Equipment monitoring method and system based on edge intelligent computing architecture

Abstract

The invention provides an equipment monitoring method and system based on an edge intelligent computing architecture, and relates to the technical field of industrial automation and intelligent manufacturing, the method is applied to an edge intelligent monitoring system adopting the edge intelligent computing architecture, and the method comprises the following steps: obtaining a target data set corresponding to target equipment, the target data set comprises equipment attribute information and real-time operation information of the target equipment; performing AI reasoning according to the target data set to obtain a reasoning result; performing target monitoring according to the reasoning result and the target data set to obtain a target monitoring result, and sending corresponding alarm information under the condition that the target monitoring result indicates that abnormal data exists; according to the method and the device, optimization monitoring is performed according to the target monitoring result and the reasoning result to obtain an optimization monitoring result, and under the condition that the optimization monitoring result indicates that optimization needs to be performed, optimization is performed by adopting an optimization scheme corresponding to the optimization monitoring result, so that the efficiency and the accuracy of equipment monitoring are improved.

Description

Technical Field

[0001] The present application relates to industrial automation and intelligent manufacturing, and specifically to an equipment monitoring method and system based on edge intelligent computing architecture. Background Art

[0002] With the continuous development of science and technology, the requirements for monitoring industrial production equipment are getting higher and higher. Ensuring the safety of equipment and the safety of equipment during operation is an important guarantee for ensuring the production efficiency and safety of industrial production. Traditional industrial production equipment monitoring mainly relies on regular manual inspections and manual analysis of real-time data collected by cameras and sensors. However, manual inspections and simple analysis of data collected by cameras and sensors will inevitably lead to inaccurate and inefficient monitoring of industrial equipment due to human negligence. The fixed data collected by cameras and sensor equipment for simple analysis of operating data will inevitably lead to problems such as inaccurate and inefficient monitoring of industrial equipment.

[0003] With respect to the above-mentioned problems existing in the equipment monitoring methods adopted in the related technologies, no effective technical solutions have been proposed so far. Summary of the invention

[0004] In response to the technical problems of low efficiency and accuracy of equipment monitoring methods in the prior art, the embodiments of the present application provide an equipment monitoring method and system based on edge intelligent computing architecture to solve at least one of the above technical problems.

[0005] According to one aspect of an embodiment of the present application, a device monitoring method based on an edge intelligent computing architecture is provided, which is applied to an edge intelligent monitoring system. The edge intelligent monitoring system adopts an edge intelligent computing architecture, and the method includes: obtaining a target data set corresponding to a target device, the target data set including device attribute information of the target device and real-time operation information of the target device; performing AI reasoning based on the target data set to obtain a reasoning result, and the AI ​​reasoning is used to perform real-time operation monitoring and fault prediction on the target device based on the target data set; performing target monitoring based on the reasoning result and the target data set to obtain a target monitoring result, and when the target monitoring result indicates that there is abnormal data in the target data set, sending an alarm information corresponding to the target monitoring result; performing optimization monitoring based on the target monitoring result and the reasoning result to obtain an optimization monitoring result, and when the optimization monitoring result indicates that the target device needs to be optimized, optimizing the target device using an optimization scheme corresponding to the optimization monitoring result.

[0006] According to another aspect of an embodiment of the present application, an edge intelligent monitoring system is also provided. The edge intelligent monitoring system adopts an edge intelligent computing architecture. The edge intelligent monitoring system integrates multiple units in the edge intelligent computing architecture. The multiple units include: an acquisition unit, used to acquire a target data set corresponding to a target device, the target data set including device attribute information of the target device and real-time operation information of the target device; an AI reasoning unit, used to perform AI reasoning based on the target data set to obtain a reasoning result, and the AI ​​reasoning is used to perform real-time operation monitoring and fault prediction of the target device based on the target data set; an alarm management unit, used to perform target monitoring based on the reasoning result and the target data set to obtain a target monitoring result, and when the target monitoring result indicates that there is abnormal data in the target data set, send an alarm information corresponding to the target monitoring result; an optimization unit, used to perform optimization monitoring based on the target monitoring result and the reasoning result to obtain an optimization monitoring result, and when the optimization monitoring result indicates that the target device needs to be optimized, optimize the target device using an optimization scheme corresponding to the optimization monitoring result.

[0007] Optionally, the above-mentioned AI reasoning unit includes an acquisition subunit, which is used to acquire a monitoring data set and an operation threshold set in the target data set, wherein the monitoring data set includes a historical operation data set and a real-time operation data set of the target device; an input subunit, which is used to input the historical operation data set into the drawing model to obtain a historical operation trend chart of the target device, and determine a reference real-time operation result of the target device based on the operation threshold set and the real-time operation data set; a real-time monitoring subunit, which is used to perform real-time operation monitoring of the target device according to the historical operation trend chart and the reference real-time operation result, and obtain a target real-time operation result corresponding to the target device, and the inference result includes the target real-time operation result; a prediction subunit, which is used to predict faults of the target device according to the target data set and the target real-time operation result to obtain an inference result.

[0008] Optionally, the above-mentioned prediction subunit includes: an acquisition module, used to obtain an absolute difference set between an operation threshold set and a real-time operation data set; an input module, used to input the absolute difference set and a historical operation trend chart into a target prediction model to obtain a prediction result, the inference result includes the prediction result, and the target prediction model is used to predict faults of the target equipment.

[0009] Optionally, the above-mentioned edge intelligent monitoring system also includes: an equipment data table management unit, which is used to generate an equipment information report based on the target data set; an equipment utilization rate analysis unit, which is used to perform equipment utilization rate analysis based on the target data set and / or the equipment information report to obtain a utilization rate analysis result; an energy management unit, which is used to perform a first optimization monitoring based on the utilization rate analysis result and the inference result to obtain a first monitoring result, and the first optimization monitoring is used to indicate that energy consumption monitoring of the target equipment is to be performed, and when the first monitoring result indicates that the target equipment needs to be energy-optimized, a first optimization plan is formulated based on the first monitoring result, and energy consumption of the target equipment is optimized based on the first optimization plan; a production management unit is used to perform a second optimization monitoring based on the first monitoring result and the target monitoring result to obtain To the second monitoring result, the second optimization monitoring is used to indicate task monitoring of the target device, and when the second monitoring result indicates that the target device needs to be optimized for task, a second optimization plan is formulated according to the second monitoring result, and task optimization is performed on the target device according to the second optimization plan; a BI report and data analysis unit is used to obtain multiple data types corresponding to the target data set, and a target data subset corresponding to each data type; determine the reasoning sub-results, target monitoring sub-results and optimization monitoring sub-results corresponding to each target data subset according to the reasoning results, target monitoring results and optimization monitoring results; and visualize the reasoning sub-results, target monitoring sub-results and optimization monitoring sub-results corresponding to each target data subset through charts and visualization tools.

[0010] Optionally, the above-mentioned edge intelligent monitoring system also includes a data acquisition unit, which is used to collect data from the target device through the AI-assisted programming module using the collection method of the self-developed control kernel before obtaining the target data set corresponding to the target device, so as to obtain a collected data set, and the self-developed control kernel supports multi-task parallel processing; a data cleaning unit, which is used to clean the collected data set according to the data cleaning rules set by the AI-assisted programming module to obtain a cleaned data set; a data storage unit, which is used to store the cleaned data set using a shared data pool, and the shared data pool is used to centrally store key public data generated or needed in different data streams.

[0011] Optionally, the above-mentioned edge intelligent monitoring system also includes an adjustment unit, which is used to formulate or adjust data collection rules through the AI-assisted programming module according to at least one of the reasoning results, target monitoring results and optimization monitoring results; a data collection subunit, which is used to collect data from the target device according to the data collection rules and through the AI-assisted programming module using the collection method of the self-developed control kernel.

[0012] According to another aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a computer to execute the above device monitoring method based on edge intelligent computing architecture.

[0013] According to another aspect of the embodiments of the present application, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the device monitoring method based on the edge intelligent computing architecture as described above.

[0014] Compared with the prior art, the technical solution provided by the embodiment of the present application may have the following beneficial effects: The device monitoring method based on edge intelligent computing architecture, which is applied to an edge intelligent monitoring system using edge intelligent computing architecture, includes: obtaining a target data set corresponding to a target device, the target data set includes device attribute information of the target device, and real-time operation information of the target device; performing AI reasoning according to the target data set to obtain a reasoning result, and AI reasoning is used to perform real-time operation monitoring and fault prediction of the target device according to the target data set; performing target monitoring according to the reasoning result and the target data set to obtain a target monitoring result, and sending an alarm information corresponding to the target monitoring result when the target monitoring result indicates that there is abnormal data in the target data set; performing optimization monitoring according to the target monitoring result and the reasoning result to obtain an optimization monitoring result, and when the optimization monitoring result indicates that the target device needs to be optimized, the optimization scheme corresponding to the optimization monitoring result is used to optimize the target device. The above method can not only improve the accuracy of device monitoring, but also improve the efficiency of device monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 is a schematic diagram of the structure of an optional edge intelligent monitoring system according to an embodiment of the present invention; Figure 2 is a flow chart of an optional device monitoring method based on edge intelligent computing architecture according to an embodiment of the present invention; Figure 3It is a schematic diagram of an optional device monitoring method based on edge intelligent computing architecture according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0018] Before introducing the technical solution of this application, some background technical knowledge involved in this application is first introduced and explained. The following related technologies can be combined arbitrarily with the technical solution of the embodiment of this application as optional solutions, and they all belong to the protection scope of the embodiment of this application. The embodiment of this application includes at least part of the following contents.

[0019] Edge intelligent computing architecture (also referred to as edge computing architecture) is an emerging computing architecture that pushes computing and data storage capabilities to the edge of the network, near devices or end users, to relieve the pressure on cloud computing and provide faster and more reliable services.

[0020] The solution provided in the embodiments of the present application relates to an edge intelligent computing architecture. The efficiency and accuracy of equipment monitoring can be improved through the embodiments of the present application, which is specifically illustrated by the following embodiments.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] With the rapid development of industrial Internet of Things, edge computing is becoming more and more common in industrial sites. However, the existing edge intelligent control system architecture has the following problems: 1. Insufficient computing power: Existing edge devices are prone to insufficient computing power when dealing with high-frequency data collection and AI reasoning, and cannot meet the requirements of real-time and high efficiency.

[0024] 2. Functional dispersion: Existing systems usually deploy data collection, cleaning, storage, etc. in a decentralized manner, resulting in low system integration, large communication delays, and complex management.

[0025] 3. Low efficiency of cloud-edge-end collaboration: The existing system lacks an efficient cloud-edge-end collaboration mechanism, and cannot achieve real-time interaction and feedback in device management, resource scheduling, and policy execution.

[0026] 4. The existing manual and system equipment monitoring methods have low efficiency and accuracy.

[0027] In order to solve the above technical problems existing in the prior art, the embodiment of the present application provides a device monitoring method based on edge intelligent computing architecture applied to an edge intelligent monitoring system integrating multiple units. As an optional implementation method, the above device monitoring method based on edge intelligent computing architecture can be applied to, but not limited to, Figure 1 The edge intelligent monitoring system 100 shown in the figure integrates units with data collection, cleaning, storage, AI reasoning and real-time policy distribution functions to achieve efficient edge intelligent control and cloud-edge-end collaboration. The edge intelligent monitoring system 100 improves the calculation and real-time processing capabilities of edge devices through self-developed control kernel and edge computing platform to adapt to various task requirements of industrial sites. Figure 1As shown, the edge intelligent monitoring system 100 integrates multiple units, among which the data acquisition unit 102 is connected to the data cleaning unit 104, the data cleaning unit 104 is connected to the data storage unit 106, the data storage unit 106 is connected to the alarm management unit 108, the AI ​​reasoning unit 110, and the equipment data table management unit 112-1 in the optimization unit 112, the alarm management unit 108 is connected to the production management unit 112-4 in the optimization unit 112, the AI ​​reasoning unit 110 is connected to the energy management unit 112-3 in the optimization unit 112, the equipment data table management unit 112-1 in the optimization unit 112 is connected to the equipment utilization rate analysis unit 112-2, and the production management unit 112-4 in the optimization unit 112 is connected to the BI report and data analysis unit 112-5. The multiple units are connected through a network, and the above-mentioned network may include but is not limited to: a wired network, a wireless network, wherein the wired network includes: a local area network, a metropolitan area network and a wide area network, and the wireless network includes: Bluetooth, WIFI and other networks that realize wireless communication.

[0028] The device monitoring method based on edge intelligent computing architecture can be executed by a terminal device or a server. The terminal device can include but is not limited to at least one of the following: mobile phones (such as Android phones, iOS phones, etc.), laptops, tablet computers, PDAs, MIDs (Mobile Internet Devices), PADs, desktop computers, smart TVs, vehicle-mounted devices, etc. The server can be a single server, a server cluster consisting of multiple servers, or a cloud server.

[0029] According to one aspect of an embodiment of the present invention, the above-mentioned edge intelligent monitoring system may further perform the following steps: the data acquisition unit 102 uses the self-developed control kernel acquisition method to acquire data from the target device through the AI-assisted programming module to obtain a collection data set, the self-developed control kernel supports multi-task parallel processing, or formulates or adjusts data acquisition rules through the AI-assisted programming module according to at least one of the inference results, target monitoring results, and optimization monitoring results; according to the data acquisition rules, and using the self-developed control kernel acquisition method to acquire data from the target device through the AI-assisted programming module, the data cleaning unit 104 then cleans the collected data set through the data cleaning rules set by the AI-assisted programming module to obtain a cleaned data set; the data storage unit 106 uses a shared data pool to store the cleaned data set, and the shared data pool is used to centrally store key public data generated or required in different data streams. The acquisition unit acquires the target data set corresponding to the target device from the shared data pool, and the target data set includes device attribute information of the target device and real-time operation information of the target device. The AI ​​reasoning unit 110 performs AI reasoning based on the target data set to obtain a reasoning result, and the AI ​​reasoning is used to perform real-time operation monitoring and fault prediction of the target device based on the target data set; the alarm management unit 108 performs target monitoring based on the reasoning result and the target data set to obtain a target monitoring result, and when the target monitoring result indicates that there is abnormal data in the target data set, sends an alarm message corresponding to the target monitoring result; the optimization unit 112 performs optimization monitoring based on the target monitoring result and the reasoning result to obtain an optimization monitoring result, and when the optimization monitoring result indicates that the target device needs to be optimized, the optimization plan corresponding to the optimization monitoring result is used to optimize the target device.

[0030] In the above embodiment of the present invention, the above method is adopted to improve the accuracy of equipment monitoring. At the same time, the present application integrates all units and modules on the same platform, avoids complex communication between multiple devices, reduces delays, improves data processing efficiency, and achieves the technical effect of high-efficiency and high-accuracy monitoring of equipment. Moreover, the modular design of the system in the present application enables the system to be flexibly configured according to different production needs and adapt to various industrial scenarios.

[0031] The above is only an example and is not limited in this embodiment.

[0032] As an optional implementation, please refer to Figure 2, which shows a schematic diagram of the structure of an edge intelligent monitoring system provided by an embodiment of the present application. The execution subject of each step of the method can be the terminal device or server introduced above. In the following method embodiment, for the convenience of description, only the execution subject of each step is introduced as a "computer device". The method may include at least one of the following steps (S202 to S208): S202, obtaining a target data set corresponding to a target device, where the target data set includes device attribute information of the target device and real-time operation information of the target device; S204, performing AI reasoning according to the target data set to obtain a reasoning result, where the AI ​​reasoning is used to perform real-time operation monitoring and fault prediction on the target device according to the target data set; S206, performing target monitoring according to the inference result and the target data set to obtain a target monitoring result, and sending an alarm message corresponding to the target monitoring result when the target monitoring result indicates that there is abnormal data in the target data set; S208, performing optimization monitoring according to the target monitoring result and the reasoning result to obtain the optimization monitoring result, and when the optimization monitoring result indicates that the target device needs to be optimized, optimizing the target device using the optimization scheme corresponding to the optimization monitoring result.

[0033] It should be noted that the target device in S202 can be understood as, but not limited to, a production device used for industrial production, or a device used to perform other tasks, such as a robot, PLC, sensor, etc. The operation of obtaining the target data set can be understood as, but not limited to, the operation of the acquisition unit in the edge intelligent monitoring system obtaining data from the shared data pool. The above-mentioned device attribute information includes the device model or name, device type, device manufacturer, device processor (CPU model and speed), device memory (RAM size), device storage (internal storage capacity, such as SSD or HDD), device graphics card (graphics processing unit model), device operating system (operating system and version running on the device), device application (installed software and version information), device connection mode, device IP address, device encryption type, device firewall status, device color, device size and device weight, etc. The above-mentioned real-time operation information can be understood as, but not limited to, the operation data generated in real time when the device is running.

[0034] The AI ​​model in the AI ​​reasoning unit performs AI reasoning in the above S204. The AI ​​model is loaded through the edge control system (i.e., the edge intelligent monitoring system in this application). The AI ​​reasoning function performed by the AI ​​model includes analysis of the real-time collected production data (real-time operation information), equipment health prediction (predicting whether the equipment operation status will fail, that is, the possibility of future equipment failure), anomaly detection (identifying abnormal data that may affect the efficiency of the production line or the engraving accuracy), and efficiency optimization suggestions (providing production efficiency optimization solutions based on equipment data and production needs). That is, the AI ​​reasoning unit uses the AI ​​model for reasoning and prediction, and the reasoning process can be understood, but not limited to, as the model predicts whether the equipment will fail (such as overheating damage) based on the historical changes in the equipment temperature, environmental factors, etc., and gives early warning suggestions. Finally, the AI ​​reasoning unit outputs the reasoning result, and the AI ​​reasoning unit will output suggestions on whether maintenance or adjustment is needed in advance for reference by the production management unit.

[0035] The target monitoring in S206 is performed by the alarm management unit in the edge control system. The alarm management unit can monitor abnormal conditions in the production process in real time (such as equipment failure, data exceeding the limit, etc.), and automatically generate alarm information to notify relevant personnel to intervene. For example, if the target monitoring is real-time temperature monitoring, the alarm management unit will monitor the temperature data of the equipment in real time and compare it with the preset threshold (for example, the temperature exceeding 100 degrees Celsius is abnormal), and obtain the comparison result (that is, the above target monitoring result). In the case where the temperature exceeds the threshold, the alarm management unit will immediately trigger an alarm, send an alarm message, and notify the operator to intervene (such as shutdown or cooling). When an abnormality occurs in the system, the alarm management unit will connect with the production management unit in the optimization unit through the real-time data stream to trigger the emergency response mechanism of the target equipment. The above-mentioned target monitoring can monitor various types of data, and the various types are the types of data included in the target data set, that is, the target monitoring can be one or more of the temperature, humidity, and operating status of the equipment. After obtaining the target monitoring result, when the target monitoring result indicates that there is abnormal data in the target data set, such as abnormal temperature, abnormal humidity, abnormal operating status, etc. (it can be understood but not limited to that the target monitoring result indicates that the target equipment has an abnormality), while sending the alarm information corresponding to the target monitoring result, the abnormal adjustment plan of the target equipment corresponding to the target monitoring result will also be sent.

[0036] The above-mentioned optimization monitoring includes monitoring of the properties of the equipment itself and monitoring of the tasks performed by the equipment. The above-mentioned situations that require optimization include both optimization of the equipment itself (such as replacing equipment, repairing equipment, etc.) and optimization of the tasks performed by the equipment (such as optimization of production plans).

[0037] Through the above-mentioned implementation mode of the present application, the above-mentioned method is applied to an edge intelligent monitoring system that adopts an edge intelligent computing architecture, thereby improving the efficiency of equipment monitoring. At the same time, diversified and multi-faceted equipment monitoring is adopted within the system, thereby improving the accuracy of equipment monitoring.

[0038] As an optional implementation, the AI ​​reasoning is performed based on the target data set to obtain the reasoning result, including: S1, obtaining a monitoring data set and an operation threshold set in a target data set, wherein the monitoring data set includes a historical operation data set and a real-time operation data set of a target device; S2, inputting the historical operation data set into the drawing model to obtain the historical operation trend graph of the target device, and determining the reference real-time operation result of the target device according to the operation threshold set and the real-time operation data set; S3, monitoring the target device in real time according to the historical operation trend graph and the reference real-time operation result, and obtaining the target real-time operation result corresponding to the target device, wherein the inference result includes the target real-time operation result; S4, predicting the fault of the target device according to the target data set and the target real-time operation result to obtain the inference result.

[0039] It should be noted that the above-mentioned monitoring data set includes multiple types of data, such as temperature data, humidity data, equipment status data, etc. of the equipment during the production process, and each type of data has a corresponding pre-set operating threshold, thus constituting an operating threshold set.

[0040] The above-mentioned drawing model is used to construct a historical operation trend chart of the target device based on the historical operation data set, and the specific view type of the trend chart can be one or more of a line chart, a bar chart, a scatter chart, a pie chart, etc., which is not limited in this application. The above-mentioned determination of the reference real-time operation result of the target device based on the operation threshold set and the real-time operation data set can be understood, but not limited to, as comparing each type of data in the real-time operation data set with the operation threshold of the corresponding type in the operation threshold set, thereby obtaining a comparison result between each type of data and the corresponding operation threshold, and obtaining a reference real-time operation result.

[0041] The operation in S3 above can be understood, but is not limited to, as determining whether the current operating state of the target device is normal based on the reference real-time operating results and the historical operating trend graph. It can be understood that, under normal circumstances, the reference real-time operating results can already reflect whether the current operating state of the target device is normal. However, in this application, the historical operating trend graph can be combined to further determine whether the target device really needs to be adjusted. For example, real-time operation monitoring is monitoring the temperature of the device. If so, Figure 3The line graph shown is a historical operating trend graph of the target device temperature. The data of 40 degrees Celsius at 13:05 is the real-time operating temperature of the above target device. Assuming that the temperature threshold is 40 degrees Celsius, although the real-time operating temperature is equal to the temperature threshold at this time (i.e., refer to the real-time operating result), it can be determined from the historical operating trend graph of the target device temperature that the temperature of the target device has been gradually decreasing. In this case, real-time operating monitoring will be obtained without making any relevant adjustments to achieve cooling of the target device.

[0042] The above S4 performs fault prediction, and the operations in S4 specifically include: S4-1, obtaining a set of absolute differences between an operation threshold set and a set of real-time operation data; S4-2, input the absolute difference set and the historical operation trend chart into the target prediction model to obtain the prediction result. The inference result includes the prediction result. The target prediction model is used to predict the failure of the target equipment.

[0043] The above absolute difference set can be understood as, but not limited to, the absolute value of the difference between various types of operating thresholds in the operating threshold set and the corresponding types of real-time operating data in the real-time operating data set, such as the absolute difference between the temperature operating threshold and the temperature real-time operating data, the absolute difference between the humidity operating threshold and the humidity real-time operating data, etc., thereby obtaining an absolute difference set. Then, the absolute difference set and the historical operating trend graph are input into the target prediction model to obtain the prediction result.

[0044] Through the above-mentioned implementation mode of the present application, a method of real-time monitoring and fault prediction of the target equipment is adopted, which can not only timely alarm and determine the adjustment plan when there are abnormalities in the relevant attribute information of the equipment or the real-time data generated by the operation of the equipment, but also predict the faults of the target equipment and prevent them before the target equipment fails, so that the target equipment can be repaired or replaced in advance before the abnormality occurs, thereby ensuring the smooth progress of the production task.

[0045] As an optional implementation, the optimization monitoring is performed according to the target monitoring result and the reasoning result to obtain the optimization monitoring result, including: S1, generating a device information report according to the target data set; S2, performing equipment utilization rate analysis based on the target data set and / or the equipment information report to obtain utilization rate analysis results; S3, performing optimization monitoring according to the utilization rate analysis results, target monitoring results and reasoning results to obtain optimization monitoring results.

[0046] It should be noted that the execution of the above S1 is as follows Figure 1The device data table management unit 112-1 shown in the figure generates device information reports, centrally manages the data of all devices, and provides visual data tables, thereby helping managers to quickly check the operation status, fault records and other information of each device, thereby improving management efficiency. That is, the device data table management unit is used to generate reports, and displays the data information related to the device as reports (in the form of reports).

[0047] The execution of S2 is as follows Figure 1 The equipment utilization rate analysis unit 112-2 shown in the figure monitors the operating status of the equipment, calculates the utilization rate, and provides maintenance suggestions. The unit can also predict potential failures of the equipment and help avoid production downtime through early warning, such as Figure 1 As shown, the data of the equipment utilization rate analysis unit 112-2 can come from the equipment data table management unit 112-1, and can also come from the data storage unit 106. After that, the equipment utilization rate analysis unit 112-2 will have an utilization rate analysis result, and then give this result to the energy management unit 112-3 for optimization monitoring. It can be understood that optimization monitoring includes optimization monitoring of the equipment itself (for example, whether the equipment needs to be repaired or replaced), and also includes optimization monitoring of the production tasks performed by the equipment (for example, whether the production tasks performed by the equipment need to be optimized). The energy management unit in this application optimizes energy utilization by real-time monitoring of the energy consumption of production line equipment and using intelligent algorithms for dynamic mediation. The module can automatically adjust energy consumption and reduce energy waste based on information such as equipment operating load and production task priority.

[0048] The operations in S3 above specifically include: S3-1, performing a first optimization monitoring according to the utilization rate analysis result and the inference result to obtain a first monitoring result, wherein the first optimization monitoring is used to indicate energy consumption monitoring of the target device; S3-2, when the first monitoring result indicates that the target device needs to be energy-consumption optimized, formulate a first optimization plan according to the first monitoring result, and optimize the energy consumption of the target device according to the first optimization plan; S3-3, performing a second optimization monitoring according to the first monitoring result and the target monitoring result to obtain a second monitoring result, wherein the second optimization monitoring is used to indicate to perform task monitoring on the target device; S3-4, when the second monitoring result indicates that the target device needs to perform task optimization, formulate a second optimization plan according to the second monitoring result, and perform task optimization on the target device according to the second optimization plan.

[0049] It should be noted that the above first optimization monitoring (is performed by Figure 1The monitoring performed by the energy management unit 112-3 shown in the figure) can be understood as, but not limited to, monitoring the target device itself, for monitoring the energy consumption of the target device, determining whether the target device needs to be repaired or replaced based on the monitoring results of the energy consumption of the target device, and repairing or replacing the target device if it needs to be repaired or replaced (i.e., the above-mentioned energy consumption optimization), and the operation in the above S3-2 can be understood as, but not limited to, when the target device needs to be optimized, a device optimization plan corresponding to the first monitoring result can be flexibly formulated based on the first monitoring result, and optimization is performed based on the formulated device optimization plan. The above-mentioned second optimization monitoring (performed by, for example, Figure 1 The monitoring performed by the production management unit 112-4 shown in the figure, the production management unit in the present application integrates functions such as production scheduling, task allocation, and resource management to improve the automation level of the production line, so that the system can adjust the production plan according to the analysis of real-time data (the second monitoring result) to ensure the smoothness and efficiency of the production process) can be understood as but not limited to monitoring the production tasks performed by the target device, and when the target device needs to optimize the task, an optimization plan corresponding to the second monitoring result (i.e., the second optimization plan) is flexibly formulated according to the second monitoring result, and the production task is optimized according to the formulated optimization plan.

[0050] Through the above-mentioned implementation mode of the present application, the method of generating equipment information reports is adopted to realize the visual management of the target data set. At the same time, multi-faceted optimization monitoring is carried out according to the equipment utilization rate analysis results, target monitoring results and reasoning results, thereby improving the accuracy of monitoring and the prevention and optimization of equipment failures.

[0051] As an optional implementation manner, before obtaining the target data set corresponding to the target device, the method further includes: S1, through the AI-assisted programming module, the target device is collected using the collection method of the self-developed control core to obtain a collection data set. The self-developed control core supports multi-task parallel processing; S2, performing data cleaning on the collected data set according to the data cleaning rules set by the AI-assisted programming module to obtain a cleaned data set; S3 uses a shared data pool to store the cleaned data set. The shared data pool is used to centrally store key public data generated or needed in different data streams.

[0052] The operation in S1 above can be understood, but is not limited to, as the AI-assisted programming module (which can not only assist manual programming, but also generate optimal operating instructions and task planning for production equipment through AI algorithms) formulates the collection method of the self-developed control kernel, and then the data acquisition unit uses the collection method formulated by the AI-assisted programming module to collect data and obtain the collected data set, and then executes S2, that is, the AI-assisted programming module formulates data cleaning rules, and then the data cleaning unit cleans the data according to the formulated data cleaning rules, and then the data storage module uses a shared data pool to store the cleaned data set. The above self-developed control kernel supports multi-task parallel processing, ensuring real-time collection, cleaning storage and reasoning of high-concurrency data.

[0053] When formulating collection rules, the AI-assisted programming module can also formulate data collection rules based on at least one of the reasoning results, target monitoring results, and optimization monitoring results, or adjust the formulated data collection rules based on at least one of the reasoning results, target monitoring results, and optimization monitoring results, and use the adjusted data collection rules as the latest data collection rules; then the data collection unit collects data from the target device according to the latest data collection rules and the collection method of the self-developed control kernel through the AI-assisted programming module.

[0054] Through the above-mentioned implementation mode of the present application, an AI-assisted programming module is used to formulate a variety of data collection methods, thereby realizing data collection in various ways. At the same time, data cleaning rules are formulated through the AI-assisted programming module to realize intelligent cleaning of the collected data, thereby improving the efficiency of data collection and cleaning. Combined with the shared pool design of the data storage module, multiple units and modules in the edge intelligent monitoring system can share data in the shared pool, thereby ensuring the uniformity of data involved in multiple units and modules when performing equipment monitoring.

[0055] As an optional implementation manner, after optimizing the target device using the optimization scheme corresponding to the optimization monitoring result, the method further includes: S1, obtaining multiple data types corresponding to the target data set, and the target data subset corresponding to each data type; S2, determining the reasoning sub-result, the target monitoring sub-result and the optimization monitoring sub-result corresponding to each target data subset according to the reasoning result, the target monitoring result and the optimization monitoring result; S3, visualizes the reasoning sub-results, target monitoring sub-results, and optimization monitoring sub-results corresponding to each target data subset through charts and visualization tools.

[0056] The execution subject of the operations in S1 to S3 above can be understood, but not limited to, as follows: Figure 1The BI report and data analysis unit 112 - 5 shown can provide multi-dimensional business intelligence analysis reports to help production managers understand key information such as production status, equipment operation status, energy usage, etc. in real time, so as to make data-driven decisions.

[0057] Through the above implementation of the present application, an integrated edge computing architecture is adopted, and the above method is implemented by using an edge intelligent monitoring system that integrates units and modules such as data collection, cleaning, storage, AI reasoning, and energy management on the same edge computing platform, thereby improving the efficiency and accuracy of multi-faceted equipment monitoring. At the same time, by integrating units and modules such as AI-assisted programming and equipment utilization rate analysis in the edge intelligent monitoring system, production efficiency and equipment utilization are improved through AI and real-time utilization rate analysis. Energy management and alarm management mechanisms are also integrated into the edge intelligent monitoring system to protect the energy management unit and alarm management unit in the edge computing platform, ensure the efficient operation of the system, and respond to abnormal situations in production in real time. At the same time, production management units and BI reports and data analysis units are integrated into the edge intelligent monitoring system to improve the automation level and decision-making efficiency of the production line through intelligent scheduling and data analysis.

[0058] The following uses automatic laser engraving in the industrial manufacturing field as a specific business application scenario to provide an overall description of the above-mentioned equipment monitoring method based on the edge intelligent computing architecture: Scenario description: On the automatic laser engraving production line, multiple production equipment (such as robots, sensors, PLCs, etc.) collaborate in real time to complete high-precision engraving operations. During the production process, each device will generate a large amount of high-frequency data, including equipment operating status (such as temperature, vibration, and operating time), production indicators (such as engraving accuracy, workpiece number), and environmental monitoring data (such as temperature and humidity, and dust concentration). This data needs to be collected, cleaned, and analyzed in real time through an edge intelligent control system, and optimized control instructions are generated according to IT-side strategies and distributed to relevant equipment for execution in real time. The production line must also have rapid response capabilities to cope with complex requirements such as engraving task switching, anomaly detection, and processing.

[0059] Data flow process: (1) Data collection Multi-source adaptation and high-frequency acquisition: The system connects laser engraving equipment, sensors and PLCs through a variety of industrial protocol adapters (such as Modbus, OPC UA), and uses multi-threading technology for high-frequency data acquisition to ensure the real-time data of the production line.

[0060] Equipment status monitoring and disconnection resumption: Real-time monitoring of data source connection status. In case of abnormal interruption, the system automatically attempts to reconnect and continue data collection after recovery to ensure data integrity and stability.

[0061] (2) Data cleaning Real-time data cleaning and flexible algorithm switching: The system can perform operations such as deduplication, format conversion, and missing value completion on the collected data. The cleaning rules support user-defined algorithms, and can also dynamically select the optimal algorithm based on data characteristics (such as special status values ​​and abnormal value ratios).

[0062] (3) Data storage Cache: The cleaned structured data is first stored in a cache (such as Redis, memory registers) to support real-time task scheduling, and is asynchronously written to the database for long-term storage.

[0063] Multiple database support: The system supports multiple database types (such as MySQL, Oracle, MongoDB, etc.), and users can choose the most suitable storage solution according to their needs.

[0064] (4) AI reasoning and analysis module: The edge control system loads the AI ​​model to analyze the production data collected in real time. Functions include: Equipment health prediction: predicting whether the equipment will fail in operation; Anomaly detection: identifying abnormal data that may affect production line efficiency or engraving accuracy; Efficiency optimization suggestions: providing production efficiency optimization solutions based on equipment data and production needs.

[0065] (5) Strategy distribution and feedback Strategy generation and distribution: Generate specific control instructions based on IT-side strategies and AI reasoning results, and distribute them to related equipment (robots, PLCs, etc.). For example, task switching instructions for laser engraving equipment, engraving path optimization instructions, task issuance instructions, etc. Equipment feedback: The system monitors the execution status of the equipment in real time (such as instruction completion rate, response delay, etc.), and uploads feedback data to the IT side for further optimization of strategies to form a closed-loop management.

[0066] Through the above-mentioned equipment monitoring method based on edge intelligent computing architecture of the present application, the above-mentioned method is implemented through an edge intelligent monitoring system integrating multiple modules, thereby improving the efficiency and accuracy of equipment monitoring.

[0067] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0068] According to another aspect of an embodiment of the present invention, there is also provided an electronic device for implementing the above-mentioned device monitoring method based on edge intelligent computing architecture, and the electronic device may be a terminal device or a server. This embodiment is illustrated by taking the electronic device as a terminal device as an example. The electronic device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores a computer program executable by at least one processor, and the computer program is executed by at least one processor so that at least one processor performs the steps in any one of the above-mentioned method embodiments.

[0069] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0070] Optionally, in this embodiment, the processor may be configured to execute each step of the device monitoring method based on edge intelligent computing architecture through a computer program.

[0071] Alternatively, a person skilled in the art may understand that the description of the electronic device structure is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, and other terminal devices. The above description does not limit the structure of the electronic device. For example, the electronic device may include more or fewer components (such as a network interface, etc.) than described, or have a configuration different from the description.

[0072] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the device monitoring method and system based on the edge intelligent computing architecture in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned device monitoring method based on the edge intelligent computing architecture. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. Among them, the memory can be specifically but not limited to being used to store all data information involved in this application.

[0073] Optionally, the transmission device is used to receive or send data via a network. Specific examples of the network may include wired networks and wireless networks. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0074] In addition, the electronic device mentioned above further comprises: a display and a connection bus for connecting various module components in the electronic device mentioned above.

[0075] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes may form a peer-to-peer (P2P, Peer To Peer) network, and any form of computing device, such as a server, terminal and other electronic devices, may become a node in the blockchain system by joining the peer-to-peer network.

[0076] According to one aspect of the present application, a computer program product is provided, the computer program product comprising a computer program / instruction, the computer program / instruction comprising a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit, various functions provided by the embodiments of the present application are executed.

[0077] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0078] According to one aspect of the present application, a computer-readable storage medium is provided, and a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned device monitoring method based on edge intelligent computing architecture.

[0079] Optionally, in this embodiment, the above-mentioned computer-readable storage medium can be configured to store a computer program for executing the above-mentioned device monitoring method based on edge intelligent computing architecture.

[0080] Those skilled in the art can understand that the implementation of all or part of the processes in the above method embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above method embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FM), a hard disk (HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0081] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to perform all or part of the steps of the above methods of various embodiments of the present invention.

[0082] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0084] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0086] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A device monitoring method based on edge intelligent computing architecture, characterized in that: Applied to an edge intelligent monitoring system, the edge intelligent monitoring system adopts an edge intelligent computing architecture, and the method includes: Acquire a target data set corresponding to a target device, wherein the target data set includes device attribute information of the target device and real-time operation information of the target device; Performing AI reasoning according to the target data set to obtain a reasoning result, wherein the AI ​​reasoning is used to perform real-time operation monitoring and fault prediction on the target device according to the target data set; Performing target monitoring according to the inference result and the target data set to obtain a target monitoring result, and sending an alarm message corresponding to the target monitoring result when the target monitoring result indicates that abnormal data exists in the target data set; Optimization monitoring is performed according to the target monitoring result and the reasoning result to obtain an optimization monitoring result, and when the optimization monitoring result indicates that the target device needs to be optimized, the target device is optimized using an optimization scheme corresponding to the optimization monitoring result.

2. The method according to claim 1, characterized in that Perform AI reasoning according to the target data set to obtain reasoning results, including: Acquire a monitoring data set and an operation threshold set in the target data set, wherein the monitoring data set includes a historical operation data set and a real-time operation data set of the target device; Inputting the historical operation data set into a drawing model to obtain a historical operation trend graph of the target device, and determining a reference real-time operation result of the target device according to the operation threshold set and the real-time operation data set; Performing real-time operation monitoring on the target device according to the historical operation trend graph and the reference real-time operation result to obtain a target real-time operation result corresponding to the target device, wherein the inference result includes the target real-time operation result; Fault prediction is performed on the target device according to the target data set and the target real-time operation result to obtain the inference result.

3. The method according to claim 2, characterized in that Performing fault prediction on the target device according to the target data set and the target real-time operation result to obtain the inference result includes: Acquire a set of absolute differences between the operation threshold set and the real-time operation data set; The absolute difference set and the historical operation trend graph are input into a target prediction model to obtain a prediction result, the prediction result is included in the inference result, and the target prediction model is used to predict faults of the target device.

4. The method according to claim 1, characterized in that: Performing optimization monitoring according to the target monitoring result and the reasoning result to obtain an optimization monitoring result, including: Generate a device information report according to the target data set; Performing equipment utilization rate analysis according to the target data set and / or the equipment information report to obtain utilization rate analysis results; Optimization monitoring is performed according to the utilization rate analysis result, the target monitoring result and the inference result to obtain the optimization monitoring result.

5. The method according to claim 4, characterized in that Performing optimization monitoring according to the utilization rate analysis result, the target monitoring result and the inference result to obtain the optimization monitoring result includes: Performing first optimization monitoring according to the utilization rate analysis result and the inference result to obtain a first monitoring result, wherein the first optimization monitoring is used to indicate energy consumption monitoring of the target device; When the first monitoring result indicates that the target device needs to be energy-consumption optimized, formulating a first optimization plan according to the first monitoring result, and optimizing the energy consumption of the target device according to the first optimization plan; Performing a second optimization monitoring according to the first monitoring result and the target monitoring result to obtain a second monitoring result, wherein the second optimization monitoring is used to indicate that task monitoring is performed on the target device; When the second monitoring result indicates that the target device needs to perform task optimization, a second optimization plan is formulated according to the second monitoring result, and task optimization is performed on the target device according to the second optimization plan.

6. The method according to claim 1, characterized in that Before obtaining the target data set corresponding to the target device, it also includes: The target device is collected data by using an AI-assisted programming module and a self-developed control core to obtain a collection data set, wherein the self-developed control core supports multi-task parallel processing; Performing data cleaning on the collected data set according to the data cleaning rules set by the AI-assisted programming module to obtain a cleaned data set; The cleaned data set is stored in a shared data pool, and the shared data pool is used to centrally store key common data generated or required to be used in different data streams.

7. The method according to claim 1, characterized in that Also includes: According to at least one of the reasoning result, the target monitoring result and the optimization monitoring result, a data collection rule is formulated or adjusted through an AI-assisted programming module; According to the data collection rules, data is collected from the target device using the collection method of the self-developed control kernel through the AI-assisted programming module.

8. The method according to claim 1, characterized in that: After optimizing the target device using the optimization scheme corresponding to the optimization monitoring result, the method further includes: Acquire multiple data types corresponding to the target data set, and target data subsets corresponding to each data type; Determine the reasoning sub-result, the target monitoring sub-result and the optimization monitoring sub-result corresponding to each of the target data subsets according to the reasoning result, the target monitoring result and the optimization monitoring result; The reasoning sub-result, target monitoring sub-result and optimization monitoring sub-result corresponding to each target data subset are visualized through charts and visualization tools.

9. An edge intelligent monitoring system, characterized in that: The edge intelligent monitoring system adopts an edge intelligent computing architecture. The edge intelligent monitoring system integrates multiple units in the edge intelligent computing architecture. The multiple units include: An acquisition unit, configured to acquire a target data set corresponding to a target device, wherein the target data set includes device attribute information of the target device and real-time operation information of the target device; An AI reasoning unit, configured to perform AI reasoning according to the target data set to obtain a reasoning result, wherein the AI ​​reasoning is used to perform real-time operation monitoring and fault prediction on the target device according to the target data set; an alarm management unit, configured to perform target monitoring according to the inference result and the target data set, obtain a target monitoring result, and send an alarm message corresponding to the target monitoring result when the target monitoring result indicates that abnormal data exists in the target data set; An optimization unit is used to perform optimization monitoring according to the target monitoring result and the reasoning result to obtain the optimization monitoring result, and when the optimization monitoring result indicates that the target device needs to be optimized, optimize the target device using an optimization scheme corresponding to the optimization monitoring result.

10. The system according to claim 9, characterized in that The optimization unit comprises: A device data table management unit, used to generate a device information report according to the target data set; An equipment utilization rate analysis unit, used to perform equipment utilization rate analysis according to the target data set and / or the equipment information report to obtain an utilization rate analysis result; an energy management unit, configured to perform a first optimization monitoring according to the utilization rate analysis result and the inference result to obtain a first monitoring result, wherein the first optimization monitoring is used to indicate that energy consumption monitoring of the target device is performed, and when the first monitoring result indicates that energy consumption optimization of the target device is required, formulate a first optimization plan according to the first monitoring result, and optimize energy consumption of the target device according to the first optimization plan; a production management unit, configured to perform a second optimization monitoring according to the first monitoring result and the target monitoring result to obtain a second monitoring result, wherein the second optimization monitoring is used to indicate that task monitoring is performed on the target device, and when the second monitoring result indicates that task optimization is required for the target device, formulate a second optimization plan according to the second monitoring result, and perform task optimization on the target device according to the second optimization plan; The BI report and data analysis unit is used to obtain multiple data types corresponding to the target data set, and the target data subset corresponding to each data type; determine the reasoning sub-results, target monitoring sub-results and optimization monitoring sub-results corresponding to each of the target data subsets according to the reasoning results, the target monitoring results and the optimization monitoring results; and visualize the reasoning sub-results, target monitoring sub-results and optimization monitoring sub-results corresponding to each of the target data subsets through charts and visualization tools.

Images