warning probabilities, the warning types are generated in a descending order, and the warning type at the first place in the sequence is taken as the warning type for the future time nodes;

[0026] When the warning type of the future time node does not belong to normal, warning information is generated based on the warning type.

[0027] As a preferred technical solution, the processing module includes a statistics unit and a security index unit:

[0028] The statistics unit obtains and processes the device operation status data of all Internet of Things devices through the monitoring module. The operation status includes normal operation and abnormal operation. The statistics unit is used to count the number of currently normally operating and abnormally operating Internet of Things devices;

[0029] The statistics unit is also used to extract the warning information of the warning module and respectively count the number of currently pending and processed warnings;

[0030] The said statistical unit further extracts the warning information at the current time node and separately counts the number of warnings to be processed and the number of warnings that have been processed currently;

[0031] The said security index unit is used to calculate the dynamic security index of the cloud platform in real time based on the above statistical data. The calculation formula is:

[0032]

[0033] Among them, S represents the dynamic security index of the closed-loop control cloud platform, M represents the total number of sensors, w m represents the dynamic weight of the m-th sensor, v m represents the standardized risk value of the m-th sensor, w represents the dynamic weight of the Internet of Things device, N Normal 、N Unusual respectively represent the number of Internet of Things devices operating normally and abnormally currently, represents the risk accumulation value;

[0034] When the dynamic security index is less than the security threshold, the system will automatically send a maintenance signal to the management personnel.

[0035] As a preferred technical solution, the said risk accumulation value is used to reflect the risk accumulation of unprocessed alarm information and warning information in time;

[0036] Based on the number of alarms to be processed and the number of alarms that have been processed, calculate the processing index of the current alarm information. The calculation formula is:

[0037]

[0038] Among them, H represents the processing index of the current alarm information, I represents the alarm level, represents the risk weight of the alarm information with the alarm level of i, N i represents the number of alarms with the alarm level of i to be processed currently, M i represents the number of alarms with the alarm level of i that have been processed currently;

[0039] Based on the number of warnings to be processed and the number of warnings that have been processed currently, calculate the risk index of the current warning information:

[0040]

[0041] Among them, P represents the risk index of the current warning information, γ1 and γ2 respectively represent the risk weights of high-threshold warnings and fault warnings, N pre1 、N pre2 respectively represent the number of high-threshold warnings and the number of fault warnings among the processed warnings, N finish represents the number of processed warnings, and γ3 represents the error;

[0042] Calculate the risk accumulation value based on the processing index of the current alarm information and the risk index of the current early warning information. The calculation formula is:

[0043]

[0044] Among them, ρ1 and ρ2 respectively represent the risk coefficients of the alarm information and the early warning information.

[0045] As a preferred technical solution, the feedback module includes an interaction unit and a visualization unit;

[0046] The interaction unit is used to transmit information between the user and the system bidirectionally, and supports multi-modal feedback input and instruction response;

[0047] The visualization unit automatically generates a visualization chart based on the visualization template from the data generated by the monitoring module, the alarm module, the early warning module, the processing module, and the interaction unit.

[0048] It should be noted that the visualization chart includes the system security status, gas usage, and equipment operation and equipment alarm situation. Among them, the system security status includes a security index, which reflects the overall security status of the system and is obtained by summarizing the equipment status, alarm information, and early warning information; the equipment status shows the real-time operation status of all equipment in the system; the alarm information shows the processing situation of all alarm information in the system; the early warning information shows the processing situation of all early warning information in the system; the gas usage includes the usage of liquid gas and gaseous gas, and shows the monthly usage of each liquid gas and each gaseous gas; the equipment operation and equipment alarm situation includes the equipment operation situation, the equipment alarm situation, and the laboratory alarm records, realizing the classification and statistical quantity of equipment and the running status, classifying and statistically counting the alarm times of equipment, and showing the alarm times of three levels of each laboratory. The horizontal axis is the laboratory door number, and the vertical axis is the alarm times; through the setting of the visualization unit, the data of the space-time dimension is integrated to assist the user in quickly positioning the root cause of the risk; through the setting of the interaction unit, a closed loop of "machine decision-making - manual confirmation - model optimization" is realized to reduce the risk of misoperation.

[0049] As a preferred technical solution, the minimum environmental standards of the database server include a quad-core processor, 8G of I / O-optimized memory, a 50G hard disk, and a standard network connection with a 5Mbps bandwidth; the minimum environmental standards of the application server environment include an octa-core processor, 32G of I / O-optimized memory, a 100G hard disk, and a standard network connection with a 10Mbps bandwidth.

[0050] The closed-loop control method for Internet of Things devices based on the dynamic security index, the method includes the following steps:

[0051] Step S100: Real-time collect the device operation status data of the Internet of Things devices through the multi-source sensor network of the Internet of Things terminals, and synchronously record the monitoring data of the multi-source sensors and the device operation status data of the Internet of Things devices in the database;

[0052] Step S200: Based on the monitoring data of the multi-source sensors and the preset dynamic threshold determination mechanism, judge the working status of each sensor, and the working status includes normal working status and abnormal working status;

[0053] When the monitoring data of the sensor is within the alarm threshold interval, it is determined that the sensor is in the normal working state, where the alarm threshold interval includes an upper bound value and a lower bound value; when the monitoring data of the sensor is not within the alarm threshold interval, it is determined that the sensor is in the abnormal working state;

[0054] Extract the monitoring data of the sensors in the abnormal working state, divide the alarm levels according to the preset sensor level division mechanism, and generate alarm information according to the preset push mechanism for multi-channel alarm, and the channels include SMS notification method, email notification method, APP notification method and voice notification method;

[0055] Step S300: Extract the working logs and real-time monitoring data of the multi-source sensors from the database server, and the working logs include the historical monitoring data and warning types of the multi-source sensors, and the warning types include normal, high threshold warning and fault warning;

[0056] Establish a feature data set according to the historical monitoring data, construct a prediction model based on the LSTM neural network, input the time series feature data and output the warning probabilities of different warning types within the future time nodes, generate a descending order sequence according to the warning probabilities for the warning types, and take the warning type at the first place in the sequence as the warning type for the future time nodes;

[0057] When the warning type of the future time node does not belong to normal, generate warning information based on the warning type, and the warning information includes the warning time node, warning type, sensor name and sensor data;

[0058] Step S400: Based on the device operation status data of all Internet of Things devices at the current time node, where the operation status includes normal operation and abnormal operation, count the number of Internet of Things devices in normal operation and abnormal operation currently;

[0059] Extract the alarm information at the current time node, and count the number of alarms to be processed and the number of alarms that have been processed currently;

[0060] Extract the warning information at the current time node, and count the number of warnings to be processed and the number of warnings that have been processed currently;

[0061] Calculate the processing index of the current alarm information based on the number of alarms to be processed and the number of alarms that have been processed;

[0062] Calculate the risk index of the current warning information based on the number of warnings to be processed and the number of warnings that have been processed currently;

[0063] Calculate the risk accumulation value based on the processing index of the current alarm information and the risk index of the current warning information;

[0064] Monitor the dynamic security index of the cloud platform in real time;

[0065] When the dynamic security index is less than the security threshold, automatically send a maintenance signal to the administrator.

[0066] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In the Internet of Things device closed-loop control cloud platform and method based on the dynamic security index provided by the present invention, it includes a database server, an application server, a monitoring module for real-time collecting and synchronizing device operation status data, an alarm module for judging the working status of sensors, a warning module for warning future time nodes, a processing module for calculating the dynamic security index of the cloud platform, and a feedback module for two-way transmission; the monitoring module, the alarm module, the warning module, the processing module, and the feedback module are all deployed in the application server, and the operation data, alarm information, warning information, and processing results generated by each module are all stored in the database server; by introducing the dynamic security index, the dynamic changes of potential device failures are adjusted in real time, avoiding response lags; through a complete closed-loop control mechanism, the processing efficiency is improved, and an effective device control system is formed. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0068] Among them:

[0069] Figure 1 is the structural schematic diagram in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the embodiments of the present invention with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the described embodiments of the present invention fall within the scope of protection of the present invention.

[0071] As Figure 1 shown, this is an embodiment of the present invention. This embodiment provides an Internet of Things device closed-loop control cloud platform based on a dynamic security index, including a database server, an application server, and a monitoring module, an alarm module, a warning module, a processing module, and a feedback module deployed in the application server;

[0072] The monitoring module, alarm module, warning module, processing module, and feedback module are respectively used to generate operation data, alarm information, warning information, and processing results, and the above information is stored in the database server;

[0073] The monitoring module is used to collect and synchronize device operation status data in real time;

[0074] The alarm module is used to judge the working state of the sensor and perform multi-channel alarms according to a preset push mechanism;

[0075] The warning module is used to give warnings for future time nodes and generate warning information;

[0076] The processing module is used to calculate the dynamic security index of the cloud platform;

[0077] The feedback module is used to bidirectionally transmit information between the user and the system and support multi-modal feedback input and command response.

[0078] Specifically, the monitoring module includes a collection unit and a transmission unit:

[0079] The collection unit collects the device operation status data of the Internet of Things device in real time through a multi-source sensor network deployed on the Internet of Things terminal;

[0080] The transmission unit synchronously transmits the collected device operation data and the monitoring data of the multi-source sensor to the database server for storage using a secure encryption transmission protocol, and sends it to the alarm module in real time for working state analysis.

[0081] Specifically, the alarm module includes a judgment unit, a level division unit, and an alarm unit;

[0082] The judgment unit judges the working state of the sensor according to a preset dynamic threshold determination mechanism:

[0083] When the monitoring data of the sensor is within the warning threshold interval, it is determined that the sensor is in a normal working state, where the warning threshold interval includes an upper bound value and a lower bound value;

[0084] When the monitoring data of the sensor is not within the warning threshold interval, it is determined that the sensor is in an abnormal working state;

[0085] The level division unit extracts the monitoring data of the sensors in the abnormal working state and divides the warning levels according to a preset sensor level division mechanism;

[0086] The warning unit generates warning information according to a preset push mechanism and conducts multi-channel warnings.

[0087] Specifically, the early warning module includes an extraction unit and a prediction unit:

[0088] The extraction unit is used to extract the working logs and real-time monitoring data of multi-source sensors from the database server. The working logs include the historical monitoring data and warning types of the multi-source sensors, and the warning types include normal, high threshold warning, and fault warning;

[0089] The prediction unit establishes a feature data set according to the historical monitoring data, constructs a prediction model based on the LSTM neural network, outputs the warning probabilities of different warning types within the future time node after inputting the time series feature data, generates a descending sequence of the warning types according to the warning probabilities, and takes the warning type at the first place of the sequence as the warning type of the future time node;

[0090] When the warning type of the future time node does not belong to normal, warning information is generated based on the warning type.

[0091] Specifically, the processing module includes a statistics unit and a security index unit:

[0092] The statistics unit obtains and processes the device operation status data of all Internet of Things devices through the monitoring module. The operation status includes normal operation and abnormal operation. The statistics unit is used to count the number of currently normally operating and abnormally operating Internet of Things devices;

[0093] The statistics unit is also used to extract the warning information of the warning module and respectively count the number of currently pending and processed warnings;

[0094] The statistics unit further extracts the warning information of the current time node and respectively counts the number of currently pending and processed warnings;

[0095] The security index unit is used to calculate the dynamic security index of the cloud platform in real time based on the above statistical data. The calculation formula is as follows:

[0096]

[0097] Among them, S represents the dynamic security index of the closed-loop control cloud platform, M represents the total number of sensors, w m represents the dynamic weight of the m-th sensor, v m represents the normalized risk value of the m-th sensor, w represents the dynamic weight of the Internet of Things device, N Normal 、N Unusual respectively represent the number of Internet of Things devices operating normally and abnormally currently, represents the risk accumulation value;

[0098] When the dynamic security index is less than the security threshold, the system will automatically send a maintenance signal to the management personnel.

[0099] Specifically, the risk accumulation value is used to reflect the risk accumulation of unprocessed alarm information and early warning information;

[0100] Based on the number of alarms to be processed and the number of alarms that have been processed, calculate the processing index of the current alarm information. The calculation formula is:

[0101]

[0102] Among them, H represents the processing index of the current alarm information, I represents the alarm level, represents the risk weight of the alarm information with the alarm level of i, N i represents the number of alarms with the alarm level of i to be processed currently, M i represents the number of alarms with the alarm level of i that have been processed currently;

[0103] Based on the number of early warnings to be processed and the number of early warnings that have been processed currently, calculate the risk index of the current early warning information:

[0104]

[0105] Among them, P represents the risk index of the current early warning information, γ1 and γ2 respectively represent the risk weights of high-threshold early warning and fault early warning, N pre1 、N pre2 respectively represent the number of high-threshold early warnings and the number of fault early warnings in the processed early warnings, N finish represents the number of processed early warnings, γ3 represents the error;

[0106] Based on the processing index of the current alarm information and the risk index of the current early warning information, calculate the risk accumulation value. The calculation formula is:

[0107]

[0108] Among them, ρ1 and ρ2 respectively represent the risk coefficients of alarm information and early warning information.

[0109] Specifically, the feedback module includes an interaction unit and a visualization unit:

[0110] The interaction unit is used to transmit information between the user and the system bidirectionally, and supports multi-modal feedback input and instruction response;

[0111] The visualization unit automatically generates corresponding charts according to the visualization template from the data generated by the monitoring module, the alarm module, the early warning module, the processing module, and the interaction unit.

[0112] Specifically, the minimum environmental standards of the database server include a quad-core processor, 8G of I / O optimized memory, a 50G hard disk, and a standard network connection with a 5Mbps bandwidth; the minimum environmental standards of the application server environment include an octa-core processor, 32G of I / O optimized memory, a 100G hard disk, and a standard network connection with a 10Mbps bandwidth.

[0113] The closed-loop control method for Internet of Things devices based on the dynamic security index, the method includes the following steps:

[0114] Step S100: Real-time collect the device operation status data of the Internet of Things devices through the multi-source sensor network of the Internet of Things terminals, and synchronously record the monitoring data of the multi-source sensors and the device operation status data of the Internet of Things devices in the database;

[0115] Step S200: Based on the monitoring data of the multi-source sensors and the preset dynamic threshold determination mechanism, judge the working status of each sensor, and the working status includes normal working status and abnormal working status;

[0116] When the monitoring data of the sensor is within the alarm threshold interval, it is determined that the sensor is in the normal working state, where the alarm threshold interval includes an upper bound value and a lower bound value; when the monitoring data of the sensor is not within the alarm threshold interval, it is determined that the sensor is in the abnormal working state;

[0117] Extract the monitoring data of the sensors in the abnormal working state, divide the alarm levels according to the preset sensor level division mechanism, and generate alarm information according to the preset push mechanism for multi-channel alarm, and the channels include SMS notification method, email notification method, APP notification method, and voice notification method;

[0118] Step S300: Extract the working logs and real-time monitoring data of the multi-source sensors from the database server, and the working logs include the historical monitoring data and early warning types of the multi-source sensors, and the early warning types include normal, high threshold early warning, and fault early warning;

[0119] Establish a feature dataset according to historical monitoring data, construct a prediction model based on the LSTM neural network, input time series feature data, and output the warning probabilities of different warning types within future time nodes. Generate a descending sequence of warning types according to the warning probabilities, and take the warning type at the head of the sequence as the warning type for future time nodes;

[0120] When the warning type of the future time node is not normal, generate a warning message based on the warning type. The warning message includes the warning time node, warning type, sensor name, and sensor data;

[0121] Step S400: Based on the device operation status data of all Internet of Things devices at the current time node, where the operation status includes normal operation and abnormal operation, count the number of Internet of Things devices in normal operation and abnormal operation currently;

[0122] Extract the alarm information at the current time node, and count the number of alarms to be processed and the number of alarms that have been processed currently;

[0123] Extract the warning information at the current time node, and count the number of warnings to be processed and the number of warnings that have been processed currently;

[0124] Based on the number of alarms to be processed and the number of alarms that have been processed, calculate the processing index of the current alarm information:

[0125]

[0126] Among them, H represents the processing index of the current alarm information, I represents the alarm level, represents the risk weight of the alarm information with the alarm level of i, N i represents the number of alarms with the alarm level of i to be processed currently, M i represents the number of alarms with the alarm level of i that have been processed currently;

[0127] Based on the number of warnings to be processed and the number of warnings that have been processed currently, calculate the risk index of the current warning information:

[0128]

[0129] Among them, P represents the risk index of the current warning information, γ1 and γ2 respectively represent the risk weights of high threshold warnings and fault warnings, N pre1 、N pre2 respectively represent the number of high threshold warnings and the number of fault warnings among the processed warnings, N finish represents the number of processed warnings, and γ3 represents the error;

[0130] Calculate the risk accumulation value based on the processing index of the current alarm information and the risk index of the current early warning information. The calculation formula is as follows:

[0131]

[0132] Among them, ρ1 and ρ2 respectively represent the risk coefficients of the alarm information and the early warning information;

[0133] Real-time monitor the dynamic security index of the cloud platform. The calculation formula is:

[0134]

[0135] Among them, S represents the dynamic security index of the closed-loop control cloud platform, M represents the total number of sensors, w m represents the dynamic weight of the m-th sensor, v m represents the normalized risk value of the m-th sensor, w represents the dynamic weight of the Internet of Things device, N Normal 、N Unusual respectively represent the number of Internet of Things devices operating normally and abnormally currently, represents the risk accumulation value;

[0136] When the dynamic security index is less than the security threshold, automatically send a maintenance signal to the administrator.

[0137] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0138] In addition, in each embodiment of the present application, the functional units can be integrated in a processing module, or each unit can exist physically alone, or two or more units can be integrated in a module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a magnetic disk or an optical disc, etc.

[0139] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various changes or substitutions thereof, and these should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A closed-loop control cloud platform for IoT devices based on dynamic security index, characterized by: It includes a database server, an application server, and a monitoring module, an alarm module, an early warning module, a processing module and a feedback module deployed in the application server; The monitoring module, alarm module, early warning module, processing module and feedback module are used to generate operation data, alarm information, early warning information and processing results respectively, and the above information is stored in the database server; The monitoring module is used to collect and synchronize equipment operation status data in real time; The alarm module is used to determine the working status of the sensor and issue multi-channel alarms according to a preset push mechanism; The warning module is used to warn of future time nodes and generate warning information; The processing module is used to calculate the dynamic security index of the cloud platform; The feedback module is used to bidirectionally transmit information between the user and the system, and supports multi-modal feedback input and instruction response.

2. The closed-loop control cloud platform for IoT devices based on dynamic security index according to claim 1 is characterized in that: The monitoring module includes a collection unit and a transmission unit: The collection unit collects the device operation status data of the IoT device in real time through a multi-source sensor network deployed on the IoT terminal; The transmission unit uses a secure encrypted transmission protocol to synchronously transmit the collected equipment operation data and monitoring data of the multi-source sensors to the database server for storage, and sends them to the alarm module in real time for working status analysis.

3. The closed-loop control cloud platform for IoT devices based on dynamic security index according to claim 2 is characterized in that: The alarm module includes a judgment unit, a level classification unit and an alarm unit; The judging unit judges the working state of the sensor according to a preset dynamic threshold judging mechanism: When the monitoring data of the sensor is within the alarm threshold interval, it is determined that the sensor is in a normal working state, wherein the alarm threshold interval includes an upper limit value and a lower limit value; When the monitoring data of the sensor is not within the alarm threshold interval, it is determined that the sensor is in an abnormal working state; The level division unit extracts monitoring data of sensors in abnormal working state and divides the alarm level according to a preset sensor level division mechanism; The alarm unit generates alarm information according to a preset push mechanism and performs multi-channel alarm.

4. The closed-loop control cloud platform for IoT devices based on dynamic security index according to claim 3 is characterized in that: The early warning module includes an extraction unit and a prediction unit: The extraction unit is used to extract the work log and real-time monitoring data of the multi-source sensor from the database server, wherein the work log includes the historical monitoring data and warning types of the multi-source sensor, and the warning types include normal, high threshold warning and fault warning; The prediction unit establishes a feature data set according to the historical monitoring data, builds a prediction model based on the LSTM neural network, outputs the warning probabilities of different warning types in the future time nodes after inputting the time series feature data, generates a descending sequence of the warning types according to the warning probabilities, and takes the first warning type in the sequence as the warning type of the future time node; When the warning type of the future time node is not normal, warning information is generated based on the warning type.

5. The closed-loop control cloud platform for IoT devices based on dynamic security index according to claim 4 is characterized in that: The processing module includes a statistical unit and a safety index unit: The statistical unit acquires and processes the device operation status data of all IoT devices through the monitoring module, wherein the operation status includes normal operation and abnormal operation, and the statistical unit is used to count the number of IoT devices that are currently operating normally and abnormally; The statistical unit is also used to extract the alarm information of the alarm module, and count the number of alarms to be processed and processed respectively; The statistical unit further extracts the warning information of the current time node, and respectively counts the number of warnings to be processed and processed; The security index unit is used to calculate the dynamic security index of the cloud platform in real time based on the above statistical data. The calculation formula is as follows: Among them, S represents the dynamic security index of the closed-loop control cloud platform, M represents the total number of sensors, and w m represents the dynamic weight of the mth sensor, v m represents the standardized risk value of the mth sensor, w represents the dynamic weight of the IoT device, and N Normal 、N Unusual Respectively represent the number of IoT devices that are currently operating normally and abnormally. represents the cumulative risk value; When the dynamic safety index is less than the safety threshold, the system will automatically send a maintenance signal to the management personnel.

6. The closed-loop control cloud platform for IoT devices based on dynamic security index according to claim 5 is characterized in that: The risk accumulation value is used to reflect the risk accumulation of not processing alarm information and warning information in a timely manner; Based on the number of alarms to be processed and the number of alarms that have been processed, the processing index of the current alarm information is calculated. The calculation formula is: Among them, H represents the processing index of the current alarm information, I represents the alarm level, Indicates the risk weight of the alarm information with alarm level i, N i Indicates the number of alarms with alarm level i that are currently pending. i Indicates the number of alarms with alarm level i that have been processed. Based on the current number of pending warnings and the number of processed warnings, calculate the risk index of the current warning information: Among them, P represents the risk index of the current warning information, γ1 and γ2 represent the risk weights of high threshold warning and fault warning respectively, and N pre1 、N pre2 They represent the number of high threshold warnings and fault warnings among the processed warnings, respectively. finish represents the number of warnings processed, and γ3 represents the error; Based on the processing index of the current alarm information and the risk index of the current warning information, the risk accumulation value is calculated using the following formula: Among them, ρ1 and ρ2 represent the risk coefficients of warning information and early warning information respectively.

7. The closed-loop control cloud platform for IoT devices based on dynamic security index according to claim 6 is characterized in that: The feedback module includes an interaction unit and a visualization unit: The interaction unit is used to bidirectionally transmit information between the user and the system, and supports multi-modal feedback input and command response; The visualization unit automatically generates corresponding charts based on the visualization template using the data generated by the monitoring module, the alarm module, the early warning module, the processing module and the interaction unit.

8. The closed-loop control cloud platform for IoT devices based on dynamic security index according to claim 7 is characterized in that: The minimum environmental standards for the database server include a quad-core processor, 8G I / O-optimized memory, a 50G hard disk, and a standard network connection with a 5Mbps bandwidth; the minimum environmental standards for the application server environment include an eight-core processor, 32G I / O-optimized memory, a 100G hard disk, and a standard network connection with a 10Mbps bandwidth.

9. The closed-loop control method of the closed-loop control cloud platform of the Internet of Things device based on the dynamic security index according to any one of claims 1 to 8, characterized in that: The method comprises the following steps: Step S100: collecting device operation status data of the IoT device in real time through the multi-source sensor network of the IoT terminal, and synchronously recording the monitoring data of the multi-source sensor and the device operation status data of the IoT device in a database; Step S200: judging the working state of each sensor based on the monitoring data of the multi-source sensors and the preset dynamic threshold determination mechanism, wherein the working state includes a normal working state and an abnormal working state; When the monitoring data of the sensor is within the alarm threshold interval, the sensor is determined to be in a normal working state, wherein the alarm threshold interval includes an upper limit value and a lower limit value; when the monitoring data of the sensor is not within the alarm threshold interval, the sensor is determined to be in an abnormal working state; Extract monitoring data of sensors in abnormal working state, classify alarm levels according to preset sensor level classification mechanism, generate alarm information according to preset push mechanism, and perform multi-channel alarm, including SMS notification method, email notification method, APP notification method and voice notification method; Step S300: extracting the work log and real-time monitoring data of the multi-source sensor from the database server, wherein the work log includes the historical monitoring data and warning types of the multi-source sensor, and the warning types include normal, high threshold warning and fault warning; Establish a feature data set according to historical monitoring data, build a prediction model based on LSTM neural network, input time series feature data and output the warning probability of different warning types in future time nodes, generate a descending sequence of warning types according to the warning probability, and take the first warning type in the sequence as the warning type of future time nodes; When the warning type of the future time node is not normal, generating warning information based on the warning type, the warning information includes the warning time node, the warning type, the sensor name and the sensor data; Step S400: Based on the device operation status data of all IoT devices at the current time node, where the operation status includes normal operation and abnormal operation, the number of IoT devices that are currently operating normally and abnormally is counted; Extract alarm information at the current time node, and count the number of alarms to be processed and the number of alarms that have been processed; Extract the warning information of the current time node, and count the number of warnings to be processed and the number of warnings that have been processed; Based on the number of pending alarms and the number of processed alarms, the processing index of the current alarm information is calculated: Among them, H represents the processing index of the current alarm information, I represents the alarm level, Indicates the risk weight of the alarm information with alarm level i, N i Indicates the number of alarms with alarm level i that are currently pending. i Indicates the number of alarms with alarm level i that have been processed. Based on the current number of pending warnings and the number of processed warnings, calculate the risk index of the current warning information: Among them, P represents the risk index of the current warning information, γ1 and γ2 represent the risk weights of high threshold warning and fault warning respectively, and N pre1 、N pre2 They represent the number of high threshold warnings and fault warnings among the processed warnings, respectively. finish represents the number of warnings processed, and γ3 represents the error; Based on the processing index of the current alarm information and the risk index of the current warning information, the risk accumulation value is calculated using the following formula: Among them, ρ1 and ρ2 represent the risk coefficients of warning information and early warning information respectively; Real-time monitoring of the dynamic security index of the cloud platform, calculation formula: Among them, S represents the dynamic security index of the closed-loop control cloud platform, M represents the total number of sensors, and w m represents the dynamic weight of the mth sensor, v m represents the standardized risk value of the mth sensor, w represents the dynamic weight of the IoT device, and N Normal 、N Unusual Respectively represent the number of IoT devices that are currently operating normally and abnormally. represents the cumulative risk value; When the dynamic safety index is less than the safety threshold, a maintenance signal is automatically sent to the administrator.

Images