A sensor module intelligent monitoring system and method based on the Internet of Things
By building a data monitoring cloud platform and data classification model in the Internet of Things system, intelligently selecting sensor modules for monitoring, the problem of excessive sensors and complicated data in regional Internet of Things monitoring is solved, and the flexibility and intelligence of the system are improved , realize timely monitoring and early warning of abnormal events.
Patent Information
- Application Number
- CN202410464700.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-18
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-04-18
AI Technical Summary
There are too many sensors in the existing regional IoT monitoring systems, complex data summary and large calculation volume, resulting in huge resource consumption and insufficient system flexibility and intelligence, making it difficult to effectively monitor abnormal events.
Using an intelligent monitoring system for sensor modules based on the Internet of Things, the IoT cloud platform is built to obtain working conditions and environment information, and a data classification model is built based on the historical large database to form sensor module data monitoring, and summarize it on the visual monitoring page. It is intelligent Select the identification sensor module for monitoring and promptly warn.
It reduces the computing level, improves the flexibility and intelligence of the regional Internet of Things detection system, can effectively monitor and warning of abnormal events, and solves the problems of excessive sensors and complex data.
Smart Images

Figure CN118518157B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of sensor module monitoring technology, and in particular to an Internet of Things-based sensor module intelligent monitoring system and method. Background Art
[0002] The Internet of Things is a network that connects any object to the Internet through information sensing devices such as radio frequency identification (RFID), infrared sensors, global positioning systems, laser scanners, etc., according to agreed protocols, to exchange information and communicate, so as to achieve intelligent identification, positioning, tracking, monitoring and management. In the current technology, regional Internet of Things monitoring belongs to a new monitoring field, ranging from smart homes and smart factories to smart cities. With the help of sensors, data is collected and summarized in the region, and analyzed and sorted on the Internet of Things cloud platform, so as to monitor and solve abnormal events in time. However, there is a big problem in the current regional Internet of Things monitoring, that is, there are too many sensors, data aggregation is too complicated, the amount of calculation is large, and the resource consumption is huge. Although the use of effective modules can greatly reduce the calculation level, the fixed selection of modules reduces the flexibility and intelligence of the entire detection system, resulting in the difficulty in exerting advantages in the overall regional monitoring level. Summary of the invention
[0003] The purpose of the present invention is to provide a sensor module intelligent monitoring system and method based on the Internet of Things to solve the problems raised in the above background technology.
[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a sensor module intelligent monitoring method based on the Internet of Things, the method comprising the following steps:
[0005] S1. Build a regional data monitoring IoT cloud platform to call the collected data of system sensors in the region;
[0006] S2. Obtain working environment information and build a data classification model for each working environment based on the historical big database;
[0007] S3. Based on different data classification models, sensor module data monitoring is formed and summarized on the visual monitoring page for administrators to view.
[0008] According to the above technical solution, in steps S1-S2, the working environment includes a day and night environment and a monitoring environment;
[0009] The day and night environment includes daytime and nighttime, the daytime refers to 7:00 to 19:00; the nighttime refers to 19:00 to 7:00, and the endpoint time in the day and night environment includes the time before but not the time after; the monitoring environment includes the weather environment, the flow of people environment, the traffic environment and the construction environment in the area;
[0010] The monitoring environment uses fixed time periods as monitoring nodes, and the data at the end time of the fixed time period of the previous monitoring node is used as the initial data of the next monitoring node. Whether the fixed time period is continuous is set by the system;
[0011] The weather environment includes sunny days, rainy and snowy days, bad weather and other weather; among them, bad weather refers to the weather warning disaster level exceeding the system set level, and other weather refers to weather conditions other than sunny days, rainy and snowy days and bad weather; the pedestrian flow environment refers to the pedestrian flow density data in the area; the traffic environment refers to the vehicle flow density data in the area; the construction environment in the area refers to the number of regional constructions in the area. The regional construction is marked with a level by the system, and the level threshold is set based on whether it affects normal life in the area. Regional construction that exceeds the level threshold will be recorded in the construction environment in the area.
[0012] According to the above technical solution, the construction of the data classification model under each working condition includes:
[0013] Construct a training data set, use the day and night environment as classification nodes, and classify the historical big data database to form daytime historical big data and nighttime historical big data after classification;
[0014] Select one of the daytime historical big data and the nighttime historical big data, and perform analysis and processing to form a corresponding data classification model. The forming of the corresponding data classification model includes:
[0015] Obtain the initial data of the current monitoring node, use any monitoring environment as the first priority analysis node in the monitoring environment, and use other monitoring environments as secondary analysis nodes. In the corresponding historical big data, mark the data with abnormal events. The abnormal event refers to the event in which the system in the area has an alarm record. The alarm in the area generally refers to the emergency situation in the area at that time that does not meet the system preset conditions, such as traffic congestion, excessive flow of people, etc. For example, the preset traffic volume in the system is 10. Once the sensor feedback exceeds 10, an alarm record will appear, and the feedback sensor will also be marked;
[0016] Randomly select N groups of historical big data similar to the data of the first priority analysis node, where the similarity means that the selected historical big data and the initial data of the current monitoring node are in the same range on the first priority analysis node, and the range is preset by the system for several range values;
[0017] Obtain data of abnormal events in the selected historical big data, and mark the associated sensors of each abnormal event. For each abnormal event, the number of times the associated sensor is marked is increased by 1, until all the selected historical big data are traversed to form a sensor sequence from large to small;
[0018] All monitoring environments are processed in turn to form four sensor queues, which are then mixed into a queue from largest to smallest in terms of the number of markings, and the number of markings of the same sensor is added up.
[0019] According to the above technical solution, it also includes:
[0020] The system sets the number of sensors in the sensor module to M, selects M sensors from large to small in the mixed queue as identification sensor modules for intelligent monitoring, obtains the number of abnormal events corresponding to each sensor in the identification sensor module, calculates the data proportion of the number of abnormal events in the selected historical big data, and sums and averages the data proportion of each sensor in the identification sensor module to form a monitoring threshold. If the probability of the number of sensors in the identification sensor module that do not meet the system-set threshold exceeds the monitoring threshold during the monitoring process, an early warning is performed and summarized on the visual monitoring page.
[0021] A sensor module intelligent monitoring system based on the Internet of Things, the system includes: an Internet of Things cloud platform module, a regional operating condition processing module, a historical big database, a data classification module and an intelligent monitoring module;
[0022] The IoT cloud platform module is used to build an IoT cloud platform for data monitoring in the region and call the collected data of system sensors in the region; the regional working condition processing module is used to obtain working condition environment information and build a data classification model for each working condition environment based on the historical big database; the historical big database is used to store the historical monitoring big data and abnormal event records of sensors in the region; the data classification module forms sensor module data monitoring based on different data classification models and summarizes it on the visual monitoring page; the intelligent monitoring module is used to control the visual monitoring page, connect to the administrator port, and send out an alarm signal;
[0023] The output end of the Internet of Things cloud platform module is connected to the input end of the regional operating condition processing module and the historical big database; the output end of the regional operating condition processing module is connected to the input end of the data classification module; the output end of the historical big database is connected to the input end of the regional operating condition processing module; the output end of the data classification module is connected to the input end of the intelligent monitoring module.
[0024] According to the above technical solution, the IoT cloud platform module includes a regional construction unit and a sensor distribution control unit;
[0025] The area construction unit is used to construct an intelligent monitoring area, arrange sensors in the area, build a cloud platform, and aggregate sensor transmission data; the sensor distribution control unit is used to control the on / off and combination of sensors arranged in the area;
[0026] An output end of the area construction unit is connected to an input end of the sensor distribution control unit.
[0027] According to the above technical solution, the regional operating condition processing module includes an operating condition environment classification unit and a model analysis unit;
[0028] The working environment classification unit is used to obtain working environment information, and the working environment includes a day and night environment and a monitoring environment; the day and night environment includes daytime and nighttime, and the daytime refers to 7:00 to 19:00; the nighttime refers to 19:00 to 7:00, and the endpoint time in the day and night environment includes the time before but not the time after; the monitoring environment includes the weather environment, the flow of people environment, the traffic environment, and the construction environment in the area; the model analysis unit constructs a data classification model under each working environment based on the data of the historical big data database;
[0029] The output end of the operating environment classification unit is connected to the input end of the model analysis unit.
[0030] According to the above technical solution, the data classification module includes a sensor module data monitoring unit and a summary analysis unit;
[0031] The sensor module data monitoring unit forms sensor module data monitoring based on different data classification models and constructs an identification sensor module; the summary analysis unit is used to perform early warning processing during the monitoring process when the probability of the number of sensors in the identification sensor module that do not meet the system set threshold exceeds the monitoring threshold, and summarizes it on the visual monitoring page;
[0032] The output end of the sensor module data monitoring unit is connected to the input end of the summary analysis unit.
[0033] According to the above technical solution, the intelligent monitoring module includes a visualization unit and an early warning unit;
[0034] The visualization unit is used to build a visualization platform and control the visualization monitoring page; the early warning unit is used to connect to the administrator port and send out an alarm signal;
[0035] The output end of the visualization unit is connected to the input end of the early warning unit.
[0036] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention forms an identification sensor module by adopting classification analysis of working condition environment data. In the field of regional Internet of Things monitoring, it can solve the problems of too many sensors, too complicated data aggregation, large amount of calculation, and huge resource consumption. It adopts an effective module intelligent selection method to greatly reduce the calculation level, improve the flexibility and intelligence of the regional Internet of Things detection system, and timely monitor and solve early warning of abnormal events. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0038] Figure 1 It is a flow chart of a sensor module intelligent monitoring system and method based on the Internet of Things of the present invention. DETAILED DESCRIPTION
[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0040] See also Figure 1 The present invention provides a technical solution: a sensor module intelligent monitoring method based on the Internet of Things, the method comprising the following steps:
[0041] S1. Build a regional data monitoring IoT cloud platform to call the collected data of system sensors in the region;
[0042] S2. Obtain working environment information and build a data classification model for each working environment based on the historical big database;
[0043] S3. Based on different data classification models, sensor module data monitoring is formed and summarized on the visual monitoring page for administrators to view.
[0044] In steps S1-S2, the working environment includes a day and night environment and a monitoring environment;
[0045] The day and night environment includes daytime and nighttime, the daytime refers to 7:00 to 19:00; the nighttime refers to 19:00 to 7:00, and the endpoint time in the day and night environment includes the time before but not the time after; the monitoring environment includes the weather environment, the flow of people environment, the traffic environment and the construction environment in the area;
[0046] The monitoring environment uses fixed time periods as monitoring nodes, and the data at the end time of the fixed time period of the previous monitoring node is used as the initial data of the next monitoring node. Whether the fixed time period is continuous is set by the system;
[0047] The weather environment includes sunny days, rainy and snowy days, bad weather and other weather; among them, bad weather refers to the weather warning disaster level exceeding the system set level, and other weather refers to weather conditions other than sunny days, rainy and snowy days and bad weather; the pedestrian flow environment refers to the pedestrian flow density data in the area; the traffic environment refers to the vehicle flow density data in the area; the construction environment in the area refers to the number of regional constructions in the area. The regional construction is marked with a level by the system, and the level threshold is set based on whether it affects normal life in the area. Regional construction that exceeds the level threshold will be recorded in the construction environment in the area.
[0048] The construction of the data classification model under each working condition includes:
[0049] Construct a training data set, use the day and night environment as classification nodes, and classify the historical big data database to form daytime historical big data and nighttime historical big data after classification;
[0050] Select one of the daytime historical big data and the nighttime historical big data, and perform analysis and processing to form a corresponding data classification model. The forming of the corresponding data classification model includes:
[0051] Obtain the initial data of the current monitoring node, use any monitoring environment as the first priority analysis node in the monitoring environment, and use other monitoring environments as secondary analysis nodes. In the corresponding historical big data, mark the data with abnormal events, where the abnormal event refers to an event in which an alarm record occurs in the system in the area;
[0052] Randomly select N groups of historical big data similar to the data of the first priority analysis node, where the similarity means that the selected historical big data and the initial data of the current monitoring node are in the same range on the first priority analysis node, and the range is preset by the system for several range values;
[0053] Obtain data of abnormal events in the selected historical big data, and mark the associated sensors of each abnormal event. For each abnormal event, the number of times the associated sensor is marked is increased by 1, until all the selected historical big data are traversed to form a sensor sequence from large to small;
[0054] All monitoring environments are processed in turn to form four sensor queues, which are then mixed into a queue from largest to smallest in terms of the number of markings, and the number of markings of the same sensor is added up.
[0055] The system sets the number of sensors in the sensor module to M, selects M sensors from large to small in the mixed queue as identification sensor modules for intelligent monitoring, obtains the number of abnormal events corresponding to each sensor in the identification sensor module, calculates the data proportion of the number of abnormal events in the selected historical big data, and sums and averages the data proportion of each sensor in the identification sensor module to form a monitoring threshold. If the probability of the number of sensors in the identification sensor module that do not meet the system-set threshold exceeds the monitoring threshold during the monitoring process, an early warning is performed and summarized on the visual monitoring page.
[0056] A sensor module intelligent monitoring system based on the Internet of Things is also provided, which includes: an Internet of Things cloud platform module, a regional working condition processing module, a historical big database, a data classification module and an intelligent monitoring module;
[0057] The IoT cloud platform module is used to build an IoT cloud platform for data monitoring in the region and call the collected data of system sensors in the region; the regional working condition processing module is used to obtain working condition environment information and build a data classification model for each working condition environment based on the historical big database; the historical big database is used to store the historical monitoring big data and abnormal event records of sensors in the region; the data classification module forms sensor module data monitoring based on different data classification models and summarizes it on the visual monitoring page; the intelligent monitoring module is used to control the visual monitoring page, connect to the administrator port, and send out an alarm signal;
[0058] The output end of the Internet of Things cloud platform module is connected to the input end of the regional operating condition processing module and the historical big database; the output end of the regional operating condition processing module is connected to the input end of the data classification module; the output end of the historical big database is connected to the input end of the regional operating condition processing module; the output end of the data classification module is connected to the input end of the intelligent monitoring module.
[0059] The IoT cloud platform module includes a regional construction unit and a sensor distribution control unit;
[0060] The area construction unit is used to construct an intelligent monitoring area, arrange sensors in the area, build a cloud platform, and aggregate sensor transmission data; the sensor distribution control unit is used to control the on / off and combination of sensors arranged in the area;
[0061] An output end of the area construction unit is connected to an input end of the sensor distribution control unit.
[0062] The regional operating condition processing module includes an operating condition environment classification unit and a model analysis unit;
[0063] The working environment classification unit is used to obtain working environment information, and the working environment includes a day and night environment and a monitoring environment; the day and night environment includes daytime and nighttime, and the daytime refers to 7:00 to 19:00; the nighttime refers to 19:00 to 7:00, and the endpoint time in the day and night environment includes the time before but not the time after; the monitoring environment includes the weather environment, the flow of people environment, the traffic environment, and the construction environment in the area; the model analysis unit constructs a data classification model under each working environment based on the data of the historical big data database;
[0064] The output end of the operating environment classification unit is connected to the input end of the model analysis unit.
[0065] The data classification module includes a sensor module data monitoring unit and a summary analysis unit;
[0066] The sensor module data monitoring unit forms sensor module data monitoring based on different data classification models and constructs an identification sensor module; the summary analysis unit is used to perform early warning processing during the monitoring process when the probability of the number of sensors in the identification sensor module that do not meet the system set threshold exceeds the monitoring threshold, and summarizes it on the visual monitoring page;
[0067] The output end of the sensor module data monitoring unit is connected to the input end of the summary analysis unit.
[0068] The intelligent monitoring module includes a visualization unit and an early warning unit;
[0069] The visualization unit is used to build a visualization platform and control the visualization monitoring page; the early warning unit is used to connect to the administrator port and send out an alarm signal;
[0070] The output end of the visualization unit is connected to the input end of the early warning unit.
[0071] In this embodiment:
[0072] Build a monitoring area, construct a monitoring IoT cloud platform in the area, deploy sensor systems in the area, monitor data in the area, and record the data in the historical big database;
[0073] Acquire working environment information, wherein the working environment includes day and night environment and monitoring environment;
[0074] The day and night environment includes daytime and nighttime, the daytime refers to 7:00 to 19:00; the nighttime refers to 19:00 to 7:00, and the endpoint time in the day and night environment includes the time before but not the time after; the monitoring environment includes the weather environment, the flow of people environment, the traffic environment and the construction environment in the area;
[0075] The monitoring environment uses fixed time periods as monitoring nodes, and the data at the end time of the fixed time period of the previous monitoring node is used as the initial data of the next monitoring node. Whether the fixed time period is continuous is set by the system;
[0076] In this embodiment, the fixed time period is set continuously as one hour, that is, 3 o'clock to 4 o'clock is a fixed time period, and the period includes the time point of 3 o'clock but does not include the time point of 4 o'clock;
[0077] The weather environment includes sunny days, rainy and snowy days, bad weather and other weather; among them, bad weather refers to the weather warning disaster level exceeding the system set level, and other weather refers to weather conditions other than sunny days, rainy and snowy days and bad weather; the pedestrian flow environment refers to the pedestrian flow density data in the area; the traffic environment refers to the vehicle flow density data in the area; the construction environment in the area refers to the number of regional constructions in the area. The regional construction is marked with a level by the system, and the level threshold is set based on whether it affects normal life in the area. Regional construction that exceeds the level threshold will be recorded in the construction environment in the area.
[0078] For example, if the system sets the level as 3 for road construction and power grid construction, and 1 for building construction, then road construction and power grid construction will affect normal life in the area, while building construction will generally not affect it;
[0079] The construction of the data classification model under each working condition includes:
[0080] Construct a training data set, use the day and night environment as classification nodes, and classify the historical big data database to form daytime historical big data and nighttime historical big data after classification;
[0081] Select one of the daytime historical big data and the nighttime historical big data, and perform analysis and processing to form a corresponding data classification model. The forming of the corresponding data classification model includes:
[0082] Obtain the initial data of the current monitoring node, use any monitoring environment as the first priority analysis node in the monitoring environment, and use other monitoring environments as secondary analysis nodes. In the corresponding historical big data, mark the data with abnormal events, where the abnormal event refers to an event in which an alarm record occurs in the system in the area;
[0083] Randomly select N groups of historical big data similar to the data of the first priority analysis node, where the similarity means that the selected historical big data and the initial data of the current monitoring node are in the same range on the first priority analysis node, and the range is preset by the system for several range values;
[0084] For example, if the weather environment is the first priority for analyzing node data, and the initial data of the current monitoring node is sunny, then when selecting, all historical big data with sunny days are selected, and N groups are randomly selected from them;
[0085] Obtain data of abnormal events in the selected historical big data, and mark the associated sensors of each abnormal event. For each abnormal event, the number of times the associated sensor is marked is increased by 1, until all the selected historical big data are traversed to form a sensor sequence from large to small;
[0086] All monitoring environments are processed in turn to form four sensor queues, which are then mixed into a queue from largest to smallest in terms of the number of markings, and the number of markings of the same sensor is added up.
[0087] The system sets the number of sensors in the sensor module to M, selects M sensors from the largest to the smallest in the mixed queue as identification sensor modules for intelligent monitoring, obtains the number of abnormal events corresponding to each sensor in the identification sensor module, calculates the data proportion of the number of abnormal events in the selected historical big data, and sums and averages the data proportion of each sensor in the identification sensor module to form a monitoring threshold;
[0088] For example, if the number of abnormal events corresponding to a certain sensor is 10 and the total data set is 100, then the data accounts for one tenth. The abnormal events here are repeatable, because while one abnormal event corresponds to changes in multiple sensor data, the total data set remains unchanged.
[0089] If during the monitoring process, the probability that the number of sensors in the identification sensor module that do not meet the system-set threshold exceeds the monitoring threshold, an early warning will be processed and summarized on the visual monitoring page.
[0090] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0091] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A sensor module intelligent monitoring method based on the Internet of Things, characterized in that: The method comprises the following steps: S1. Build a regional data monitoring IoT cloud platform to call the collected data of system sensors in the region; S2. Obtain working environment information and build a data classification model for each working environment based on the historical big database; S3. Based on different data classification models, sensor module data monitoring is formed and summarized on a visual monitoring page for administrators to view; In steps S1-S2, the working environment includes a day and night environment and a monitoring environment; The day and night environment includes daytime and nighttime, the daytime refers to 7:00 to 19:00; the nighttime refers to 19:00 to 7:00, and the endpoint time in the day and night environment includes the time before but not the time after; the monitoring environment includes the weather environment, the flow of people environment, the traffic environment and the construction environment in the area; The monitoring environment uses fixed time periods as monitoring nodes, and the data at the end time of the fixed time period of the previous monitoring node is used as the initial data of the next monitoring node. Whether the fixed time period is continuous is set by the system; The weather environment includes sunny days, rainy and snowy days, bad weather and other weather; among which bad weather refers to weather warning disaster levels exceeding the system set level, and other weather refers to weather conditions other than sunny days, rainy and snowy days and bad weather; the pedestrian flow environment refers to pedestrian flow density data in the area; the traffic environment refers to vehicle flow density data in the area; the construction environment in the area refers to the number of regional constructions in the area, and the regional construction is marked with a level by the system, and the level threshold is set based on whether it affects normal life in the area, and regional constructions that exceed the level threshold are recorded in the regional construction environment; The construction of the data classification model under each working condition includes: Construct a training data set, use the day and night environment as classification nodes, and classify the historical big data database to form daytime historical big data and nighttime historical big data after classification; Select one of the daytime historical big data and the nighttime historical big data, and perform analysis and processing to form a corresponding data classification model. The forming of the corresponding data classification model includes: Obtain the initial data of the current monitoring node, use any monitoring environment as the first priority analysis node in the monitoring environment, and use other monitoring environments as secondary analysis nodes. In the corresponding historical big data, mark the data with abnormal events, where the abnormal event refers to an event in which an alarm record occurs in the system in the area; Randomly select N groups of historical big data similar to the data of the first priority analysis node, where the similarity means that the selected historical big data and the initial data of the current monitoring node are in the same range on the first priority analysis node, and the range is preset by the system for several range values; Obtain data of abnormal events in the selected historical big data, and mark the associated sensors of each abnormal event. For each abnormal event, the number of times the associated sensor is marked is increased by 1, until all the selected historical big data are traversed to form a sensor sequence from large to small; All monitoring environments are processed in turn to form four sensor queues, which are then mixed into a queue from largest to smallest in terms of the number of markings, and the number of markings of the same sensor is added up.
2. The method for intelligent monitoring of sensor modules based on the Internet of Things according to claim 1, characterized in that: Also includes: The system sets the number of sensors in the sensor module to M, selects M sensors from large to small in the mixed queue as identification sensor modules for intelligent monitoring, obtains the number of abnormal events corresponding to each sensor in the identification sensor module, calculates the data proportion of the number of abnormal events in the selected historical big data, and sums and averages the data proportion of each sensor in the identification sensor module to form a monitoring threshold. If the probability of the number of sensors in the identification sensor module that do not meet the system-set threshold exceeds the monitoring threshold during the monitoring process, an early warning is performed and summarized on the visual monitoring page.
3. A sensor module intelligent monitoring system based on the Internet of Things, using the sensor module intelligent monitoring method based on the Internet of Things as claimed in claim 1, characterized in that: The system includes: Internet of Things cloud platform module, regional working condition processing module, historical big database, data classification module and intelligent monitoring module; The IoT cloud platform module is used to build an IoT cloud platform for data monitoring in the region and call the collected data of system sensors in the region; the regional working condition processing module is used to obtain working condition environment information and build a data classification model for each working condition environment based on the historical big database; the historical big database is used to store the historical monitoring big data and abnormal event records of sensors in the region; the data classification module forms sensor module data monitoring based on different data classification models and summarizes it on the visual monitoring page; the intelligent monitoring module is used to control the visual monitoring page, connect to the administrator port, and send out an alarm signal; The output end of the Internet of Things cloud platform module is connected to the input end of the regional operating condition processing module and the historical big database; the output end of the regional operating condition processing module is connected to the input end of the data classification module; the output end of the historical big database is connected to the input end of the regional operating condition processing module; the output end of the data classification module is connected to the input end of the intelligent monitoring module.
4. The sensor module intelligent monitoring system based on the Internet of Things according to claim 3 is characterized in that: The IoT cloud platform module includes a regional construction unit and a sensor distribution control unit; The area construction unit is used to construct an intelligent monitoring area, arrange sensors in the area, build a cloud platform, and aggregate sensor transmission data; the sensor distribution control unit is used to control the on / off and combination of sensors arranged in the area; An output end of the area construction unit is connected to an input end of the sensor distribution control unit.
5. The sensor module intelligent monitoring system based on the Internet of Things according to claim 3 is characterized in that: The regional operating condition processing module includes an operating condition environment classification unit and a model analysis unit; The working environment classification unit is used to obtain working environment information, and the working environment includes a day and night environment and a monitoring environment; the day and night environment includes daytime and nighttime, and the daytime refers to 7:00 to 19:00; the nighttime refers to 19:00 to 7:00, and the endpoint time in the day and night environment includes the time before but not the time after; the monitoring environment includes the weather environment, the flow of people environment, the traffic environment, and the construction environment in the area; the model analysis unit constructs a data classification model under each working environment based on the data of the historical big data database; The output end of the operating environment classification unit is connected to the input end of the model analysis unit.
6. The sensor module intelligent monitoring system based on the Internet of Things according to claim 3 is characterized in that: The data classification module includes a sensor module data monitoring unit and a summary analysis unit; The sensor module data monitoring unit forms sensor module data monitoring based on different data classification models and constructs an identification sensor module; The summary analysis unit is used to perform early warning processing during the monitoring process when the probability of the number of sensors in the identification sensor module that do not meet the system set threshold exceeds the monitoring threshold, and summarize them on the visual monitoring page; The output end of the sensor module data monitoring unit is connected to the input end of the summary analysis unit.
7. The sensor module intelligent monitoring system based on the Internet of Things according to claim 3 is characterized in that: The intelligent monitoring module includes a visualization unit and an early warning unit; The visualization unit is used to build a visualization platform and control the visualization monitoring page; the early warning unit is used to connect to the administrator port and send out an alarm signal; The output end of the visualization unit is connected to the input end of the early warning unit.
Citation Information
Patent Citations
Information processing method for system of internet of things
CN104346409A
Environment monitoring method based on big data
CN112799155A
Industrial equipment real-time monitoring system based on Internet of Things technology
CN113155501A
Risk early warning method, system and equipment based on urban pipe network and storage medium
CN116402346A
Intelligent state sensing system and method based on big data
CN117354468A
