Monitoring data acquisition and transmission method and device, terminal and storage medium

Abstract

The invention provides a monitoring data acquisition and transmission method and device, a terminal and a storage medium. The method comprises the following steps: screening a monitoring data set according to an edge processing rule; generating a prediction damage index and prediction credibility of the special data set; determining the risk level of the special data set, and adding the credibility level label to the special data set; correcting the risk level of the special data set according to the credibility level label; and according to the corrected risk level of the special data set, determining the transmission priority, the transmission channel and the transmission content of the special data set, and sending data to a cloud data center. According to the monitoring data acquisition and transmission method and device, the terminal and the storage medium provided by the invention, the problem of data redundancy can be reduced, and the accuracy and reliability of structural health monitoring, the emergency response speed and the information transmission effectiveness are improved.

Description

Technical Field

[0001] This invention belongs to the field of structural health monitoring technology, and in particular relates to a monitoring data acquisition and transmission method, device, terminal and storage medium. Background Technology

[0002] With the development of the Internet of Things and sensor technology, real-time, online structural health monitoring (SHM) of large infrastructure such as bridges, tunnels, dams, and high-pile wharves has become an important means of ensuring their safe operation.

[0003] Currently, mainstream SHM (Structured Health Management) systems typically employ an "edge-cloud" collaborative architecture. Their operating mode generally involves deploying multiple sensors at critical structural locations on-site. These sensors collect data via data acquisition devices, which then transmit the data to a remote cloud data center via wired or wireless networks. Powerful servers in the cloud store, process, and analyze the massive amounts of received data, running damage identification algorithms to ultimately provide structural health assessments and early warning information to management personnel.

[0004] While this traditional "edge-cloud" monitoring model has achieved unmanned and automated monitoring to some extent, its inherent technical shortcomings are becoming increasingly apparent as the requirements for monitoring accuracy and range increase. First, the existing methods suffer from a single and inefficient data transmission mode, leading to high communication and storage costs. To ensure no potential damage information is missed, a continuous or high-frequency timed data transmission strategy is often employed, which significantly consumes communication bandwidth and increases the burden on subsequent data analysis and computation. Second, existing methods result in severe delays in emergency response, preventing managers from obtaining damage information in a timely manner and thus missing the optimal window for disaster relief. Furthermore, existing methods rely excessively on public terrestrial network communication, and their reliability cannot be guaranteed under extreme conditions.

[0005] In summary, optimizing data transmission strategies to reduce costs, improving the system's emergency response speed, and ensuring communication reliability in harsh and remote environments are the key technical challenges that urgently need to be addressed in the field of structural health monitoring. Summary of the Invention

[0006] In view of this, the present invention aims to provide a monitoring data acquisition and transmission method, device, terminal and storage medium to solve the above-mentioned technical problems.

[0007] To achieve the above objectives, the technical solution created by this invention is implemented as follows:

[0008] In a first aspect, embodiments of the present invention provide a monitoring data acquisition and transmission method, comprising:

[0009] Obtain a monitoring dataset containing at least one real-time monitoring data point, filter the monitoring dataset according to edge processing rules, set the monitoring dataset that does not conform to the edge processing rules as a regular dataset, and set the monitoring dataset that conforms to the edge processing rules as a special dataset;

[0010] A special dataset is input into a preset machine learning algorithm model to generate a predicted damage index and prediction confidence level for the special dataset.

[0011] Based on the predicted damage index, the risk level of the special dataset is determined, wherein the risk levels include L3 risk level, L2 risk level, L1 risk level and L0 risk level with gradually decreasing risk; based on the predicted confidence level, a confidence level label is generated and added to the special dataset, wherein the confidence level label includes: reliable label, unverified label and system health warning label.

[0012] The risk level of the special dataset is adjusted based on the credibility level label;

[0013] Based on the risk level corrected by the special dataset, the transmission priority, transmission channel, and transmission content of the special dataset are determined. Data is then sent to the cloud data center according to the transmission priority and transmission channel of the special dataset. The transmission priority includes P1, P2, P3, P4, and P5 levels with gradually decreasing priorities. The transmission channels include the Beidou alarm channel and the mobile communication data channel.

[0014] Secondly, embodiments of the present invention also provide a monitoring data acquisition and transmission device, comprising:

[0015] The acquisition module is used to acquire a monitoring dataset containing at least one real-time monitoring data, filter the monitoring dataset according to edge processing rules, set the monitoring dataset that does not conform to the edge processing rules as a regular dataset, and set the monitoring dataset that conforms to the edge processing rules as a special dataset;

[0016] The prediction module is used to input a special dataset into a preset machine learning algorithm model and generate a prediction damage index and prediction confidence of the special dataset.

[0017] The generation module is used to determine the risk level of the special dataset based on the predicted damage index, wherein the risk levels include L3 risk level, L2 risk level, L1 risk level and L0 risk level with gradually decreasing risk; and to generate a confidence level label based on the predicted confidence level and add the confidence level label to the special dataset, wherein the confidence level label includes: reliable label, unverified label and system health warning label.

[0018] The correction module is used to correct the risk level of the special dataset based on the credibility level label;

[0019] The transmission module is used to determine the transmission priority, transmission channel, and transmission content of the special dataset based on the risk level after correction of the special dataset, and to send data to the cloud data center according to the transmission priority and transmission channel of the special dataset. The transmission priority includes P1, P2, P3, P4 and P5 levels with gradually decreasing priority, and the transmission channel includes the Beidou alarm channel and the mobile communication data channel.

[0020] Thirdly, embodiments of the present invention also provide a terminal, including:

[0021] One or more processors;

[0022] Storage device for storing one or more programs;

[0023] When the one or more programs are executed by the one or more processors, the one or more processors implement the monitoring data acquisition and transmission method provided in the above embodiments.

[0024] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the monitoring data acquisition and transmission method provided in the above embodiments.

[0025] Compared with existing technologies, the monitoring data acquisition and transmission method, device, terminal, and storage medium described in this invention have the following advantages:

[0026] This invention provides a monitoring data acquisition and transmission method, device, terminal, and storage medium. It can filter monitoring datasets through edge processing rules, thereby avoiding excessive consumption of subsequent data transmission and computing power by conventional datasets, achieving front-end data filtering and reducing data redundancy. Secondly, this invention can determine the risk level of special datasets based on predicted damage indices and correct the risk level using confidence level labels generated based on prediction confidence, thereby improving the accuracy and reliability of structural health monitoring. Furthermore, this invention can determine the transmission priority, transmission channel, and transmission content of special datasets based on their risk level, thereby improving emergency response speed and the effectiveness of information transmission, and adapting to practical applications under harsh working conditions. Attached Figure Description

[0027] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0028] Figure 1 A flowchart of the monitoring data acquisition and transmission method described in Embodiment 1 of this invention is provided;

[0029] Figure 2 This invention provides a schematic diagram of the monitoring data acquisition and transmission device described in Embodiment 2 of the present invention.

[0030] Figure 3 The structural diagram of the terminal described in Embodiment 3 of the present invention is shown. Detailed Implementation

[0031] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0032] Example 1

[0033] Figure 1 The flowchart of the monitoring data acquisition and transmission method provided in Embodiment 1 of the present invention is as follows: Figure 1 As shown, the monitoring data acquisition and transmission method specifically includes the following steps:

[0034] Step 110: Obtain a monitoring dataset containing at least one real-time monitoring data. Filter the monitoring dataset according to edge processing rules, setting the monitoring datasets that do not conform to the edge processing rules as regular datasets and the monitoring datasets that conform to the edge processing rules as special datasets.

[0035] When conducting structural health monitoring on large infrastructure projects (such as bridges, tunnels, dams, and high-pile wharves), staff will deploy sensors such as accelerometers, stress change meters, and hydrostatic levels on key structural parts of the infrastructure to collect real-time monitoring data of the key structural parts. This data will then be transmitted to a cloud data center, which will use the real-time monitoring data to determine the real-time health status of the large infrastructure.

[0036] However, existing technologies typically employ continuous or high-frequency timed data transmission strategies to avoid missing any potential damage information. This can easily lead to invalid information or real-time monitoring data without any risk consuming communication bandwidth, thus increasing the burden on subsequent data analysis and computation. To address this issue, this embodiment filters monitoring datasets containing at least one real-time monitoring data point based on edge processing rules. If a monitoring dataset meets the edge processing rules, it indicates that the dataset can reflect potential structural health issues in large infrastructure and should be designated as a special dataset. Conversely, if a monitoring dataset does not meet the edge processing rules, it indicates that the dataset cannot reflect potential structural health issues in large infrastructure or that the infrastructure is in a normal state and should be designated as a regular dataset. By distinguishing between special and regular datasets, monitoring datasets can be differentiated, and regular datasets can be prevented from excessively consuming subsequent data transmission and computational resources during processing. This allows for front-end filtering of monitoring data and reduces data redundancy.

[0037] Optionally, in this embodiment, the monitoring dataset is filtered according to edge processing rules. Monitoring datasets that do not conform to the edge processing rules are set as regular datasets, and monitoring datasets that conform to the edge processing rules are set as special datasets. This can be specifically optimized as follows:

[0038] Compare the real-time monitoring data contained in the monitoring dataset with the preset trigger threshold;

[0039] When all real-time monitoring data contained in the monitoring dataset are less than the preset trigger threshold, the monitoring dataset is determined to be inconsistent with the edge processing rules, and the monitoring dataset is set as a regular dataset.

[0040] When any real-time monitoring data in the monitoring dataset is greater than or equal to a preset trigger threshold, the monitoring dataset is determined to meet the edge processing rules, and the monitoring dataset is set as a special dataset.

[0041] For example, taking the structural health monitoring of a high-pile wharf as an example, under normal circumstances, the structural health monitoring of a high-pile wharf can collect real-time monitoring data on the stress change of key sections (the preset trigger threshold can be set to 50με), the change rate of pile inclination angle (the preset trigger threshold can be set to 0.01° / hour), the settlement rate of the wharf (the preset trigger threshold can be set to 0.5mm / hour), and the instantaneous acceleration of the contents of the wharf (the preset trigger threshold can be set to 50mg). Therefore, the monitoring datasets obtained in different time periods should all include the above-mentioned real-time monitoring data.

[0042] After acquiring a monitoring dataset, each real-time monitoring data point can be compared with its preset trigger threshold. If all real-time monitoring data points are below the preset trigger threshold, it indicates that all real-time monitoring data points in the current dataset are in a normal state. Therefore, the current monitoring dataset cannot reflect potential structural health issues in large-scale infrastructure or prove that the large-scale infrastructure is in a normal state. In this case, the monitoring dataset can be set as a regular dataset. If any real-time monitoring data point is greater than or equal to the preset trigger threshold, it indicates that there is an anomaly in the real-time monitoring data in the current dataset. Therefore, the current monitoring dataset can reflect potential structural health issues in large-scale infrastructure. In this case, the monitoring dataset can be set as a special dataset.

[0043] Step 120: Input the special dataset into the preset machine learning algorithm model to generate the predicted damage index and prediction confidence of the special dataset.

[0044] After identifying a specific dataset, the dataset can be input into a pre-defined machine learning algorithm model. This model can then be used to identify and predict structural damage to large infrastructure, generating a Predictive Damage Index (CDI, used to quantify the degree of physical damage to the structure corresponding to real-time monitoring data) and a Predictive Confidence (DC, used to assess the confidence of the diagnostic results, reflecting the model's "confidence" in the judgment results). This improves the accuracy and reliability of structural health monitoring.

[0045] For example, the preset machine learning algorithm model in this embodiment can be a 1D-CNN+XGBoost model, or other lightweight neural network models in the prior art can be used instead, so as to identify and predict structural damage.

[0046] Step 130: Determine the risk level of the special dataset based on the predicted damage index, wherein the risk levels include L3 risk level, L2 risk level, L1 risk level and L0 risk level with gradually decreasing risk; generate a credibility level label based on the predicted credibility and add the credibility level label to the special dataset, wherein the credibility level label includes: reliable label, unverified label and system health warning label.

[0047] In practical applications, since different real-time monitoring data correspond to different risks of large-scale infrastructure, and in order to reflect the prediction credibility of the preset machine learning algorithm model, this embodiment will determine the risk level of the special dataset based on the predicted damage index, generate a credibility level label based on the prediction credibility, and add the credibility level label to the special dataset.

[0048] Specifically, when the predicted damage index is less than or equal to 5%, the risk level of the special dataset can be determined as L0 risk level; when the predicted damage index is greater than 5% and less than or equal to 15%, the risk level can be determined as L1 risk level; when the predicted damage index is greater than 15% and less than or equal to 30%, the risk level can be determined as L2 risk level; and when the predicted damage index is greater than 30%, the risk level can be determined as L3 risk level. This allows for different risk levels to reflect the risk situation of the large-scale infrastructure represented by the current special dataset.

[0049] Correspondingly, when the prediction confidence level is greater than 85%, a reliable label can be generated and added to the special dataset; when the prediction confidence level is between 60% and 85%, a label to be verified can be generated and added to the special dataset; when the prediction confidence level is less than 60%, a system health warning label can be generated and added to the special dataset. When the special dataset has a reliable label, it proves that the predicted damage index generated by the preset machine learning algorithm model based on real-time monitoring data has high confidence, and therefore its corresponding risk level is relatively reliable. When the special dataset has a label to be verified, it proves that the predicted damage index generated by the preset machine learning algorithm model based on real-time monitoring data may have errors, and therefore it should be manually monitored and verified in subsequent processing. When the special dataset has a system health warning label, it proves that the predicted damage index generated by the preset machine learning algorithm model based on real-time monitoring data has low confidence, and therefore it should be given special attention in subsequent processing. Staff should also check the relevant sensors and built-in algorithms to avoid affecting the accuracy of subsequent monitoring due to sensor or algorithm malfunctions.

[0050] Step 140: Correct the risk level of the special dataset according to the credibility level label.

[0051] Since the reliability of the predicted damage index with the system health warning label is low, this embodiment will also correct the risk level of the special dataset according to the reliability level label, so that the risk level of the special dataset with the reliability level label of system health warning label is downgraded by one level, thereby avoiding the impact of sensor or algorithm failure on the accuracy of the results and improving the reliability of the entire monitoring system.

[0052] Specifically, adjusting the risk level of the specific dataset based on the aforementioned credibility level label can be optimized as follows:

[0053] When the credibility level label is a reliable label or a label to be verified, the original risk level of the special dataset is retained;

[0054] When the credibility level label is a system health warning label, if the risk level of the special dataset is L3, then the risk level of the special dataset will be corrected to L2; if the risk level of the special dataset is L2, then the risk level of the special dataset will be corrected to L1; if the risk level of the special dataset is L1, then the risk level of the special dataset will be corrected to L0; if the risk level of the special dataset is L0, then the original risk level of the special dataset will be retained.

[0055] Step 150: Based on the risk level corrected by the special dataset, determine the transmission priority, transmission channel, and transmission content of the special dataset, and send data to the cloud data center according to the transmission priority and transmission channel of the special dataset. The transmission priority includes P1, P2, P3, P4, and P5 levels with gradually decreasing priorities, and the transmission channel includes the Beidou alarm channel and the mobile communication data channel.

[0056] After the risk level of the special dataset is corrected, this embodiment will determine the transmission priority, transmission channel and transmission content of the special dataset based on the corrected risk level, so as to rationally plan the use of resources and computing power, improve the speed of emergency response and the effectiveness of information transmission, and adapt to actual applications under harsh working conditions.

[0057] Specifically, based on the risk level corrected for the special dataset, the transmission priority, transmission channel, and transmission content of the special dataset are determined. Data is then sent to the cloud data center according to the transmission priority and transmission channel of the special dataset. This can be optimized as follows:

[0058] When the risk level of the special dataset after correction is L3, the transmission priority of the special dataset is set to P1, and the transmission channel of the special dataset is set to the Beidou alarm channel and the mobile communication data channel. A special data packet is generated based on the corrected risk level of the special dataset, the credibility level label of the special dataset, and the real-time monitoring data contained in the special dataset. An alarm message is generated based on the data acquisition time node of the special dataset, the corrected risk level of the special dataset, the credibility level label of the special dataset, the predicted damage index of the special dataset, and the predicted credibility of the special dataset. The special data packet and the alarm message are used as the transmission content of the special dataset. The special data packet is sent to the cloud data center as P1 level data via the mobile communication data channel, and the alarm message is sent to the cloud data center as P1 level data via the Beidou alarm channel.

[0059] When the risk level of the special dataset after correction is L2, the transmission priority of the special dataset is set to P2 level, and the transmission channel of the special dataset is set to the Beidou alarm channel and the mobile communication data channel. A special data packet is generated based on the risk level of the special dataset after correction, the credibility level label of the special dataset, and the real-time monitoring data contained in the special dataset. An alarm message is generated based on the data acquisition time node of the special dataset, the risk level of the special dataset after correction, the credibility level label of the special dataset, the predicted damage index of the special dataset, and the predicted credibility of the special dataset. The special data packet and the alarm message are used as the transmission content of the special dataset. The special data packet is sent to the cloud data center as P2 level data via the mobile communication data channel, and the alarm message is sent to the cloud data center as P2 level data via the Beidou alarm channel.

[0060] When the risk level of the special dataset after correction is L1, the transmission priority of the special dataset is set to P3, and the transmission channel of the special dataset is set to a mobile communication data channel; a special data packet is generated based on the risk level of the special dataset after correction, the credibility level label of the special dataset, and the real-time monitoring data contained in the special dataset, and the special data packet is used as the transmission content of the special dataset; the special data packet is sent to the cloud data center as P3 level data through the mobile communication data channel;

[0061] When the risk level of the special dataset after correction is L0, the transmission priority of the special dataset is set to P5, and the transmission channel of the special dataset is set to a mobile communication data channel. A special data packet is generated based on the risk level of the special dataset after correction, the credibility level label of the special dataset, and the real-time monitoring data contained in the special dataset, and the special data packet is used as the transmission content of the special dataset. The special data packet is sent to the cloud data center as P5 level data through the mobile communication data channel.

[0062] When the risk level of the special dataset is corrected to L3 or L2, it indicates that the current special dataset reflects structural damage to large infrastructure with a high risk and critical situation. In this case, this embodiment will use a dual-track data transmission system consisting of a BeiDou alarm channel and a mobile communication data channel. Due to the high reliability of the BeiDou alarm channel, alarm messages are transmitted through it to ensure that subsequent personnel can promptly obtain a core overview of the structural damage, improving emergency response speed and ensuring effective information transmission under adverse conditions. Simultaneously, because the mobile communication data channel (e.g., 4G / 5G data channel) has good bandwidth and data transmission capabilities, special data packets are transmitted through it to send the completed real-time monitoring data and related analysis results to the cloud data center for subsequent detailed data analysis.

[0063] When the risk level of a special dataset, after correction, is L1 or L0, it indicates that the current special dataset reflects a low or non-existent risk of structural damage to large infrastructure. In this case, special data packets can be sent via mobile communication data channels to avoid excessive occupancy of data transmission channels and ensure that truly urgent data is sent in a timely manner.

[0064] It should be noted that the transmission priority described in this embodiment can be used for data transmission sequence planning. When there are transmission contents with different transmission priorities in the same transmission channel, the transmission of the higher priority content should be performed first. When all transmission contents in the same transmission channel have the same transmission priority, the transmission is performed according to the order in which the content enters the transmission channel. Correspondingly, the operator can also further control the transmission cycle of the content based on the transmission priority. For example, P1, P2, and P3 level content can be transmitted immediately, P4 level content can be transmitted periodically, and P5 level content can be transmitted during idle periods.

[0065] As an example rather than a limitation, the following will use a high-pile wharf as an example to illustrate the specific data transmission method for a special dataset in this embodiment.

[0066] Scenario setting: At 22:14:33 on June 11, 2025, the ship went out of control and its bow struck the dock pile foundation directly at a speed of 0.5 m / s, causing the pile to crack and tilt severely.

[0067] At this point, the predicted damage index is 55%, the risk level is L3, the prediction confidence level is 99%, and the confidence level label is reliable. After the risk level is corrected by the confidence level label, the corrected risk level of this special dataset is L3, therefore its transmission priority is P1, and the transmission channels are the Beidou alarm channel and the mobile communication data channel.

[0068] During data transmission, the BeiDou alarm channel transmits the alarm message at P1 level as follows: (2025-6-11, 22:14:33), L3, CDI: 55%, DC: 99%, reliable. The mobile communication data channel will transmit the special data packet for this special dataset at P1 level.

[0069] This embodiment filters the monitoring dataset using edge processing rules, thereby avoiding excessive consumption of subsequent data transmission and computing power by conventional datasets and reducing data redundancy. It also determines the risk level by predicting damage indices and corrects the risk level based on credibility level labels, thus improving the accuracy and reliability of structural health monitoring. Furthermore, it can determine the transmission priority, transmission channel, and transmission content of special datasets based on their risk levels, improving emergency response speed and the effectiveness of information transmission, and adapting to practical applications under harsh working conditions.

[0070] Based on the above embodiments, to ensure that regular datasets can be successfully transmitted to the cloud data center and to facilitate the cloud data center in obtaining complete data on the monitored large-scale infrastructure, the monitoring data collection and transmission method can be further improved by adding the following steps before inputting the special datasets into the preset machine learning algorithm model:

[0071] Set the transmission priority of the regular dataset to P4 level and set the transmission channel of the regular dataset to the mobile communication data channel;

[0072] Extract data features from real-time monitoring data contained in a regular dataset, generate a summary data packet based on the data features, and set the summary data packet as the transmission content of the regular dataset;

[0073] The summary data packet is sent to the cloud data center as P4 level data via the mobile communication data channel.

[0074] It should be noted that when extracting data features from real-time monitoring data contained in a regular dataset and generating summary data packages based on these features, the average value of low-frequency data (such as temperature and tide position) can be calculated, and the root mean square of high-frequency data (such as acceleration and stress change) can be calculated. The average value of low-frequency data and the root mean square of high-frequency data can be used as data features to generate corresponding summary data packages, thereby reducing the overall size of the summary data packages and reflecting the effective content of the regular dataset through the summary data packages.

[0075] Furthermore, in practical applications, since the data transmission quality of mobile communication data channels is directly affected by their network status, in order to promptly detect changes in the network status of mobile communication data channels and ensure data transmission through these channels in subsequent work, the data acquisition and transmission monitoring method may also include the following steps:

[0076] The system acquires the real-time network status of the mobile communication data channel; when the real-time network status of the mobile communication data channel is in a network interruption state, it generates a network fault data packet; and sends the network fault data packet as P3 level data to the cloud data center through the Beidou alarm channel.

[0077] When the cloud data center receives a network fault data packet, it should send a network maintenance reminder to the relevant staff so that the staff can promptly repair the network status of the mobile communication data channel.

[0078] Example 2

[0079] Figure 2 This is a schematic diagram of the monitoring data acquisition and transmission device provided in Embodiment 2 of the present invention, as shown below. Figure 2 As shown, the monitoring data acquisition and transmission device includes:

[0080] The acquisition module 210 is used to acquire a monitoring dataset containing at least one real-time monitoring data, filter the monitoring dataset according to edge processing rules, set the monitoring dataset that does not conform to the edge processing rules as a regular dataset, and set the monitoring dataset that conforms to the edge processing rules as a special dataset.

[0081] The prediction module 220 is used to input a special dataset into a preset machine learning algorithm model to generate a prediction damage index and prediction confidence of the special dataset.

[0082] The generation module 230 is used to determine the risk level of the special dataset based on the predicted damage index; generate a confidence level label based on the predicted confidence level, and add the confidence level label to the special dataset.

[0083] Correction module 240 is used to correct the risk level of the special dataset according to the credibility level label;

[0084] The transmission module 250 is used to determine the transmission priority, transmission channel, and transmission content of the special dataset based on the risk level after the special dataset is corrected, and to send data to the cloud data center according to the transmission priority and transmission channel of the special dataset. The transmission priority includes P1, P2, P3, P4 and P5 levels with gradually decreasing priorities, and the transmission channel includes the Beidou alarm channel and the mobile communication data channel.

[0085] The monitoring data acquisition and transmission device provided in this embodiment can filter monitoring datasets through edge processing rules, determine risk levels by predicting damage indices, correct risk levels based on credibility level labels, and determine transmission priority, transmission channels, and transmission content based on the risk levels of special datasets.

[0086] In addition to the technology described in the above embodiments, the monitoring data acquisition and transmission device further includes:

[0087] The regular dataset processing module is used to set the transmission priority of the regular dataset to P4 level and set the transmission channel of the regular dataset to a mobile communication data channel; extract the data features of the real-time monitoring data contained in the regular dataset, generate a summary data packet based on the data features, and set the summary data packet as the transmission content of the regular dataset; and send the summary data packet as P4 level data to the cloud data center through the mobile communication data channel.

[0088] The network fault handling module is used to obtain the real-time network status of the mobile communication data channel; when the real-time network status of the mobile communication data channel is a network interruption state, it generates a network fault data packet; and sends the network fault data packet as P3 level data to the cloud data center through the Beidou alarm channel.

[0089] The monitoring data acquisition and transmission device provided in the embodiments of the present invention can execute the monitoring data acquisition and transmission method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0090] Example 3

[0091] Figure 3 This is a schematic diagram of the structure of a terminal provided in Embodiment 3 of the present invention. Figure 3 A block diagram is shown of an exemplary terminal 12 suitable for implementing embodiments of the present invention. Figure 3 The terminal 12 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0092] like Figure 3 As shown, terminal 12 is presented in the form of a general-purpose computing terminal. The components of terminal 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0093] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0094] Terminal 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by terminal 12, including volatile and non-volatile media, removable and non-removable media.

[0095] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Terminal 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 3 Not shown; usually referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0096] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0097] Terminal 12 can also communicate with one or more external terminals 14 (e.g., keyboard, pointing terminal, display 24, etc.), one or more terminals that enable a user to interact with terminal 12, and / or any terminal (e.g., network card, modem, etc.) that enables terminal 12 to communicate with one or more other computing terminals. This communication can be performed via input / output (I / O) interface 22. Furthermore, terminal 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of terminal 12 via bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with terminal 12, including but not limited to: microcode, terminal drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0098] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the monitoring data acquisition and transmission method provided in the embodiments of the present invention.

[0099] Example 4

[0100] Embodiment 4 of the present invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform any of the monitoring data acquisition and transmission methods provided in the above embodiments.

[0101] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0102] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0103] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0104] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for monitoring data acquisition and transmission, characterized in that... include: Obtain a monitoring dataset containing at least one real-time monitoring data point, filter the monitoring dataset according to edge processing rules, set the monitoring dataset that does not conform to the edge processing rules as a regular dataset, and set the monitoring dataset that conforms to the edge processing rules as a special dataset; A special dataset is input into a preset machine learning algorithm model to generate a predicted damage index and prediction confidence level for the special dataset. Based on the predicted damage index, the risk level of the special dataset is determined, wherein the risk levels include L3 risk level, L2 risk level, L1 risk level and L0 risk level, which are gradually decreasing in risk. Based on the predicted credibility, credibility level labels are generated and added to the special dataset. The credibility level labels include: reliable label, unverified label, and system health warning label. The risk level of the special dataset is adjusted based on the credibility level label; Based on the risk level corrected by the special dataset, the transmission priority, transmission channel, and transmission content of the special dataset are determined. Data is then sent to the cloud data center according to the transmission priority and transmission channel of the special dataset. The transmission priority includes P1, P2, P3, P4, and P5 levels with gradually decreasing priorities. The transmission channels include the Beidou alarm channel and the mobile communication data channel.

2. The monitoring data acquisition and transmission method according to claim 1, characterized in that: The step of filtering the monitoring dataset according to edge processing rules, setting monitoring datasets that do not conform to the edge processing rules as regular datasets, and setting monitoring datasets that conform to the edge processing rules as special datasets, includes: Compare the real-time monitoring data contained in the monitoring dataset with the preset trigger threshold; When all real-time monitoring data in the monitoring dataset are less than the preset trigger threshold, the monitoring dataset is determined to be inconsistent with the edge processing rules, and the monitoring dataset is set as a regular dataset. When any real-time monitoring data in the monitoring dataset is greater than or equal to a preset trigger threshold, the monitoring dataset is determined to meet the edge processing rules, and the monitoring dataset is set as a special dataset.

3. The monitoring data acquisition and transmission method according to claim 1, characterized in that: Before inputting the specific dataset into the preset machine learning algorithm model, the monitoring data acquisition and transmission method further includes: The transmission priority of the regular dataset is set to P4, and the transmission channel of the regular dataset is set to the mobile communication data channel. Extract the data features of the real-time monitoring data contained in the regular dataset, generate a summary data packet based on the data features, and set the summary data packet as the transmission content of the regular dataset; The summary data packet is sent to the cloud data center as P4 level data via the mobile communication data channel.

4. The monitoring data acquisition and transmission method according to claim 1, characterized in that: The monitoring data acquisition and transmission method further includes: Obtain the real-time network status of the mobile communication data channel; When the real-time network status of the mobile communication data channel is in a network interruption state, a network fault data packet is generated; Network fault data packets are treated as P3 level data and sent to the cloud data center through the Beidou alarm channel.

5. The monitoring data acquisition and transmission method according to claim 1, characterized in that: Determining the risk level of the special dataset based on the predicted damage index includes: When the predicted damage index is less than or equal to 5%, the risk level of the special dataset is determined to be L0 risk level; When the predicted damage index is greater than 5% and less than or equal to 15%, the risk level of the special dataset is determined to be L1 risk level; When the predicted damage index is greater than 15% and less than or equal to 30%, the risk level of the special dataset is determined to be L2 risk level; When the predicted damage index is greater than 30%, the risk level of the special dataset is determined to be L3 risk level; The step of generating a credibility level label based on the predicted credibility and adding the credibility level label to the special dataset includes: When the prediction confidence level is greater than 85%, a reliable label is generated and added to the special dataset. When the prediction confidence level is between 60% and 85%, a label to be verified is generated and added to the special dataset. When the prediction confidence is less than 60%, a system health warning label is generated and added to the special dataset.

6. The monitoring data acquisition and transmission method according to claim 1, characterized in that: The step of correcting the risk level of the special dataset based on the credibility level label includes: When the credibility level label is a reliable label or a label to be verified, the original risk level of the special dataset is retained; When the credibility level label is a system health warning label, If the risk level of the special dataset is L3, then the risk level of the special dataset will be revised to L2. If the risk level of the special dataset is L2, then the risk level of the special dataset will be adjusted to L1. If the risk level of the special dataset is L1, then the risk level of the special dataset will be adjusted to L0. If the risk level of the special dataset is L0, then the original risk level of the special dataset is retained.

7. The monitoring data acquisition and transmission method according to claim 1, characterized in that: The step of determining the transmission priority, transmission channel, and transmission content of the special dataset based on the risk level adjusted according to the special dataset, and sending data to the cloud data center according to the transmission priority and transmission channel of the special dataset, includes: When the risk level of the special dataset after correction is L3, the transmission priority of the special dataset is set to P1, and the transmission channel of the special dataset is set to the Beidou alarm channel and the mobile communication data channel. A special data packet is generated based on the corrected risk level of the special dataset, the credibility level label of the special dataset, and the real-time monitoring data contained in the special dataset. An alarm message is generated based on the data acquisition time node of the special dataset, the corrected risk level of the special dataset, the credibility level label of the special dataset, the predicted damage index of the special dataset, and the predicted credibility of the special dataset. The special data packet and the alarm message are used as the transmission content of the special dataset. The special data packet is sent to the cloud data center as P1 level data via the mobile communication data channel, and the alarm message is sent to the cloud data center as P1 level data via the Beidou alarm channel. When the risk level of the special dataset after correction is L2, the transmission priority of the special dataset is set to P2 level, and the transmission channel of the special dataset is set to the Beidou alarm channel and the mobile communication data channel. A special data packet is generated based on the risk level of the special dataset after correction, the credibility level label of the special dataset, and the real-time monitoring data contained in the special dataset. An alarm message is generated based on the data acquisition time node of the special dataset, the risk level of the special dataset after correction, the credibility level label of the special dataset, the predicted damage index of the special dataset, and the predicted credibility of the special dataset. The special data packet and the alarm message are used as the transmission content of the special dataset. The special data packet is sent to the cloud data center as P2 level data via the mobile communication data channel, and the alarm message is sent to the cloud data center as P2 level data via the Beidou alarm channel. When the risk level of the special dataset after correction is L1, the transmission priority of the special dataset is set to P3, and the transmission channel of the special dataset is set to a mobile communication data channel; a special data packet is generated based on the risk level of the special dataset after correction, the credibility level label of the special dataset, and the real-time monitoring data contained in the special dataset, and the special data packet is used as the transmission content of the special dataset; the special data packet is sent to the cloud data center as P3 level data through the mobile communication data channel; When the risk level of the special dataset after correction is L0, the transmission priority of the special dataset is set to P5, and the transmission channel of the special dataset is set to a mobile communication data channel. A special data packet is generated based on the risk level of the special dataset after correction, the credibility level label of the special dataset, and the real-time monitoring data contained in the special dataset, and the special data packet is used as the transmission content of the special dataset. The special data packet is sent to the cloud data center as P5 level data through the mobile communication data channel.

8. A monitoring data acquisition and transmission device, characterized in that, include: The acquisition module is used to acquire a monitoring dataset containing at least one real-time monitoring data, filter the monitoring dataset according to edge processing rules, set the monitoring dataset that does not conform to the edge processing rules as a regular dataset, and set the monitoring dataset that conforms to the edge processing rules as a special dataset; The prediction module is used to input a special dataset into a preset machine learning algorithm model and generate a prediction damage index and prediction confidence of the special dataset. A generation module is used to determine the risk level of the special dataset based on the predicted damage index; Based on the predicted confidence level, a confidence level label is generated and added to the special dataset; The correction module is used to correct the risk level of the special dataset based on the credibility level label; The transmission module is used to determine the transmission priority, transmission channel, and transmission content of the special dataset based on the risk level after correction of the special dataset, and to send data to the cloud data center according to the transmission priority and transmission channel of the special dataset. The transmission priority includes P1, P2, P3, P4 and P5 levels with gradually decreasing priority, and the transmission channel includes the Beidou alarm channel and the mobile communication data channel.

9. A terminal, characterized in that, The terminal includes: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the monitoring data acquisition and transmission method as described in any one of claims 1-7.

10. A storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the monitoring data acquisition and transmission method as described in any one of claims 1-7.

Images