Internet of Things equipment monitoring system and method based on big data

Abstract

The invention relates to the technical field of cloud computing, and discloses an Internet of Things equipment monitoring system and method based on big data, and the system comprises an Internet of Things equipment monitoring environment recognition module, a cloud processing strategy switching module, a cloud processing risk recognition module, a cloud early warning information prompt module, and an equipment monitoring maintenance tracking module. Internet-of-things communication signal evaluation is carried out by acquiring Internet-of-things equipment communication signal data, an abnormal target is identified based on an evaluation result, a cloud processing strategy is switched to carry out cloud processing, and the cloud state is monitored in real time. And obtaining a risk index of the non-recognition target unit and a risk index of the recognition target tracking unit, performing risk assessment according to a risk recognition result, sending out an early warning information prompt by the cloud according to a risk assessment result, and performing maintenance tracking on the non-recognition target unit and the recognition abnormal target unit. And comprehensive monitoring and maintenance of the Internet of Things equipment are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing, and more particularly to an Internet of Things device monitoring system and method based on big data. Background Art

[0002] With the rapid development of Internet of Things technology, the number and application scenarios of Internet of Things devices are increasing day by day. Especially in the monitoring field, regional monitoring has been realized through Internet of Things devices based on big data technology. However, the dispersion and complexity of Internet of Things devices have brought great challenges to the monitoring and maintenance of devices. Traditional device monitoring methods often rely on manual inspections and regular maintenance, which are not only inefficient but also difficult to detect and handle device failures in a timely manner. In the prior art, there are some Internet of Things device monitoring systems, but most of these systems have problems such as limited monitoring scope and insufficient data processing capabilities. Especially when facing a large number of Internet of Things devices, these systems often struggle to achieve comprehensive monitoring and real-time warning of devices.

[0003] On the other hand, although Internet of Things-based monitoring devices can achieve real-time monitoring of the monitored area, they often only focus on the monitoring itself and ignore the in-depth analysis of Internet of Things communication signals. This single monitoring method may still conduct real-time monitoring of the monitored area when there are quality problems with the Internet of Things communication signals. On this basis, the system will attempt to use big data technology to process and analyze the monitoring data. However, due to the lack of consideration of the communication signal quality, this approach may lead to false alarms in the monitoring system in some cases, that is, wrongly sending out alarms, or missed alarms, that is, failing to detect and report real anomalies in a timely manner, thereby affecting the effectiveness of the entire monitoring system and the user's trust. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an Internet of Things device monitoring system based on big data to solve the problems existing in the above background art.

[0005] The present invention provides the following technical solutions: An Internet of Things device monitoring system based on big data, comprising: an Internet of Things device monitoring environment recognition module, a cloud processing strategy switching module, a cloud processing risk recognition module, a cloud warning information prompt module, and a device monitoring and maintenance tracking module; The Internet of Things device monitoring environment recognition module includes an Internet of Things communication signal data acquisition unit and an Internet of Things communication signal evaluation unit. The Internet of Things communication signal data acquisition unit acquires Internet of Things device communication signal data, and evaluates the Internet of Things communication signal based on the data; The cloud processing strategy switching module includes an unidentified target unit and an identified target tracking unit, which identify abnormal targets based on the evaluation result of the IoT communication signal of the IoT device monitoring environment identification module, and switch the cloud processing strategy for cloud processing; The cloud processing risk identification module, when performing cloud processing, monitors the cloud status in real time, obtains the risk index of the unidentified target unit and the risk index of the identified target tracking unit, and conducts risk assessment based on the risk identification result; The cloud warning information prompt module, the cloud issues warning information prompts based on the risk assessment result, including the risk warning information prompt of the unidentified target unit and the risk warning information prompt of the identified abnormal target unit; The device monitoring and maintenance tracking module respectively conducts maintenance tracking on the unidentified target unit and the identified abnormal target unit according to the warning information prompt, locates the maintenance tracking result and transmits it to the human-computer interaction.

[0006] Preferably, in the IoT device monitoring environment identification module, the IoT communication signal data acquisition unit obtains the received power of the communication signal at the environment sensor interface through the environment sensor, and the environment sensor performs communication denoising processing on the IoT communication signal when collecting IoT communication signal data; The IoT communication signal evaluation unit evaluates the IoT communication signal based on the received power of the communication signal at the environment sensor interface, and the calculation formula is: , where represents the IoT communication signal evaluation value, represents the received power of the communication signal at the environment sensor interface, represents the reference received power of the preset communication signal, represents the received intensity of the preset communication signal; When the IoT communication signal evaluation value is greater than or equal to the preset evaluation threshold, the evaluation result of the IoT communication signal is that the communication signal is normal, and a cloud classification processing strategy switching instruction is sent to the cloud classification processing strategy switching module; when the IoT communication signal evaluation value is less than the preset evaluation threshold, the evaluation result of the IoT communication signal is that the communication signal is abnormal, and a cloud warning information prompt instruction is sent to the cloud warning information prompt module.

[0007] Preferably, in the cloud processing strategy switching module: the unidentified target unit is used for performing cloud security processing on the IoT device; the identified target tracking unit is used for performing cloud tracking processing on the identified target; When the evaluation result of the Internet of Things communication signal is normal, target recognition is performed on the monitoring area. When there are no moving targets in the monitoring area, cloud security processing is performed on the Internet of Things devices through the no-recognition target unit; when there are moving targets in the monitoring area, the dual-unit processing strategy is switched to perform dual-unit cloud processing using the no-recognition target unit and the recognized target tracking unit.

[0008] Preferably, the specific content of the no-recognition target unit for performing cloud security processing on the Internet of Things devices is as follows: The data packets on the network link from the Internet of Things devices to the cloud network are sliced according to a time window with a length of T into n sub-data packets, where i = 1, 2, 3,..., n, and i represents the number of the sub-data packet; Based on the time window, network situation analysis is performed on each sub-data packet to obtain the network situation awareness index of each sub-data packet. The calculation formula is: , where represents the network situation awareness index of each sub-data packet within a time window with a length of T, represents the number of attacks on each sub-data packet within a time window with a length of T, represents the number of unfixed vulnerabilities of each sub-data packet within a time window with a length of T, represents the total number of vulnerabilities generated by each sub-data packet within a time window with a length of T, and represent the weight coefficients of the network situation awareness index.

[0009] Preferably, the specific content of the recognized target tracking unit for performing cloud tracking processing on the recognized target is as follows: The video stream of the recognized target is obtained through a camera, and the video stream is frame-divided to obtain M frame-divided images of the recognized target, where m = 1, 2, 3,..., M, and m represents the number of the frame-divided image; According to the pixel point coordinates within the target contour area in the frame-divided image, where k represents the number of pixel points within the target contour area in each frame-divided image, k = 1, 2, 3,..., K, and K represents the total number of pixel points within the target contour area in each frame-divided image, calculate the centroid point coordinates of each frame-divided image: , where represents the abscissa of the centroid point of each frame-divided image; , where represents the ordinate of the centroid point of each frame-divided image; Connect the centroid point coordinates of each frame-divided image in sequence to obtain the cloud tracking path curve of the recognized target.

[0010] Preferably, in the cloud processing risk identification module, the specific content of obtaining the risk index of the non-identified target unit and the risk index of the identified target tracking unit and performing risk assessment based on the risk identification result is as follows: Judging the number of risk data packets based on the network situation awareness index of each sub-data packet obtained by the non-identified target unit: When the network situation awareness index is greater than the preset risk judgment threshold, the data packet is judged as a risk data packet; Calculating the risk index of the non-identified target unit, and the calculation formula is: , where represents the risk index of the non-identified target unit, represents the number of risk data packets judged by the non-identified target unit, represents the total number of data packets segmented by the non-identified target unit; Calculating the risk index of the identified target tracking unit according to the cloud tracking path curve obtained by the identified target tracking unit, and the calculation formula is: , where represents the risk index of the identified target tracking unit, represents the interval time from the m-th centroid point to the m + 1-th centroid point of the identified target.

[0011] Preferably, the specific content of performing risk assessment based on the risk identification result is as follows: When the risk index of the non-identified target unit is greater than the preset first cloud threshold, the first risk assessment result is high risk; otherwise, the first risk assessment result is low risk; When the risk index of the identified target tracking unit is greater than the preset second cloud threshold, the second risk assessment result is high risk; otherwise, the second risk assessment result is low risk.

[0012] Preferably, the cloud warning information prompt module issues an Internet of Things device network warning information prompt according to the first risk assessment result; and issues an identified target behavior warning information prompt according to the second risk assessment result.

[0013] Preferably, the device monitoring and maintenance tracking module performs maintenance tracking on the non-identified target unit and the identified abnormal target unit respectively according to the warning information prompt, locates the maintenance tracking result and transmits it to the human-computer interaction end.

[0014] An Internet of Things device monitoring method based on big data includes the following steps: Step S01: Obtaining the communication signal data of the Internet of Things device through the Internet of Things communication signal data acquisition unit, and performing Internet of Things communication signal evaluation based on the data; Step S02: Identify abnormal targets based on the evaluation results of IoT communication signals, and switch the cloud processing strategy for cloud processing; Step S03: Monitor the cloud status in real time, obtain the risk index of the unit without identified targets and the risk index of the unit for tracking identified targets, and conduct risk assessment based on the risk identification results; Step S04: The cloud issues a warning message prompt according to the risk assessment results; Step S05: Maintain and track the unit without identified targets and the unit with identified abnormal targets respectively according to the warning message prompt.

[0015] Technical effects and advantages of the present invention: The present invention obtains the communication signal data of IoT devices through the IoT communication signal data acquisition unit, evaluates the data, discovers communication signal anomalies in a timely manner, thereby switches the cloud processing strategy, and conducts targeted processing on abnormal targets. At the same time, it monitors the cloud status in real time, obtains the risk index of the unit without identified targets and the risk index of the unit for tracking identified targets, and conducts risk assessment based on the risk identification results, further improving the security and reliability of the system; When the risk assessment result shows high risk, the cloud warning message prompt module will issue a warning message prompt in a timely manner so that relevant personnel can quickly take measures for processing. Finally, the device monitoring and maintenance tracking module maintains and tracks the unit without identified targets and the unit with identified abnormal targets according to the warning message prompt to ensure the normal operation and security of the device. Brief description of the drawings

[0016] Figure 1 It is a schematic structural diagram of an IoT device monitoring system based on big data.

[0017] Figure 2 It is a schematic flow diagram of an IoT device monitoring method based on big data. Detailed implementation manners

[0018] Next, the technical solutions in the present invention will be clearly and completely described in conjunction with the drawings in the present invention. In addition, the forms of the various structures described in the following embodiments are merely illustrative, and an IoT device monitoring system and method based on big data involved in the present invention are not limited to the various structures described in the following embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0019] Such as Figure 1As shown in the figure, the present invention provides an Internet of Things device monitoring system based on big data, including: an Internet of Things device monitoring environment recognition module, a cloud processing strategy switching module, a cloud processing risk recognition module, a cloud warning information prompt module, and a device monitoring maintenance tracking module; The Internet of Things device monitoring environment recognition module includes an Internet of Things communication signal data acquisition unit and an Internet of Things communication signal evaluation unit. The Internet of Things communication signal data acquisition unit acquires Internet of Things device communication signal data, and evaluates the Internet of Things communication signal based on the data; The cloud processing strategy switching module includes an unrecognized target unit and a recognized target tracking unit. Based on the Internet of Things communication signal evaluation result of the Internet of Things device monitoring environment recognition module, it recognizes abnormal targets and switches the cloud processing strategy for cloud processing; The cloud processing risk recognition module, when performing cloud processing, monitors the cloud status in real time, obtains the risk index of the unrecognized target unit and the risk index of the recognized target tracking unit, and performs risk assessment based on the risk recognition result; The cloud warning information prompt module, the cloud issues warning information prompts based on the risk assessment result, including the risk warning information prompt of the unrecognized target unit and the risk warning information prompt of the recognized abnormal target unit; The device monitoring maintenance tracking module respectively performs maintenance tracking on the unrecognized target unit and the recognized abnormal target unit according to the warning information prompt, locates the maintenance tracking result and transmits it to the human-computer interaction terminal.

[0020] In this embodiment, it should be specifically noted that for the Internet of Things device monitoring environment recognition module, the Internet of Things communication signal data acquisition unit obtains the received power of the communication signal at the environment sensor interface through the environment sensor. The environment sensor performs communication denoising processing on the Internet of Things communication signal during the acquisition of Internet of Things communication signal data. Noise is an inevitable problem in the signal acquisition process, which will affect the authenticity and accuracy of the data. Through communication denoising processing, the influence of noise on the signal can be effectively reduced, thereby improving the accuracy of the collected data. This is crucial for the Internet of Things system because accurate data is the basis for subsequent analysis and decision-making; The Internet of Things communication signal evaluation unit evaluates the Internet of Things communication signal based on the received power of the communication signal at the environment sensor interface. The calculation formula is: , where represents the Internet of Things communication signal evaluation value, represents the received power of the communication signal at the environment sensor interface, represents the reference received power of the preset communication signal, represents the received strength of the preset communication signal, where It represents the received strength of the communication signal at the environmental sensor interface, and the ratio of it to the preset received strength of the communication signal reflects the quality of the Internet of Things communication signal; When the received power of the communication signal at the environmental sensor interface is 0.2 mW and the reference received power of the preset communication signal is 0.1 mW, the received strength of the communication signal at the environmental sensor interface is: ; When the Internet of Things communication signal evaluation value is greater than or equal to the preset evaluation threshold, the evaluation result of the Internet of Things communication signal is that the communication signal is normal, and a cloud hierarchical processing strategy switching instruction is sent to the cloud hierarchical processing strategy switching module; when the Internet of Things communication signal evaluation value is less than the preset evaluation threshold, the evaluation result of the Internet of Things communication signal is that the communication signal is abnormal, and a cloud warning information prompt instruction is sent to the cloud warning information prompt module.

[0021] In this embodiment, it should be specifically noted that in the cloud processing strategy switching module: the no recognition target unit is used for cloud security processing of Internet of Things devices; the recognition target tracking unit is used for cloud tracking processing of recognition targets; When the evaluation result of the Internet of Things communication signal is that the communication signal is normal, target recognition is performed on the monitoring area. When there is no moving target in the monitoring area, the no recognition target unit is used to perform cloud security processing on the Internet of Things devices; when there is a moving target in the monitoring area, the dual-unit processing strategy is switched to perform dual-unit cloud processing using the no recognition target unit and the recognition target tracking unit.

[0022] In this embodiment, it should be specifically noted that the specific content of the no recognition target unit for performing cloud security processing on Internet of Things devices is as follows: The data packets entering the cloud network link from the Internet of Things device network are segmented according to a time window with a length of T into n sub-data packets, where i = 1, 2, 3,..., n, and i represents the number of the sub-data packet; Based on the time window, network situation analysis is performed on each sub-data packet to obtain the network situation awareness index of each sub-data packet. The calculation formula is: , where represents the network situation awareness index of each sub-data packet within a time window with a length of T. The larger the network situation awareness index, the higher the risk, represents the number of attacks on each sub-data packet within a time window with a length of T, represents the number of unpatched vulnerabilities of each sub-data packet within a time window with a length of T, represents the total number of vulnerabilities generated by each sub-data packet within a time window with a length of T, and Represents the weight coefficient of the network situation awareness index, and ; The parameter sets the time window T = 1h, and the weight coefficient of the network situation awareness index , , when the number of attacks on each sub - data packet within the time window of length T , the number of unpatched vulnerabilities of each sub - data packet within the time window of length T , the total number of vulnerabilities generated by each sub - data packet within the time window of length T , then .

[0023] In this embodiment, it should be specifically noted that the specific content of the recognition target tracking unit for cloud - tracking the recognition target is as follows: Obtain the video stream of the recognition target through a camera, and perform frame - by - frame processing on the video stream to obtain M frames of the recognition target's frame - by - frame images, where m = 1, 2, 3,..., M, and m represents the number of the frame - by - frame image; According to the pixel point coordinates within the target contour area in the frame - by - frame image , where k represents the pixel point number within the target contour area in each frame - by - frame image, k = 1, 2, 3,..., K, and K represents the total number of pixel points within the target contour area in each frame - by - frame image, calculate the centroid point coordinates of each frame - by - frame image : , where represents the abscissa of the centroid point of each frame - by - frame image; , where represents the ordinate of the centroid point of each frame - by - frame image; Connect the centroid point coordinates of each frame - by - frame image in sequence to obtain the cloud - tracking path curve of the recognition target.

[0024] In this embodiment, it should be specifically noted that in the cloud - processing risk recognition module, the specific content of obtaining the risk index of the non - recognition - target unit and the risk index of the recognition target tracking unit and performing risk assessment based on the risk recognition result is as follows: Judge the number of risk data packets based on the network situation awareness index of each sub - data packet obtained by the non - recognition - target unit: when the network situation awareness index is greater than the preset risk judgment threshold, then judge the data packet as a risk data packet; Calculate the risk index of the non - recognition - target unit, and the calculation formula is: , where represents the risk index of the non - recognition - target unit, represents the number of risk data packets judged by the non - recognition - target unit, Indicates the total number of data packets without segmentation of the recognized target unit; Calculate the risk index of the recognized target tracking unit based on the cloud tracking path curve obtained by the recognized target tracking unit. The calculation formula is: , where Indicates the risk index of the recognized target tracking unit, Indicates the interval time of the recognized target from the m-th centroid point to the m + 1-th centroid point, where Indicates the interval time of the recognized target from the 1st centroid point to the 2nd centroid point, Indicates the interval time of the recognized target from the 2nd centroid point to the 3rd centroid point, Indicates the interval time of the recognized target from the 3rd centroid point to the 4th centroid point, Indicates the interval time of the recognized target from the M - 1-th centroid point to the M-th centroid point.

[0025] In this embodiment, it should be specifically noted that the specific content of risk assessment based on the risk recognition result is as follows: When the risk index of the unit without recognized target is greater than the preset first cloud threshold, the first risk assessment result is high risk; otherwise, the first risk assessment result is low risk; When the risk index of the recognized target tracking unit is greater than the preset second cloud threshold, the second risk assessment result is high risk; otherwise, the second risk assessment result is low risk.

[0026] In this embodiment, it should be specifically noted that the cloud warning information prompt module issues an Internet of Things device network warning information prompt based on the first risk assessment result; and issues a recognized target behavior warning information prompt based on the second risk assessment result.

[0027] In this embodiment, it should be specifically noted that the device monitoring, maintenance and tracking module respectively performs maintenance and tracking on the unit without recognized target and the unit with abnormal recognition target according to the warning information prompt, locates the maintenance and tracking result and transmits it to the human-computer interaction end.

[0028] As Figure 2 shown, in this embodiment, it should be specifically noted that an Internet of Things device monitoring method based on big data includes the following steps: Step S01: Obtain the communication signal data of the Internet of Things device through the Internet of Things communication signal data acquisition unit, and perform an evaluation of the Internet of Things communication signal based on the data; Step S02: Identify abnormal targets based on the evaluation result of the Internet of Things communication signal, and switch the cloud processing strategy for cloud processing; Step S03: Monitor the cloud status in real time, obtain the risk index of the unit without recognized target and the risk index of the unit for tracking recognized target, and conduct risk assessment based on the risk recognition result; Step S04: The cloud issues a warning information prompt according to the risk assessment result; Step S05: Maintain and track the unit without recognized target and the unit with abnormal recognized target respectively according to the warning information prompt.

[0029] In this embodiment, it should be specifically noted that the main difference between this embodiment and the prior art is that this embodiment obtains the communication signal data of the Internet of Things device through the Internet of Things communication signal data acquisition unit, evaluates the data, discovers communication signal anomalies in time, thereby switches the cloud processing strategy, and conducts targeted processing on abnormal targets. At the same time, it monitors the cloud status in real time, obtains the risk index of the unit without recognized target and the risk index of the unit for tracking recognized target, and conducts risk assessment based on the risk recognition result, further improving the security and reliability of the system; When the risk assessment result shows high risk, the cloud warning information prompt module will issue a warning information prompt in time so that relevant personnel can quickly take measures for processing. Finally, the device monitoring, maintenance and tracking module maintains and tracks the unit without recognized target and the unit with abnormal recognized target according to the warning information prompt to ensure the normal operation and security of the device.

[0030] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0031] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. An Internet of Things device monitoring system based on big data, characterized in that: Including: An Internet of Things device monitoring environment recognition module, a cloud processing strategy switching module, a cloud processing risk recognition module, a cloud warning information prompting module, and a device monitoring and maintenance tracking module; The Internet of Things device monitoring environment recognition module includes an Internet of Things communication signal data acquisition unit and an Internet of Things communication signal evaluation unit. The Internet of Things communication signal data acquisition unit obtains the communication signal data of the Internet of Things device and evaluates the Internet of Things communication signal based on the data; The cloud processing strategy switching module includes an unrecognized target unit and a recognized target tracking unit. Based on the Internet of Things communication signal evaluation result of the Internet of Things device monitoring environment recognition module, it recognizes abnormal targets and switches the cloud processing strategy for cloud processing; The cloud processing risk recognition module, when performing cloud processing, monitors the cloud status in real time, obtains the risk index of the unrecognized target unit and the risk index of the recognized target tracking unit, and conducts risk assessment based on the risk recognition result; The cloud warning information prompting module, the cloud issues warning information prompts based on the risk assessment result, including the risk warning information prompt of the unrecognized target unit and the risk warning information prompt of the recognized abnormal target unit; The device monitoring and maintenance tracking module respectively conducts maintenance tracking on the unrecognized target unit and the recognized abnormal target unit according to the warning information prompt, locates the maintenance tracking result and transmits it to the human-computer interaction terminal.

2. The Internet of Things device monitoring system based on big data according to claim 1, wherein: In the Internet of Things device monitoring environment recognition module, the Internet of Things communication signal data acquisition unit obtains the received power of the communication signal at the environment sensor interface through the environment sensor, and the environment sensor performs communication denoising processing on the Internet of Things communication signal when collecting the Internet of Things communication signal data; The Internet of Things communication signal evaluation unit evaluates the Internet of Things communication signal based on the received power of the communication signal at the environmental sensor interface, and the calculation formula is: , where represents the evaluation value of the Internet of Things communication signal, represents the received power of the communication signal at the environmental sensor interface, represents the reference received power of the preset communication signal, represents the received strength of the preset communication signal; When the Internet of Things communication signal evaluation value is greater than or equal to the preset evaluation threshold, the Internet of Things communication signal evaluation result is that the communication signal is normal, and a cloud classification processing strategy switching instruction is sent to the cloud classification processing strategy switching module; when the Internet of Things communication signal evaluation value is less than the preset evaluation threshold, the Internet of Things communication signal evaluation result is that the communication signal is abnormal, and a cloud warning information prompting instruction is sent to the cloud warning information prompting module.

3. The Internet of Things device monitoring system based on big data according to claim 1, characterized in that: In the cloud processing strategy switching module: The unrecognized target unit is used for cloud security processing of the Internet of Things device; The recognized target tracking unit is used for cloud tracking processing of the recognized target; When the Internet of Things communication signal evaluation result is that the communication signal is normal, target recognition is performed on the monitoring area. When there is no moving target in the monitoring area, the unrecognized target unit is used for cloud security processing of the Internet of Things device; when there is a moving target in the monitoring area, the dual-unit processing strategy is switched to use the unrecognized target unit and the recognized target tracking unit for dual-unit cloud processing.

4. An Internet of Things device monitoring system based on big data according to claim 3, characterized in that: The specific content of the unrecognized target unit for cloud security processing of the Internet of Things device is as follows: The data packets on the network link from the Internet of Things device network to the cloud network are sliced according to a time window with a length of T into n sub-data packets, where i = 1, 2, 3,..., n, and i represents the serial number of the sub-data packet; Perform network situation analysis on each sub-packet according to the time window to obtain the network situation awareness index of each sub-packet. The calculation formula is: , where represents the network situation awareness index of each sub-packet within a time window of length T, represents the number of attacks on each sub-packet within a time window of length T, represents the number of unfixed vulnerabilities of each sub-packet within a time window of length T, represents the total number of vulnerabilities generated by each sub-packet within a time window of length T, and represent the weight coefficients of the network situation awareness index.

5. The Internet of Things device monitoring system based on big data according to claim 3, characterized in that: The specific content of the recognized target tracking unit for cloud tracking processing of the recognized target is as follows: Obtain the video stream of the recognition target through the camera, and perform frame segmentation processing on the video stream to obtain M frames of segmented images of the recognition target, where m = 1, 2, 3,..., M, and m represents the serial number of the segmented image; According to the pixel point coordinates within the target contour area in the framed image , where k represents the pixel point number within the target contour area in each framed image, k = 1, 2, 3,..., K, and K represents the total number of pixel points within the target contour area in each framed image, calculate the centroid point coordinates of each framed image : , where represents the abscissa of the centroid point of each sub-frame image; , where represents the ordinate of the centroid point of each sub-frame image; Connect the centroid coordinates of each segmented image in sequence to obtain the cloud tracking path curve of the recognition target.

6. The Internet of Things device monitoring system based on big data according to claim 1, characterized in that: In the cloud processing risk recognition module, the specific content of obtaining the risk index of the unit without recognition target and the risk index of the recognition target tracking unit and performing risk assessment based on the risk recognition result is as follows: Judge the number of risk data packets according to the network situation awareness index of each sub-data packet obtained by the unit without recognition target: when the network situation awareness index is greater than the preset risk judgment threshold, the data packet is judged as a risk data packet; Calculate the risk index of the unit without recognized target, and the calculation formula is: , where represents the risk index of the unit without recognized target, represents the number of risk data packets judged by the unit without recognized target, represents the total number of data packets segmented by the unit without recognized target; Calculate the risk index of the recognition target tracking unit based on the cloud tracking path curve obtained by the recognition target tracking unit. The calculation formula is as follows: , where represents the risk index of the recognition target tracking unit, represents the time interval from the m-th centroid point to the (m + 1)-th centroid point of the recognition target.

7. An Internet of Things device monitoring system based on big data according to claim 6, characterized in that: The specific content of performing risk assessment based on the risk recognition result is as follows: When the risk index of the unit without recognition target is greater than the preset first cloud threshold, the first risk assessment result is high risk; otherwise, the first risk assessment result is low risk; When the risk index of the recognition target tracking unit is greater than the preset second cloud threshold, the second risk assessment result is high risk; otherwise, the second risk assessment result is low risk.

8. An Internet of Things device monitoring system based on big data according to claim 1, characterized in that: The cloud warning information prompt module issues an Internet of Things device network warning information prompt according to the first risk assessment result; issues a recognition target behavior warning information prompt according to the second risk assessment result.

9. An Internet of Things device monitoring system based on big data according to claim 1, characterized in that: The device monitoring, maintenance and tracking module performs maintenance and tracking on the unit without recognition target and the unit with abnormal recognition target respectively according to the warning information prompt, locates the maintenance and tracking result and transmits it to the human-computer interaction terminal.

10. A method for monitoring Internet of Things devices based on big data, which is used for a system for monitoring Internet of Things devices based on big data according to any one of claims 1-9 above, characterized in that: It includes the following steps: Step S01: Obtain the communication signal data of the Internet of Things device through the Internet of Things communication signal data acquisition unit, and perform Internet of Things communication signal evaluation based on the data; Step S02: Identify abnormal targets based on the Internet of Things communication signal evaluation result, and switch the cloud processing strategy for cloud processing; Step S03: Monitor the cloud status in real time, obtain the risk index of the unit without recognition target and the risk index of the recognition target tracking unit, and perform risk assessment based on the risk recognition result; Step S04: The cloud issues a warning information prompt according to the risk assessment result; Step S05: Perform maintenance and tracking on the unit without recognition target and the unit with abnormal recognition target respectively according to the warning information prompt.

Images